version: 3.3.14

Signed-off-by: Gyuho Lee <leegyuho@amazon.com>

.gitignore

@@ -1,15 +1,20 @@
+/agent-*
 /coverage
+/covdir
+/docs
 /gopath
 /gopath.proto
 /go-bindata
+/release
 /machine*
 /bin
 .vagrant
 *.etcd
+*.log
 /etcd
 *.swp
 /hack/insta-discovery/.env
 *.test
-tools/functional-tester/docker/bin
 hack/tls-setup/certs
 .idea
+*.bak

.travis.yml

@@ -1,11 +1,15 @@
-dist: trusty
 language: go
 go_import_path: github.com/coreos/etcd
-sudo: false
+
+sudo: required
+
+services: docker
 
 go:
-  - 1.8.3
-  - tip
+- 1.12.9
+
+env:
+- GO111MODULE=on
 
 notifications:
   on_success: never
@@ -13,71 +17,50 @@ notifications:
 
 env:
   matrix:
-   - TARGET=amd64
-   - TARGET=darwin-amd64
-   - TARGET=windows-amd64
-   - TARGET=arm64
-   - TARGET=arm
-   - TARGET=386
-   - TARGET=ppc64le
+  - TARGET=linux-amd64-integration-1-cpu
+  - TARGET=linux-amd64-integration-4-cpu
+  - TARGET=linux-amd64-functional
+  - TARGET=linux-amd64-unit
+  - TARGET=linux-amd64-e2e
+  - TARGET=all-build
+  - TARGET=linux-386-unit
 
 matrix:
   fast_finish: true
   allow_failures:
-    - go: tip
-  exclude:
-  - go: tip
-    env: TARGET=darwin-amd64
-  - go: tip
-    env: TARGET=windows-amd64
-  - go: tip
-    env: TARGET=arm
-  - go: tip
-    env: TARGET=arm64
-  - go: tip
-    env: TARGET=386
-  - go: tip
-    env: TARGET=ppc64le
+  - go: 1.12.9
+    env: TARGET=linux-386-unit
 
-addons:
-  apt:
-    sources:
-    - debian-sid
-    packages:
-    - libpcap-dev
-    - libaspell-dev
-    - libhunspell-dev
-    - shellcheck
-
-before_install:
- - go get -v -u github.com/chzchzchz/goword
- - go get -v -u github.com/coreos/license-bill-of-materials
- - go get -v -u honnef.co/go/tools/cmd/gosimple
- - go get -v -u honnef.co/go/tools/cmd/unused
- - go get -v -u honnef.co/go/tools/cmd/staticcheck
- - ./scripts/install-marker.sh amd64
-
-# disable godep restore override
 install:
- - pushd cmd/etcd && go get -t -v ./... && popd
+- go get -t -v -d ./...
 
 script:
+ - echo "TRAVIS_GO_VERSION=${TRAVIS_GO_VERSION}"
  - >
     case "${TARGET}" in
-      amd64)
-        GOARCH=amd64 ./test
+      linux-amd64-integration-1-cpu)
+        GOARCH=amd64 CPU=1 PASSES='integration' ./test
         ;;
-      darwin-amd64)
-        GO_BUILD_FLAGS="-a -v"  GOPATH="" GOOS=darwin GOARCH=amd64 ./build
+      linux-amd64-integration-4-cpu)
+        GOARCH=amd64 CPU=4 PASSES='integration' ./test
         ;;
-      windows-amd64)
-        GO_BUILD_FLAGS="-a -v"  GOPATH="" GOOS=windows GOARCH=amd64 ./build
+      linux-amd64-functional)
+        ./build && GOARCH=amd64 PASSES='functional' ./test
         ;;
-      386)
-        GOARCH=386 PASSES="build unit" ./test
+      linux-amd64-unit)
+        ./build && GOARCH=amd64 PASSES='unit' ./test
         ;;
-      *)
-        # test building out of gopath
-        GO_BUILD_FLAGS="-a -v" GOPATH="" GOARCH="${TARGET}" ./build
+      linux-amd64-e2e)
+        GOARCH=amd64 PASSES='build release e2e' MANUAL_VER=v3.3.13 ./test
+        ;;
+      all-build)
+        GOARCH=386 PASSES='build' ./test \
+          && GO_BUILD_FLAGS='-v' GOOS=darwin GOARCH=amd64 ./build \
+          && GO_BUILD_FLAGS='-v' GOARCH=arm ./build \
+          && GO_BUILD_FLAGS='-v' GOARCH=arm64 ./build \
+          && GO_BUILD_FLAGS='-v' GOARCH=ppc64le ./build
+        ;;
+      linux-386-unit)
+        GOARCH=386 ./build && GOARCH=386 PASSES='unit' ./test
         ;;
     esac

.words

@@ -0,0 +1,44 @@
+DefaultMaxRequestBytes
+ErrCodeEnhanceYourCalm
+ErrTimeout
+GoAway
+KeepAlive
+Keepalive
+MiB
+ResourceExhausted
+RPC
+RPCs
+TODO
+backoff
+blackhole
+blackholed
+cancelable
+cancelation
+cluster_proxy
+defragment
+defragmenting
+etcd
+gRPC
+goroutine
+goroutines
+healthcheck
+iff
+inflight
+keepalive
+keepalives
+keyspace
+linearization
+localhost
+mutex
+prefetching
+protobuf
+prometheus
+rafthttp
+repin
+serializable
+teardown
+too_many_pings
+uncontended
+unprefixed
+unlisting
+

CONTRIBUTING.md

@@ -5,7 +5,7 @@ etcd is Apache 2.0 licensed and accepts contributions via GitHub pull requests.
 # Email and chat
 
 - Email: [etcd-dev](https://groups.google.com/forum/?hl=en#!forum/etcd-dev)
-- IRC: #[coreos](irc://irc.freenode.org:6667/#coreos) IRC channel on freenode.org
+- IRC: #[etcd](irc://irc.freenode.org:6667/#etcd) IRC channel on freenode.org
 
 ## Getting started
 

Dockerfile-functional-tester

@@ -0,0 +1,53 @@
+FROM ubuntu:17.10
+
+RUN rm /bin/sh && ln -s /bin/bash /bin/sh
+RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections
+
+RUN apt-get -y update \
+  && apt-get -y install \
+  build-essential \
+  gcc \
+  apt-utils \
+  pkg-config \
+  software-properties-common \
+  apt-transport-https \
+  libssl-dev \
+  sudo \
+  bash \
+  curl \
+  wget \
+  tar \
+  git \
+  && apt-get -y update \
+  && apt-get -y upgrade \
+  && apt-get -y autoremove \
+  && apt-get -y autoclean
+
+ENV GOROOT /usr/local/go
+ENV GOPATH /go
+ENV PATH ${GOPATH}/bin:${GOROOT}/bin:${PATH}
+ENV GO_VERSION REPLACE_ME_GO_VERSION
+ENV GO_DOWNLOAD_URL https://storage.googleapis.com/golang
+RUN rm -rf ${GOROOT} \
+  && curl -s ${GO_DOWNLOAD_URL}/go${GO_VERSION}.linux-amd64.tar.gz | tar -v -C /usr/local/ -xz \
+  && mkdir -p ${GOPATH}/src ${GOPATH}/bin \
+  && go version
+
+RUN mkdir -p ${GOPATH}/src/github.com/coreos/etcd
+ADD . ${GOPATH}/src/github.com/coreos/etcd
+
+RUN go get -v github.com/coreos/gofail \
+  && pushd ${GOPATH}/src/github.com/coreos/etcd \
+  && GO_BUILD_FLAGS="-v" ./build \
+  && cp ./bin/etcd /etcd \
+  && cp ./bin/etcdctl /etcdctl \
+  && GO_BUILD_FLAGS="-v" FAILPOINTS=1 ./build \
+  && cp ./bin/etcd /etcd-failpoints \
+  && ./tools/functional-tester/build \
+  && cp ./bin/etcd-agent /etcd-agent \
+  && cp ./bin/etcd-tester /etcd-tester \
+  && cp ./bin/etcd-runner /etcd-runner \
+  && go build -v -o /benchmark ./cmd/tools/benchmark \
+  && go build -v -o /etcd-test-proxy ./cmd/tools/etcd-test-proxy \
+  && popd \
+  && rm -rf ${GOPATH}/src/github.com/coreos/etcd

Dockerfile-test

@@ -0,0 +1,58 @@
+FROM ubuntu:16.10
+
+RUN rm /bin/sh && ln -s /bin/bash /bin/sh
+RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections
+
+RUN apt-get -y update \
+  && apt-get -y install \
+  build-essential \
+  gcc \
+  apt-utils \
+  pkg-config \
+  software-properties-common \
+  apt-transport-https \
+  libssl-dev \
+  sudo \
+  bash \
+  curl \
+  wget \
+  tar \
+  git \
+  netcat \
+  libaspell-dev \
+  libhunspell-dev \
+  hunspell-en-us \
+  aspell-en \
+  shellcheck \
+  && apt-get -y update \
+  && apt-get -y upgrade \
+  && apt-get -y autoremove \
+  && apt-get -y autoclean
+
+ENV GOROOT /usr/local/go
+ENV GOPATH /go
+ENV PATH ${GOPATH}/bin:${GOROOT}/bin:${PATH}
+ENV GO_VERSION REPLACE_ME_GO_VERSION
+ENV GO_DOWNLOAD_URL https://storage.googleapis.com/golang
+RUN rm -rf ${GOROOT} \
+  && curl -s ${GO_DOWNLOAD_URL}/go${GO_VERSION}.linux-amd64.tar.gz | tar -v -C /usr/local/ -xz \
+  && mkdir -p ${GOPATH}/src ${GOPATH}/bin \
+  && go version
+
+RUN mkdir -p ${GOPATH}/src/github.com/coreos/etcd
+WORKDIR ${GOPATH}/src/github.com/coreos/etcd
+
+ADD ./scripts/install-marker.sh /tmp/install-marker.sh
+
+RUN go get -v -u -tags spell github.com/chzchzchz/goword \
+  && go get -v -u github.com/coreos/license-bill-of-materials \
+  && go get -v -u honnef.co/go/tools/cmd/gosimple \
+  && go get -v -u honnef.co/go/tools/cmd/unused \
+  && go get -v -u honnef.co/go/tools/cmd/staticcheck \
+  && go get -v -u github.com/gyuho/gocovmerge \
+  && go get -v -u github.com/gordonklaus/ineffassign \
+  && go get -v -u github.com/alexkohler/nakedret \
+  && /tmp/install-marker.sh amd64 \
+  && rm -f /tmp/install-marker.sh \
+  && curl -s https://codecov.io/bash >/codecov \
+  && chmod 700 /codecov

Documentation/_index.md

@@ -0,0 +1,3 @@
+---
+title: etcd version 3.3.12
+---

Documentation/benchmarks/README.md

@@ -1,18 +0,0 @@
-# Benchmarks
-
-etcd benchmarks will be published regularly and tracked for each release below:
-
-- [etcd v2.1.0-alpha][2.1]
-- [etcd v2.2.0-rc][2.2]
-- [etcd v3 demo][3.0]
-
-# Memory Usage Benchmarks
-
-It records expected memory usage in different scenarios.
-
-- [etcd v2.2.0-rc][2.2-mem]
-
-[2.1]: etcd-2-1-0-alpha-benchmarks.md
-[2.2]: etcd-2-2-0-rc-benchmarks.md
-[2.2-mem]: etcd-2-2-0-rc-memory-benchmarks.md
-[3.0]: etcd-3-demo-benchmarks.md

Documentation/benchmarks/_index.md

@@ -0,0 +1,3 @@
+---
+title: Benchmarks
+---

Documentation/benchmarks/etcd-2-1-0-alpha-benchmarks.md

@@ -1,3 +1,7 @@
+---
+title: Benchmarking etcd v2.1.0
+---
+
 ## Physical machines
 
 GCE n1-highcpu-2 machine type

Documentation/benchmarks/etcd-2-2-0-benchmarks.md

@@ -1,4 +1,6 @@
-# Benchmarking etcd v2.2.0
+---
+title: Benchmarking etcd v2.2.0
+---
 
 ## Physical Machines
 
@@ -26,7 +28,7 @@ Go OS/Arch: linux/amd64
 
 Bootstrap another machine, outside of the etcd cluster, and run the [`hey` HTTP benchmark tool](https://github.com/rakyll/hey) with a connection reuse patch to send requests to each etcd cluster member. See the [benchmark instructions](../../hack/benchmark/) for the patch and the steps to reproduce our procedures.
 
-The performance is calulated through results of 100 benchmark rounds.
+The performance is calculated through results of 100 benchmark rounds.
 
 ## Performance
 

Documentation/benchmarks/etcd-2-2-0-rc-benchmarks.md

@@ -1,4 +1,8 @@
-## Physical machines
+---
+title: Benchmarking etcd v2.2.0-rc
+---
+
+## Physical machine
 
 GCE n1-highcpu-2 machine type
 

Documentation/benchmarks/etcd-2-2-0-rc-memory-benchmarks.md

@@ -1,3 +1,7 @@
+---
+title: Benchmarking etcd v2.2.0-rc-memory
+---
+
 ## Physical machine
 
 GCE n1-standard-2 machine type

Documentation/benchmarks/etcd-3-demo-benchmarks.md

@@ -1,3 +1,7 @@
+---
+title: Benchmarking etcd v3
+---
+
 ## Physical machines
 
 GCE n1-highcpu-2 machine type

Documentation/benchmarks/etcd-3-watch-memory-benchmark.md

@@ -1,4 +1,6 @@
-# Watch Memory Usage Benchmark
+---
+title: Watch Memory Usage Benchmark
+---
 
 *NOTE*: The watch features are under active development, and their memory usage may change as that development progresses. We do not expect it to significantly increase beyond the figures stated below.
 

Documentation/benchmarks/etcd-storage-memory-benchmark.md

@@ -1,4 +1,6 @@
-# Storage Memory Usage Benchmark
+---
+title: Storage Memory Usage Benchmark
+---
 
 <!---todo: link storage to storage design doc-->
 Two components of etcd storage consume physical memory. The etcd process allocates an *in-memory index* to speed key lookup. The process's *page cache*, managed by the operating system, stores recently-accessed data from disk for quick re-use.

Documentation/branch_management.md

@@ -1,4 +1,6 @@
-# Branch management
+---
+title: Branch management
+---
 
 ## Guide
 
@@ -7,7 +9,7 @@
 * Backwards-compatible bug fixes should target the master branch and subsequently be ported to stable branches.
 * Once the master branch is ready for release, it will be tagged and become the new stable branch.
 
-The etcd team has adopted a *rolling release model* and supports one stable version of etcd.
+The etcd team has adopted a *rolling release model* and supports two stable versions of etcd.
 
 ### Master branch
 
@@ -15,12 +17,12 @@ The `master` branch is our development branch. All new features land here first.
 
 To try new and experimental features, pull `master` and play with it. Note that `master` may not be stable because new features may introduce bugs.
 
-Before the release of the next stable version, feature PRs will be frozen. We will focus on the testing, bug-fix and documentation for one to two weeks.
+Before the release of the next stable version, feature PRs will be frozen. A [release manager](./dev-internal/release.md#release-management) will be assigned to major/minor version and will lead the etcd community in test, bug-fix and documentation of the release for one to two weeks.
 
 ### Stable branches
 
 All branches with prefix `release-` are considered _stable_ branches.
 
-After every minor release (http://semver.org/), we will have a new stable branch for that release. We will keep fixing the backwards-compatible bugs for the latest stable release, but not previous releases. The _patch_ release, incorporating any bug fixes, will be once every two weeks, given any patches.
+After every minor release (http://semver.org/), we will have a new stable branch for that release, managed by a [patch release manager](./dev-internal/release.md#release-management). We will keep fixing the backwards-compatible bugs for the latest two stable releases. A _patch_ release to each supported release branch, incorporating any bug fixes, will be once every two weeks, given any patches.
 
 [master]: https://github.com/coreos/etcd/tree/master

Documentation/demo.md

@@ -1,4 +1,6 @@
-# Demo
+---
+title: Demo
+---
 
 This series of examples shows the basic procedures for working with an etcd cluster.
 

Documentation/dev-guide/_index.md

@@ -0,0 +1,3 @@
+---
+title: Developer guide
+---

Documentation/dev-guide/api_concurrency_reference_v3.md

@@ -1,4 +1,6 @@
-### etcd concurrency API Reference
+---
+title: etcd concurrency API Reference
+---
 
 
 This is a generated documentation. Please read the proto files for more.
@@ -20,7 +22,7 @@ The lock service exposes client-side locking facilities as a gRPC interface.
 | Field | Description | Type |
 | ----- | ----------- | ---- |
 | name | name is the identifier for the distributed shared lock to be acquired. | bytes |
-| lease | lease is the ID of the lease that will be attached to ownership of the lock. If the lease expires or is revoked and currently holds the lock, the lock is automatically released. Calls to Lock with the same lease will be treated as a single acquistion; locking twice with the same lease is a no-op. | int64 |
+| lease | lease is the ID of the lease that will be attached to ownership of the lock. If the lease expires or is revoked and currently holds the lock, the lock is automatically released. Calls to Lock with the same lease will be treated as a single acquisition; locking twice with the same lease is a no-op. | int64 |
 
 
 

Documentation/dev-guide/api_grpc_gateway.md

@@ -1,14 +1,29 @@
+---
+title: Why gRPC gateway
+---
 
-## Why grpc-gateway
+etcd v3 uses [gRPC][grpc] for its messaging protocol. The etcd project includes a gRPC-based [Go client][go-client] and a command line utility, [etcdctl][etcdctl], for communicating with an etcd cluster through gRPC. For languages with no gRPC support, etcd provides a JSON [gRPC gateway][grpc-gateway]. This gateway serves a RESTful proxy that translates HTTP/JSON requests into gRPC messages.
 
-etcd v3 uses [gRPC][grpc] for its messaging protocol. The etcd project includes a gRPC-based [Go client][go-client] and a command line utility, [etcdctl][etcdctl], for communicating with an etcd cluster through gRPC. For languages with no gRPC support, etcd provides a JSON [grpc-gateway][grpc-gateway]. This gateway serves a RESTful proxy that translates HTTP/JSON requests into gRPC messages.
+## Using gRPC gateway
 
+The gateway accepts a [JSON mapping][json-mapping] for etcd's [protocol buffer][api-ref] message definitions. Note that `key` and `value` fields are defined as byte arrays and therefore must be base64 encoded in JSON. The following examples use `curl`, but any HTTP/JSON client should work all the same.
 
-## Using grpc-gateway
+### Notes
 
-The gateway accepts a [JSON mapping][json-mapping] for etcd's [protocol buffer][api-ref] message definitions. Note that `key` and `value` fields are defined as byte arrays and therefore must be base64 encoded in JSON.
+gRPC gateway endpoint has changed since etcd v3.3:
 
-Use `curl` to put and get a key:
+- etcd v3.2 or before uses only `[CLIENT-URL]/v3alpha/*`.
+- etcd v3.3 uses `[CLIENT-URL]/v3beta/*` while keeping `[CLIENT-URL]/v3alpha/*`.
+- etcd v3.4 uses `[CLIENT-URL]/v3/*` while keeping `[CLIENT-URL]/v3beta/*`.
+  - **`[CLIENT-URL]/v3alpha/*` is deprecated**.
+- etcd v3.5 or later uses only `[CLIENT-URL]/v3/*`.
+  - **`[CLIENT-URL]/v3beta/*` is deprecated**.
+
+gRPC-gateway does not support authentication using TLS Common Name.
+
+### Put and get keys
+
+Use the `/v3/kv/range` and `/v3/kv/put` services to read and write keys:
 
 ```bash
 <<COMMENT
@@ -17,36 +32,97 @@ foo is 'Zm9v' in Base64
 bar is 'YmFy'
 COMMENT
 
-curl -L http://localhost:2379/v3alpha/kv/put \
-	-X POST -d '{"key": "Zm9v", "value": "YmFy"}'
+curl -L http://localhost:2379/v3/kv/put \
+  -X POST -d '{"key": "Zm9v", "value": "YmFy"}'
 # {"header":{"cluster_id":"12585971608760269493","member_id":"13847567121247652255","revision":"2","raft_term":"3"}}
 
-curl -L http://localhost:2379/v3alpha/kv/range \
-	-X POST -d '{"key": "Zm9v"}'
+curl -L http://localhost:2379/v3/kv/range \
+  -X POST -d '{"key": "Zm9v"}'
+# {"header":{"cluster_id":"12585971608760269493","member_id":"13847567121247652255","revision":"2","raft_term":"3"},"kvs":[{"key":"Zm9v","create_revision":"2","mod_revision":"2","version":"1","value":"YmFy"}],"count":"1"}
+
+# get all keys prefixed with "foo"
+curl -L http://localhost:2379/v3/kv/range \
+  -X POST -d '{"key": "Zm9v", "range_end": "Zm9w"}'
 # {"header":{"cluster_id":"12585971608760269493","member_id":"13847567121247652255","revision":"2","raft_term":"3"},"kvs":[{"key":"Zm9v","create_revision":"2","mod_revision":"2","version":"1","value":"YmFy"}],"count":"1"}
 ```
 
-Use `curl` to watch a key:
+### Watch keys
+
+Use the `/v3/watch` service to watch keys:
 
 ```bash
-curl http://localhost:2379/v3alpha/watch \
-        -X POST -d '{"create_request": {"key":"Zm9v"} }' &
+curl -N http://localhost:2379/v3/watch \
+  -X POST -d '{"create_request": {"key":"Zm9v"} }' &
 # {"result":{"header":{"cluster_id":"12585971608760269493","member_id":"13847567121247652255","revision":"1","raft_term":"2"},"created":true}}
 
-curl -L http://localhost:2379/v3alpha/kv/put \
-	-X POST -d '{"key": "Zm9v", "value": "YmFy"}' >/dev/null 2>&1
+curl -L http://localhost:2379/v3/kv/put \
+  -X POST -d '{"key": "Zm9v", "value": "YmFy"}' >/dev/null 2>&1
 # {"result":{"header":{"cluster_id":"12585971608760269493","member_id":"13847567121247652255","revision":"2","raft_term":"2"},"events":[{"kv":{"key":"Zm9v","create_revision":"2","mod_revision":"2","version":"1","value":"YmFy"}}]}}
 ```
 
-Use `curl` to issue a transaction:
+### Transactions
+
+Issue a transaction with `/v3/kv/txn`:
 
 ```bash
-curl -L http://localhost:2379/v3alpha/kv/txn \
-	-X POST \
-	-d '{"compare":[{"target":"CREATE","key":"Zm9v","createRevision":"2"}],"success":[{"requestPut":{"key":"Zm9v","value":"YmFy"}}]}'
+# target CREATE
+curl -L http://localhost:2379/v3/kv/txn \
+  -X POST \
+  -d '{"compare":[{"target":"CREATE","key":"Zm9v","createRevision":"2"}],"success":[{"requestPut":{"key":"Zm9v","value":"YmFy"}}]}'
 # {"header":{"cluster_id":"12585971608760269493","member_id":"13847567121247652255","revision":"3","raft_term":"2"},"succeeded":true,"responses":[{"response_put":{"header":{"revision":"3"}}}]}
 ```
 
+```bash
+# target VERSION
+curl -L http://localhost:2379/v3/kv/txn \
+  -X POST \
+  -d '{"compare":[{"version":"4","result":"EQUAL","target":"VERSION","key":"Zm9v"}],"success":[{"requestRange":{"key":"Zm9v"}}]}'
+# {"header":{"cluster_id":"14841639068965178418","member_id":"10276657743932975437","revision":"6","raft_term":"3"},"succeeded":true,"responses":[{"response_range":{"header":{"revision":"6"},"kvs":[{"key":"Zm9v","create_revision":"2","mod_revision":"6","version":"4","value":"YmF6"}],"count":"1"}}]}
+```
+
+### Authentication
+
+Set up authentication with the `/v3/auth` service:
+
+```bash
+# create root user
+curl -L http://localhost:2379/v3/auth/user/add \
+  -X POST -d '{"name": "root", "password": "pass"}'
+# {"header":{"cluster_id":"14841639068965178418","member_id":"10276657743932975437","revision":"1","raft_term":"2"}}
+
+# create root role
+curl -L http://localhost:2379/v3/auth/role/add \
+  -X POST -d '{"name": "root"}'
+# {"header":{"cluster_id":"14841639068965178418","member_id":"10276657743932975437","revision":"1","raft_term":"2"}}
+
+# grant root role
+curl -L http://localhost:2379/v3/auth/user/grant \
+  -X POST -d '{"user": "root", "role": "root"}'
+# {"header":{"cluster_id":"14841639068965178418","member_id":"10276657743932975437","revision":"1","raft_term":"2"}}
+
+# enable auth
+curl -L http://localhost:2379/v3/auth/enable -X POST -d '{}'
+# {"header":{"cluster_id":"14841639068965178418","member_id":"10276657743932975437","revision":"1","raft_term":"2"}}
+```
+
+Authenticate with etcd for an authentication token using `/v3/auth/authenticate`:
+
+```bash
+# get the auth token for the root user
+curl -L http://localhost:2379/v3/auth/authenticate \
+  -X POST -d '{"name": "root", "password": "pass"}'
+# {"header":{"cluster_id":"14841639068965178418","member_id":"10276657743932975437","revision":"1","raft_term":"2"},"token":"sssvIpwfnLAcWAQH.9"}
+```
+
+Set the `Authorization` header to the authentication token to fetch a key using authentication credentials:
+
+```bash
+curl -L http://localhost:2379/v3/kv/put \
+  -H 'Authorization : sssvIpwfnLAcWAQH.9' \
+  -X POST -d '{"key": "Zm9v", "value": "YmFy"}'
+# {"header":{"cluster_id":"14841639068965178418","member_id":"10276657743932975437","revision":"2","raft_term":"2"}}
+```
+
 ## Swagger
 
 Generated [Swagger][swagger] API definitions can be found at [rpc.swagger.json][swagger-doc].
@@ -54,9 +130,8 @@ Generated [Swagger][swagger] API definitions can be found at [rpc.swagger.json][
 [api-ref]: ./api_reference_v3.md
 [go-client]: https://github.com/coreos/etcd/tree/master/clientv3
 [etcdctl]: https://github.com/coreos/etcd/tree/master/etcdctl
-[grpc]: http://www.grpc.io/
+[grpc]: https://www.grpc.io/
 [grpc-gateway]: https://github.com/grpc-ecosystem/grpc-gateway
 [json-mapping]: https://developers.google.com/protocol-buffers/docs/proto3#json
 [swagger]: http://swagger.io/
 [swagger-doc]: apispec/swagger/rpc.swagger.json
-

Documentation/dev-guide/api_reference_v3.md

@@ -1,4 +1,6 @@
-### etcd API Reference
+---
+title: etcd API Reference
+---
 
 
 This is a generated documentation. Please read the proto files for more.
@@ -58,6 +60,7 @@ This is a generated documentation. Please read the proto files for more.
 | LeaseRevoke | LeaseRevokeRequest | LeaseRevokeResponse | LeaseRevoke revokes a lease. All keys attached to the lease will expire and be deleted. |
 | LeaseKeepAlive | LeaseKeepAliveRequest | LeaseKeepAliveResponse | LeaseKeepAlive keeps the lease alive by streaming keep alive requests from the client to the server and streaming keep alive responses from the server to the client. |
 | LeaseTimeToLive | LeaseTimeToLiveRequest | LeaseTimeToLiveResponse | LeaseTimeToLive retrieves lease information. |
+| LeaseLeases | LeaseLeasesRequest | LeaseLeasesResponse | LeaseLeases lists all existing leases. |
 
 
 
@@ -68,8 +71,10 @@ This is a generated documentation. Please read the proto files for more.
 | Alarm | AlarmRequest | AlarmResponse | Alarm activates, deactivates, and queries alarms regarding cluster health. |
 | Status | StatusRequest | StatusResponse | Status gets the status of the member. |
 | Defragment | DefragmentRequest | DefragmentResponse | Defragment defragments a member's backend database to recover storage space. |
-| Hash | HashRequest | HashResponse | Hash returns the hash of the local KV state for consistency checking purpose. This is designed for testing; do not use this in production when there are ongoing transactions. |
+| Hash | HashRequest | HashResponse | Hash computes the hash of whole backend keyspace, including key, lease, and other buckets in storage. This is designed for testing ONLY! Do not rely on this in production with ongoing transactions, since Hash operation does not hold MVCC locks. Use "HashKV" API instead for "key" bucket consistency checks. |
+| HashKV | HashKVRequest | HashKVResponse | HashKV computes the hash of all MVCC keys up to a given revision. It only iterates "key" bucket in backend storage. |
 | Snapshot | SnapshotRequest | SnapshotResponse | Snapshot sends a snapshot of the entire backend from a member over a stream to a client. |
+| MoveLeader | MoveLeaderRequest | MoveLeaderResponse | MoveLeader requests current leader node to transfer its leadership to transferee. |
 
 
 
@@ -223,8 +228,8 @@ Empty field.
 | Field | Description | Type |
 | ----- | ----------- | ---- |
 | role |  | string |
-| key |  | string |
-| range_end |  | string |
+| key |  | bytes |
+| range_end |  | bytes |
 
 
 
@@ -401,6 +406,8 @@ CompactionRequest compacts the key-value store up to a given revision. All super
 | create_revision | create_revision is the creation revision of the given key | int64 |
 | mod_revision | mod_revision is the last modified revision of the given key. | int64 |
 | value | value is the value of the given key, in bytes. | bytes |
+| lease | lease is the lease id of the given key. | int64 |
+| range_end | range_end compares the given target to all keys in the range [key, range_end). See RangeRequest for more details on key ranges. | bytes |
 
 
 
@@ -438,6 +445,24 @@ Empty field.
 
 
 
+##### message `HashKVRequest` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| revision | revision is the key-value store revision for the hash operation. | int64 |
+
+
+
+##### message `HashKVResponse` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| header |  | ResponseHeader |
+| hash | hash is the hash value computed from the responding member's MVCC keys up to a given revision. | uint32 |
+| compact_revision | compact_revision is the compacted revision of key-value store when hash begins. | int64 |
+
+
+
 ##### message `HashRequest` (etcdserver/etcdserverpb/rpc.proto)
 
 Empty field.
@@ -449,7 +474,32 @@ Empty field.
 | Field | Description | Type |
 | ----- | ----------- | ---- |
 | header |  | ResponseHeader |
-| hash | hash is the hash value computed from the responding member's key-value store. | uint32 |
+| hash | hash is the hash value computed from the responding member's KV's backend. | uint32 |
+
+
+
+##### message `LeaseCheckpoint` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| ID | ID is the lease ID to checkpoint. | int64 |
+| remaining_TTL | Remaining_TTL is the remaining time until expiry of the lease. | int64 |
+
+
+
+##### message `LeaseCheckpointRequest` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| checkpoints |  | (slice of) LeaseCheckpoint |
+
+
+
+##### message `LeaseCheckpointResponse` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| header |  | ResponseHeader |
 
 
 
@@ -457,7 +507,7 @@ Empty field.
 
 | Field | Description | Type |
 | ----- | ----------- | ---- |
-| TTL | TTL is the advisory time-to-live in seconds. | int64 |
+| TTL | TTL is the advisory time-to-live in seconds. Expired lease will return -1. | int64 |
 | ID | ID is the requested ID for the lease. If ID is set to 0, the lessor chooses an ID. | int64 |
 
 
@@ -491,6 +541,21 @@ Empty field.
 
 
 
+##### message `LeaseLeasesRequest` (etcdserver/etcdserverpb/rpc.proto)
+
+Empty field.
+
+
+
+##### message `LeaseLeasesResponse` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| header |  | ResponseHeader |
+| leases |  | (slice of) LeaseStatus |
+
+
+
 ##### message `LeaseRevokeRequest` (etcdserver/etcdserverpb/rpc.proto)
 
 | Field | Description | Type |
@@ -507,6 +572,14 @@ Empty field.
 
 
 
+##### message `LeaseStatus` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| ID |  | int64 |
+
+
+
 ##### message `LeaseTimeToLiveRequest` (etcdserver/etcdserverpb/rpc.proto)
 
 | Field | Description | Type |
@@ -607,6 +680,22 @@ Empty field.
 
 
 
+##### message `MoveLeaderRequest` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| targetID | targetID is the node ID for the new leader. | uint64 |
+
+
+
+##### message `MoveLeaderResponse` (etcdserver/etcdserverpb/rpc.proto)
+
+| Field | Description | Type |
+| ----- | ----------- | ---- |
+| header |  | ResponseHeader |
+
+
+
 ##### message `PutRequest` (etcdserver/etcdserverpb/rpc.proto)
 
 | Field | Description | Type |
@@ -644,7 +733,7 @@ Empty field.
 | count_only | count_only when set returns only the count of the keys in the range. | bool |
 | min_mod_revision | min_mod_revision is the lower bound for returned key mod revisions; all keys with lesser mod revisions will be filtered away. | int64 |
 | max_mod_revision | max_mod_revision is the upper bound for returned key mod revisions; all keys with greater mod revisions will be filtered away. | int64 |
-| min_create_revision | min_create_revision is the lower bound for returned key create revisions; all keys with lesser create trevisions will be filtered away. | int64 |
+| min_create_revision | min_create_revision is the lower bound for returned key create revisions; all keys with lesser create revisions will be filtered away. | int64 |
 | max_create_revision | max_create_revision is the upper bound for returned key create revisions; all keys with greater create revisions will be filtered away. | int64 |
 
 
@@ -668,6 +757,7 @@ Empty field.
 | request_range |  | RangeRequest |
 | request_put |  | PutRequest |
 | request_delete_range |  | DeleteRangeRequest |
+| request_txn |  | TxnRequest |
 
 
 
@@ -677,7 +767,7 @@ Empty field.
 | ----- | ----------- | ---- |
 | cluster_id | cluster_id is the ID of the cluster which sent the response. | uint64 |
 | member_id | member_id is the ID of the member which sent the response. | uint64 |
-| revision | revision is the key-value store revision when the request was applied. | int64 |
+| revision | revision is the key-value store revision when the request was applied. For watch progress responses, the header.revision indicates progress. All future events recieved in this stream are guaranteed to have a higher revision number than the header.revision number. | int64 |
 | raft_term | raft_term is the raft term when the request was applied. | uint64 |
 
 
@@ -690,6 +780,7 @@ Empty field.
 | response_range |  | RangeResponse |
 | response_put |  | PutResponse |
 | response_delete_range |  | DeleteRangeResponse |
+| response_txn |  | TxnResponse |
 
 
 
@@ -721,10 +812,13 @@ Empty field.
 | ----- | ----------- | ---- |
 | header |  | ResponseHeader |
 | version | version is the cluster protocol version used by the responding member. | string |
-| dbSize | dbSize is the size of the backend database, in bytes, of the responding member. | int64 |
+| dbSize | dbSize is the size of the backend database physically allocated, in bytes, of the responding member. | int64 |
 | leader | leader is the member ID which the responding member believes is the current leader. | uint64 |
-| raftIndex | raftIndex is the current raft index of the responding member. | uint64 |
+| raftIndex | raftIndex is the current raft committed index of the responding member. | uint64 |
 | raftTerm | raftTerm is the current raft term of the responding member. | uint64 |
+| raftAppliedIndex | raftAppliedIndex is the current raft applied index of the responding member. | uint64 |
+| errors | errors contains alarm/health information and status. | (slice of) string |
+| dbSizeInUse | dbSizeInUse is the size of the backend database logically in use, in bytes, of the responding member. | int64 |
 
 
 
@@ -768,6 +862,16 @@ From google paxosdb paper: Our implementation hinges around a powerful primitive
 | progress_notify | progress_notify is set so that the etcd server will periodically send a WatchResponse with no events to the new watcher if there are no recent events. It is useful when clients wish to recover a disconnected watcher starting from a recent known revision. The etcd server may decide how often it will send notifications based on current load. | bool |
 | filters | filters filter the events at server side before it sends back to the watcher. | (slice of) FilterType |
 | prev_kv | If prev_kv is set, created watcher gets the previous KV before the event happens. If the previous KV is already compacted, nothing will be returned. | bool |
+| watch_id | If watch_id is provided and non-zero, it will be assigned to this watcher. Since creating a watcher in etcd is not a synchronous operation, this can be used ensure that ordering is correct when creating multiple watchers on the same stream. Creating a watcher with an ID already in use on the stream will cause an error to be returned. | int64 |
+| fragment | fragment enables splitting large revisions into multiple watch responses. | bool |
+
+
+
+##### message `WatchProgressRequest` (etcdserver/etcdserverpb/rpc.proto)
+
+Requests the a watch stream progress status be sent in the watch response stream as soon as possible.
+
+Empty field.
 
 
 
@@ -778,6 +882,7 @@ From google paxosdb paper: Our implementation hinges around a powerful primitive
 | request_union | request_union is a request to either create a new watcher or cancel an existing watcher. | oneof |
 | create_request |  | WatchCreateRequest |
 | cancel_request |  | WatchCancelRequest |
+| progress_request |  | WatchProgressRequest |
 
 
 
@@ -791,6 +896,7 @@ From google paxosdb paper: Our implementation hinges around a powerful primitive
 | canceled | canceled is set to true if the response is for a cancel watch request. No further events will be sent to the canceled watcher. | bool |
 | compact_revision | compact_revision is set to the minimum index if a watcher tries to watch at a compacted index.  This happens when creating a watcher at a compacted revision or the watcher cannot catch up with the progress of the key-value store.  The client should treat the watcher as canceled and should not try to create any watcher with the same start_revision again. | int64 |
 | cancel_reason | cancel_reason indicates the reason for canceling the watcher. | string |
+| fragment | framgment is true if large watch response was split over multiple responses. | bool |
 | events |  | (slice of) mvccpb.Event |
 
 
@@ -824,6 +930,7 @@ From google paxosdb paper: Our implementation hinges around a powerful primitive
 | ----- | ----------- | ---- |
 | ID |  | int64 |
 | TTL |  | int64 |
+| RemainingTTL |  | int64 |
 
 
 

Documentation/dev-guide/apispec/swagger/v3election.swagger.json

@@ -15,13 +15,13 @@
     "application/json"
   ],
   "paths": {
-    "/v3alpha/election/campaign": {
+    "/v3/election/campaign": {
       "post": {
         "summary": "Campaign waits to acquire leadership in an election, returning a LeaderKey\nrepresenting the leadership if successful. The LeaderKey can then be used\nto issue new values on the election, transactionally guard API requests on\nleadership still being held, and resign from the election.",
         "operationId": "Campaign",
         "responses": {
           "200": {
-            "description": "",
+            "description": "A successful response.",
             "schema": {
               "$ref": "#/definitions/v3electionpbCampaignResponse"
             }
@@ -42,13 +42,13 @@
         ]
       }
     },
-    "/v3alpha/election/leader": {
+    "/v3/election/leader": {
       "post": {
         "summary": "Leader returns the current election proclamation, if any.",
         "operationId": "Leader",
         "responses": {
           "200": {
-            "description": "",
+            "description": "A successful response.",
             "schema": {
               "$ref": "#/definitions/v3electionpbLeaderResponse"
             }
@@ -69,13 +69,13 @@
         ]
       }
     },
-    "/v3alpha/election/observe": {
+    "/v3/election/observe": {
       "post": {
         "summary": "Observe streams election proclamations in-order as made by the election's\nelected leaders.",
         "operationId": "Observe",
         "responses": {
           "200": {
-            "description": "(streaming responses)",
+            "description": "A successful response.(streaming responses)",
             "schema": {
               "$ref": "#/definitions/v3electionpbLeaderResponse"
             }
@@ -96,13 +96,13 @@
         ]
       }
     },
-    "/v3alpha/election/proclaim": {
+    "/v3/election/proclaim": {
       "post": {
         "summary": "Proclaim updates the leader's posted value with a new value.",
         "operationId": "Proclaim",
         "responses": {
           "200": {
-            "description": "",
+            "description": "A successful response.",
             "schema": {
               "$ref": "#/definitions/v3electionpbProclaimResponse"
             }
@@ -123,13 +123,13 @@
         ]
       }
     },
-    "/v3alpha/election/resign": {
+    "/v3/election/resign": {
       "post": {
         "summary": "Resign releases election leadership so other campaigners may acquire\nleadership on the election.",
         "operationId": "Resign",
         "responses": {
           "200": {
-            "description": "",
+            "description": "A successful response.",
             "schema": {
               "$ref": "#/definitions/v3electionpbResignResponse"
             }
@@ -168,7 +168,7 @@
         "revision": {
           "type": "string",
           "format": "int64",
-          "description": "revision is the key-value store revision when the request was applied."
+          "description": "revision is the key-value store revision when the request was applied.\nFor watch progress responses, the header.revision indicates progress. All future events\nrecieved in this stream are guaranteed to have a higher revision number than the\nheader.revision number."
         },
         "raft_term": {
           "type": "string",

Documentation/dev-guide/apispec/swagger/v3lock.swagger.json

@@ -15,13 +15,13 @@
     "application/json"
   ],
   "paths": {
-    "/v3alpha/lock/lock": {
+    "/v3/lock/lock": {
       "post": {
         "summary": "Lock acquires a distributed shared lock on a given named lock.\nOn success, it will return a unique key that exists so long as the\nlock is held by the caller. This key can be used in conjunction with\ntransactions to safely ensure updates to etcd only occur while holding\nlock ownership. The lock is held until Unlock is called on the key or the\nlease associate with the owner expires.",
         "operationId": "Lock",
         "responses": {
           "200": {
-            "description": "",
+            "description": "A successful response.",
             "schema": {
               "$ref": "#/definitions/v3lockpbLockResponse"
             }
@@ -42,13 +42,13 @@
         ]
       }
     },
-    "/v3alpha/lock/unlock": {
+    "/v3/lock/unlock": {
       "post": {
         "summary": "Unlock takes a key returned by Lock and releases the hold on lock. The\nnext Lock caller waiting for the lock will then be woken up and given\nownership of the lock.",
         "operationId": "Unlock",
         "responses": {
           "200": {
-            "description": "",
+            "description": "A successful response.",
             "schema": {
               "$ref": "#/definitions/v3lockpbUnlockResponse"
             }
@@ -87,7 +87,7 @@
         "revision": {
           "type": "string",
           "format": "int64",
-          "description": "revision is the key-value store revision when the request was applied."
+          "description": "revision is the key-value store revision when the request was applied.\nFor watch progress responses, the header.revision indicates progress. All future events\nrecieved in this stream are guaranteed to have a higher revision number than the\nheader.revision number."
         },
         "raft_term": {
           "type": "string",
@@ -107,7 +107,7 @@
         "lease": {
           "type": "string",
           "format": "int64",
-          "description": "lease is the ID of the lease that will be attached to ownership of the\nlock. If the lease expires or is revoked and currently holds the lock,\nthe lock is automatically released. Calls to Lock with the same lease will\nbe treated as a single acquistion; locking twice with the same lease is a\nno-op."
+          "description": "lease is the ID of the lease that will be attached to ownership of the\nlock. If the lease expires or is revoked and currently holds the lock,\nthe lock is automatically released. Calls to Lock with the same lease will\nbe treated as a single acquisition; locking twice with the same lease is a\nno-op."
         }
       }
     },

Documentation/dev-guide/experimental_apis.md

@@ -1,11 +1,9 @@
-# Experimental APIs and features
+---
+title: Experimental APIs and features
+---
 
 For the most part, the etcd project is stable, but we are still moving fast! We believe in the release fast philosophy. We want to get early feedback on features still in development and stabilizing. Thus, there are, and will be more, experimental features and APIs. We plan to improve these features based on the early feedback from the community, or abandon them if there is little interest, in the next few releases. Please do not rely on any experimental features or APIs in production environment.
 
 ## The current experimental API/features are:
 
-- [gateway][gateway]: beta, to be stable in 3.2 release
-- [gRPC proxy][grpc-proxy]: alpha, to be stable in 3.2 release
-
-[gateway]: ../op-guide/gateway.md
-[grpc-proxy]: ../op-guide/grpc_proxy.md
+- [KV ordering](https://godoc.org/github.com/etcd-io/etcd/clientv3/ordering) wrapper. When an etcd client switches endpoints, responses to serializable reads may go backward in time if the new endpoint is lagging behind the rest of the cluster. The ordering wrapper caches the current cluster revision from response headers. If a response revision is less than the cached revision, the client selects another endpoint and reissues the read. Enable in grpcproxy with `--experimental-serializable-ordering`.

Documentation/dev-guide/grpc_naming.md

@@ -1,4 +1,6 @@
-# gRPC naming and discovery
+---
+title: gRPC naming and discovery
+---
 
 etcd provides a gRPC resolver to support an alternative name system that fetches endpoints from etcd for discovering gRPC services. The underlying mechanism is based on watching updates to keys prefixed with the service name.
 
@@ -8,8 +10,8 @@ The etcd client provides a gRPC resolver for resolving gRPC endpoints with an et
 
 ```go
 import (
-	"github.com/coreos/etcd/clientv3"
-	etcdnaming "github.com/coreos/etcd/clientv3/naming"
+	"go.etcd.io/etcd/clientv3"
+	etcdnaming "go.etcd.io/etcd/clientv3/naming"
 
 	"google.golang.org/grpc"
 )
@@ -19,7 +21,7 @@ import (
 cli, cerr := clientv3.NewFromURL("http://localhost:2379")
 r := &etcdnaming.GRPCResolver{Client: cli}
 b := grpc.RoundRobin(r)
-conn, gerr := grpc.Dial("my-service", grpc.WithBalancer(b))
+conn, gerr := grpc.Dial("my-service", grpc.WithBalancer(b), grpc.WithBlock(), ...)
 ```
 
 ## Managing service endpoints

Documentation/dev-guide/interacting_v3.md

@@ -1,8 +1,13 @@
-# Interacting with etcd
+---
+title: Interacting with etcd
+---
 
 Users mostly interact with etcd by putting or getting the value of a key. This section describes how to do that by using etcdctl, a command line tool for interacting with etcd server. The concepts described here should apply to the gRPC APIs or client library APIs.
 
-By default, etcdctl talks to the etcd server with the v2 API for backward compatibility. For etcdctl to speak to etcd using the v3 API, the API version must be set to version 3 via the `ETCDCTL_API` environment variable.
+The API version used by etcdctl to speak to etcd may be set to version `2` or `3` via the `ETCDCTL_API` environment variable. By default, etcdctl on master (3.4) uses the v3 API and earlier versions (3.3 and earlier) default to the v2 API.
+
+Note that any key that was created using the v2 API will not be able to be queried via the v2 API.  A v3 API ```etcdctl get``` of a v2 key will exit with 0 and no key data, this is the expected behaviour.
+
 
 ```bash
 export ETCDCTL_API=3
@@ -215,7 +220,7 @@ $ etcdctl del foo foo9
 Here is the command to delete key `zoo` with the deleted key value pair returned:
 
 ```bash
-$ etcdctl del --prev-kv zoo 
+$ etcdctl del --prev-kv zoo
 1   # one key is deleted
 zoo # deleted key
 val # the value of the deleted key
@@ -224,7 +229,7 @@ val # the value of the deleted key
 Here is the command to delete keys having prefix as `zoo`:
 
 ```bash
-$ etcdctl del --prefix zoo 
+$ etcdctl del --prefix zoo
 2 # two keys are deleted
 ```
 
@@ -290,7 +295,7 @@ barz1
 Here is the command to watch on multiple keys `foo` and `zoo`:
 
 ```bash
-$ etcdctl watch -i 
+$ etcdctl watch -i
 $ watch foo
 $ watch zoo
 # in another terminal: etcdctl put foo bar
@@ -354,6 +359,26 @@ foo         # key
 bar_latest  # value of foo key after modification
 ```
 
+## Watch progress
+
+Applications may want to check the progress of a watch to determine how up-to-date the watch stream is. For example, if a watch is used to update a cache, it can be useful to know if the cache is stale compared to the revision from a quorum read. 
+
+Progress requests can be issued using the "progress" command in interactive watch session to ask the etcd server to send a progress notify update in the watch stream:
+
+```bash
+$ etcdctl watch -i
+$ watch a
+$ progress
+progress notify: 1
+# in another terminal: etcdctl put x 0
+# in another terminal: etcdctl put y 1
+$ progress
+progress notify: 3
+```
+
+Note: The revision number in the progress notify response is the revision from the local etcd server node that the watch stream is connected to. If this node is partitioned and not part of quorum, this progress notify revision might be lower than 
+than the revision returned by a quorum read against a non-partitioned etcd server node.
+
 ## Compacted revisions
 
 As we mentioned, etcd keeps revisions so that applications can read past versions of keys. However, to avoid accumulating an unbounded amount of history, it is important to compact past revisions. After compacting, etcd removes historical revisions, releasing resources for future use. All superseded data with revisions before the compacted revision will be unavailable.
@@ -430,9 +455,9 @@ Here is the command to keep the same lease alive:
 
 ```bash
 $ etcdctl lease keep-alive 32695410dcc0ca06
-lease 32695410dcc0ca06 keepalived with TTL(100)
-lease 32695410dcc0ca06 keepalived with TTL(100)
-lease 32695410dcc0ca06 keepalived with TTL(100)
+lease 32695410dcc0ca06 keepalived with TTL(10)
+lease 32695410dcc0ca06 keepalived with TTL(10)
+lease 32695410dcc0ca06 keepalived with TTL(10)
 ...
 ```
 
@@ -472,4 +497,3 @@ lease 694d5765fc71500b granted with TTL(500s), remaining(132s), attached keys([z
 # if the lease has expired or does not exist it will give the below response:
 Error:  etcdserver: requested lease not found
 ```
-

Documentation/dev-guide/limit.md

@@ -1,10 +1,11 @@
-# System limits
+---
+title: System limits
+---
 
 ## Request size limit
 
-etcd is designed to handle small key value pairs typical for metadata. Larger requests will work, but may increase the latency of other requests. For the time being, etcd guarantees to support RPC requests with up to 1MB of data. In the future, the size limit may be loosened or made configurable.
+etcd is designed to handle small key value pairs typical for metadata. Larger requests will work, but may increase the latency of other requests. By default, the maximum size of any request is 1.5 MiB. This limit is configurable through `--max-request-bytes` flag for etcd server.
 
 ## Storage size limit
 
-The default storage size limit is 2GB, configurable with `--quota-backend-bytes` flag; supports up to 8GB.
-
+The default storage size limit is 2GB, configurable with `--quota-backend-bytes` flag. 8GB is a suggested maximum size for normal environments and etcd warns at startup if the configured value exceeds it.

Documentation/dev-guide/local_cluster.md

@@ -1,90 +1,151 @@
-# Setup a local cluster
+---
+title: Set up a local cluster
+---
 
-For testing and development deployments, the quickest and easiest way is to set up a local cluster. For a production deployment, refer to the [clustering][clustering] section.
+For testing and development deployments, the quickest and easiest way is to configure a local cluster. For a production deployment, refer to the [clustering][clustering] section.
 
 ## Local standalone cluster
 
-Deploying an etcd cluster as a standalone cluster is straightforward. Start it with just one command:
+### Starting a cluster
+
+Run the following to deploy an etcd cluster as a standalone cluster:
 
 ```
 $ ./etcd
 ...
 ```
 
-The started etcd member listens on `localhost:2379` for client requests.
+If the `etcd` binary is not present in the current working directory, it might be located either at `$GOPATH/bin/etcd` or at `/usr/local/bin/etcd`. Run the command appropriately.
 
-To interact with the started cluster by using etcdctl:
+The running etcd member listens on `localhost:2379` for client requests.
 
-```
-# use API version 3
-$ export ETCDCTL_API=3
+### Interacting with the cluster
 
-$ ./etcdctl put foo bar
-OK
+Use `etcdctl` to interact with the running cluster:
 
-$ ./etcdctl get foo
-bar
-```
+1. Store an example key-value pair in the cluster:
+
+    ```
+      $ ./etcdctl put foo bar
+      OK
+    ```
+
+    If OK is printed, storing key-value pair is successful.
+
+2. Retrieve the value of `foo`:
+
+    ```
+    $ ./etcdctl get foo
+    bar
+    ```
+
+    If `bar` is returned, interaction with the etcd cluster is working as expected.
 
 ## Local multi-member cluster
 
-A `Procfile` at the base of this git repo is provided to easily set up a local multi-member cluster. To start a multi-member cluster go to the root of an etcd source tree and run:
+### Starting a cluster
 
-```
-# install goreman program to control Profile-based applications.
-$ go get github.com/mattn/goreman
-$ goreman -f Procfile start
-...
-```
+A `Procfile` at the base of the etcd git repository is provided to easily configure a local multi-member cluster. To start a multi-member cluster, navigate to the root of the etcd source tree and perform the following:
 
-The started members listen on `localhost:2379`, `localhost:22379`, and `localhost:32379` for client requests respectively.
+1. Install `goreman` to control Procfile-based applications:
 
-To interact with the started cluster by using etcdctl:
+    ```
+    $ go get github.com/mattn/goreman
+    ```
 
-```
-# use API version 3
-$ export ETCDCTL_API=3
+2. Start a cluster with `goreman` using etcd's stock Procfile:
 
-$ etcdctl --write-out=table --endpoints=localhost:2379 member list
-+------------------+---------+--------+------------------------+------------------------+
-|        ID        | STATUS  |  NAME  |       PEER ADDRS       |      CLIENT ADDRS      |
-+------------------+---------+--------+------------------------+------------------------+
-| 8211f1d0f64f3269 | started | infra1 | http://127.0.0.1:2380  | http://127.0.0.1:2379  |
-| 91bc3c398fb3c146 | started | infra2 | http://127.0.0.1:22380 | http://127.0.0.1:22379 |
-| fd422379fda50e48 | started | infra3 | http://127.0.0.1:32380 | http://127.0.0.1:32379 |
-+------------------+---------+--------+------------------------+------------------------+
+    ```
+    $ goreman -f Procfile start
+    ```
 
-$ etcdctl put foo bar
-OK
-```
+    The members start running. They listen on `localhost:2379`, `localhost:22379`, and `localhost:32379` respectively for client requests.
 
-To exercise etcd's fault tolerance, kill a member:
+### Interacting with the cluster
 
-```
-# kill etcd2
-$ goreman run stop etcd2
+Use `etcdctl` to interact with the running cluster:
 
-$ etcdctl put key hello
-OK
+1. Print the list of members:
 
-$ etcdctl get key
-hello
+    ```
+    $ etcdctl --write-out=table --endpoints=localhost:2379 member list
+    ```
+    The list of etcd members are displayed as follows:
 
-# try to get key from the killed member
-$ etcdctl --endpoints=localhost:22379 get key
-2016/04/18 23:07:35 grpc: Conn.resetTransport failed to create client transport: connection error: desc = "transport: dial tcp 127.0.0.1:22379: getsockopt: connection refused"; Reconnecting to "localhost:22379"
-Error:  grpc: timed out trying to connect
+    ```
+    +------------------+---------+--------+------------------------+------------------------+
+    |        ID        | STATUS  |  NAME  |       PEER ADDRS       |      CLIENT ADDRS      |
+    +------------------+---------+--------+------------------------+------------------------+
+    | 8211f1d0f64f3269 | started | infra1 | http://127.0.0.1:2380  | http://127.0.0.1:2379  |
+    | 91bc3c398fb3c146 | started | infra2 | http://127.0.0.1:22380 | http://127.0.0.1:22379 |
+    | fd422379fda50e48 | started | infra3 | http://127.0.0.1:32380 | http://127.0.0.1:32379 |
+    +------------------+---------+--------+------------------------+------------------------+
+    ```
 
-# restart the killed member
-$ goreman run restart etcd2
+2. Store an example key-value pair in the cluster:
 
-# get the key from restarted member
-$ etcdctl --endpoints=localhost:22379 get key
-hello
-```
+    ```
+    $ etcdctl put foo bar
+    OK
+    ```
 
-To learn more about interacting with etcd, read [interacting with etcd section][interacting].
+    If OK is printed, storing key-value pair is successful.
+
+### Testing fault tolerance  
+
+To exercise etcd's fault tolerance, kill a member and attempt to retrieve the key.
+
+1. Identify the process name of the member to be stopped.
+
+    The `Procfile` lists the properties of the multi-member cluster. For example, consider the member with the process name, `etcd2`.
+
+2. Stop the member:
+
+    ```
+    # kill etcd2
+    $ goreman run stop etcd2
+    ```
+
+3. Store a key:
+
+    ```
+    $ etcdctl put key hello
+    OK
+    ```
+
+4.  Retrieve the key that is stored in the previous step:
+
+    ```
+    $ etcdctl get key
+    hello
+    ```
+
+5. Retrieve a key from the stopped member:
+
+    ```
+    $ etcdctl --endpoints=localhost:22379 get key
+    ```
+
+    The command should display an error caused by connection failure:
+
+    ```
+    2017/06/18 23:07:35 grpc: Conn.resetTransport failed to create client transport: connection error: desc = "transport: dial tcp 127.0.0.1:22379: getsockopt: connection refused"; Reconnecting to "localhost:22379"
+    Error:  grpc: timed out trying to connect
+    ```
+6. Restart the stopped member:
+
+    ```
+    $ goreman run restart etcd2
+    ```
+
+7. Get the key from the restarted member:
+
+    ```
+    $ etcdctl --endpoints=localhost:22379 get key
+    hello
+    ```
+
+    Restarting the member re-establish the connection. `etcdctl` will now be able to retrieve the key successfully. To learn more about interacting with etcd, read [interacting with etcd section][interacting].
 
 [interacting]: ./interacting_v3.md
 [clustering]: ../op-guide/clustering.md
-

Documentation/dev-internal/discovery_protocol.md

@@ -1,4 +1,6 @@
-# Discovery service protocol
+---
+title: Discovery service protocol
+---
 
 Discovery service protocol helps new etcd member to discover all other members in cluster bootstrap phase using a shared discovery URL.
 

Documentation/dev-internal/logging.md

@@ -1,4 +1,6 @@
-# Logging conventions
+---
+title: Logging conventions
+---
 
 etcd uses the [capnslog][capnslog] library for logging application output categorized into *levels*. A log message's level is determined according to these conventions:
 

Documentation/dev-internal/release.md

@@ -1,9 +1,23 @@
-# etcd release guide
+---
+title: etcd release guide
+---
 
 The guide talks about how to release a new version of etcd.
 
 The procedure includes some manual steps for sanity checking, but it can probably be further scripted. Please keep this document up-to-date if making changes to the release process.
 
+## Release management
+
+etcd community members are assigned to manage the release each etcd major/minor version as well as manage patches
+and to each stable release branch. The managers are responsible for communicating the timelines and status of each
+release and for ensuring the stability of the release branch.
+
+| Releases | Manager |
+| -------- | ------- |
+| 3.1 patch (post 3.1.0) | Joe Betz [@jpbetz](https://github.com/jpbetz) |
+| 3.2 patch (post 3.2.0) | Joe Betz [@jpbetz](https://github.com/jpbetz) |
+| 3.3 patch (post 3.3.0) | Gyuho Lee [@gyuho](https://github.com/gyuho) |
+
 ## Prepare release
 
 Set desired version as environment variable for following steps. Here is an example to release 2.3.0:
@@ -18,15 +32,17 @@ All releases version numbers follow the format of [semantic versioning 2.0.0](ht
 ### Major, minor version release, or its pre-release
 
 - Ensure the relevant milestone on GitHub is complete. All referenced issues should be closed, or moved elsewhere.
-- Remove this release from [roadmap](https://github.com/coreos/etcd/blob/master/ROADMAP.md), if necessary.
+- Remove this release from [roadmap](https://github.com/etcd-io/etcd/blob/master/ROADMAP.md), if necessary.
 - Ensure the latest upgrade documentation is available.
-- Bump [hardcoded MinClusterVerion in the repository](https://github.com/coreos/etcd/blob/master/version/version.go#L29), if necessary.
+- Bump [hardcoded MinClusterVerion in the repository](https://github.com/etcd-io/etcd/blob/master/version/version.go#L29), if necessary.
 - Add feature capability maps for the new version, if necessary.
 
 ### Patch version release
 
-- Discuss about commits that are backported to the patch release. The commits should not include merge commits.
-- Cherry-pick these commits starting from the oldest one into stable branch.
+- To request a backport, devlopers submit cherrypick PRs targeting the release branch. The commits should not include merge commits. The commits should be restricted to bug fixes and security patches.
+- The cherrypick PRs should target the appropriate release branch (`base:release-<major>-<minor>`). `hack/patch/cherrypick.sh` may be used to automatically generate cherrypick PRs.
+- The release patch manager reviews the cherrypick PRs. Please discuss carefully what is backported to the patch release. Each patch release should be strictly better than it's predecessor.
+- The release patch manager will cherry-pick these commits starting from the oldest one into stable branch.
 
 ## Write release note
 
@@ -36,14 +52,14 @@ All releases version numbers follow the format of [semantic versioning 2.0.0](ht
 
 ## Tag version
 
-- Bump [hardcoded Version in the repository](https://github.com/coreos/etcd/blob/master/version/version.go#L30) to the latest version `${VERSION}`.
+- Bump [hardcoded Version in the repository](https://github.com/etcd-io/etcd/blob/master/version/version.go#L30) to the latest version `${VERSION}`.
 - Ensure all tests on CI system are passed.
 - Manually check etcd is buildable in Linux, Darwin and Windows.
 - Manually check upgrade etcd cluster of previous minor version works well.
 - Manually check new features work well.
 - Add a signed tag through `git tag -s ${VERSION}`.
 - Sanity check tag correctness through `git show tags/$VERSION`.
-- Push the tag to GitHub through `git push origin tags/$VERSION`. This assumes `origin` corresponds to "https://github.com/coreos/etcd".
+- Push the tag to GitHub through `git push origin tags/$VERSION`. This assumes `origin` corresponds to "https://github.com/etcd-io/etcd".
 
 ## Build release binaries and images
 
@@ -53,7 +69,7 @@ All releases version numbers follow the format of [semantic versioning 2.0.0](ht
 Run release script in root directory:
 
 ```
-./scripts/release.sh ${VERSION}
+TAG=gcr.io/etcd-development/etcd ./scripts/release.sh ${VERSION}
 ```
 
 It generates all release binaries and images under directory ./release.
@@ -70,11 +86,11 @@ for i in etcd-*{.zip,.tar.gz}; do gpg2 --default-key $SUBKEYID --armor --output
 for i in etcd-*{.zip,.tar.gz}; do gpg2 --verify ${i}.asc ${i}; done
 
 # sign zipped source code files
-wget https://github.com/coreos/etcd/archive/${VERSION}.zip
+wget https://github.com/etcd-io/etcd/archive/${VERSION}.zip
 gpg2 --armor --default-key $SUBKEYID --output ${VERSION}.zip.asc --detach-sign ${VERSION}.zip
 gpg2 --verify ${VERSION}.zip.asc ${VERSION}.zip
 
-wget https://github.com/coreos/etcd/archive/${VERSION}.tar.gz
+wget https://github.com/etcd-io/etcd/archive/${VERSION}.tar.gz
 gpg2 --armor --default-key $SUBKEYID --output ${VERSION}.tar.gz.asc --detach-sign ${VERSION}.tar.gz
 gpg2 --verify ${VERSION}.tar.gz.asc ${VERSION}.tar.gz
 ```
@@ -86,17 +102,45 @@ The public key for GPG signing can be found at [CoreOS Application Signing Key](
 
 - Set release title as the version name.
 - Follow the format of previous release pages.
-- Attach the generated binaries, aci image and signatures.
+- Attach the generated binaries and signatures.
 - Select whether it is a pre-release.
 - Publish the release!
 
+## Publish docker image in gcr.io
+
+- Push docker image:
+
+```
+gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd.json)" https://gcr.io
+
+for TARGET_ARCH in "-arm64" "-ppc64le" ""; do
+  gcloud docker -- push gcr.io/etcd-development/etcd:${VERSION}${TARGET_ARCH}
+done
+```
+
+- Add `latest` tag to the new image on [gcr.io](https://console.cloud.google.com/gcr/images/etcd-development/GLOBAL/etcd?project=etcd-development&authuser=1) if this is a stable release.
+
 ## Publish docker image in Quay.io
 
+- Build docker images with quay.io:
+
+```
+for TARGET_ARCH in "amd64" "arm64" "ppc64le"; do
+  TAG=quay.io/coreos/etcd GOARCH=${TARGET_ARCH} \
+    BINARYDIR=release/etcd-${VERSION}-linux-${TARGET_ARCH} \
+    BUILDDIR=release \
+    ./scripts/build-docker ${VERSION}
+done
+```
+
 - Push docker image:
 
 ```
 docker login quay.io
-docker push quay.io/coreos/etcd:${VERSION}
+
+for TARGET_ARCH in "-arm64" "-ppc64le" ""; do
+  docker push quay.io/coreos/etcd:${VERSION}${TARGET_ARCH}
+done
 ```
 
 - Add `latest` tag to the new image on [quay.io](https://quay.io/repository/coreos/etcd?tag=latest&tab=tags) if this is a stable release.
@@ -114,5 +158,5 @@ git log ...${PREV_VERSION} --pretty=format:"%an" | sort | uniq | tr '\n' ',' | s
 
 ## Post release
 
-- Create new stable branch through `git push origin ${VERSION_MAJOR}.${VERSION_MINOR}` if this is a major stable release. This assumes `origin` corresponds to "https://github.com/coreos/etcd".
-- Bump [hardcoded Version in the repository](https://github.com/coreos/etcd/blob/master/version/version.go#L30) to the version `${VERSION}+git`.
+- Create new stable branch through `git push origin ${VERSION_MAJOR}.${VERSION_MINOR}` if this is a major stable release. This assumes `origin` corresponds to "https://github.com/etcd-io/etcd".
+- Bump [hardcoded Version in the repository](https://github.com/etcd-io/etcd/blob/master/version/version.go#L30) to the version `${VERSION}+git`.

Documentation/dl_build.md

@@ -1,4 +1,7 @@
-# Download and build
+---
+title: Download and build
+weight: 1
+---
 
 ## System requirements
 
@@ -10,12 +13,12 @@ The easiest way to get etcd is to use one of the pre-built release binaries whic
 
 ## Build the latest version
 
-For those wanting to try the very latest version, build etcd from the `master` branch. [Go](https://golang.org/) version 1.8+ is required to build the latest version of etcd. To ensure etcd is built against well-tested libraries, etcd vendors its dependencies for official release binaries. However, etcd's vendoring is also optional to avoid potential import conflicts when embedding the etcd server or using the etcd client.
+For those wanting to try the very latest version, build etcd from the `master` branch. [Go](https://golang.org/) version 1.9+ is required to build the latest version of etcd. To ensure etcd is built against well-tested libraries, etcd vendors its dependencies for official release binaries. However, etcd's vendoring is also optional to avoid potential import conflicts when embedding the etcd server or using the etcd client.
 
 To build `etcd` from the `master` branch without a `GOPATH` using the official `build` script:
 
 ```sh
-$ git clone https://github.com/coreos/etcd.git
+$ git clone https://github.com/etcd-io/etcd.git
 $ cd etcd
 $ ./build
 ```
@@ -26,16 +29,8 @@ To build a vendored `etcd` from the `master` branch via `go get`:
 # GOPATH should be set
 $ echo $GOPATH
 /Users/example/go
-$ go get github.com/coreos/etcd/cmd/etcd
-```
-
-To build `etcd` from the `master` branch without vendoring (may not build due to upstream conflicts):
-
-```sh
-# GOPATH should be set
-$ echo $GOPATH
-/Users/example/go
-$ go get github.com/coreos/etcd
+$ go get -v go.etcd.io/etcd
+$ go get -v go.etcd.io/etcd/etcdctl
 ```
 
 ## Test the installation
@@ -44,14 +39,14 @@ Check the etcd binary is built correctly by starting etcd and setting a key.
 
 ### Starting etcd
 
-If etcd is built without using GOPATH, run the following:
+If etcd is built without using `go get`, run the following:
 
-```
+```sh
 $ ./bin/etcd
 ```
-If etcd is built using GOPATH, run the following:
+If etcd is built using `go get`, run the following:
 
-```
+```sh
 $ $GOPATH/bin/etcd
 ```
 
@@ -59,14 +54,16 @@ $ $GOPATH/bin/etcd
 
 Run the following:
 
-```
-$ ETCDCTL_API=3 ./bin/etcdctl put foo bar
+```sh
+$ ./bin/etcdctl put foo bar
 OK
 ```
 
+(or `$GOPATH/bin/etcdctl put foo bar` if etcdctl was installed with `go get`)
+
 If OK is printed, then etcd is working!
 
-[github-release]: https://github.com/coreos/etcd/releases/
+[github-release]: https://github.com/etcd-io/etcd/releases/
 [go]: https://golang.org/doc/install
 [build-script]: ../build
 [cmd-directory]: ../cmd

Documentation/docs.md

@@ -1,113 +0,0 @@
-# Documentation
-
-etcd is a distributed key-value store designed to reliably and quickly preserve and provide access to critical data. It enables reliable distributed coordination through distributed locking, leader elections, and write barriers. An etcd cluster is intended for high availability and permanent data storage and retrieval.
-
-## Getting started
-
-New etcd users and developers should get started by [downloading and building][download_build] etcd. After getting etcd, follow this [quick demo][demo] to see the basics of creating and working with an etcd cluster.
-
-## Developing with etcd
-
-The easiest way to get started using etcd as a distributed key-value store is to [set up a local cluster][local_cluster].
-
- - [Setting up local clusters][local_cluster]
- - [Interacting with etcd][interacting]
- - gRPC [etcd core][api_ref] and [etcd concurrency][api_concurrency_ref] API references
- - [HTTP JSON API through the gRPC gateway][api_grpc_gateway]
- - [gRPC naming and discovery][grpc_naming]
- - [Client][namespace_client] and [proxy][namespace_proxy] namespacing
- - [Embedding etcd][embed_etcd]
- - [Experimental features and APIs][experimental]
- - [System limits][system-limit]
-
-## Operating etcd clusters
-
-Administrators who need to create reliable and scalable key-value stores for the developers they support should begin with a [cluster on multiple machines][clustering].
-
- - [Setting up etcd clusters][clustering]
- - [Setting up etcd gateways][gateway]
- - [Setting up etcd gRPC proxy][grpc_proxy]
- - [Hardware recommendations][hardware]
- - [Configuration][conf]
- - [Security][security]
- - [Authentication][authentication]
- - [Monitoring][monitoring]
- - [Maintenance][maintenance]
- - [Understand failures][failures]
- - [Disaster recovery][recovery]
- - [Performance][performance]
- - [Versioning][versioning]
-
-### Platform guides
-
- - [Supported systems][supported_platforms]
- - [Docker container][container_docker]
- - [Container Linux, systemd][container_linux_platform]
- - [rkt container][container_rkt]
- - [Amazon Web Services][aws_platform]
- - [FreeBSD][freebsd_platform]
-
-### Upgrading and compatibility
-
- - [Migrate applications from using API v2 to API v3][v2_migration]
- - [Upgrading a v2.3 cluster to v3.0][v3_upgrade]
- - [Upgrading a v3.0 cluster to v3.1][v31_upgrade]
- - [Upgrading a v3.1 cluster to v3.2][v32_upgrade]
-
-## Learning
-
-To learn more about the concepts and internals behind etcd, read the following pages:
-
- - [Why etcd?][why]
- - [Understand data model][data_model]
- - [Understand APIs][understand_apis]
- - [Glossary][glossary]
- - Internals
-   - [Auth subsystem][auth_design]
-
-## Frequently Asked Questions (FAQ)
-
-Answers to [common questions] about etcd.
-
-[api_ref]: dev-guide/api_reference_v3.md
-[api_concurrency_ref]: dev-guide/api_concurrency_reference_v3.md
-[api_grpc_gateway]: dev-guide/api_grpc_gateway.md
-[clustering]: op-guide/clustering.md
-[conf]: op-guide/configuration.md
-[system-limit]: dev-guide/limit.md
-[common questions]: faq.md
-[why]: learning/why.md
-[data_model]: learning/data_model.md
-[demo]: demo.md
-[download_build]: dl_build.md
-[embed_etcd]: https://godoc.org/github.com/coreos/etcd/embed
-[grpc_naming]: dev-guide/grpc_naming.md
-[failures]: op-guide/failures.md
-[gateway]: op-guide/gateway.md
-[glossary]: learning/glossary.md
-[namespace_client]: https://godoc.org/github.com/coreos/etcd/clientv3/namespace
-[namespace_proxy]: op-guide/grpc_proxy.md#namespacing
-[grpc_proxy]: op-guide/grpc_proxy.md
-[hardware]: op-guide/hardware.md
-[interacting]: dev-guide/interacting_v3.md
-[local_cluster]: dev-guide/local_cluster.md
-[performance]: op-guide/performance.md
-[recovery]: op-guide/recovery.md
-[maintenance]: op-guide/maintenance.md
-[security]: op-guide/security.md
-[monitoring]: op-guide/monitoring.md
-[v2_migration]: op-guide/v2-migration.md
-[container_rkt]: op-guide/container.md#rkt
-[container_docker]: op-guide/container.md#docker
-[understand_apis]: learning/api.md
-[versioning]: op-guide/versioning.md
-[supported_platforms]: op-guide/supported-platform.md
-[container_linux_platform]: platforms/container-linux-systemd.md
-[freebsd_platform]: platforms/freebsd.md
-[aws_platform]: platforms/aws.md
-[experimental]: dev-guide/experimental_apis.md
-[v3_upgrade]: upgrades/upgrade_3_0.md
-[v31_upgrade]: upgrades/upgrade_3_1.md
-[v32_upgrade]: upgrades/upgrade_3_2.md
-[authentication]: op-guide/authentication.md
-[auth_design]: learning/auth_design.md

Documentation/faq.md

@@ -1,40 +1,42 @@
-## Frequently Asked Questions (FAQ)
+---
+title: Frequently Asked Questions (FAQ)
+---
 
-### etcd, general
+## etcd, general
 
-#### Do clients have to send requests to the etcd leader?
+### Do clients have to send requests to the etcd leader?
 
 [Raft][raft] is leader-based; the leader handles all client requests which need cluster consensus. However, the client does not need to know which node is the leader. Any request that requires consensus sent to a follower is automatically forwarded to the leader. Requests that do not require consensus (e.g., serialized reads) can be processed by any cluster member.
 
-### Configuration
+## Configuration
 
-#### What is the difference between advertise-urls and listen-urls?
+### What is the difference between listen-<client,peer>-urls, advertise-client-urls or initial-advertise-peer-urls?
 
-`listen-urls` specifies the local addresses etcd server binds to for accepting incoming connections. To listen on a port for all interfaces, specify `0.0.0.0` as the listen IP address.
+`listen-client-urls` and `listen-peer-urls` specify the local addresses etcd server binds to for accepting incoming connections. To listen on a port for all interfaces, specify `0.0.0.0` as the listen IP address.
 
-`advertise-urls` specifies the addresses etcd clients or other etcd members should use to contact the etcd server. The advertise addresses must be reachable from the remote machines. Do not advertise addresses like `localhost` or `0.0.0.0` for a production setup since these addresses are unreachable from remote machines.
+`advertise-client-urls` and `initial-advertise-peer-urls` specify the addresses etcd clients or other etcd members should use to contact the etcd server. The advertise addresses must be reachable from the remote machines. Do not advertise addresses like `localhost` or `0.0.0.0` for a production setup since these addresses are unreachable from remote machines.
 
-#### Why doesn't changing `--listen-peer-urls` or `--initial-advertise-peer-urls` update the advertised peer URLs in `etcdctl member list`?
+### Why doesn't changing `--listen-peer-urls` or `--initial-advertise-peer-urls` update the advertised peer URLs in `etcdctl member list`?
 
 A member's advertised peer URLs come from `--initial-advertise-peer-urls` on initial cluster boot. Changing the listen peer URLs or the initial advertise peers after booting the member won't affect the exported advertise peer URLs since changes must go through quorum to avoid membership configuration split brain. Use `etcdctl member update` to update a member's peer URLs.
 
-### Deployment
+## Deployment
 
-#### System requirements
+### System requirements
 
-Since etcd writes data to disk, SSD is highly recommended. To prevent performance degradation or unintentionally overloading the key-value store, etcd enforces a 2GB default storage size quota, configurable up to 8GB. To avoid swapping or running out of memory, the machine should have at least as much RAM to cover the quota. At CoreOS, an etcd cluster is usually deployed on dedicated CoreOS Container Linux machines with dual-core processors, 2GB of RAM, and 80GB of SSD *at the very least*. **Note that performance is intrinsically workload dependent; please test before production deployment**. See [hardware][hardware-setup] for more recommendations.
+Since etcd writes data to disk, SSD is highly recommended. To prevent performance degradation or unintentionally overloading the key-value store, etcd enforces a configurable storage size quota set to 2GB by default. To avoid swapping or running out of memory, the machine should have at least as much RAM to cover the quota. 8GB is a suggested maximum size for normal environments and etcd warns at startup if the configured value exceeds it. At CoreOS, an etcd cluster is usually deployed on dedicated CoreOS Container Linux machines with dual-core processors, 2GB of RAM, and 80GB of SSD *at the very least*. **Note that performance is intrinsically workload dependent; please test before production deployment**. See [hardware][hardware-setup] for more recommendations.
 
 Most stable production environment is Linux operating system with amd64 architecture; see [supported platform][supported-platform] for more.
 
-#### Why an odd number of cluster members?
+### Why an odd number of cluster members?
 
 An etcd cluster needs a majority of nodes, a quorum, to agree on updates to the cluster state. For a cluster with n members, quorum is (n/2)+1. For any odd-sized cluster, adding one node will always increase the number of nodes necessary for quorum. Although adding a node to an odd-sized cluster appears better since there are more machines, the fault tolerance is worse since exactly the same number of nodes may fail without losing quorum but there are more nodes that can fail. If the cluster is in a state where it can't tolerate any more failures, adding a node before removing nodes is dangerous because if the new node fails to register with the cluster (e.g., the address is misconfigured), quorum will be permanently lost.
 
-#### What is maximum cluster size?
+### What is maximum cluster size?
 
 Theoretically, there is no hard limit. However, an etcd cluster probably should have no more than seven nodes. [Google Chubby lock service][chubby], similar to etcd and widely deployed within Google for many years, suggests running five nodes. A 5-member etcd cluster can tolerate two member failures, which is enough in most cases. Although larger clusters provide better fault tolerance, the write performance suffers because data must be replicated across more machines.
 
-#### What is failure tolerance?
+### What is failure tolerance?
 
 An etcd cluster operates so long as a member quorum can be established. If quorum is lost through transient network failures (e.g., partitions), etcd automatically and safely resumes once the network recovers and restores quorum; Raft enforces cluster consistency. For power loss, etcd persists the Raft log to disk; etcd replays the log to the point of failure and resumes cluster participation. For permanent hardware failure, the node may be removed from the cluster through [runtime reconfiguration][runtime reconfiguration].
 
@@ -54,19 +56,19 @@ It is recommended to have an odd number of members in a cluster. An odd-size clu
 
 Adding a member to bring the size of cluster up to an even number doesn't buy additional fault tolerance. Likewise, during a network partition, an odd number of members guarantees that there will always be a majority partition that can continue to operate and be the source of truth when the partition ends.
 
-#### Does etcd work in cross-region or cross data center deployments?
+### Does etcd work in cross-region or cross data center deployments?
 
 Deploying etcd across regions improves etcd's fault tolerance since members are in separate failure domains. The cost is higher consensus request latency from crossing data center boundaries. Since etcd relies on a member quorum for consensus, the latency from crossing data centers will be somewhat pronounced because at least a majority of cluster members must respond to consensus requests. Additionally, cluster data must be replicated across all peers, so there will be bandwidth cost as well.
 
 With longer latencies, the default etcd configuration may cause frequent elections or heartbeat timeouts. See [tuning] for adjusting timeouts for high latency deployments.
 
-### Operation
+## Operation
 
-#### How to backup a etcd cluster?
+### How to backup a etcd cluster?
 
 etcdctl provides a `snapshot` command to create backups. See [backup][backup] for more details.
 
-#### Should I add a member before removing an unhealthy member?
+### Should I add a member before removing an unhealthy member?
 
 When replacing an etcd node, it's important  to remove the member first and then add its replacement.
 
@@ -78,21 +80,21 @@ Additionally, that new member is risky because it may turn out to be misconfigur
 
 On the other hand, if the downed member is removed from cluster membership first, the number of members becomes 2 and the quorum remains at 2. Following that removal by adding a new member will also keep the quorum steady at 2. So, even if the new node can't be brought up, it's still possible to remove the new member through quorum on the remaining live members.
 
-#### Why won't etcd accept my membership changes?
+### Why won't etcd accept my membership changes?
 
 etcd sets `strict-reconfig-check` in order to reject reconfiguration requests that would cause quorum loss. Abandoning quorum is really risky (especially when the cluster is already unhealthy). Although it may be tempting to disable quorum checking if there's quorum loss to add a new member, this could lead to full fledged cluster inconsistency. For many applications, this will make the problem even worse ("disk geometry corruption" being a candidate for most terrifying).
 
-#### Why does etcd lose its leader from disk latency spikes?
+### Why does etcd lose its leader from disk latency spikes?
 
 This is intentional; disk latency is part of leader liveness. Suppose the cluster leader takes a minute to fsync a raft log update to disk, but the etcd cluster has a one second election timeout. Even though the leader can process network messages within the election interval (e.g., send heartbeats), it's effectively unavailable because it can't commit any new proposals; it's waiting on the slow disk. If the cluster frequently loses its leader due to disk latencies, try [tuning][tuning] the disk settings or etcd time parameters.
 
-#### What does the etcd warning "request ignored (cluster ID mismatch)" mean?
+### What does the etcd warning "request ignored (cluster ID mismatch)" mean?
 
 Every new etcd cluster generates a new cluster ID based on the initial cluster configuration and a user-provided unique `initial-cluster-token` value. By having unique cluster ID's, etcd is protected from cross-cluster interaction which could corrupt the cluster.
 
 Usually this warning happens after tearing down an old cluster, then reusing some of the peer addresses for the new cluster. If any etcd process from the old cluster is still running it will try to contact the new cluster. The new cluster will recognize a cluster ID mismatch, then ignore the request and emit this warning. This warning is often cleared by ensuring peer addresses among distinct clusters are disjoint.
 
-#### What does "mvcc: database space exceeded" mean and how do I fix it?
+### What does "mvcc: database space exceeded" mean and how do I fix it?
 
 The [multi-version concurrency control][api-mvcc] data model in etcd keeps an exact history of the keyspace. Without periodically compacting this history (e.g., by setting `--auto-compaction`), etcd will eventually exhaust its storage space. If etcd runs low on storage space, it raises a space quota alarm to protect the cluster from further writes. So long as the alarm is raised, etcd responds to write requests with the error `mvcc: database space exceeded`.
 
@@ -102,16 +104,22 @@ To recover from the low space quota alarm:
 2. [Defragment][maintenance-defragment] every etcd endpoint.
 3. [Disarm][maintenance-disarm] the alarm.
 
-### Performance
+### What does the etcd warning "etcdserver/api/v3rpc: transport: http2Server.HandleStreams failed to read frame: read tcp 127.0.0.1:2379->127.0.0.1:43020: read: connection reset by peer" mean?
 
-#### How should I benchmark etcd?
+This is gRPC-side warning when a server receives a TCP RST flag with client-side streams being prematurely closed. For example, a client closes its connection, while gRPC server has not yet processed all HTTP/2 frames in the TCP queue. Some data may have been lost in server side, but it is ok so long as client connection has already been closed.
+
+Only [old versions of gRPC](https://github.com/grpc/grpc-go/issues/1362) log this. etcd [>=v3.2.13 by default log this with DEBUG level](https://github.com/etcd-io/etcd/pull/9080), thus only visible with `--debug` flag enabled.
+
+## Performance
+
+### How should I benchmark etcd?
 
 Try the [benchmark] tool. Current [benchmark results][benchmark-result] are available for comparison.
 
-#### What does the etcd warning "apply entries took too long" mean?
+### What does the etcd warning "apply entries took too long" mean?
 
 After a majority of etcd members agree to commit a request, each etcd server applies the request to its data store and persists the result to disk. Even with a slow mechanical disk or a virtualized network disk, such as Amazon’s EBS or Google’s PD, applying a request should normally take fewer than 50 milliseconds. If the average apply duration exceeds 100 milliseconds, etcd will warn that entries are taking too long to apply.
- 
+
 Usually this issue is caused by a slow disk. The disk could be experiencing contention among etcd and other applications, or the disk is too simply slow (e.g., a shared virtualized disk). To rule out a slow disk from causing this warning, monitor  [backend_commit_duration_seconds][backend_commit_metrics] (p99 duration should be less than 25ms) to confirm the disk is reasonably fast. If the disk is too slow, assigning a dedicated disk to etcd or using faster disk will typically solve the problem.
 
 The second most common cause is CPU starvation. If monitoring of the machine’s CPU usage shows heavy utilization, there may not be enough compute capacity for etcd. Moving etcd to dedicated machine, increasing process resource isolation  cgroups, or renicing the etcd server process into a higher priority can usually solve the problem.
@@ -120,7 +128,7 @@ Expensive user requests which access too many keys (e.g., fetching the entire ke
 
 If none of the above suggestions clear the warnings, please [open an issue][new_issue] with detailed logging, monitoring, metrics and optionally workload information.
 
-#### What does the etcd warning "failed to send out heartbeat on time" mean?
+### What does the etcd warning "failed to send out heartbeat on time" mean?
 
 etcd uses a leader-based consensus protocol for consistent data replication and log execution. Cluster members elect a single leader, all other members become followers. The elected leader must periodically send heartbeats to its followers to maintain its leadership. Followers infer leader failure if no heartbeats are received within an election interval and trigger an election. If a leader doesn’t send its heartbeats in time but is still running, the election is spurious and likely caused by insufficient resources. To catch these soft failures, if the leader skips two heartbeat intervals, etcd will warn it failed to send a heartbeat on time.
 
@@ -132,7 +140,7 @@ A slow network can also cause this issue. If network metrics among the etcd mach
 
 If none of the above suggestions clear the warnings, please [open an issue][new_issue] with detailed logging, monitoring, metrics and optionally workload information.
 
-#### What does the etcd warning "snapshotting is taking more than x seconds to finish ..." mean?
+### What does the etcd warning "snapshotting is taking more than x seconds to finish ..." mean?
 
 etcd sends a snapshot of its complete key-value store to refresh slow followers and for [backups][backup]. Slow snapshot transfer times increase MTTR; if the cluster is ingesting data with high throughput, slow followers may livelock by needing a new snapshot before finishing receiving a snapshot. To catch slow snapshot performance, etcd warns when sending a snapshot takes more than thirty seconds and exceeds the expected transfer time for a 1Gbps connection.
 
@@ -141,14 +149,14 @@ etcd sends a snapshot of its complete key-value store to refresh slow followers
 [supported-platform]: ./op-guide/supported-platform.md
 [wal_fsync_duration_seconds]: ./metrics.md#disk
 [tuning]: ./tuning.md
-[new_issue]: https://github.com/coreos/etcd/issues/new
+[new_issue]: https://github.com/etcd-io/etcd/issues/new
 [backend_commit_metrics]: ./metrics.md#disk
 [raft]: https://raft.github.io/raft.pdf
-[backup]: https://github.com/coreos/etcd/blob/master/Documentation/op-guide/recovery.md#snapshotting-the-keyspace
+[backup]: https://github.com/etcd-io/etcd/blob/master/Documentation/op-guide/recovery.md#snapshotting-the-keyspace
 [chubby]: http://static.googleusercontent.com/media/research.google.com/en//archive/chubby-osdi06.pdf
-[runtime reconfiguration]: https://github.com/coreos/etcd/blob/master/Documentation/op-guide/runtime-configuration.md
+[runtime reconfiguration]: https://github.com/etcd-io/etcd/blob/master/Documentation/op-guide/runtime-configuration.md
 [benchmark]: https://github.com/coreos/etcd/tree/master/tools/benchmark
-[benchmark-result]: https://github.com/coreos/etcd/blob/master/Documentation/op-guide/performance.md
+[benchmark-result]: https://github.com/etcd-io/etcd/blob/master/Documentation/op-guide/performance.md
 [api-mvcc]: learning/api.md#revisions
 [maintenance-compact]:  op-guide/maintenance.md#history-compaction
 [maintenance-defragment]: op-guide/maintenance.md#defragmentation

Documentation/integrations.md

@@ -1,8 +1,11 @@
-# Libraries and tools
+---
+title: Libraries and tools
+weight: 2
+---
 
 **Tools**
 
-- [etcdctl](https://github.com/coreos/etcd/tree/master/etcdctl) - A command line client for etcd
+- [etcdctl](https://github.com/etcd-io/etcd/tree/master/etcdctl) - A command line client for etcd
 - [etcd-backup](https://github.com/fanhattan/etcd-backup) - A powerful command line utility for dumping/restoring etcd - Supports v2
 - [etcd-dump](https://npmjs.org/package/etcd-dump) - Command line utility for dumping/restoring etcd.
 - [etcd-fs](https://github.com/xetorthio/etcd-fs) - FUSE filesystem for etcd
@@ -15,17 +18,18 @@
 - [etcd-rest](https://github.com/mickep76/etcd-rest) - Create generic REST API in Go using etcd as a backend with validation using JSON schema
 - [etcdsh](https://github.com/kamilhark/etcdsh) - A command line client with support of command history and tab completion. Supports v2
 - [etcdloadtest](https://github.com/sinsharat/etcdloadtest) - A command line load test client for etcd version 3.0 and above.
+- [lucas](https://github.com/ringtail/lucas) - A web-based key-value viewer for kubernetes etcd3.0+ cluster.
 
 **Go libraries**
 
-- [etcd/clientv3](https://github.com/coreos/etcd/blob/master/clientv3) - the officially maintained Go client for v3
-- [etcd/client](https://github.com/coreos/etcd/blob/master/client) - the officially maintained Go client for v2
+- [etcd/clientv3](https://github.com/etcd-io/etcd/blob/master/clientv3) - the officially maintained Go client for v3
+- [etcd/client](https://github.com/etcd-io/etcd/blob/master/client) - the officially maintained Go client for v2
 - [go-etcd](https://github.com/coreos/go-etcd) - the deprecated official client. May be useful for older (<2.0.0) versions of etcd.
 - [encWrapper](https://github.com/lumjjb/etcd/tree/enc_wrapper/clientwrap/encwrapper) - encWrapper is an encryption wrapper for the etcd client Keys API/KV.
 
 **Java libraries**
 
-- [coreos/jetcd](https://github.com/coreos/jetcd) - Supports v3
+- [coreos/jetcd](https://github.com/etcd-io/jetcd) - Supports v3
 - [boonproject/etcd](https://github.com/boonproject/boon/blob/master/etcd/README.md) - Supports v2, Async/Sync and waits
 - [justinsb/jetcd](https://github.com/justinsb/jetcd)
 - [diwakergupta/jetcd](https://github.com/diwakergupta/jetcd) - Supports v2
@@ -38,6 +42,11 @@
 - [maciej/etcd-client](https://github.com/maciej/etcd-client) - Supports v2. Akka HTTP-based fully async client
 - [eiipii/etcdhttpclient](https://bitbucket.org/eiipii/etcdhttpclient) - Supports v2. Async HTTP client based on Netty and Scala Futures.
 
+**Perl libraries**
+
+- [hexfusion/perl-net-etcd](https://github.com/hexfusion/perl-net-etcd) - Supports v3 grpc gateway HTTP API
+- [robn/p5-etcd](https://github.com/robn/p5-etcd) - Supports v2
+
 **Python libraries**
 
 - [kragniz/python-etcd3](https://github.com/kragniz/python-etcd3) - Client for v3
@@ -47,6 +56,8 @@
 - [lisael/aioetcd](https://github.com/lisael/aioetcd) - (Python 3.4+) Asyncio coroutines client (Supports v2)
 - [txaio-etcd](https://github.com/crossbario/txaio-etcd) - Asynchronous etcd v3-only client library for Twisted (today) and asyncio (future)
 - [dims/etcd3-gateway](https://github.com/dims/etcd3-gateway) - etcd v3 API library using the HTTP grpc gateway
+- [aioetcd3](https://github.com/gaopeiliang/aioetcd3) - (Python 3.6+) etcd v3 API for asyncio
+- [Revolution1/etcd3-py](https://github.com/Revolution1/etcd3-py) - (python2.7 and python3.5+) Python client for etcd v3, using gRPC-JSON-Gateway
 
 **Node libraries**
 
@@ -82,17 +93,20 @@
 
 **Erlang libraries**
 
-- [marshall-lee/etcd.erl](https://github.com/marshall-lee/etcd.erl)
+- [marshall-lee/etcd.erl](https://github.com/marshall-lee/etcd.erl) - Supports v2
+- [zhongwencool/eetcd](https://github.com/zhongwencool/eetcd) - Supports v3+ (GRPC only)
 
 **.Net Libraries**
 
 - [wangjia184/etcdnet](https://github.com/wangjia184/etcdnet) - Supports v2
 - [drusellers/etcetera](https://github.com/drusellers/etcetera)
+- [shubhamranjan/dotnet-etcd](https://github.com/shubhamranjan/dotnet-etcd) - Supports v3+ (GRPC only)
 
 **PHP Libraries**
 
 - [linkorb/etcd-php](https://github.com/linkorb/etcd-php)
 - [activecollab/etcd](https://github.com/activecollab/etcd)
+- [ouqiang/etcd-php](https://github.com/ouqiang/etcd-php) - Client for v3 gRPC gateway
 
 **Haskell libraries**
 
@@ -133,6 +147,7 @@
 
 **Projects using etcd**
 
+- [etcd Raft users](../raft/README.md#notable-users) - projects using etcd's raft library implementation.
 - [apache/celix](https://github.com/apache/celix) - an implementation of the OSGi specification adapted to C and C++
 - [binocarlos/yoda](https://github.com/binocarlos/yoda) - etcd + ZeroMQ
 - [blox/blox](https://github.com/blox/blox) - a collection of open source projects for container management and orchestration with AWS ECS
@@ -146,7 +161,6 @@
 - [mattn/etcdenv](https://github.com/mattn/etcdenv) - "env" shebang with etcd integration
 - [kelseyhightower/confd](https://github.com/kelseyhightower/confd) - Manage local app config files using templates and data from etcd
 - [configdb](https://git.autistici.org/ai/configdb/tree/master) - A REST relational abstraction on top of arbitrary database backends, aimed at storing configs and inventories.
-- [fleet](https://github.com/coreos/fleet) - Distributed init system
 - [kubernetes/kubernetes](https://github.com/kubernetes/kubernetes) - Container cluster manager introduced by Google.
 - [mailgun/vulcand](https://github.com/mailgun/vulcand) - HTTP proxy that uses etcd as a configuration backend.
 - [duedil-ltd/discodns](https://github.com/duedil-ltd/discodns) - Simple DNS nameserver using etcd as a database for names and records.
@@ -157,3 +171,11 @@
 - [ryandoyle/nss-etcd](https://github.com/ryandoyle/nss-etcd) - A GNU libc NSS module for resolving names from etcd.
 - [Gru](https://github.com/dnaeon/gru) - Orchestration made easy with Go
 - [Vitess](http://vitess.io/) - Vitess is a database clustering system for horizontal scaling of MySQL.
+- [lclarkmichalek/etcdhcp](https://github.com/lclarkmichalek/etcdhcp) - DHCP server that uses etcd for persistence and coordination.
+- [openstack/networking-vpp](https://github.com/openstack/networking-vpp) - A networking driver that programs the [FD.io VPP dataplane](https://wiki.fd.io/view/VPP) to provide [OpenStack](https://www.openstack.org/) cloud virtual networking
+- [OpenStack](https://github.com/openstack/governance/blob/master/reference/base-services.rst) - OpenStack services can rely on etcd as a base service.
+- [CoreDNS](https://github.com/coredns/coredns/tree/master/plugin/etcd) - CoreDNS is a DNS server that chains plugins, part of CNCF and Kubernetes
+- [Uber M3](https://github.com/m3db/m3) - M3: Uber’s Open Source, Large-scale Metrics Platform for Prometheus
+- [Rook](https://github.com/rook/rook) - Storage Orchestration for Kubernetes
+- [Patroni](https://github.com/zalando/patroni) - A template for PostgreSQL High Availability with ZooKeeper, etcd, or Consul
+- [Trillian](https://github.com/google/trillian) - Trillian implements a Merkle tree whose contents are served from a data storage layer, to allow scalability to extremely large trees.

Documentation/learning/_index.md

@@ -0,0 +1,3 @@
+---
+title: Learning
+---

Documentation/learning/api.md

@@ -1,4 +1,6 @@
-# etcd3 API
+---
+title: etcd3 API
+---
 
 This document is meant to give an overview of the etcd3 API's central design. It is by no means all encompassing, but intended to focus on the basic ideas needed to understand etcd without the distraction of less common API calls. All etcd3 API's are defined in [gRPC services][grpc-service], which categorize remote procedure calls (RPCs) understood by the etcd server. A full listing of all etcd RPCs are documented in markdown in the [gRPC API listing][grpc-api].
 
@@ -45,9 +47,9 @@ message ResponseHeader {
 * Revision - the revision of the key-value store when generating the response.
 * Raft_Term - the Raft term of the member when generating the response.
 
-An application may read the Cluster_ID (Member_ID) field to ensure it is communicating with the intended cluster (member).
+An application may read the `Cluster_ID` or `Member_ID` field to ensure it is communicating with the intended cluster (member).
 
-Applications can use the `Revision` to know the latest revision of the key-value store. This is especially useful when applications specify a historical revision to make time `travel query` and wishes to know the latest revision at the time of the request.
+Applications can use the `Revision` field to know the latest revision of the key-value store. This is especially useful when applications specify a historical revision to make a `time travel query` and wish to know the latest revision at the time of the request.
 
 Applications can use `Raft_Term` to detect when the cluster completes a new leader election.
 
@@ -84,9 +86,9 @@ In addition to just the key and value, etcd attaches additional revision metadat
 
 #### Revisions
 
-etcd maintains a 64-bit cluster-wide counter, the store revision, that is incremented each time the key space is modified. The revision serves as a global logical clock, sequentially ordering all updates to the store. The change represented by a new revisions is incremental; the data associated with a revision is the data that changed the store. Internally, a new revision means writing the changes to the backend's B+tree, keyed by the incremented revision.
+etcd maintains a 64-bit cluster-wide counter, the store revision, that is incremented each time the key space is modified. The revision serves as a global logical clock, sequentially ordering all updates to the store. The change represented by a new revision is incremental; the data associated with a revision is the data that changed the store. Internally, a new revision means writing the changes to the backend's B+tree, keyed by the incremented revision.
 
-Revisions become more valuable when taking considering etcd3's [multi-version concurrency control][mvcc] backend. The MVCC model means that the key-value store can be viewed from past revisions since historical key revisions are retained. The retention policy for this history can be configured by cluster administrators for fine-grained storage management; usually etcd3 discards old revisions of keys on a timer. A typical etcd3 cluster retains superseded key data for hours. This also buys reliable handling for long client disconnection, not just transient network disruptions: watchers simply resume from the last observed historical revision. Similarly, to read from the store at a particular point-in-time, read requests can be tagged with a revision to return keys from a view of the key space at the point in time that revision was committed.
+Revisions become more valuable when considering etcd3's [multi-version concurrency control][mvcc] backend. The MVCC model means that the key-value store can be viewed from past revisions since historical key revisions are retained. The retention policy for this history can be configured by cluster administrators for fine-grained storage management; usually etcd3 discards old revisions of keys on a timer. A typical etcd3 cluster retains superseded key data for hours. This also provides reliable handling for long client disconnection, not just transient network disruptions: watchers simply resume from the last observed historical revision. Similarly, to read from the store at a particular point-in-time, read requests can be tagged with a revision to return keys from a view of the key space at the point-in-time that revision was committed.
 
 #### Key ranges
 
@@ -94,7 +96,7 @@ The etcd3 data model indexes all keys over a flat binary key space. This differs
 
 These intervals are often referred to as "ranges" in etcd3. Operations over ranges are more powerful than operations on directories. Like a hierarchical store, intervals support single key lookups via `[a, a+1)` (e.g., ['a', 'a\x00') looks up 'a') and directory lookups by encoding keys by directory depth. In addition to those operations, intervals can also encode prefixes; for example  the interval `['a', 'b')` looks up all keys prefixed by the string 'a'.
 
-By convention, ranges for a Request are denoted by the fields `key` and `range_end`. The `key` field is the first key of the range and should be non-empty. The `range_end` is the key following the last key of the range. If `range_end` is not given or empty, the range is defined to contain only the key argument. If `range_end` is `key` plus one (e.g., "aa"+1 == "ab", "a\xff"+1 == "b"), then the range represents all keys prefixed with key. If both `key` and `range_end` are '\0', then range represents all keys. If `range_end` is '\0', the range is all keys greater than or equal to the key argument.
+By convention, ranges for a request are denoted by the fields `key` and `range_end`. The `key` field is the first key of the range and should be non-empty. The `range_end` is the key following the last key of the range. If `range_end` is not given or empty, the range is defined to contain only the key argument. If `range_end` is `key` plus one (e.g., "aa"+1 == "ab", "a\xff"+1 == "b"), then the range represents all keys prefixed with key. If both `key` and `range_end` are '\0', then range represents all keys. If `range_end` is '\0', the range is all keys greater than or equal to the key argument.
 
 ### Range
 
@@ -133,7 +135,7 @@ message RangeRequest {
 
 * Key, Range_End - The key range to fetch.
 * Limit - the maximum number of keys returned for the request. When limit is set to 0, it is treated as no limit.
-* Revision - the point-in-time of the key-value store to use for the range. If revision is less or equal to zero, the range is over the latest key-value store If the revision is compacted, ErrCompacted is returned as a response.
+* Revision - the point-in-time of the key-value store to use for the range. If revision is less or equal to zero, the range is over the latest key-value store. If the revision is compacted, ErrCompacted is returned as a response.
 * Sort_Order - the ordering for sorted requests.
 * Sort_Target - the key-value field to sort.
 * Serializable - sets the range request to use serializable member-local reads. By default, Range is linearizable; it reflects the current consensus of the cluster. For better performance and availability, in exchange for possible stale reads, a serializable range request is served locally without needing to reach consensus with other nodes in the cluster.
@@ -218,7 +220,7 @@ message DeleteRangeResponse {
 ```
 
 * Deleted - number of keys deleted.
-* Prev_Kv - a list of all key-value pairs deleted by the DeleteRange operation.
+* Prev_Kv - a list of all key-value pairs deleted by the `DeleteRange` operation.
 
 ### Transaction
 
@@ -226,7 +228,7 @@ A transaction is an atomic If/Then/Else construct over the key-value store. It p
 
 A transaction can atomically process multiple requests in a single request. For modifications to the key-value store, this means the store's revision is incremented only once for the transaction and all events generated by the transaction will have the same revision. However, modifications to the same key multiple times within a single transaction are forbidden.
 
-All transactions are guarded by a conjunction of comparisons, similar to an "If" statement. Each comparison checks a single key in the store. It may check for the absence or presence of a value, compare with a given value, or check a key's revision or version. Two different comparisons may apply to the same or different keys. All comparisons are applied atomically; if all comparisons are true, the transaction is said to succeed and etcd applies the transaction's then / `success` request block, otherwise it is said to fail and applies the else / `failure` request block.
+All transactions are guarded by a conjunction of comparisons, similar to an `If` statement. Each comparison checks a single key in the store. It may check for the absence or presence of a value, compare with a given value, or check a key's revision or version. Two different comparisons may apply to the same or different keys. All comparisons are applied atomically; if all comparisons are true, the transaction is said to succeed and etcd applies the transaction's then / `success` request block, otherwise it is said to fail and applies the else / `failure` request block.
 
 Each comparison is encoded as a `Compare` message:
 
@@ -321,7 +323,7 @@ message ResponseOp {
 
 ## Watch API
 
-The Watch API provides an event-based interface for asynchronously monitoring changes to keys. An etcd3 watch waits for changes to keys by continuously watching from a given revision, either current or historical, and streams key updates back to the client.
+The `Watch` API provides an event-based interface for asynchronously monitoring changes to keys. An etcd3 watch waits for changes to keys by continuously watching from a given revision, either current or historical, and streams key updates back to the client.
 
 ### Events
 
@@ -345,7 +347,7 @@ message Event {
 
 ### Watch streams
 
-Watches are long-running requests and use gRPC streams to stream event data. A watch stream is bi-directional; the client writes to the stream to establish watches and reads to receive watch event. A single watch stream can multiplex many distinct watches by tagging events with per-watch identifiers. This multiplexing helps reducing the memory footprint and connection overhead on the core etcd cluster.
+Watches are long-running requests and use gRPC streams to stream event data. A watch stream is bi-directional; the client writes to the stream to establish watches and reads to receive watch events. A single watch stream can multiplex many distinct watches by tagging events with per-watch identifiers. This multiplexing helps reducing the memory footprint and connection overhead on the core etcd cluster.
 
 Watches make three guarantees about events:
 * Ordered - events are ordered by revision; an event will never appear on a watch if it precedes an event in time that has already been posted.
@@ -391,7 +393,7 @@ message WatchResponse {
 ```
 
 * Watch_ID - the ID of the watch that corresponds to the response.
-* Created - set to true if the response is for a create watch request. The client should record ID and expect to receive events for the watch on the stream. All events sent to the created watcher will have the same watch_id.
+* Created - set to true if the response is for a create watch request. The client should store the ID and expect to receive events for the watch on the stream. All events sent to the created watcher will have the same watch_id.
 * Canceled - set to true if the response is for a cancel watch request. No further events will be sent to the canceled watcher.
 * Compact_Revision - set to the minimum historical revision available to etcd if a watcher tries watching at a compacted revision. This happens when creating a watcher at a compacted revision or the watcher cannot catch up with the progress of the key-value store. The watcher will be canceled; creating new watches with the same start_revision will fail.
 * Events - a list of new events in sequence corresponding to the given watch ID.
@@ -449,7 +451,7 @@ message LeaseRevokeRequest {
 
 ### Keep alives
 
-Leases are refreshed using a bi-directional stream created with the `LeaseKeepAlive` API call. When the client wishes to refresh a lease, it sends a `LeaseGrantRequest` over the stream:
+Leases are refreshed using a bi-directional stream created with the `LeaseKeepAlive` API call. When the client wishes to refresh a lease, it sends a `LeaseKeepAliveRequest` over the stream:
 
 ```protobuf
 message LeaseKeepAliveRequest {
@@ -472,10 +474,10 @@ message LeaseKeepAliveResponse {
 * ID - the lease that was refreshed with a new TTL.
 * TTL - the new time-to-live, in seconds, that the lease has remaining.
 
-[elections]: https://github.com/coreos/etcd/blob/master/clientv3/concurrency/election.go
-[kv-proto]: https://github.com/coreos/etcd/blob/master/mvcc/mvccpb/kv.proto
+[elections]: https://github.com/etcd-io/etcd/blob/master/clientv3/concurrency/election.go
+[kv-proto]: https://github.com/etcd-io/etcd/blob/master/mvcc/mvccpb/kv.proto
 [grpc-api]: ../dev-guide/api_reference_v3.md
-[grpc-service]: https://github.com/coreos/etcd/blob/master/etcdserver/etcdserverpb/rpc.proto
-[locks]: https://github.com/coreos/etcd/blob/master/clientv3/concurrency/mutex.go
+[grpc-service]: https://github.com/etcd-io/etcd/blob/master/etcdserver/etcdserverpb/rpc.proto
+[locks]: https://github.com/etcd-io/etcd/blob/master/clientv3/concurrency/mutex.go
 [mvcc]: https://en.wikipedia.org/wiki/Multiversion_concurrency_control
-[stm]: https://github.com/coreos/etcd/blob/master/clientv3/concurrency/stm.go
+[stm]: https://github.com/etcd-io/etcd/blob/master/clientv3/concurrency/stm.go

Documentation/learning/api_guarantees.md

@@ -1,4 +1,6 @@
-# KV API guarantees
+---
+title: KV API guarantees
+---
 
 etcd is a consistent and durable key value store with [mini-transaction][txn] support. The key value store is exposed through the KV APIs. etcd tries to ensure the strongest consistency and durability guarantees for a distributed system. This specification enumerates the KV API guarantees made by etcd.
 
@@ -51,7 +53,7 @@ Linearizability (also known as Atomic Consistency or External Consistency) is a
 
 For linearizability, suppose each operation receives a timestamp from a loosely synchronized global clock. Operations are linearized if and only if they always complete as though they were executed in a sequential order and each operation appears to complete in the order specified by the program. Likewise, if an operation’s timestamp precedes another, that operation must also precede the other operation in the sequence.
 
-For example, consider a client completing a write at time point 1 (*t1*). A client issuing a read at *t2* (for *t2* > *t1*) should receive a value at least as recent as the previous write, completed at *t1*. However, the read might actually complete only by *t3*, and the returned value, current at *t2* when the read began, might be "stale" by *t3*.
+For example, consider a client completing a write at time point 1 (*t1*). A client issuing a read at *t2* (for *t2* > *t1*) should receive a value at least as recent as the previous write, completed at *t1*. However, the read might actually complete only by *t3*. Linearizability guarantees the read returns the most current value. Without linearizability guarantee, the returned value, current at *t2* when the read began, might be "stale" by *t3* because a concurrent write might happen between *t2* and *t3*.
 
 etcd does not ensure linearizability for watch operations. Users are expected to verify the revision of watch responses to ensure correct ordering.
 

Documentation/learning/auth_design.md

@@ -1,4 +1,6 @@
-# etcd v3 authentication design
+---
+title: etcd v3 authentication design
+---
 
 ## Why not reuse the v2 auth system?
 
@@ -26,7 +28,7 @@ The metadata for auth should also be stored and managed in the storage controlle
 The authentication mechanism in the etcd v2 protocol has a tricky part because the metadata consistency should work as in the above, but does not: each permission check is processed by the etcd member that receives the client request (etcdserver/api/v2http/client.go), including follower members. Therefore, it's possible the check may be based on stale metadata.
 
 
-This staleness means that auth configuration cannot be reflected as soon as operators execute etcdctl. Therefore there is no way to know how long the stale metadata is active. Practically, the configuration change is reflected immediately after the command execution. However, in some cases of heavy load, the inconsistent state can be prolonged and it might result in counter-intuitive situations for users and developers. It requires a workaround like this: https://github.com/coreos/etcd/pull/4317#issuecomment-179037582
+This staleness means that auth configuration cannot be reflected as soon as operators execute etcdctl. Therefore there is no way to know how long the stale metadata is active. Practically, the configuration change is reflected immediately after the command execution. However, in some cases of heavy load, the inconsistent state can be prolonged and it might result in counter-intuitive situations for users and developers. It requires a workaround like this: https://github.com/etcd-io/etcd/pull/4317#issuecomment-179037582
 
 ### Inconsistent permissions are unsafe for linearized requests
 
@@ -38,7 +40,7 @@ Therefore, the permission checking logic should be added to the state machine of
 
 ### Authentication
 
-At first, a client must create a gRPC connection only to authenticate its user ID and password. An etcd server will respond with an authentication reply. The reponse will be an authentication token on success or an error on failure. The client can use its authentication token to present its credentials to etcd when making API requests.
+At first, a client must create a gRPC connection only to authenticate its user ID and password. An etcd server will respond with an authentication reply. The response will be an authentication token on success or an error on failure. The client can use its authentication token to present its credentials to etcd when making API requests.
 
 The client connection used to request the authentication token is typically thrown away; it cannot carry the new token's credentials. This is because gRPC doesn't provide a way for adding per RPC credential after creation of the connection (calling `grpc.Dial()`). Therefore, a client cannot assign a token to its connection that is obtained through the connection. The client needs a new connection for using the token.
 

Documentation/learning/client-architecture.md

@@ -0,0 +1,114 @@
+---
+title: etcd client architecture
+weight: 1
+---
+
+## Introduction
+
+etcd server has proven its robustness with years of failure injection testing. Most complex application logic is already handled by etcd server and its data stores (e.g. cluster membership is transparent to clients, with Raft-layer forwarding proposals to leader). Although server components are correct, its composition with client requires a different set of intricate protocols to guarantee its correctness and high availability under faulty conditions. Ideally, etcd server provides one logical cluster view of many physical machines, and client implements automatic failover between replicas. This documents client architectural decisions and its implementation details.
+
+## Glossary
+
+**clientv3** --- etcd Official Go client for etcd v3 API.
+
+**clientv3-grpc1.0** --- Official client implementation, with [grpc-go v1.0.x](https://github.com/grpc/grpc-go/releases/tag/v1.0.0), which is used in latest etcd v3.1.
+
+**clientv3-grpc1.7** --- Official client implementation, with [grpc-go v1.7.x](https://github.com/grpc/grpc-go/releases/tag/v1.7.0), which is used in latest etcd v3.2 and v3.3.
+
+**clientv3-grpc1.14** --- Official client implementation, with [grpc-go v1.14.x](https://github.com/grpc/grpc-go/releases/tag/v1.14.0), which is used in latest etcd v3.4.
+
+**Balancer** --- etcd client load balancer that implements retry and failover mechanism. etcd client should automatically balance loads between multiple endpoints.
+
+**Endpoints** --- A list of etcd server endpoints that clients can connect to. Typically, 3 or 5 client URLs of an etcd cluster.
+
+**Pinned endpoint** --- When configured with multiple endpoints, <= v3.3 client balancer chooses only one endpoint to establish a TCP connection, in order to conserve total open connections to etcd cluster. In v3.4, balancer round-robins pinned endpoints for every request, thus distributing loads more evenly.
+
+**Client Connection** --- TCP connection that has been established to an etcd server, via gRPC Dial.
+
+**Sub Connection** --- gRPC SubConn interface. Each sub-connection contains a list of addresses. Balancer creates a SubConn from a list of resolved addresses. gRPC ClientConn can map to multiple SubConn (e.g. example.com resolves to `10.10.10.1` and `10.10.10.2` of two sub-connections). etcd v3.4 balancer employs internal resolver to establish one sub-connection for each endpoint.
+
+**Transient disconnect** --- When gRPC server returns a status error of [code Unavailable](https://godoc.org/google.golang.org/grpc/codes#Code).
+
+## Client requirements
+
+**Correctness** --- Requests may fail in the presence of server faults. However, it never violates consistency guarantees: global ordering properties, never write corrupted data, at-most once semantics for mutable operations, watch never observes partial events, and so on.
+
+**Liveness** --- Servers may fail or disconnect briefly. Clients should make progress in either way. Clients should [never deadlock](https://github.com/etcd-io/etcd/issues/8980) waiting for a server to come back from offline, unless configured to do so. Ideally, clients detect unavailable servers with HTTP/2 ping and failover to other nodes with clear error messages.
+
+**Effectiveness** --- Clients should operate effectively with minimum resources: previous TCP connections should be [gracefully closed](https://github.com/etcd-io/etcd/issues/9212) after endpoint switch. Failover mechanism should effectively predict the next replica to connect, without wastefully retrying on failed nodes.
+
+**Portability** --- Official client should be clearly documented and its implementation be applicable to other language bindings. Error handling between different language bindings should be consistent. Since etcd is fully committed to gRPC, implementation should be closely aligned with gRPC long-term design goals (e.g. pluggable retry policy should be compatible with [gRPC retry](https://github.com/grpc/proposal/blob/master/A6-client-retries.md)). Upgrades between two client versions should be non-disruptive.
+
+## Client overview
+
+The etcd client implements the following components:
+
+* balancer that establishes gRPC connections to an etcd cluster,
+* API client that sends RPCs to an etcd server, and
+* error handler that decides whether to retry a failed request or switch endpoints.
+
+Languages may differ in how to establish an initial connection (e.g. configure TLS), how to encode and send Protocol Buffer messages to server, how to handle stream RPCs, and so on. However, errors returned from etcd server will be the same. So should be error handling and retry policy.
+
+For example, etcd server may return `"rpc error: code = Unavailable desc = etcdserver: request timed out"`, which is transient error that expects retries. Or return `rpc error: code = InvalidArgument desc = etcdserver: key is not provided`, which means request was invalid and should not be retried. Go client can parse errors with `google.golang.org/grpc/status.FromError`, and Java client with `io.grpc.Status.fromThrowable`.
+
+### clientv3-grpc1.0: Balancer Overview
+
+`clientv3-grpc1.0` maintains multiple TCP connections when configured with multiple etcd endpoints. Then pick one address and use it to send all client requests. The pinned address is maintained until the client object is closed (see *Figure 1*). When the client receives an error, it randomly picks another and retries.
+
+{{< figure src="/img/client-architecture-balancer-figure-01.png" >}}
+
+### clientv3-grpc1.0: Balancer Limitation
+
+`clientv3-grpc1.0` opening multiple TCP connections may provide faster balancer failover but requires more resources. The balancer does not understand node’s health status or cluster membership. So, it is possible that balancer gets stuck with one failed or partitioned node.
+
+### clientv3-grpc1.7: Balancer Overview
+
+`clientv3-grpc1.7` maintains only one TCP connection to a chosen etcd server. When given multiple cluster endpoints, a client first tries to connect to them all. As soon as one connection is up, balancer pins the address, closing others (see **Figure 2**).
+
+{{< figure src="/img/client-architecture-balancer-figure-02.png" >}}
+
+The pinned address is to be maintained until the client object is closed. An error, from server or client network fault, is sent to client error handler (see **Figure 3**).
+
+{{< figure src="/img/client-architecture-balancer-figure-03.png" >}}
+
+The client error handler takes an error from gRPC server, and decides whether to retry on the same endpoint, or to switch to other addresses, based on the error code and message (see **Figure 4** and **Figure 5**).
+
+{{< figure src="/img/client-architecture-balancer-figure-04.png" >}}
+
+{{< figure src="/img/client-architecture-balancer-figure-05.png" >}}
+
+Stream RPCs, such as Watch and KeepAlive, are often requested with no timeouts. Instead, client can send periodic HTTP/2 pings to check the status of a pinned endpoint; if the server does not respond to the ping, balancer switches to other endpoints (see **Figure 6**).
+
+{{< figure src="/img/client-architecture-balancer-figure-06.png" >}}
+
+### clientv3-grpc1.7: Balancer Limitation
+
+`clientv3-grpc1.7` balancer sends HTTP/2 keepalives to detect disconnects from streaming requests. It is a simple gRPC server ping mechanism and does not reason about cluster membership, thus unable to detect network partitions. Since partitioned gRPC server can still respond to client pings, balancer may get stuck with a partitioned node. Ideally, keepalive ping detects partition and triggers endpoint switch, before request time-out (see [issue #8673](https://github.com/etcd-io/etcd/issues/8673) and **Figure 7**).
+
+{{< figure src="/img/client-architecture-balancer-figure-07.png" >}}
+
+`clientv3-grpc1.7` balancer maintains a list of unhealthy endpoints. Disconnected addresses are added to “unhealthy” list, and considered unavailable until after wait duration, which is hard coded as dial timeout with default value 5-second. Balancer can have false positives on which endpoints are unhealthy. For instance, endpoint A may come back right after being blacklisted, but still unusable for next 5 seconds (see **Figure 8**).
+
+`clientv3-grpc1.0` suffered the same problems above.
+
+{{< figure src="/img/client-architecture-balancer-figure-08.png" >}}
+
+Upstream gRPC Go had already migrated to new balancer interface. For example, `clientv3-grpc1.7` underlying balancer implementation uses new gRPC balancer and tries to be consistent with old balancer behaviors. While its compatibility has been maintained reasonably well, etcd client still [suffered from subtle breaking changes](https://github.com/grpc/grpc-go/issues/1649). Furthermore, gRPC maintainer recommends [not relying on the old balancer interface](https://github.com/grpc/grpc-go/issues/1942#issuecomment-375368665). In general, to get better support from upstream, it is best to be in sync with latest gRPC releases. And new features, such as retry policy, may not be backported to gRPC 1.7 branch. Thus, both etcd server and client must migrate to latest gRPC versions.
+
+### clientv3-grpc1.14: Balancer Overview
+
+`clientv3-grpc1.7` is so tightly coupled with old gRPC interface, that every single gRPC dependency upgrade broke client behavior. Majority of development and debugging efforts were devoted to fixing those client behavior changes. As a result, its implementation has become overly complicated with bad assumptions on server connectivities.
+
+The primary goal of `clientv3-grpc1.14` is to simplify balancer failover logic; rather than maintaining a list of unhealthy endpoints, which may be stale, simply roundrobin to the next endpoint whenever client gets disconnected from the current endpoint. It does not assume endpoint status. Thus, no more complicated status tracking is needed (see *Figure 8* and above). Upgrading to `clientv3-grpc1.14` should be no issue; all changes were internal while keeping all the backward compatibilities.
+
+Internally, when given multiple endpoints, `clientv3-grpc1.14` creates multiple sub-connections (one sub-connection per each endpoint), while `clientv3-grpc1.7` creates only one connection to a pinned endpoint (see *Figure 9*). For instance, in 5-node cluster, `clientv3-grpc1.14` balancer would require 5 TCP connections, while `clientv3-grpc1.7` only requires one. By preserving the pool of TCP connections, `clientv3-grpc1.14` may consume more resources but provide more flexible load balancer with better failover performance. The default balancing policy is round robin but can be easily extended to support other types of balancers (e.g. power of two, pick leader, etc.). `clientv3-grpc1.14` uses gRPC resolver group and implements balancer picker policy, in order to delegate complex balancing work to upstream gRPC. On the other hand, `clientv3-grpc1.7` manually handles each gRPC connection and balancer failover, which complicates the implementation. `clientv3-grpc1.14` implements retry in the gRPC interceptor chain that automatically handles gRPC internal errors and enables more advanced retry policies like backoff, while `clientv3-grpc1.7` manually interprets gRPC errors for retries.
+
+{{< figure src="/img/client-architecture-balancer-figure-09.png" >}}
+
+### clientv3-grpc1.14: Balancer Limitation
+
+Improvements can be made by caching the status of each endpoint. For instance, balancer can ping each server in advance to maintain a list of healthy candidates, and use this information when doing round-robin. Or when disconnected, balancer can prioritize healthy endpoints. This may complicate the balancer implementation, thus can be addressed in later versions.
+
+Client-side keepalive ping still does not reason about network partitions. Streaming request may get stuck with a partitioned node. Advanced health checking service need to be implemented to understand the cluster membership (see [issue #8673](https://github.com/etcd-io/etcd/issues/8673) for more detail).
+
+Currently, retry logic is handled manually as an interceptor. This may be simplified via [official gRPC retries](https://github.com/grpc/proposal/blob/master/A6-client-retries.md).

Documentation/learning/client-feature-matrix.md

@@ -0,0 +1,157 @@
+---
+title: Client feature matrix
+---
+
+## Features
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+Automatic retry | Yes | .
+Retry backoff | Yes | .
+Automatic failover | Yes | .
+Load balancer |	Round-Robin | ·
+`WithRequireLeader(context.Context)` | Yes | .
+`TLS` | Yes | Yes
+`SetEndpoints` | Yes | .
+`Sync` endpoints | Yes | .
+`AutoSyncInterval` | Yes | .
+`KeepAlive` ping | Yes | .
+`MaxCallSendMsgSize` | Yes | .
+`MaxCallRecvMsgSize` | Yes | .
+`RejectOldCluster` | Yes | .
+
+## [KV](https://godoc.org/go.etcd.io/etcd/clientv3#KV)
+
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`Put` | Yes | .
+`Get` | Yes | .
+`Delete` | Yes | .
+`Compact` | Yes | .
+`Do(Op)` | Yes | .
+`Txn` | Yes | .
+
+## [Lease](https://godoc.org/go.etcd.io/etcd/clientv3#Lease)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`Grant` | Yes | .
+`Revoke` | Yes | .
+`TimeToLive` | Yes | .
+`Leases` | Yes | .
+`KeepAlive` | Yes | .
+`KeepAliveOnce` | Yes | .
+
+## [Watcher](https://godoc.org/go.etcd.io/etcd/clientv3#Watcher)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`Watch` | Yes | Yes
+`RequestProgress` | Yes | .
+
+## [Cluster](https://godoc.org/go.etcd.io/etcd/clientv3#Cluster)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`MemberList` | Yes | Yes
+`MemberAdd` | Yes | Yes
+`MemberRemove` | Yes | Yes
+`MemberUpdate` | Yes | Yes
+
+## [Maintenance](https://godoc.org/go.etcd.io/etcd/clientv3#Maintenance)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`AlarmList` | Yes | Yes
+`AlarmDisarm` | Yes | ·
+`Defragment` | Yes | ·
+`Status` | Yes | ·
+`HashKV` | Yes | ·
+`Snapshot` | Yes | ·
+`MoveLeader` | Yes | ·
+
+## [Auth](https://godoc.org/go.etcd.io/etcd/clientv3#Auth)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`AuthEnable` | Yes | .
+`AuthDisable` | Yes | .
+`UserAdd` | Yes | .
+`UserDelete` | Yes | .
+`UserChangePassword` | Yes | .
+`UserGrantRole` | Yes | .
+`UserGet` | Yes | .
+`UserList` | Yes | .
+`UserRevokeRole` | Yes | .
+`RoleAdd` | Yes | .
+`RoleGrantPermission` | Yes | .
+`RoleGet` | Yes | .
+`RoleList` | Yes | .
+`RoleRevokePermission` | Yes | .
+`RoleDelete` | Yes | .
+
+## [clientv3util](https://godoc.org/go.etcd.io/etcd/clientv3/clientv3util)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`KeyExists` | Yes | No
+`KeyMissing` | Yes | No
+
+## [Concurrency](https://godoc.org/go.etcd.io/etcd/clientv3/concurrency)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`Session` | Yes | No
+`NewMutex(Session, prefix)` | Yes | No
+`NewElection(Session, prefix)` | Yes | No
+`NewLocker(Session, prefix)` | Yes | No
+`STM Isolation SerializableSnapshot` | Yes | No
+`STM Isolation Serializable` | Yes | No
+`STM Isolation RepeatableReads` | Yes | No
+`STM Isolation ReadCommitted` | Yes | No
+`STM Get` | Yes | No
+`STM Put` | Yes | No
+`STM Rev` | Yes | No
+`STM Del` | Yes | No
+
+## [Leasing](https://godoc.org/go.etcd.io/etcd/clientv3/leasing)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`NewKV(Client, prefix)` | Yes | No
+
+## [Mirror](https://godoc.org/go.etcd.io/etcd/clientv3/mirror)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`SyncBase` | Yes | No
+`SyncUpdates` | Yes | No
+
+## [Namespace](https://godoc.org/go.etcd.io/etcd/clientv3/namespace)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`KV` | Yes | No
+`Lease` | Yes | No
+`Watcher` | Yes | No
+
+## [Naming](https://godoc.org/go.etcd.io/etcd/clientv3/naming)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`GRPCResolver` | Yes | No
+
+## [Ordering](https://godoc.org/go.etcd.io/etcd/clientv3/ordering)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`KV` | Yes | No
+
+## [Snapshot](https://godoc.org/go.etcd.io/etcd/clientv3/snapshot)
+
+Feature | `clientv3-grpc1.14` | `jetcd v0.0.2`
+:-------|:--------------------|:--------------
+`Save` | Yes | No
+`Status` | Yes | No
+`Restore` | Yes | No

Documentation/learning/data_model.md

@@ -1,20 +1,22 @@
-# Data model
+---
+title: Data model
+---
 
 etcd is designed to reliably store infrequently updated data and provide reliable watch queries. etcd exposes previous versions of key-value pairs to support inexpensive snapshots and watch history events (“time travel queries”). A persistent, multi-version, concurrency-control data model is a good fit for these use cases.
 
-etcd stores data in a multiversion [persistent][persistent-ds] key-value store. The persistent key-value store preserves the previous version of a key-value pair when its value is superseded with new data. The key-value store is effectively immutable; its operations do not update the structure in-place, but instead always generates a new updated structure. All past versions of keys are still accessible and watchable after modification. To prevent the data store from growing indefinitely over time from maintaining old versions, the store may be compacted to shed the oldest versions of superseded data.
+etcd stores data in a multiversion [persistent][persistent-ds] key-value store. The persistent key-value store preserves the previous version of a key-value pair when its value is superseded with new data. The key-value store is effectively immutable; its operations do not update the structure in-place, but instead always generate a new updated structure. All past versions of keys are still accessible and watchable after modification. To prevent the data store from growing indefinitely over time and from maintaining old versions, the store may be compacted to shed the oldest versions of superseded data.
 
 ### Logical view
 
 The store’s logical view is a flat binary key space. The key space has a lexically sorted index on byte string keys so range queries are inexpensive.
 
-The key space maintains multiple revisions. Each atomic mutative operation (e.g., a transaction operation may contain multiple operations) creates a new revision on the key space. All data held by previous revisions remains unchanged. Old versions of key can still be accessed through previous revisions. Likewise, revisions are indexed as well; ranging over revisions with watchers is efficient. If the store is compacted to recover space, revisions before the compact revision will be removed.
+The key space maintains multiple **revisions**. Each atomic mutative operation (e.g., a transaction operation may contain multiple operations) creates a new revision on the key space. All data held by previous revisions remains unchanged. Old versions of key can still be accessed through previous revisions. Likewise, revisions are indexed as well; ranging over revisions with watchers is efficient. If the store is compacted to save space, revisions before the compact revision will be removed. Revisions are monotonically increasing over the lifetime of a cluster.
 
-A key’s lifetime spans a generation. Each key may have one or multiple generations. Creating a key increments the generation of that key, starting at 1 if the key never existed. Deleting a key generates a key tombstone, concluding the key’s current generation. Each modification of a key creates a new version of the key. Once a compaction happens, any generation ended before the given revision will be removed and values set before the compaction revision except the latest one will be removed.
+A key's life spans a generation, from creation to deletion. Each key may have one or multiple generations. Creating a key increments the **version** of that key, starting at 1 if the key does not exist at the current revision. Deleting a key generates a key tombstone, concluding the key’s current generation by resetting its version to 0. Each modification of a key increments its version; so, versions are monotonically increasing within a key's generation. Once a compaction happens, any generation ended before the compaction revision will be removed, and values set before the compaction revision except the latest one will be removed.
 
 ### Physical view
 
-etcd stores the physical data as key-value pairs in a persistent [b+tree][b+tree]. Each revision of the store’s state only contains the delta from its previous revision to be efficient. A single revision may correspond to multiple keys in the tree. 
+etcd stores the physical data as key-value pairs in a persistent [b+tree][b+tree]. Each revision of the store’s state only contains the delta from its previous revision to be efficient. A single revision may correspond to multiple keys in the tree.
 
 The key of key-value pair is a 3-tuple (major, sub, type). Major is the store revision holding the key. Sub differentiates among  keys within the same revision. Type is an optional suffix for special value (e.g., `t` if the value contains a tombstone). The value of the key-value pair contains the modification from previous revision, thus one delta from previous revision. The b+tree is ordered by key in lexical byte-order. Ranged lookups over revision deltas are fast; this enables quickly finding modifications from one specific revision to another. Compaction removes out-of-date keys-value pairs.
 

Documentation/learning/glossary.md

@@ -1,4 +1,6 @@
-# Glossary
+---
+title: Glossary
+---
 
 This document defines the various terms used in etcd documentation, command line and source code.
 

Documentation/learning/learner.md

@@ -0,0 +1,106 @@
+---
+title: Learner
+---
+
+## Background
+
+Membership reconfiguration has been one of the biggest operational challenges. Let’s review common challenges.
+
+A newly joined etcd member starts with no data, thus demanding more updates from leader until it catches up with leader’s logs. Then leader’s network is more likely to be overloaded, blocking or dropping leader heartbeats to followers. In such case, a follower may election-timeout to start a new leader election. That is, a cluster with a new member is more vulnerable to leader election. Both leader election and the subsequent update propagation to the new member are prone to causing periods of cluster unavailability (see **Figure 1** below).
+
+{{< figure src="/img/server-learner-figure-01.png" >}}
+
+What if network partition happens? It depends on leader partition. If the leader still maintains the active quorum, the cluster would continue to operate (see **Figure 2**).
+
+{{< figure src="/img/server-learner-figure-02.png" >}}
+
+What if the leader becomes isolated from the rest of the cluster? Leader monitors progress of each follower. When leader loses connectivity from the quorum it reverts back to follower which will affect the cluster availability (see **Figure 3**).
+
+{{< figure src="/img/server-learner-figure-03.png" >}}
+
+When a new node is added to 3 node cluster, the cluster size becomes 4 and the quorum size becomes 3. What if a new node had joined the cluster, and then network partition happens? It depends on which partition the new member gets located after partition. If the new node happens to be located in the same partition as leader’s, the leader still maintains the active quorum of 3. No leadership election happens, and no cluster availability gets affected (see **Figure 4**).
+
+{{< figure src="/img/server-learner-figure-04.png" >}}
+
+If the cluster is 2-and-2 partitioned, then neither of partition maintains the quorum of 3. In this case, leadership election happens (see **Figure 5**).
+
+{{< figure src="/img/server-learner-figure-05.png" >}}
+
+What if network partition happens first, and then a new member gets added? A partitioned 3-node cluster already has one disconnected follower. When a new member is added, the quorum changes from 2 to 3. Now, this cluster has only 2 active nodes out 4, thus losing quorum and starting a new leadership election (see **Figure 6**).
+
+{{< figure src="/img/server-learner-figure-06.png" >}}
+
+Since member add operation can change the size of quorum, it is always recommended to “member remove” first to replace an unhealthy node.
+
+Adding a new member to a 1-node cluster changes the quorum size to 2, immediately causing a leader election when the previous leader finds out quorum is not active. This is because “member add” operation is a 2-step process where user needs to apply “member add” command first, and then starts the new node process (see **Figure 7**).
+
+{{< figure src="/img/server-learner-figure-07.png" >}}
+
+An even worse case is when an added member is misconfigured. Membership reconfiguration is a two-step process: “etcdctl member add” and starting an etcd server process with the given peer URL. That is, “member add” command is applied regardless of URL, even when the URL value is invalid. If the first step is applied with invalid URLs, the second step cannot even start the new etcd. Once the cluster loses quorum, there is no way to revert the membership change (see **Figure 8**).
+
+{{< figure src="/img/server-learner-figure-08.png" >}}
+
+Same applies to a multi-node cluster. For example, the cluster has two members down (one is failed, the other is misconfigured) and two members up, but now it requires at least 3 votes to change the cluster membership (see **Figure 9**).
+
+{{< figure src="/img/server-learner-figure-09.png" >}}
+
+As seen above, a simple misconfiguration can fail the whole cluster into an inoperative state. In such case, an operator need manually recreate the cluster with `etcd --force-new-cluster` flag. As etcd has become a mission-critical service for [Kubernetes](https://kubernetes.io), even the slightest outage may have significant impact on users. What can we better to make etcd such operations easier? Among other things, leader election is most critical to cluster availability: Can we make membership reconfiguration less disruptive by not changing the size of quorum? Can a new node be idle, only requesting the minimum updates from leader, until it catches up? Can membership misconfiguration be always reversible and handled in a more secure way (wrong member add command run should never fail the cluster)? Should an user worry about network topology when adding a new member? Can member add API work regardless of the location of nodes and ongoing network partitions?
+
+## Raft learner
+
+In order to mitigate such availability gaps in the previous section, [Raft §4.2.1](https://ramcloud.stanford.edu/~ongaro/thesis.pdf) introduces a new node state “Learner,” which joins the cluster as a **non-voting member** until it catches up to the leader’s logs.
+
+## Features in v3.4
+
+An operator should do the minimum amount of work possible to add a new learner node. `member add --learner` command to add a new learner, which joins cluster as a non-voting member but still receives all data from leader (see **Figure 10**).
+
+{{< figure src="/img/server-learner-figure-10.png" >}}
+
+When a learner has caught up with leader’s progress, the learner can be promoted to a voting member using the `member promote` API, which then counts towards the quorum (see **Figure 11**).
+
+{{< figure src="/img/server-learner-figure-11.png" >}}
+
+etcd server validates promote request to ensure its operational safety. Only after its log has caught up to leader’s can learner be promoted to a voting member (see **Figure 12**).
+
+{{< figure src="/img/server-learner-figure-12.png" >}}
+
+Learner only serves as a standby node until promoted: Leadership cannot be transferred to learner. Learner rejects client reads and writes (client balancer should not route requests to learner). Which means learner does not need issue Read Index requests to leader. Such limitation simplifies the initial learner implementation in v3.4 release (see **Figure 13**).
+
+{{< figure src="/img/server-learner-figure-13.png" >}}
+
+In addition, etcd limits the total number of learners that a cluster can have, and avoids overloading the leader with log replication. Learner never promotes itself. While etcd provides learner status information and safety checks, cluster operator must make the final decision whether to promote learner or not.
+
+## Features in v3.5
+
+**Make learner state only and default** --- Defaulting a new member state to learner will greatly improve membership reconfiguration safety, because learner does not change the size of quorum. Misconfiguration will always be reversible without losing the quorum.
+
+**Make voting-member promotion fully automatic** --- Once a learner catches up to leader’s logs, a cluster can automatically promote the learner. etcd requires certain thresholds to be defined by the user, and once the requirements are satisfied, learner promotes itself to a voting member. From a user’s perspective, “member add” command would work the same way as today but with greater safety provided by learner feature.
+
+**Make learner standby failover node** --- A learner joins as a standby node, and gets automatically promoted when the cluster availability is affected.
+
+**Make learner read-only** --- A learner can serve as a read-only node that never gets promoted. In a weak consistency mode, learner only receives data from leader and never process writes. Serving reads locally without consensus overhead would greatly decrease the workloads to leader but may serve stale data. In a strong consistency mode, learner requests read index from leader to serve latest data, but still rejects writes.
+
+## Learner vs. mirror maker
+
+etcd implements “mirror maker” using watch API to continuously relay key creates and updates to a separate cluster. Mirroring usually has low latency overhead once it completes initial synchronization. Learner and mirroring overlap in that both can be used to replicate existing data for read-only. However, mirroring does not guarantee linearizability. During network disconnects, previous key-values might have been discarded, and clients are expected to verify watch responses for correct ordering. Thus, there is no ordering guarantee in mirror. Use mirror for minimum latency (e.g. cross data center) at the costs of consistency. Use learner to retain all historical data and its ordering.
+
+## Appendix: learner implementation in v3.4
+
+### Expose "Learner" node type to "MemberAdd" API
+
+etcd client adds a flag to “MemberAdd” API for learner node. And etcd server handler applies membership change entry with `pb.ConfChangeAddLearnerNode` type. Once the command has been applied, a server joins the cluster with `etcd --initial-cluster-state=existing` flag. This learner node can neither vote nor count as quorum.
+
+etcd server must not transfer leadership to learner, since it may still lag behind and does not count as quorum. etcd server limits the number of learners that cluster can have to one: the more learners we have, the more data the leader has to propagate. Clients may talk to learner node, but learner rejects all requests other than serializable read and member status API. This is for simplicity of initial implementation. In the future, learner can be extended as a read-only server that continuously mirrors cluster data. Client balancer must provide helper function to exclude learner node endpoint. Otherwise, request sent to learner may fail. Client sync member call should factor into learner node type. So should client endpoints update call.
+
+`MemberList` and `MemberStatus` responses should indicate which node is learner.
+
+### Add "MemberPromote" API
+
+Internally in Raft, second `MemberAdd` call to learner node promotes it to a voting member. Leader maintains the progress of each follower and learner. If learner has not completed its snapshot message, reject promote request. Only accept promote request if and only if: The learner node is in a healthy state. The learner is in sync with leader or the delta is within the threshold (e.g. the number of entries to replicate to learner is less than 1/10 of snapshot count, which means it is less likely that even after promotion leader would not need send snapshot to the learner). All these logic are hard-coded in `etcdserver` package and not configurable.
+
+## Reference
+
+* Original GitHub issue ([issue #9161](https://github.com/etcd-io/etcd/issues/9161))
+* Use case ([issue #3715](https://github.com/etcd-io/etcd/issues/3715))
+* Use case ([issue #8888](https://github.com/etcd-io/etcd/issues/8888))
+* Use case ([issue #10114](https://github.com/etcd-io/etcd/issues/10114))

Documentation/learning/why.md

@@ -1,17 +1,19 @@
-# Why etcd
+---
+title: etcd versus other key-value stores
+---
 
-The name "etcd" originated from two ideas, the unix "/etc" folder and "d"istibuted systems. The "/etc" folder is a place to store configuration data for a single system whereas etcd stores configuration information for large scale distributed systems. Hence, a "d"istributed "/etc" is "etcd".
+The name "etcd" originated from two ideas, the unix "/etc" folder and "d"istributed systems. The "/etc" folder is a place to store configuration data for a single system whereas etcd stores configuration information for large scale distributed systems. Hence, a "d"istributed "/etc" is "etcd".
 
-etcd stores metadata in a consistent and fault-tolerant way. Distributed systems use etcd as a consistent key-value store for configuration management, service discovery, and coordinating distributed work. Common distributed patterns using etcd include [leader election][etcd-etcdctl-elect], [distributed locks][etcd-etcdctl-lock], and monitoring machine liveness.
+etcd is designed as a general substrate for large scale distributed systems. These are systems that will never tolerate split-brain operation and are willing to sacrifice availability to achieve this end. etcd stores metadata in a consistent and fault-tolerant way. An etcd cluster is meant to provide key-value storage with best of class stability, reliability, scalability and performance.
+
+Distributed systems use etcd as a consistent key-value store for configuration management, service discovery, and coordinating distributed work. Many [organizations][production-users] use etcd to implement production systems such as container schedulers, service discovery services, and distributed data storage. Common distributed patterns using etcd include [leader election][etcd-etcdctl-elect], [distributed locks][etcd-etcdctl-lock], and monitoring machine liveness.
 
 ## Use cases
 
-- Container Linux by CoreOS: Application running on [Container Linux][container-linux] gets automatic, zero-downtime Linux kernel updates. Container Linux uses [locksmith] to coordinate updates. locksmith implements a distributed semaphore over etcd to ensure only a subset of a cluster is rebooting at any given time.
+- Container Linux by CoreOS: Applications running on [Container Linux][container-linux] get automatic, zero-downtime Linux kernel updates. Container Linux uses [locksmith] to coordinate updates. Locksmith implements a distributed semaphore over etcd to ensure only a subset of a cluster is rebooting at any given time.
 - [Kubernetes][kubernetes] stores configuration data into etcd for service discovery and cluster management; etcd's consistency is crucial for correctly scheduling and operating services. The Kubernetes API server persists cluster state into etcd. It uses etcd's watch API to monitor the cluster and roll out critical configuration changes.
 
-## etcd versus other key-value stores
-
-When deciding whether to use etcd as a key-value store, it’s worth keeping in mind etcd’s main goal. Namely, etcd is designed as a general substrate for large scale distributed systems. These are systems that will never tolerate split-brain operation and are willing to sacrifice availability to achieve this end. An etcd cluster is meant to provide consistent key-value storage with best of class stability, reliability, scalability and performance. The upshot of this focus is many [organizations][production-users] already use etcd to implement production systems such as container schedulers, service discovery services, distributed data storage, and more.
+## Comparison chart
 
 Perhaps etcd already seems like a good fit, but as with all technological decisions, proceed with caution. Please note this documentation is written by the etcd team. Although the ideal is a disinterested comparison of technology and features, the authors’ expertise and biases obviously favor etcd. Use only as directed.
 
@@ -47,7 +49,7 @@ When considering features, support, and stability, new applications planning to
 
 ### Consul
 
-Consul bills itself as an end-to-end service discovery framework. To wit, it includes services such as health checking, failure detection, and DNS. Incidentally, Consul also exposes a key value store with mediocre performance and an intricate API. As it stands in Consul 0.7, the storage system does not scales well; systems requiring millions of keys will suffer from high latencies and memory pressure. The key value API is missing, most notably, multi-version keys, conditional transactions, and reliable streaming watches.
+Consul is an end-to-end service discovery framework. It provides built-in health checking, failure detection, and DNS services. In addition, Consul exposes a key value store with RESTful HTTP APIs. [As it stands in Consul 1.0][dbtester-comparison-results], the storage system does not scale as well as other systems like etcd or Zookeeper in key-value operations; systems requiring millions of keys will suffer from high latencies and memory pressure. The key value API is missing, most notably, multi-version keys, conditional transactions, and reliable streaming watches.
 
 etcd and Consul solve different problems. If looking for a distributed consistent key value store, etcd is a better choice over Consul. If looking for end-to-end cluster service discovery, etcd will not have enough features; choose Kubernetes, Consul, or SmartStack.
 
@@ -76,18 +78,18 @@ In theory, it’s possible to build these primitives atop any storage systems pr
 For distributed coordination, choosing etcd can help prevent operational headaches and save engineering effort.
 
 [production-users]: ../production-users.md
-[grpc]: http://www.grpc.io
+[grpc]: https://www.grpc.io
 [consul-bulletproof]: https://www.consul.io/docs/internals/sessions.html
 [curator]: http://curator.apache.org/
 [cockroach]: https://github.com/cockroachdb/cockroach
 [spanner]: https://cloud.google.com/spanner/
 [tidb]: https://github.com/pingcap/tidb
-[etcd-v3lock]: https://godoc.org/github.com/coreos/etcd/etcdserver/api/v3lock/v3lockpb
-[etcd-v3election]: https://godoc.org/github.com/coreos/etcd/etcdserver/api/v3election/v3electionpb
-[etcd-etcdctl-lock]: ../../etcdctl/README.md#lock-lockname
+[etcd-v3lock]: https://godoc.org/github.com/etcd-io/etcd/etcdserver/api/v3lock/v3lockpb
+[etcd-v3election]: https://godoc.org/github.com/coreos/etcd-io/etcdserver/api/v3election/v3electionpb
+[etcd-etcdctl-lock]: ../../etcdctl/README.md#lock-lockname-command-arg1-arg2-
 [etcd-etcdctl-elect]: ../../etcdctl/README.md#elect-options-election-name-proposal
 [etcd-mvcc]: data_model.md
-[etcd-recipe]: https://godoc.org/github.com/coreos/etcd/contrib/recipes
+[etcd-recipe]: https://godoc.org/github.com/etcd-io/etcd/contrib/recipes
 [consul-lock]: https://www.consul.io/docs/commands/lock.html
 [newsql-leader]: http://dl.acm.org/citation.cfm?id=2960999
 [etcd-reconfig]: ../op-guide/runtime-configuration.md
@@ -107,10 +109,10 @@ For distributed coordination, choosing etcd can help prevent operational headach
 [etcd-rbac]: ../op-guide/authentication.md#working-with-roles
 [zk-acl]: https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html#sc_ZooKeeperAccessControl
 [consul-acl]: https://www.consul.io/docs/internals/acl.html
-[cockroach-grant]: https://www.cockroachlabs.com/docs/grant.html
+[cockroach-grant]: https://www.cockroachlabs.com/docs/stable/grant.html
 [spanner-roles]: https://cloud.google.com/spanner/docs/iam#roles
 [zk-bindings]: https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html#ch_bindings
 [container-linux]: https://coreos.com/why
 [locksmith]: https://github.com/coreos/locksmith
-[kubernetes]: http://kubernetes.io/docs/whatisk8s
-
+[kubernetes]: https://kubernetes.io/docs/concepts/overview/what-is-kubernetes/
+[dbtester-comparison-results]: https://github.com/coreos/dbtester/tree/master/test-results/2018Q1-02-etcd-zookeeper-consul

Documentation/metrics.md

@@ -1,4 +1,7 @@
-# Metrics
+---
+title: Metrics
+weight: 3
+---
 
 etcd uses [Prometheus][prometheus] for metrics reporting. The metrics can be used for real-time monitoring and debugging. etcd does not persist its metrics; if a member restarts, the metrics will be reset.
 
@@ -99,7 +102,7 @@ Abnormally high snapshot duration (`snapshot_save_total_duration_seconds`) indic
 
 ## Prometheus supplied metrics
 
-The Prometheus client library provides a number of metrics under the `go` and `process` namespaces. There are a few that are particlarly interesting.
+The Prometheus client library provides a number of metrics under the `go` and `process` namespaces. There are a few that are particularly interesting.
 
 | Name                              | Description                                | Type         |
 |-----------------------------------|--------------------------------------------|--------------|
@@ -113,4 +116,4 @@ Heavy file descriptor (`process_open_fds`) usage (i.e., near the process's file
 [prometheus-getting-started]: http://prometheus.io/docs/introduction/getting_started/
 [prometheus-naming]: http://prometheus.io/docs/practices/naming/
 [v2-http-metrics]: v2/metrics.md#http-requests
-[go-grpc-prometheus]: https://github.com/grpc-ecosystem/go-grpc-prometheus
+[go-grpc-prometheus]: https://github.com/grpc-ecosystem/go-grpc-prometheus

Documentation/op-guide/_index.md

@@ -0,0 +1,3 @@
+---
+title: Operations guide
+---

Documentation/op-guide/authentication.md

@@ -1,8 +1,10 @@
-# Authentication Guide
+---
+title: Role-based access control
+---
 
 ## Overview
 
-Authentication was added in etcd 2.1. The etcd v3 API slightly modified the authentication feature's API and user interface to better fit the new data model. This guide is intended to help users set up basic authentication in etcd v3.
+Authentication was added in etcd 2.1. The etcd v3 API slightly modified the authentication feature's API and user interface to better fit the new data model. This guide is intended to help users set up basic authentication and role-based access control in etcd v3.
 
 ## Special users and roles
 
@@ -32,7 +34,7 @@ Creating a user is as easy as
 $ etcdctl user add myusername
 ```
 
-Creating a new user will prompt for a new password. The password can be supplied from standard input when an option `--interactive=false` is given.
+Creating a new user will prompt for a new password. The password can be supplied from standard input when an option `--interactive=false` is given. `--new-user-password` can also be used for supplying the password.
 
 Roles can be granted and revoked for a user with:
 
@@ -122,12 +124,12 @@ $ etcdctl role remove myrolename
 
 ## Enabling authentication
 
-The minimal steps to enabling auth are as follows. The administrator can set up users and roles before or after enabling authentication, as a matter of preference. 
+The minimal steps to enabling auth are as follows. The administrator can set up users and roles before or after enabling authentication, as a matter of preference.
 
 Make sure the root user is created:
 
 ```
-$ etcdctl user add root 
+$ etcdctl user add root
 Password of root:
 ```
 
@@ -157,8 +159,18 @@ The password can be taken from a prompt:
 $ etcdctl --user user get foo
 ```
 
+The password can also be taken from a command line flag `--password`:
+
+```
+$ etcdctl --user user --password password get foo
+```
+
+
 Otherwise, all `etcdctl` commands remain the same. Users and roles can still be created and modified, but require authentication by a user with the root role.
 
 ## Using TLS Common Name
+As of version v3.2 if an etcd server is launched with the option `--client-cert-auth=true`, the field of Common Name (CN) in the client's TLS cert will be used as an etcd user. In this case, the common name authenticates the user and the client does not need a password. Note that if both of 1. `--client-cert-auth=true` is passed and CN is provided by the client, and 2. username and password are provided by the client, the username and password based authentication is prioritized. Note that this feature cannot be used with gRPC-proxy and gRPC-gateway. This is because gRPC-proxy terminates TLS from its client so all the clients share a cert of the proxy. gRPC-gateway uses a TLS connection internally for transforming HTTP request to gRPC request so it shares the same limitation. Therefore the clients cannot provide their CN to the server correctly. gRPC-proxy will cause an error and stop if a given cert has non empty CN. gRPC-proxy returns an error which indicates that the client has an non empty CN in its cert.
+
+As of version v3.3 if an etcd server is launched with the option `--peer-cert-allowed-cn` filtering of CN inter-peer connections is enabled.  Nodes can only join the etcd cluster if their CN match the allowed one.
+See [etcd security page](https://github.com/etcd-io/etcd/blob/master/Documentation/op-guide/security.md) for more details.
 
-If an etcd server is launched with the option `--client-cert-auth=true`, the field of Common Name (CN) in the client's TLS cert will be used as an etcd user. In this case, the common name authenticates the user and the client does not need a password.

Documentation/op-guide/clustering.md

@@ -1,4 +1,6 @@
-# Clustering Guide
+---
+title: Clustering Guide
+---
 
 ## Overview
 
@@ -342,8 +344,8 @@ etcdserver: discovery token ignored since a cluster has already been initialized
 ### DNS discovery
 
 DNS [SRV records][rfc-srv] can be used as a discovery mechanism.
-The `-discovery-srv` flag can be used to set the DNS domain name where the discovery SRV records can be found.
-The following DNS SRV records are looked up in the listed order:
+The `--discovery-srv` flag can be used to set the DNS domain name where the discovery SRV records can be found.
+Setting `--discovery-srv example.com` causes DNS SRV records to be looked up in the listed order:
 
 * _etcd-server-ssl._tcp.example.com
 * _etcd-server._tcp.example.com
@@ -357,8 +359,21 @@ To help clients discover the etcd cluster, the following DNS SRV records are loo
 
 If `_etcd-client-ssl._tcp.example.com` is found, clients will attempt to communicate with the etcd cluster over SSL/TLS.
 
+If etcd is using TLS, the discovery SRV record (e.g. `example.com`) must be included in the SSL certificate DNS SAN along with the hostname, or clustering will fail with log messages like the following:
+
+```
+[...] rejected connection from "10.0.1.11:53162" (error "remote error: tls: bad certificate", ServerName "example.com")
+```
+
 If etcd is using TLS without a custom certificate authority, the discovery domain (e.g., example.com) must match the SRV record domain (e.g., infra1.example.com). This is to mitigate attacks that forge SRV records to point to a different domain; the domain would have a valid certificate under PKI but be controlled by an unknown third party.
 
+The `-discovery-srv-name` flag additionally configures a suffix to the SRV name that is queried during discovery.
+Use this flag to differentiate between multiple etcd clusters under the same domain.
+For example, if `discovery-srv=example.com` and `-discovery-srv-name=foo` are set, the following DNS SRV queries are made:
+
+* _etcd-server-ssl-foo._tcp.example.com
+* _etcd-server-foo._tcp.example.com
+
 #### Create DNS SRV records
 
 ```
@@ -384,7 +399,8 @@ infra2.example.com.  300  IN  A  10.0.1.12
 
 #### Bootstrap the etcd cluster using DNS
 
-etcd cluster members can listen on domain names or IP address, the bootstrap process will resolve DNS A records.
+etcd cluster members can advertise domain names or IP address, the bootstrap process will resolve DNS A records.
+Since 3.2 (3.1 prints warnings) `--listen-peer-urls` and `--listen-client-urls` will reject domain name for the network interface binding.
 
 The resolved address in `--initial-advertise-peer-urls` *must match* one of the resolved addresses in the SRV targets. The etcd member reads the resolved address to find out if it belongs to the cluster defined in the SRV records.
 
@@ -395,8 +411,8 @@ $ etcd --name infra0 \
 --initial-cluster-token etcd-cluster-1 \
 --initial-cluster-state new \
 --advertise-client-urls http://infra0.example.com:2379 \
---listen-client-urls http://infra0.example.com:2379 \
---listen-peer-urls http://infra0.example.com:2380
+--listen-client-urls http://0.0.0.0:2379 \
+--listen-peer-urls http://0.0.0.0:2380
 ```
 
 ```
@@ -406,8 +422,8 @@ $ etcd --name infra1 \
 --initial-cluster-token etcd-cluster-1 \
 --initial-cluster-state new \
 --advertise-client-urls http://infra1.example.com:2379 \
---listen-client-urls http://infra1.example.com:2379 \
---listen-peer-urls http://infra1.example.com:2380
+--listen-client-urls http://0.0.0.0:2379 \
+--listen-peer-urls http://0.0.0.0:2380
 ```
 
 ```
@@ -417,8 +433,8 @@ $ etcd --name infra2 \
 --initial-cluster-token etcd-cluster-1 \
 --initial-cluster-state new \
 --advertise-client-urls http://infra2.example.com:2379 \
---listen-client-urls http://infra2.example.com:2379 \
---listen-peer-urls http://infra2.example.com:2380
+--listen-client-urls http://0.0.0.0:2379 \
+--listen-peer-urls http://0.0.0.0:2380
 ```
 
 The cluster can also bootstrap using IP addresses instead of domain names:
@@ -456,6 +472,8 @@ $ etcd --name infra2 \
 --listen-peer-urls http://10.0.1.12:2380
 ```
 
+Since v3.1.0 (except v3.2.9), when `etcd --discovery-srv=example.com` is configured with TLS, server will only authenticate peers/clients when the provided certs have root domain `example.com` as an entry in Subject Alternative Name (SAN) field. See [Notes for DNS SRV][security-guide-dns-srv].
+
 ### Gateway
 
 etcd gateway is a simple TCP proxy that forwards network data to the etcd cluster. Please read [gateway guide][gateway] for more information.
@@ -475,5 +493,6 @@ To setup an etcd cluster with proxies of v2 API, please read the the [clustering
 [proxy]: https://github.com/coreos/etcd/blob/release-2.3/Documentation/proxy.md
 [clustering_etcd2]: https://github.com/coreos/etcd/blob/release-2.3/Documentation/clustering.md
 [security-guide]: security.md
+[security-guide-dns-srv]: security.md#notes-for-dns-srv
 [tls-setup]: ../../hack/tls-setup
 [gateway]: gateway.md

Documentation/op-guide/configuration.md

@@ -1,6 +1,13 @@
-# Configuration flags
+---
+title: Configuration flags
+---
 
-etcd is configurable through command-line flags and environment variables. Options set on the command line take precedence over those from the environment.
+etcd is configurable through a configuration file, various command-line flags, and environment variables.
+
+A reusable configuration file is a YAML file made with name and value of one or more command-line flags described below. In order to use this file, specify the file path as a value to the `--config-file` flag. The [sample configuration file][sample-config-file] can be used as a starting point to create a new configuration file as needed.
+
+Options set on the command line take precedence over those from the environment. If a configuration file is provided, other command line flags and environment variables will be ignored.
+For example, `etcd --config-file etcd.conf.yml.sample --data-dir /tmp` will ignore the `--data-dir` flag.
 
 The format of environment variable for flag `--my-flag` is `ETCD_MY_FLAG`. It applies to all flags.
 
@@ -42,14 +49,14 @@ To start etcd automatically using custom settings at startup in Linux, using a [
 + env variable: ETCD_ELECTION_TIMEOUT
 
 ### --listen-peer-urls
-+ List of URLs to listen on for peer traffic. This flag tells the etcd to accept incoming requests from its peers on the specified scheme://IP:port combinations. Scheme can be either http or https.If 0.0.0.0 is specified as the IP, etcd listens to the given port on all interfaces. If an IP address is given as well as a port, etcd will listen on the given port and interface. Multiple URLs may be used to specify a number of addresses and ports to listen on. The etcd will respond to requests from any of the listed addresses and ports.
++ List of URLs to listen on for peer traffic. This flag tells the etcd to accept incoming requests from its peers on the specified scheme://IP:port combinations. Scheme can be http or https. Alternatively, use `unix://<file-path>` or `unixs://<file-path>` for unix sockets. If 0.0.0.0 is specified as the IP, etcd listens to the given port on all interfaces. If an IP address is given as well as a port, etcd will listen on the given port and interface. Multiple URLs may be used to specify a number of addresses and ports to listen on. The etcd will respond to requests from any of the listed addresses and ports.
 + default: "http://localhost:2380"
 + env variable: ETCD_LISTEN_PEER_URLS
 + example: "http://10.0.0.1:2380"
 + invalid example: "http://example.com:2380" (domain name is invalid for binding)
 
 ### --listen-client-urls
-+ List of URLs to listen on for client traffic. This flag tells the etcd to accept incoming requests from the clients on the specified scheme://IP:port combinations. Scheme can be either http or https. If 0.0.0.0 is specified as the IP, etcd listens to the given port on all interfaces. If an IP address is given as well as a port, etcd will listen on the given port and interface. Multiple URLs may be used to specify a number of addresses and ports to listen on. The etcd will respond to requests from any of the listed addresses and ports.
++ List of URLs to listen on for client traffic. This flag tells the etcd to accept incoming requests from the clients on the specified scheme://IP:port combinations. Scheme can be either http or https. Alternatively, use `unix://<file-path>` or `unixs://<file-path>` for unix sockets. If 0.0.0.0 is specified as the IP, etcd listens to the given port on all interfaces. If an IP address is given as well as a port, etcd will listen on the given port and interface. Multiple URLs may be used to specify a number of addresses and ports to listen on. The etcd will respond to requests from any of the listed addresses and ports.
 + default: "http://localhost:2379"
 + env variable: ETCD_LISTEN_CLIENT_URLS
 + example: "http://10.0.0.1:2379"
@@ -69,12 +76,52 @@ To start etcd automatically using custom settings at startup in Linux, using a [
 
 ### --cors
 + Comma-separated white list of origins for CORS (cross-origin resource sharing).
-+ default: none
++ default: ""
 + env variable: ETCD_CORS
 
+### --quota-backend-bytes
++ Raise alarms when backend size exceeds the given quota (0 defaults to low space quota).
++ default: 0
++ env variable: ETCD_QUOTA_BACKEND_BYTES
+
+### --backend-batch-limit
++ BackendBatchLimit is the maximum operations before commit the backend transaction.
++ default: 0
++ env variable: ETCD_BACKEND_BATCH_LIMIT
+
+### --backend-batch-interval
++ BackendBatchInterval is the maximum time before commit the backend transaction.
++ default: 0
++ env variable: ETCD_BACKEND_BATCH_INTERVAL
+
+### --max-txn-ops
++ Maximum number of operations permitted in a transaction.
++ default: 128
++ env variable: ETCD_MAX_TXN_OPS
+
+### --max-request-bytes
++ Maximum client request size in bytes the server will accept.
++ default: 1572864
++ env variable: ETCD_MAX_REQUEST_BYTES
+
+### --grpc-keepalive-min-time
++ Minimum duration interval that a client should wait before pinging server.
++ default: 5s
++ env variable: ETCD_GRPC_KEEPALIVE_MIN_TIME
+
+### --grpc-keepalive-interval
++ Frequency duration of server-to-client ping to check if a connection is alive (0 to disable).
++ default: 2h
++ env variable: ETCD_GRPC_KEEPALIVE_INTERVAL
+
+### --grpc-keepalive-timeout
++ Additional duration of wait before closing a non-responsive connection (0 to disable).
++ default: 20s
++ env variable: ETCD_GRPC_KEEPALIVE_TIMEOUT
+
 ## Clustering flags
 
-`--initial` prefix flags are used in bootstrapping ([static bootstrap][build-cluster], [discovery-service bootstrap][discovery] or [runtime reconfiguration][reconfig]) a new member, and ignored when restarting an existing member.
+`--initial-advertise-peer-urls`, `--initial-cluster`, `--initial-cluster-state`, and `--initial-cluster-token` flags are used in bootstrapping ([static bootstrap][build-cluster], [discovery-service bootstrap][discovery] or [runtime reconfiguration][reconfig]) a new member, and ignored when restarting an existing member.
 
 `--discovery` prefix flags need to be set when using [discovery service][discovery].
 
@@ -112,14 +159,19 @@ To start etcd automatically using custom settings at startup in Linux, using a [
 
 ### --discovery
 + Discovery URL used to bootstrap the cluster.
-+ default: none
++ default: ""
 + env variable: ETCD_DISCOVERY
 
 ### --discovery-srv
 + DNS srv domain used to bootstrap the cluster.
-+ default: none
++ default: ""
 + env variable: ETCD_DISCOVERY_SRV
 
+### --discovery-srv-name
++ Suffix to the DNS srv name queried when bootstrapping using DNS.
++ default: ""
++ env variable: ETCD_DISCOVERY_SRV_NAME
+
 ### --discovery-fallback
 + Expected behavior ("exit" or "proxy") when discovery services fails. "proxy" supports v2 API only.
 + default: "proxy"
@@ -127,12 +179,12 @@ To start etcd automatically using custom settings at startup in Linux, using a [
 
 ### --discovery-proxy
 + HTTP proxy to use for traffic to discovery service.
-+ default: none
++ default: ""
 + env variable: ETCD_DISCOVERY_PROXY
 
 ### --strict-reconfig-check
 + Reject reconfiguration requests that would cause quorum loss.
-+ default: false
++ default: true
 + env variable: ETCD_STRICT_RECONFIG_CHECK
 
 ### --auto-compaction-retention
@@ -140,6 +192,10 @@ To start etcd automatically using custom settings at startup in Linux, using a [
 + default: 0
 + env variable: ETCD_AUTO_COMPACTION_RETENTION
 
+### --auto-compaction-mode
++ Interpret 'auto-compaction-retention' one of: 'periodic', 'revision'. 'periodic' for duration based retention, defaulting to hours if no time unit is provided (e.g. '5m'). 'revision' for revision number based retention.
++ default: periodic
++ env variable: ETCD_AUTO_COMPACTION_MODE
 
 ### --enable-v2
 + Accept etcd V2 client requests
@@ -185,32 +241,38 @@ To start etcd automatically using custom settings at startup in Linux, using a [
 
 The security flags help to [build a secure etcd cluster][security].
 
-### --ca-file 
+### --ca-file
 
 **DEPRECATED**
 
 + Path to the client server TLS CA file. `--ca-file ca.crt` could be replaced by `--trusted-ca-file ca.crt --client-cert-auth` and etcd will perform the same.
-+ default: none
++ default: ""
 + env variable: ETCD_CA_FILE
 
 ### --cert-file
 + Path to the client server TLS cert file.
-+ default: none
++ default: ""
 + env variable: ETCD_CERT_FILE
 
 ### --key-file
 + Path to the client server TLS key file.
-+ default: none
++ default: ""
 + env variable: ETCD_KEY_FILE
 
 ### --client-cert-auth
 + Enable client cert authentication.
 + default: false
 + env variable: ETCD_CLIENT_CERT_AUTH
++ CN authentication is not supported by gRPC-gateway.
+
+### --client-crl-file
++ Path to the client certificate revocation list file.
++ default: ""
++ env variable: ETCD_CLIENT_CRL_FILE
 
 ### --trusted-ca-file
-+ Path to the client server TLS trusted CA key file.
-+ default: none
++ Path to the client server TLS trusted CA cert file.
++ default: ""
 + env variable: ETCD_TRUSTED_CA_FILE
 
 ### --auto-tls
@@ -218,22 +280,22 @@ The security flags help to [build a secure etcd cluster][security].
 + default: false
 + env variable: ETCD_AUTO_TLS
 
-### --peer-ca-file 
+### --peer-ca-file
 
 **DEPRECATED**
 
 + Path to the peer server TLS CA file. `--peer-ca-file ca.crt` could be replaced by `--peer-trusted-ca-file ca.crt --peer-client-cert-auth` and etcd will perform the same.
-+ default: none
++ default: ""
 + env variable: ETCD_PEER_CA_FILE
 
 ### --peer-cert-file
-+ Path to the peer server TLS cert file.
-+ default: none
++ Path to the peer server TLS cert file. This is the cert for peer-to-peer traffic, used both for server and client.
++ default: ""
 + env variable: ETCD_PEER_CERT_FILE
 
 ### --peer-key-file
-+ Path to the peer server TLS key file.
-+ default: none
++ Path to the peer server TLS key file. This is the key for peer-to-peer traffic, used both for server and client.
++ default: ""
 + env variable: ETCD_PEER_KEY_FILE
 
 ### --peer-client-cert-auth
@@ -241,9 +303,14 @@ The security flags help to [build a secure etcd cluster][security].
 + default: false
 + env variable: ETCD_PEER_CLIENT_CERT_AUTH
 
+### --peer-crl-file
++ Path to the peer certificate revocation list file.
++ default: ""
++ env variable: ETCD_PEER_CRL_FILE
+
 ### --peer-trusted-ca-file
 + Path to the peer server TLS trusted CA file.
-+ default: none
++ default: ""
 + env variable: ETCD_PEER_TRUSTED_CA_FILE
 
 ### --peer-auto-tls
@@ -251,8 +318,32 @@ The security flags help to [build a secure etcd cluster][security].
 + default: false
 + env variable: ETCD_PEER_AUTO_TLS
 
+### --peer-cert-allowed-cn
++ Allowed CommonName for inter peer authentication.
++ default: none
++ env variable: ETCD_PEER_CERT_ALLOWED_CN
+
+### --cipher-suites
++ Comma-separated list of supported TLS cipher suites between server/client and peers.
++ default: ""
++ env variable: ETCD_CIPHER_SUITES
+
 ## Logging flags
 
+### --logger
+
+**Available from v3.4**
+
++ Specify 'zap' for structured logging or 'capnslog'.
++ default: capnslog
++ env variable: ETCD_LOGGER
+
+### --log-outputs
++ Specify 'stdout' or 'stderr' to skip journald logging even when running under systemd, or list of comma separated output targets.
++ default: default
++ env variable: ETCD_LOG_OUTPUTS
++ 'default' use 'stderr' config for v3.4 during zap logger migraion
+
 ### --debug
 + Drop the default log level to DEBUG for all subpackages.
 + default: false (INFO for all packages)
@@ -260,10 +351,9 @@ The security flags help to [build a secure etcd cluster][security].
 
 ### --log-package-levels
 + Set individual etcd subpackages to specific log levels. An example being `etcdserver=WARNING,security=DEBUG`
-+ default: none (INFO for all packages)
++ default: "" (INFO for all packages)
 + env variable: ETCD_LOG_PACKAGE_LEVELS
 
-
 ## Unsafe flags
 
 Please be CAUTIOUS when using unsafe flags because it will break the guarantees given by the consensus protocol.
@@ -271,7 +361,7 @@ For example, it may panic if other members in the cluster are still alive.
 Follow the instructions when using these flags.
 
 ### --force-new-cluster
-+ Force to create a new one-member cluster. It commits configuration changes forcing to remove all existing members in the cluster and add itself. It needs to be set to [restore a backup][restore].
++ Force to create a new one-member cluster. It commits configuration changes forcing to remove all existing members in the cluster and add itself, but is strongly discouraged. Please review the [disaster recovery][recovery] documentation for preferred v3 recovery procedures.
 + default: false
 + env variable: ETCD_FORCE_NEW_CLUSTER
 
@@ -283,24 +373,52 @@ Follow the instructions when using these flags.
 
 ### --config-file
 + Load server configuration from a file.
-+ default: none
++ default: ""
++ example: [sample configuration file][sample-config-file]
++ env variable: ETCD_CONFIG_FILE
 
 ## Profiling flags
 
 ### --enable-pprof
 + Enable runtime profiling data via HTTP server. Address is at client URL + "/debug/pprof/"
 + default: false
++ env variable: ETCD_ENABLE_PPROF
 
 ### --metrics
 + Set level of detail for exported metrics, specify 'extensive' to include histogram metrics.
 + default: basic
++ env variable: ETCD_METRICS
+
+### --listen-metrics-urls
++ List of additional URLs to listen on that will respond to both the `/metrics` and `/health` endpoints
++ default: ""
++ env variable: ETCD_LISTEN_METRICS_URLS
 
 ## Auth flags
 
 ### --auth-token
-+ Specify a token type and token specific options, especially for JWT. Its format is "type,var1=val1,var2=val2,...". Possible type is 'simple' or 'jwt'. Possible variables are 'sign-method' for specifying a sign method of jwt (its possible values are 'ES256', 'ES384', 'ES512', 'HS256', 'HS384', 'HS512', 'RS256', 'RS384', 'RS512', 'PS256', 'PS384', or 'PS512'), 'pub-key' for specifying a path to a public key for verifying jwt, and 'priv-key' for specifying a path to a private key for signing jwt.
-+ Example option of JWT: '--auth-token jwt,pub-key=app.rsa.pub,priv-key=app.rsa,sign-method=RS512'
++ Specify a token type and token specific options, especially for JWT. Its format is "type,var1=val1,var2=val2,...". Possible type is 'simple' or 'jwt'. Possible variables are 'sign-method' for specifying a sign method of jwt (its possible values are 'ES256', 'ES384', 'ES512', 'HS256', 'HS384', 'HS512', 'RS256', 'RS384', 'RS512', 'PS256', 'PS384', or 'PS512'), 'pub-key' for specifying a path to a public key for verifying jwt, 'priv-key' for specifying a path to a private key for signing jwt, and 'ttl' for specifying TTL of jwt tokens.
++ For asymmetric algorithms ('RS', 'PS', 'ES'), the public key is optional, as the private key contains enough information to both sign and verify tokens.
++ Example option of JWT: '--auth-token jwt,pub-key=app.rsa.pub,priv-key=app.rsa,sign-method=RS512,ttl=10m'
 + default: "simple"
++ env variable: ETCD_AUTH_TOKEN
+
+### --bcrypt-cost
++ Specify the cost / strength of the bcrypt algorithm for hashing auth passwords. Valid values are between 4 and 31.
++ default: 10
++ env variable: (not supported)
+
+## Experimental flags
+
+### --experimental-backend-bbolt-freelist-type
++ The freelist type that etcd backend(bboltdb) uses (array and map are supported types).
++ default: array
++ env variable: ETCD_EXPERIMENTAL_BACKEND_BBOLT_FREELIST_TYPE
+
+### --experimental-corrupt-check-time
++ Duration of time between cluster corruption check passes
++ default: 0s
++ env variable: ETCD_EXPERIMENTAL_CORRUPT_CHECK_TIME
 
 [build-cluster]: clustering.md#static
 [reconfig]: runtime-configuration.md
@@ -311,3 +429,5 @@ Follow the instructions when using these flags.
 [security]: security.md
 [systemd-intro]: http://freedesktop.org/wiki/Software/systemd/
 [tuning]: ../tuning.md#time-parameters
+[sample-config-file]: ../../etcd.conf.yml.sample
+[recovery]: recovery.md#disaster-recovery

Documentation/op-guide/container.md

@@ -1,4 +1,6 @@
-# Run etcd clusters inside containers
+---
+title: Run etcd clusters inside containers
+---
 
 The following guide shows how to run etcd with rkt and Docker using the [static bootstrap process](clustering.md#static).
 
@@ -17,14 +19,14 @@ export NODE1=192.168.1.21
 Trust the CoreOS [App Signing Key](https://coreos.com/security/app-signing-key/).
 
 ```
-sudo rkt trust --prefix coreos.com/etcd
+sudo rkt trust --prefix quay.io/coreos/etcd
 # gpg key fingerprint is: 18AD 5014 C99E F7E3 BA5F  6CE9 50BD D3E0 FC8A 365E
 ```
 
-Run the `v3.1.2` version of etcd or specify another release version.
+Run the `v3.2` version of etcd or specify another release version.
 
 ```
-sudo rkt run --net=default:IP=${NODE1} coreos.com/etcd:v3.1.2 -- -name=node1 -advertise-client-urls=http://${NODE1}:2379 -initial-advertise-peer-urls=http://${NODE1}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE1}:2380 -initial-cluster=node1=http://${NODE1}:2380
+sudo rkt run --net=default:IP=${NODE1} quay.io/coreos/etcd:v3.2 -- -name=node1 -advertise-client-urls=http://${NODE1}:2379 -initial-advertise-peer-urls=http://${NODE1}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE1}:2380 -initial-cluster=node1=http://${NODE1}:2380
 ```
 
 List the cluster member.
@@ -45,13 +47,13 @@ export NODE3=172.16.28.23
 
 ```
 # node 1
-sudo rkt run --net=default:IP=${NODE1} coreos.com/etcd:v3.1.2 -- -name=node1 -advertise-client-urls=http://${NODE1}:2379 -initial-advertise-peer-urls=http://${NODE1}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE1}:2380 -initial-cluster=node1=http://${NODE1}:2380,node2=http://${NODE2}:2380,node3=http://${NODE3}:2380
+sudo rkt run --net=default:IP=${NODE1} quay.io/coreos/etcd:v3.2 -- -name=node1 -advertise-client-urls=http://${NODE1}:2379 -initial-advertise-peer-urls=http://${NODE1}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE1}:2380 -initial-cluster=node1=http://${NODE1}:2380,node2=http://${NODE2}:2380,node3=http://${NODE3}:2380
 
 # node 2
-sudo rkt run --net=default:IP=${NODE2} coreos.com/etcd:v3.1.2 -- -name=node2 -advertise-client-urls=http://${NODE2}:2379 -initial-advertise-peer-urls=http://${NODE2}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE2}:2380 -initial-cluster=node1=http://${NODE1}:2380,node2=http://${NODE2}:2380,node3=http://${NODE3}:2380
+sudo rkt run --net=default:IP=${NODE2} quay.io/coreos/etcd:v3.2 -- -name=node2 -advertise-client-urls=http://${NODE2}:2379 -initial-advertise-peer-urls=http://${NODE2}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE2}:2380 -initial-cluster=node1=http://${NODE1}:2380,node2=http://${NODE2}:2380,node3=http://${NODE3}:2380
 
 # node 3
-sudo rkt run --net=default:IP=${NODE3} coreos.com/etcd:v3.1.2 -- -name=node3 -advertise-client-urls=http://${NODE3}:2379 -initial-advertise-peer-urls=http://${NODE3}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE3}:2380 -initial-cluster=node1=http://${NODE1}:2380,node2=http://${NODE2}:2380,node3=http://${NODE3}:2380
+sudo rkt run --net=default:IP=${NODE3} quay.io/coreos/etcd:v3.2 -- -name=node3 -advertise-client-urls=http://${NODE3}:2379 -initial-advertise-peer-urls=http://${NODE3}:2380 -listen-client-urls=http://0.0.0.0:2379 -listen-peer-urls=http://${NODE3}:2380 -initial-cluster=node1=http://${NODE1}:2380,node2=http://${NODE2}:2380,node3=http://${NODE3}:2380
 ```
 
 Verify the cluster is healthy and can be reached.
@@ -76,18 +78,29 @@ Use the host IP address when configuring etcd:
 export NODE1=192.168.1.21
 ```
 
+Configure a Docker volume to store etcd data:
+
+```
+docker volume create --name etcd-data
+export DATA_DIR="etcd-data"
+```
+
 Run the latest version of etcd:
 
 ```
+REGISTRY=quay.io/coreos/etcd
+# available from v3.2.5
+REGISTRY=gcr.io/etcd-development/etcd
+
 docker run \
   -p 2379:2379 \
   -p 2380:2380 \
   --volume=${DATA_DIR}:/etcd-data \
-  --name etcd quay.io/coreos/etcd:latest \
+  --name etcd ${REGISTRY}:latest \
   /usr/local/bin/etcd \
   --data-dir=/etcd-data --name node1 \
-  --initial-advertise-peer-urls http://${NODE1}:2380 --listen-peer-urls http://${NODE1}:2380 \
-  --advertise-client-urls http://${NODE1}:2379 --listen-client-urls http://${NODE1}:2379 \
+  --initial-advertise-peer-urls http://${NODE1}:2380 --listen-peer-urls http://0.0.0.0:2380 \
+  --advertise-client-urls http://${NODE1}:2379 --listen-client-urls http://0.0.0.0:2379 \
   --initial-cluster node1=http://${NODE1}:2380
 ```
 
@@ -100,6 +113,10 @@ etcdctl --endpoints=http://${NODE1}:2379 member list
 ### Running a 3 node etcd cluster
 
 ```
+REGISTRY=quay.io/coreos/etcd
+# available from v3.2.5
+REGISTRY=gcr.io/etcd-development/etcd
+
 # For each machine
 ETCD_VERSION=latest
 TOKEN=my-etcd-token
@@ -120,11 +137,11 @@ docker run \
   -p 2379:2379 \
   -p 2380:2380 \
   --volume=${DATA_DIR}:/etcd-data \
-  --name etcd quay.io/coreos/etcd:${ETCD_VERSION} \
+  --name etcd ${REGISTRY}:${ETCD_VERSION} \
   /usr/local/bin/etcd \
   --data-dir=/etcd-data --name ${THIS_NAME} \
-  --initial-advertise-peer-urls http://${THIS_IP}:2380 --listen-peer-urls http://${THIS_IP}:2380 \
-  --advertise-client-urls http://${THIS_IP}:2379 --listen-client-urls http://${THIS_IP}:2379 \
+  --initial-advertise-peer-urls http://${THIS_IP}:2380 --listen-peer-urls http://0.0.0.0:2380 \
+  --advertise-client-urls http://${THIS_IP}:2379 --listen-client-urls http://0.0.0.0:2379 \
   --initial-cluster ${CLUSTER} \
   --initial-cluster-state ${CLUSTER_STATE} --initial-cluster-token ${TOKEN}
 
@@ -135,11 +152,11 @@ docker run \
   -p 2379:2379 \
   -p 2380:2380 \
   --volume=${DATA_DIR}:/etcd-data \
-  --name etcd quay.io/coreos/etcd:${ETCD_VERSION} \
+  --name etcd ${REGISTRY}:${ETCD_VERSION} \
   /usr/local/bin/etcd \
   --data-dir=/etcd-data --name ${THIS_NAME} \
-  --initial-advertise-peer-urls http://${THIS_IP}:2380 --listen-peer-urls http://${THIS_IP}:2380 \
-  --advertise-client-urls http://${THIS_IP}:2379 --listen-client-urls http://${THIS_IP}:2379 \
+  --initial-advertise-peer-urls http://${THIS_IP}:2380 --listen-peer-urls http://0.0.0.0:2380 \
+  --advertise-client-urls http://${THIS_IP}:2379 --listen-client-urls http://0.0.0.0:2379 \
   --initial-cluster ${CLUSTER} \
   --initial-cluster-state ${CLUSTER_STATE} --initial-cluster-token ${TOKEN}
 
@@ -150,11 +167,11 @@ docker run \
   -p 2379:2379 \
   -p 2380:2380 \
   --volume=${DATA_DIR}:/etcd-data \
-  --name etcd quay.io/coreos/etcd:${ETCD_VERSION} \
+  --name etcd ${REGISTRY}:${ETCD_VERSION} \
   /usr/local/bin/etcd \
   --data-dir=/etcd-data --name ${THIS_NAME} \
-  --initial-advertise-peer-urls http://${THIS_IP}:2380 --listen-peer-urls http://${THIS_IP}:2380 \
-  --advertise-client-urls http://${THIS_IP}:2379 --listen-client-urls http://${THIS_IP}:2379 \
+  --initial-advertise-peer-urls http://${THIS_IP}:2380 --listen-peer-urls http://0.0.0.0:2380 \
+  --advertise-client-urls http://${THIS_IP}:2379 --listen-client-urls http://0.0.0.0:2379 \
   --initial-cluster ${CLUSTER} \
   --initial-cluster-state ${CLUSTER_STATE} --initial-cluster-token ${TOKEN}
 ```
@@ -174,21 +191,30 @@ To provision a 3 node etcd cluster on bare-metal, the examples in the [baremetal
 The etcd release container does not include default root certificates. To use HTTPS with certificates trusted by a root authority (e.g., for discovery), mount a certificate directory into the etcd container:
 
 ```
+REGISTRY=quay.io/coreos/etcd
+# available from v3.2.5
+REGISTRY=docker://gcr.io/etcd-development/etcd
+
 rkt run \
+  --insecure-options=image \
   --volume etcd-ssl-certs-bundle,kind=host,source=/etc/ssl/certs/ca-certificates.crt \
   --mount volume=etcd-ssl-certs-bundle,target=/etc/ssl/certs/ca-certificates.crt \
-  quay.io/coreos/etcd:latest -- --name my-name \
+  ${REGISTRY}:latest -- --name my-name \
   --initial-advertise-peer-urls http://localhost:2380 --listen-peer-urls http://localhost:2380 \
   --advertise-client-urls http://localhost:2379 --listen-client-urls http://localhost:2379 \
   --discovery https://discovery.etcd.io/c11fbcdc16972e45253491a24fcf45e1
 ```
 
 ```
+REGISTRY=quay.io/coreos/etcd
+# available from v3.2.5
+REGISTRY=gcr.io/etcd-development/etcd
+
 docker run \
   -p 2379:2379 \
   -p 2380:2380 \
   --volume=/etc/ssl/certs/ca-certificates.crt:/etc/ssl/certs/ca-certificates.crt \
-  quay.io/coreos/etcd:latest \
+  ${REGISTRY}:latest \
   /usr/local/bin/etcd --name my-name \
   --initial-advertise-peer-urls http://localhost:2380 --listen-peer-urls http://localhost:2380 \
   --advertise-client-urls http://localhost:2379 --listen-client-urls http://localhost:2379 \

Documentation/op-guide/etcd3_alert.rules

@@ -43,8 +43,8 @@ ANNOTATIONS {
 
 # alert if more than 1% of gRPC method calls have failed within the last 5 minutes
 ALERT HighNumberOfFailedGRPCRequests
-IF sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
-  / sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m])) > 0.01
+IF 100 * (sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
+  / sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 1
 FOR 10m
 LABELS {
   severity = "warning"
@@ -56,8 +56,8 @@ ANNOTATIONS {
 
 # alert if more than 5% of gRPC method calls have failed within the last 5 minutes
 ALERT HighNumberOfFailedGRPCRequests
-IF sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
-  / sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m])) > 0.05
+IF 100 * (sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
+  / sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 5
 FOR 5m
 LABELS {
   severity = "critical"
@@ -69,7 +69,7 @@ ANNOTATIONS {
 
 # alert if the 99th percentile of gRPC method calls take more than 150ms
 ALERT GRPCRequestsSlow
-IF histogram_quantile(0.99, rate(etcd_grpc_unary_requests_duration_seconds_bucket[5m])) > 0.15
+IF histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job="etcd",grpc_type="unary"}[5m])) by (grpc_service, grpc_method, le)) > 0.15
 FOR 10m
 LABELS {
   severity = "critical"
@@ -79,47 +79,6 @@ ANNOTATIONS {
   description = "on etcd instance {{ $labels.instance }} gRPC requests to {{ $labels.grpc_method }} are slow",
 }
 
-# HTTP requests alerts
-# ====================
-
-# alert if more than 1% of requests to an HTTP endpoint have failed within the last 5 minutes
-ALERT HighNumberOfFailedHTTPRequests
-IF sum by(method) (rate(etcd_http_failed_total{job="etcd"}[5m]))
-  / sum by(method) (rate(etcd_http_received_total{job="etcd"}[5m])) > 0.01
-FOR 10m
-LABELS {
-  severity = "warning"
-}
-ANNOTATIONS {
-  summary = "a high number of HTTP requests are failing",
-  description = "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}",
-}
-
-# alert if more than 5% of requests to an HTTP endpoint have failed within the last 5 minutes
-ALERT HighNumberOfFailedHTTPRequests
-IF sum by(method) (rate(etcd_http_failed_total{job="etcd"}[5m])) 
-  / sum by(method) (rate(etcd_http_received_total{job="etcd"}[5m])) > 0.05
-FOR 5m
-LABELS {
-  severity = "critical"
-}
-ANNOTATIONS {
-  summary = "a high number of HTTP requests are failing",
-  description = "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}",
-}
-
-# alert if the 99th percentile of HTTP requests take more than 150ms
-ALERT HTTPRequestsSlow
-IF histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) > 0.15
-FOR 10m
-LABELS {
-  severity = "warning"
-}
-ANNOTATIONS {
-  summary = "slow HTTP requests",
-  description = "on etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow",
-}
-
 # file descriptor alerts
 # ======================
 
@@ -154,7 +113,7 @@ ANNOTATIONS {
 
 # alert if 99th percentile of round trips take 150ms
 ALERT EtcdMemberCommunicationSlow
-IF histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m])) > 0.15
+IF histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m])) > 0.15
 FOR 10m
 LABELS {
   severity = "warning"

Documentation/op-guide/etcd3_alert.rules.yml

@@ -0,0 +1,134 @@
+# these rules synced manually from https://github.com/etcd-io/etcd/blob/master/Documentation/etcd-mixin/mixin.libsonnet
+groups:
+- name: etcd
+  rules:
+  - alert: etcdInsufficientMembers
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value
+        }}).'
+    expr: |
+      sum(up{job=~".*etcd.*"} == bool 1) by (job) < ((count(up{job=~".*etcd.*"}) by (job) + 1) / 2)
+    for: 3m
+    labels:
+      severity: critical
+  - alert: etcdNoLeader
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has
+        no leader.'
+    expr: |
+      etcd_server_has_leader{job=~".*etcd.*"} == 0
+    for: 1m
+    labels:
+      severity: critical
+  - alert: etcdHighNumberOfLeaderChanges
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": instance {{ $labels.instance }}
+        has seen {{ $value }} leader changes within the last hour.'
+    expr: |
+      rate(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}[15m]) > 3
+    for: 15m
+    labels:
+      severity: warning
+  - alert: etcdHighNumberOfFailedGRPCRequests
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{
+        $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
+    expr: |
+      100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
+        /
+      sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
+        > 1
+    for: 10m
+    labels:
+      severity: warning
+  - alert: etcdHighNumberOfFailedGRPCRequests
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{
+        $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
+    expr: |
+      100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
+        /
+      sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
+        > 5
+    for: 5m
+    labels:
+      severity: critical
+  - alert: etcdGRPCRequestsSlow
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method
+        }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
+    expr: |
+      histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_type="unary"}[5m])) by (job, instance, grpc_service, grpc_method, le))
+      > 0.15
+    for: 10m
+    labels:
+      severity: critical
+  - alert: etcdMemberCommunicationSlow
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To
+        }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
+    expr: |
+      histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m]))
+      > 0.15
+    for: 10m
+    labels:
+      severity: warning
+  - alert: etcdHighNumberOfFailedProposals
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within
+        the last hour on etcd instance {{ $labels.instance }}.'
+    expr: |
+      rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
+    for: 15m
+    labels:
+      severity: warning
+  - alert: etcdHighFsyncDurations
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": 99th percentile fync durations are
+        {{ $value }}s on etcd instance {{ $labels.instance }}.'
+    expr: |
+      histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
+      > 0.5
+    for: 10m
+    labels:
+      severity: warning
+  - alert: etcdHighCommitDurations
+    annotations:
+      message: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations
+        {{ $value }}s on etcd instance {{ $labels.instance }}.'
+    expr: |
+      histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
+      > 0.25
+    for: 10m
+    labels:
+      severity: warning
+  - alert: etcdHighNumberOfFailedHTTPRequests
+    annotations:
+      message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
+        instance {{ $labels.instance }}'
+    expr: |
+      sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
+      BY (method) > 0.01
+    for: 10m
+    labels:
+      severity: warning
+  - alert: etcdHighNumberOfFailedHTTPRequests
+    annotations:
+      message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
+        instance {{ $labels.instance }}.'
+    expr: |
+      sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
+      BY (method) > 0.05
+    for: 10m
+    labels:
+      severity: critical
+  - alert: etcdHTTPRequestsSlow
+    annotations:
+      message: etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method
+        }} are slow.
+    expr: |
+      histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
+      > 0.15
+    for: 10m
+    labels:
+      severity: warning

Documentation/op-guide/failures.md

@@ -1,4 +1,6 @@
-# Understand failures
+---
+title: Failure modes
+---
 
 Failures are common in a large deployment of machines. A machine fails when its hardware or software malfunctions. Multiple machines fail together when there are power failures or network issues. Multiple kinds of failures can also happen at once; it is almost impossible to enumerate all possible failure cases. 
 

Documentation/op-guide/gateway.md

@@ -1,10 +1,12 @@
-# etcd gateway
+---
+title: etcd gateway
+---
 
 ## What is etcd gateway
 
 etcd gateway is a simple TCP proxy that forwards network data to the etcd cluster. The gateway is stateless and transparent; it neither inspects client requests nor interferes with cluster responses.
 
-The gateway supports multiple etcd server endpoints and works on a simple round-robin policy. It only routes to available enpoints and hides failures from its clients. Other retry policies, such as weighted round-robin, may be supported in the future.
+The gateway supports multiple etcd server endpoints and works on a simple round-robin policy. It only routes to available endpoints and hides failures from its clients. Other retry policies, such as weighted round-robin, may be supported in the future.
 
 ## When to use etcd gateway
 
@@ -60,7 +62,7 @@ infra2.example.com.  300  IN  A  10.0.1.12
 Start the etcd gateway to fetch the endpoints from the DNS SRV entries with the command:
 
 ```bash
-$ etcd gateway --discovery-srv=example.com
+$ etcd gateway start --discovery-srv=example.com
 2016-08-16 11:21:18.867350 I | tcpproxy: ready to proxy client requests to [...]
 ```
 

Documentation/op-guide/grpc_proxy.md

@@ -1,4 +1,6 @@
-# gRPC proxy
+---
+title: gRPC proxy
+---
 
 The gRPC proxy is a stateless etcd reverse proxy operating at the gRPC layer (L7). The proxy is designed to reduce the total processing load on the core etcd cluster. For horizontal scalability, it coalesces watch and lease API requests. To protect the cluster against abusive clients, it caches key range requests.
 
@@ -85,14 +87,14 @@ Start the etcd gRPC proxy to use these static endpoints with the command:
 $ etcd grpc-proxy start --endpoints=infra0.example.com,infra1.example.com,infra2.example.com --listen-addr=127.0.0.1:2379
 ```
 
-The etcd gRPC proxy starts and listens on port 8080. It forwards client requests to one of the three endpoints provided above.
+The etcd gRPC proxy starts and listens on port 2379. It forwards client requests to one of the three endpoints provided above.
 
 Sending requests through the proxy:
 
 ```bash
-$ ETCDCTL_API=3 ./etcdctl --endpoints=127.0.0.1:2379 put foo bar
+$ ETCDCTL_API=3 etcdctl --endpoints=127.0.0.1:2379 put foo bar
 OK
-$ ETCDCTL_API=3 ./etcdctl --endpoints=127.0.0.1:2379 get foo
+$ ETCDCTL_API=3 etcdctl --endpoints=127.0.0.1:2379 get foo
 foo
 bar
 ```
@@ -120,7 +122,7 @@ $ etcd grpc-proxy start --endpoints=localhost:2379 \
 The proxy will list all its members for member list:
 
 ```bash
-ETCDCTL_API=3 ./bin/etcdctl --endpoints=http://localhost:23790 member list --write-out table
+ETCDCTL_API=3 etcdctl --endpoints=http://localhost:23790 member list --write-out table
 
 +----+---------+--------------------------------+------------+-----------------+
 | ID | STATUS  |              NAME              | PEER ADDRS |  CLIENT ADDRS   |
@@ -155,10 +157,10 @@ $ etcd grpc-proxy start --endpoints=localhost:2379 \
   --advertise-client-url=127.0.0.1:23792
 ```
 
-the member list API to the grpc-proxy returns its own `advertise-client-url`:
+The member list API to the grpc-proxy returns its own `advertise-client-url`:
 
 ```bash
-ETCDCTL_API=3 ./bin/etcdctl --endpoints=http://localhost:23792 member list --write-out table
+ETCDCTL_API=3 etcdctl --endpoints=http://localhost:23792 member list --write-out table
 
 +----+---------+--------------------------------+------------+-----------------+
 | ID | STATUS  |              NAME              | PEER ADDRS |  CLIENT ADDRS   |
@@ -182,12 +184,69 @@ $ etcd grpc-proxy start --endpoints=localhost:2379 \
 Accesses to the proxy are now transparently prefixed on the etcd cluster:
 
 ```bash
-$ ETCDCTL_API=3 ./bin/etcdctl --endpoints=localhost:23790 put my-key abc
+$ ETCDCTL_API=3 etcdctl --endpoints=localhost:23790 put my-key abc
 # OK
-$ ETCDCTL_API=3 ./bin/etcdctl --endpoints=localhost:23790 get my-key
+$ ETCDCTL_API=3 etcdctl --endpoints=localhost:23790 get my-key
 # my-key
 # abc
-$ ETCDCTL_API=3 ./bin/etcdctl --endpoints=localhost:2379 get my-prefix/my-key
+$ ETCDCTL_API=3 etcdctl --endpoints=localhost:2379 get my-prefix/my-key
 # my-prefix/my-key
 # abc
 ```
+
+## TLS termination
+
+Terminate TLS from a secure etcd cluster with the gRPC proxy by serving an unencrypted local endpoint.
+
+To try it out, start a single member etcd cluster with client https:
+
+```sh
+$ etcd --listen-client-urls https://localhost:2379 --advertise-client-urls https://localhost:2379 --cert-file=peer.crt --key-file=peer.key --trusted-ca-file=ca.crt --client-cert-auth
+```
+
+Confirm the client port is serving https:
+
+```sh
+# fails
+$ ETCDCTL_API=3 etcdctl --endpoints=http://localhost:2379 endpoint status
+# works
+$ ETCDCTL_API=3 etcdctl --endpoints=https://localhost:2379 --cert=client.crt --key=client.key --cacert=ca.crt endpoint status
+```
+
+Next, start a gRPC proxy on `localhost:12379` by connecting to the etcd endpoint `https://localhost:2379` using the client certificates:
+
+```sh
+$ etcd grpc-proxy start --endpoints=https://localhost:2379 --listen-addr localhost:12379 --cert client.crt --key client.key --cacert=ca.crt --insecure-skip-tls-verify &
+```
+
+Finally, test the TLS termination by putting a key into the proxy over http:
+
+```sh
+$ ETCDCTL_API=3 etcdctl --endpoints=http://localhost:12379 put abc def
+# OK
+```
+
+## Metrics and Health
+
+The gRPC proxy exposes `/health` and Prometheus `/metrics` endpoints for the etcd members defined by `--endpoints`. An alternative define an additional URL that will respond to both the `/metrics` and `/health` endpoints with the `--metrics-addr` flag.
+
+```bash
+$ etcd grpc-proxy start \
+  --endpoints https://localhost:2379 \
+  --metrics-addr https://0.0.0.0:4443 \
+  --listen-addr 127.0.0.1:23790 \
+  --key client.key \
+  --key-file proxy-server.key \
+  --cert client.crt \
+  --cert-file proxy-server.crt \
+  --cacert ca.pem \
+  --trusted-ca-file proxy-ca.pem
+ ```
+
+### Known issue
+
+The main interface of the proxy serves both HTTP2 and HTTP/1.1. If proxy is setup with TLS as show in the above example, when using a client such as cURL against the listening interface will require explicitly setting the protocol to HTTP/1.1 on the request to return `/metrics` or `/health`. By using the `--metrics-addr` flag the secondary interface will not have this requirement.
+
+```bash
+ $ curl --cacert proxy-ca.pem --key proxy-client.key --cert proxy-client.crt https://127.0.0.1:23790/metrics --http1.1
+```

Documentation/op-guide/hardware.md

@@ -1,4 +1,6 @@
-# Hardware recommendations
+---
+title: Hardware recommendations
+---
 
 etcd usually runs well with limited resources for development or testing purposes; it’s common to develop with etcd on a  laptop or a cheap cloud machine. However, when running etcd clusters in production, some hardware guidelines are useful for proper administration. These suggestions are not hard rules; they serve as a good starting point for a robust production deployment. As always, deployments should be tested with simulated workloads before running in production.
 
@@ -48,7 +50,7 @@ Example application workload: A 50-node Kubernetes cluster
 | Provider | Type | vCPUs | Memory (GB) | Max concurrent IOPS | Disk bandwidth (MB/s) |
 |----------|------|-------|--------|------|----------------|
 | AWS | m4.large | 2 | 8 | 3600 | 56.25 |
-| GCE | n1-standard-1 + 50GB PD SSD | 2 | 7.5 | 1500 | 25 |
+| GCE | n1-standard-2 + 50GB PD SSD | 2 | 7.5 | 1500 | 25 |
 
 
 ### Medium cluster

Documentation/op-guide/maintenance.md

@@ -1,4 +1,6 @@
-# Maintenance
+---
+title: Maintenance
+---
 
 ## Overview
 
@@ -6,25 +8,27 @@ An etcd cluster needs periodic maintenance to remain reliable. Depending on an e
 
 All etcd maintenance manages storage resources consumed by the etcd keyspace. Failure to adequately control the keyspace size is guarded by storage space quotas; if an etcd member runs low on space, a quota will trigger cluster-wide alarms which will put the system into a limited-operation maintenance mode. To avoid running out of space for writes to the keyspace, the etcd keyspace history must be compacted. Storage space itself may be reclaimed by defragmenting etcd members. Finally, periodic snapshot backups of etcd member state makes it possible to recover any unintended logical data loss or corruption caused by operational error.
 
-## History compaction
+## Raft log retention
+
+`etcd --snapshot-count` configures the number of applied Raft entries to hold in-memory before compaction. When `--snapshot-count` reaches, server first persists snapshot data onto disk, and then truncates old entries. When a slow follower requests logs before a compacted index, leader sends the snapshot forcing the follower to overwrite its state.
+
+Higher `--snapshot-count` holds more Raft entries in memory until snapshot, thus causing [recurrent higher memory usage](https://github.com/kubernetes/kubernetes/issues/60589#issuecomment-371977156). Since leader retains latest Raft entries for longer, a slow follower has more time to catch up before leader snapshot. `--snapshot-count` is a tradeoff between higher memory usage and better availabilities of slow followers.
+
+Since v3.2, the default value of `--snapshot-count` has [changed from from 10,000 to 100,000](https://github.com/etcd-io/etcd/pull/7160).
+
+In performance-wise, `--snapshot-count` greater than 100,000 may impact the write throughput. Higher number of in-memory objects can slow down [Go GC mark phase `runtime.scanobject`](https://golang.org/src/runtime/mgc.go), and infrequent memory reclamation makes allocation slow. Performance varies depending on the workloads and system environments. However, in general, too frequent compaction affects cluster availabilities and write throughputs. Too infrequent compaction is also harmful placing too much pressure on Go garbage collector. See https://www.slideshare.net/mitakeh/understanding-performance-aspects-of-etcd-and-raft for more research results.
+
+## History compaction: v3 API Key-Value Database
 
 Since etcd keeps an exact history of its keyspace, this history should be periodically compacted to avoid performance degradation and eventual storage space exhaustion. Compacting the keyspace history drops all information about keys superseded prior to a given keyspace revision. The space used by these keys then becomes available for additional writes to the keyspace.
 
 The keyspace can be compacted automatically with `etcd`'s time windowed history retention policy, or manually with `etcdctl`. The `etcdctl` method provides fine-grained control over the compacting process whereas automatic compacting fits applications that only need key history for some length of time.
 
-`etcd` can be set to automatically compact the keyspace with the `--auto-compaction` option with a period of hours:
-
-```sh
-# keep one hour of history
-$ etcd --auto-compaction-retention=1
-```
-
 An `etcdctl` initiated compaction works as follows:
 
 ```sh
 # compact up to revision 3
 $ etcdctl compact 3
-
 ```
 
 Revisions prior to the compaction revision become inaccessible:
@@ -34,11 +38,43 @@ $ etcdctl get --rev=2 somekey
 Error:  rpc error: code = 11 desc = etcdserver: mvcc: required revision has been compacted
 ```
 
+### Auto Compaction
+
+`etcd` can be set to automatically compact the keyspace with the `--auto-compaction-*` option with a period of hours:
+
+```sh
+# keep one hour of history
+$ etcd --auto-compaction-retention=1
+```
+
+[v3.0.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.0.md) and [v3.1.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.1.md) with `--auto-compaction-retention=10` run periodic compaction on v3 key-value store for every 10-hour. Compactor only supports periodic compaction. Compactor records latest revisions every 5-minute, until it reaches the first compaction period (e.g. 10-hour). In order to retain key-value history of last compaction period, it uses the last revision that was fetched before compaction period, from the revision records that were collected every 5-minute. When `--auto-compaction-retention=10`, compactor uses revision 100 for compact revision where revision 100 is the latest revision fetched from 10 hours ago. If compaction succeeds or requested revision has already been compacted, it resets period timer and starts over with new historical revision records (e.g. restart revision collect and compact for the next 10-hour period). If compaction fails, it retries in 5 minutes.
+
+[v3.2.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.2.md) compactor runs [every hour](https://github.com/etcd-io/etcd/pull/7875). Compactor only supports periodic compaction. Compactor continues to record latest revisions every 5-minute. For every hour, it uses the last revision that was fetched before compaction period, from the revision records that were collected every 5-minute. That is, for every hour, compactor discards historical data created before compaction period. The retention window of compaction period moves to next hour. For instance, when hourly writes are 100 and `--auto-compaction-retention=10`, v3.1 compacts revision 1000, 2000, and 3000 for every 10-hour, while v3.2.x, v3.3.0, v3.3.1, and v3.3.2 compact revision 1000, 1100, and 1200 for every 1-hour. If compaction succeeds or requested revision has already been compacted, it resets period timer and removes used compacted revision from historical revision records (e.g. start next revision collect and compaction from previously collected revisions). If compaction fails, it retries in 5 minutes.
+
+In [v3.3.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.3.md), [v3.3.1](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.3.md), and [v3.3.2](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.3.md), `--auto-compaction-mode=revision --auto-compaction-retention=1000` automatically `Compact` on `"latest revision" - 1000` every 5-minute (when latest revision is 30000, compact on revision 29000). For instance, `--auto-compaction-mode=periodic --auto-compaction-retention=72h` automatically `Compact` with 72-hour retention windown, for every 7.2-hour. For instance, `--auto-compaction-mode=periodic --auto-compaction-retention=30m` automatically `Compact` with 30-minute retention windown, for every 3-minute. Periodic compactor continues to record latest revisions for every 1/10 of given compaction period (e.g. 1-hour when `--auto-compaction-mode=periodic --auto-compaction-retention=10h`). For every 1/10 of given compaction period, compactor uses the last revision that was fetched before compaction period, to discard historical data. The retention window of compaction period moves for every 1/10 of given compaction period. For instance, when hourly writes are 100 and `--auto-compaction-retention=10`, v3.1 compacts revision 1000, 2000, and 3000 for every 10-hour, while v3.2.x, v3.3.0, v3.3.1, and v3.3.2 compact revision 1000, 1100, and 1200 for every 1-hour. Futhermore, when writes per minute are 1000, v3.3.0, v3.3.1, and v3.3.2 with `--auto-compaction-mode=periodic --auto-compaction-retention=30m` compact revision 30000, 33000, and 36000, for every 3-minute with more finer granularity.
+
+When `--auto-compaction-retention=10h`, etcd first waits 10-hour for the first compaction, and then does compaction every hour (1/10 of 10-hour) afterwards like this:
+
+```
+0Hr  (rev = 1)
+1hr  (rev = 10)
+...
+8hr  (rev = 80)
+9hr  (rev = 90)
+10hr (rev = 100, Compact(1))
+11hr (rev = 110, Compact(10))
+...
+```
+
+Whether compaction succeeds or not, this process repeats for every 1/10 of given compaction period. If compaction succeeds, it just removes compacted revision from historical revision records.
+
+In [v3.3.3](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.3.md), `--auto-compaction-mode=revision --auto-compaction-retention=1000` automatically `Compact` on `"latest revision" - 1000` every 5-minute (when latest revision is 30000, compact on revision 29000). Previously, `--auto-compaction-mode=periodic --auto-compaction-retention=72h` automatically `Compact` with 72-hour retention windown for every 7.2-hour.  **Now, `Compact` happens, for every 1-hour but still with 72-hour retention window.** Previously, `--auto-compaction-mode=periodic --auto-compaction-retention=30m` automatically `Compact` with 30-minute retention windown for every 3-minute. **Now, `Compact` happens, for every 30-minute but still with 30-minute retention window.** Periodic compactor keeps recording latest revisions for every compaction period when given period is less than 1-hour, or for every 1-hour when given compaction period is greater than 1-hour (e.g. 1-hour when `--auto-compaction-mode=periodic --auto-compaction-retention=24h`). For every compaction period or 1-hour, compactor uses the last revision that was fetched before compaction period, to discard historical data. The retention window of compaction period moves for every given compaction period or hour. For instance, when hourly writes are 100 and `--auto-compaction-mode=periodic --auto-compaction-retention=24h`, `v3.2.x`, `v3.3.0`, `v3.3.1`, and `v3.3.2` compact revision 2400, 2640, and 2880 for every 2.4-hour, while `v3.3.3` *or later* compacts revision 2400, 2500, 2600 for every 1-hour. Furthermore, when `--auto-compaction-mode=periodic --auto-compaction-retention=30m` and writes per minute are about 1000, `v3.3.0`, `v3.3.1`, and `v3.3.2` compact revision 30000, 33000, and 36000, for every 3-minute, while `v3.3.3` *or later* compacts revision 30000, 60000, and 90000, for every 30-minute.
+
 ## Defragmentation
 
-After compacting the keyspace, the backend database may exhibit internal fragmentation. Any internal fragmentation is space that is free to use by the backend but still consumes storage space. The process of defragmentation releases this storage space back to the file system. Defragmentation is issued on a per-member so that cluster-wide latency spikes may be avoided.
+After compacting the keyspace, the backend database may exhibit internal fragmentation. Any internal fragmentation is space that is free to use by the backend but still consumes storage space. Compacting old revisions internally fragments `etcd` by leaving gaps in backend database. Fragmented space is available for use by `etcd` but unavailable to the host filesystem. In other words, deleting application data does not reclaim the space on disk.
 
-Compacting old revisions internally fragments `etcd` by leaving gaps in backend database. Fragmented space is available for use by `etcd` but unavailable to the host filesystem.
+The process of defragmentation releases this storage space back to the file system. Defragmentation is issued on a per-member so that cluster-wide latency spikes may be avoided.
 
 To defragment an etcd member, use the `etcdctl defrag` command:
 
@@ -47,6 +83,25 @@ $ etcdctl defrag
 Finished defragmenting etcd member[127.0.0.1:2379]
 ```
 
+**Note that defragmentation to a live member blocks the system from reading and writing data while rebuilding its states**.
+
+**Note that defragmentation request does not get replicated over cluster. That is, the request is only applied to the local node. Specify all members in `--endpoints` flag or `--cluster` flag to automatically find all cluster members.**
+
+Run defragment operations for all endpoints in the cluster associated with the default endpoint:
+
+```bash
+$ etcdctl defrag --cluster
+Finished defragmenting etcd member[http://127.0.0.1:2379]
+Finished defragmenting etcd member[http://127.0.0.1:22379]
+Finished defragmenting etcd member[http://127.0.0.1:32379]
+```
+
+To defragment an etcd data directory directly, while etcd is not running, use the command:
+
+``` sh
+$ etcdctl defrag --data-dir <path-to-etcd-data-dir>
+```
+
 ## Space quota
 
 The space quota in `etcd` ensures the cluster operates in a reliable fashion. Without a space quota, `etcd` may suffer from poor performance if the keyspace grows excessively large, or it may simply run out of storage space, leading to unpredictable cluster behavior. If the keyspace's backend database for any member exceeds the space quota, `etcd` raises a cluster-wide alarm that puts the cluster into a maintenance mode which only accepts key reads and deletes. Only after freeing enough space in the keyspace and defragmenting the backend database, along with clearing the space quota alarm can the cluster resume normal operation.
@@ -74,14 +129,14 @@ $ ETCDCTL_API=3 etcdctl --write-out=table endpoint status
 +----------------+------------------+-----------+---------+-----------+-----------+------------+
 # confirm alarm is raised
 $ ETCDCTL_API=3 etcdctl alarm list
-memberID:13803658152347727308 alarm:NOSPACE 
+memberID:13803658152347727308 alarm:NOSPACE
 ```
 
 Removing excessive keyspace data and defragmenting the backend database will put the cluster back within the quota limits:
 
 ```sh
 # get current revision
-$ rev=$(ETCDCTL_API=3 etcdctl --endpoints=:2379 endpoint status --write-out="json" | egrep -o '"revision":[0-9]*' | egrep -o '[0-9]*')
+$ rev=$(ETCDCTL_API=3 etcdctl --endpoints=:2379 endpoint status --write-out="json" | egrep -o '"revision":[0-9]*' | egrep -o '[0-9].*')
 # compact away all old revisions
 $ ETCDCTL_API=3 etcdctl compact $rev
 compacted revision 1516
@@ -90,12 +145,16 @@ $ ETCDCTL_API=3 etcdctl defrag
 Finished defragmenting etcd member[127.0.0.1:2379]
 # disarm alarm
 $ ETCDCTL_API=3 etcdctl alarm disarm
-memberID:13803658152347727308 alarm:NOSPACE 
+memberID:13803658152347727308 alarm:NOSPACE
 # test puts are allowed again
 $ ETCDCTL_API=3 etcdctl put newkey 123
 OK
 ```
 
+The metric `etcd_mvcc_db_total_size_in_use_in_bytes` indicates the actual database usage after a history compaction, while `etcd_debugging_mvcc_db_total_size_in_bytes` shows the database size including free space waiting for defragmentation. The latter increases only when the former is close to it, meaning when both of these metrics are close to the quota, a history compaction is required to avoid triggering the space quota.
+
+`etcd_debugging_mvcc_db_total_size_in_bytes` is renamed to `etcd_mvcc_db_total_size_in_bytes` from v3.4.
+
 ## Snapshot backup
 
 Snapshotting the `etcd` cluster on a regular basis serves as a durable backup for an etcd keyspace. By taking periodic snapshots of an etcd member's backend database, an `etcd` cluster can be recovered to a point in time with a known good state.
@@ -110,5 +169,4 @@ $ etcdctl --write-out=table snapshot status backup.db
 +----------+----------+------------+------------+
 | fe01cf57 |       10 |          7 | 2.1 MB     |
 +----------+----------+------------+------------+
-
 ```

Documentation/op-guide/monitoring.md

@@ -1,21 +1,69 @@
-# Monitoring etcd
+---
+title: Monitoring etcd
+---
 
-Each etcd server exports metrics under the `/metrics` path on its client port.
+Each etcd server provides local monitoring information on its client port through http endpoints. The monitoring data is useful for both system health checking and cluster debugging.
+
+## Debug endpoint
+
+If `--debug` is set, the etcd server exports debugging information on its client port under the `/debug` path. Take care when setting `--debug`, since there will be degraded performance and verbose logging.
+
+The `/debug/pprof` endpoint is the standard go runtime profiling endpoint. This can be used to profile CPU, heap, mutex, and goroutine utilization. For example, here `go tool pprof` gets the top 10 functions where etcd spends its time:
+
+```sh
+$ go tool pprof http://localhost:2379/debug/pprof/profile
+Fetching profile from http://localhost:2379/debug/pprof/profile
+Please wait... (30s)
+Saved profile in /home/etcd/pprof/pprof.etcd.localhost:2379.samples.cpu.001.pb.gz
+Entering interactive mode (type "help" for commands)
+(pprof) top10
+310ms of 480ms total (64.58%)
+Showing top 10 nodes out of 157 (cum >= 10ms)
+    flat  flat%   sum%        cum   cum%
+   130ms 27.08% 27.08%      130ms 27.08%  runtime.futex
+    70ms 14.58% 41.67%       70ms 14.58%  syscall.Syscall
+    20ms  4.17% 45.83%       20ms  4.17%  github.com/coreos/etcd/vendor/golang.org/x/net/http2/hpack.huffmanDecode
+    20ms  4.17% 50.00%       30ms  6.25%  runtime.pcvalue
+    20ms  4.17% 54.17%       50ms 10.42%  runtime.schedule
+    10ms  2.08% 56.25%       10ms  2.08%  github.com/coreos/etcd/vendor/github.com/coreos/etcd/etcdserver.(*EtcdServer).AuthInfoFromCtx
+    10ms  2.08% 58.33%       10ms  2.08%  github.com/coreos/etcd/vendor/github.com/coreos/etcd/etcdserver.(*EtcdServer).Lead
+    10ms  2.08% 60.42%       10ms  2.08%  github.com/coreos/etcd/vendor/github.com/coreos/etcd/pkg/wait.(*timeList).Trigger
+    10ms  2.08% 62.50%       10ms  2.08%  github.com/coreos/etcd/vendor/github.com/prometheus/client_golang/prometheus.(*MetricVec).hashLabelValues
+    10ms  2.08% 64.58%       10ms  2.08%  github.com/coreos/etcd/vendor/golang.org/x/net/http2.(*Framer).WriteHeaders
+```
+
+The `/debug/requests` endpoint gives gRPC traces and performance statistics through a web browser. For example, here is a `Range` request for the key `abc`:
+
+```
+When	Elapsed (s)
+2017/08/18 17:34:51.999317 	0.000244 	/etcdserverpb.KV/Range
+17:34:51.999382 	 .    65 	... RPC: from 127.0.0.1:47204 deadline:4.999377747s
+17:34:51.999395 	 .    13 	... recv: key:"abc"
+17:34:51.999499 	 .   104 	... OK
+17:34:51.999535 	 .    36 	... sent: header:<cluster_id:14841639068965178418 member_id:10276657743932975437 revision:15 raft_term:17 > kvs:<key:"abc" create_revision:6 mod_revision:14 version:9 value:"asda" > count:1
+```
+
+## Metrics endpoint
+
+Each etcd server exports metrics under the `/metrics` path on its client port and optionally on locations given by `--listen-metrics-urls`.
 
 The metrics can be fetched with `curl`:
 
 ```sh
-$ curl -L http://localhost:2379/metrics
+$ curl -L http://localhost:2379/metrics | grep -v debugging # ignore unstable debugging metrics
 
-# HELP etcd_debugging_mvcc_keys_total Total number of keys.
-# TYPE etcd_debugging_mvcc_keys_total gauge
-etcd_debugging_mvcc_keys_total 0
-# HELP etcd_debugging_mvcc_pending_events_total Total number of pending events to be sent.
-# TYPE etcd_debugging_mvcc_pending_events_total gauge
-etcd_debugging_mvcc_pending_events_total 0
+# HELP etcd_disk_backend_commit_duration_seconds The latency distributions of commit called by backend.
+# TYPE etcd_disk_backend_commit_duration_seconds histogram
+etcd_disk_backend_commit_duration_seconds_bucket{le="0.002"} 72756
+etcd_disk_backend_commit_duration_seconds_bucket{le="0.004"} 401587
+etcd_disk_backend_commit_duration_seconds_bucket{le="0.008"} 405979
+etcd_disk_backend_commit_duration_seconds_bucket{le="0.016"} 406464
 ...
 ```
 
+## Health Check
+
+Since v3.3.0, in addition to responding to the `/metrics` endpoint, any locations specified by `--listen-metrics-urls` will also respond to the `/health` endpoint. This can be useful if the standard endpoint is configured with mutual (client) TLS authentication, but a load balancer or monitoring service still needs access to the health check.
 
 ## Prometheus
 
@@ -24,7 +72,7 @@ Running a [Prometheus][prometheus] monitoring service is the easiest way to inge
 First, install Prometheus:
 
 ```sh
-PROMETHEUS_VERSION="1.3.1"
+PROMETHEUS_VERSION="2.0.0"
 wget https://github.com/prometheus/prometheus/releases/download/v$PROMETHEUS_VERSION/prometheus-$PROMETHEUS_VERSION.linux-amd64.tar.gz -O /tmp/prometheus-$PROMETHEUS_VERSION.linux-amd64.tar.gz
 tar -xvzf /tmp/prometheus-$PROMETHEUS_VERSION.linux-amd64.tar.gz --directory /tmp/ --strip-components=1
 /tmp/prometheus -version
@@ -56,13 +104,13 @@ nohup /tmp/prometheus \
 Now Prometheus will scrape etcd metrics every 10 seconds.
 
 
-## Alerting
+### Alerting
 
-There is a [set of default alerts for etcd v3 clusters](./etcd3_alert.rules).
+There is a set of default alerts for etcd v3 clusters for [Prometheus 1.x](./etcd3_alert.rules) as well as [Prometheus 2.x](./etcd3_alert.rules.yml).
 
 > Note: `job` labels may need to be adjusted to fit a particular need. The rules were written to apply to a single cluster so it is recommended to choose labels unique to a cluster.
 
-## Grafana
+### Grafana
 
 [Grafana][grafana] has built-in Prometheus support; just add a Prometheus data source:
 
@@ -75,8 +123,6 @@ Access: proxy
 
 Then import the default [etcd dashboard template][template] and customize. For instance, if Prometheus data source name is `my-etcd`, the `datasource` field values in JSON also need to be `my-etcd`.
 
-See the [demo][demo].
-
 Sample dashboard:
 
 ![](./etcd-sample-grafana.png)
@@ -85,4 +131,3 @@ Sample dashboard:
 [prometheus]: https://prometheus.io/
 [grafana]: http://grafana.org/
 [template]: ./grafana.json
-[demo]: http://dash.etcd.io/dashboard/db/test-etcd

Documentation/op-guide/performance.md

@@ -1,10 +1,12 @@
-# Performance
+---
+title: Performance
+---
 
 ## Understanding performance
 
 etcd provides stable, sustained high performance. Two factors define performance: latency and throughput. Latency is the time taken to complete an operation. Throughput is the total operations completed within some time period. Usually average latency increases as the overall throughput increases when etcd accepts concurrent client requests. In common cloud environments, like a standard `n-4` on Google Compute Engine (GCE) or a comparable machine type on AWS, a three member etcd cluster finishes a request in less than one millisecond under light load, and can complete more than 30,000 requests per second under heavy load.
 
-etcd uses the Raft consensus algorithm to replicate requests among members and reach agreement. Consensus performance, especially commit latency, is limited by two physical constraints: network IO latency and disk IO latency. The minimum time to finish an etcd request is the network Round Trip Time (RTT) between members, plus the time `fdatasync` requires to commit the data to permanant storage. The RTT within a datacenter may be as long as several hundred microseconds. A typical RTT within the United States is around 50ms, and can be as slow as 400ms between continents. The typical fdatasync latency for a spinning disk is about 10ms. For SSDs, the latency is often lower than 1ms. To increase throughput, etcd batches multiple requests together and submits them to Raft. This batching policy lets etcd attain high throughput despite heavy load.
+etcd uses the Raft consensus algorithm to replicate requests among members and reach agreement. Consensus performance, especially commit latency, is limited by two physical constraints: network IO latency and disk IO latency. The minimum time to finish an etcd request is the network Round Trip Time (RTT) between members, plus the time `fdatasync` requires to commit the data to permanent storage. The RTT within a datacenter may be as long as several hundred microseconds. A typical RTT within the United States is around 50ms, and can be as slow as 400ms between continents. The typical fdatasync latency for a spinning disk is about 10ms. For SSDs, the latency is often lower than 1ms. To increase throughput, etcd batches multiple requests together and submits them to Raft. This batching policy lets etcd attain high throughput despite heavy load.
 
 There are other sub-systems which impact the overall performance of etcd. Each serialized etcd request must run through etcd’s boltdb-backed MVCC storage engine, which usually takes tens of microseconds to finish. Periodically etcd incrementally snapshots its recently applied requests, merging them back with the previous on-disk snapshot. This process may lead to a latency spike. Although this is usually not a problem on SSDs, it may double the observed latency on HDD. Likewise, inflight compactions can impact etcd’s performance. Fortunately, the impact is often insignificant since the compaction is staggered so it does not compete for resources with regular requests. The RPC system, gRPC, gives etcd a well-defined, extensible API, but it also introduces additional latency, especially for local reads.
 

Documentation/op-guide/recovery.md

@@ -1,4 +1,6 @@
-## Disaster recovery
+---
+title: Disaster recovery
+---
 
 etcd is designed to withstand machine failures. An etcd cluster automatically recovers from temporary failures (e.g., machine reboots) and tolerates up to *(N-1)/2* permanent failures for a cluster of N members. When a member permanently fails, whether due to hardware failure or disk corruption, it loses access to the cluster. If the cluster permanently loses more than *(N-1)/2* members then it disastrously fails, irrevocably losing quorum. Once quorum is lost, the cluster cannot reach consensus and therefore cannot continue accepting updates.
 
@@ -6,7 +8,7 @@ To recover from disastrous failure, etcd v3 provides snapshot and restore facili
 
 [v2_recover]: ../v2/admin_guide.md#disaster-recovery
 
-### Snapshotting the keyspace
+## Snapshotting the keyspace
 
 Recovering a cluster first needs a snapshot of the keyspace from an etcd member. A snapshot may either be taken from a live member with the `etcdctl snapshot save` command or by copying the `member/snap/db` file from an etcd data directory. For example, the following command snapshots the keyspace served by `$ENDPOINT` to the file `snapshot.db`:
 
@@ -14,7 +16,7 @@ Recovering a cluster first needs a snapshot of the keyspace from an etcd member.
 $ ETCDCTL_API=3 etcdctl --endpoints $ENDPOINT snapshot save snapshot.db
 ```
 
-### Restoring a cluster
+## Restoring a cluster
 
 To restore a cluster, all that is needed is a single snapshot "db" file. A cluster restore with `etcdctl snapshot restore` creates new etcd data directories; all members should restore using the same snapshot. Restoring overwrites some snapshot metadata (specifically, the member ID and cluster ID); the member loses its former identity. This metadata overwrite prevents the new member from inadvertently joining an existing cluster. Therefore in order to start a cluster from a snapshot, the restore must start a new logical cluster.
 
@@ -61,3 +63,9 @@ $ etcd \
 ```
 
 Now the restored etcd cluster should be available and serving the keyspace given by the snapshot.
+
+## Restoring a cluster from membership mis-reconfiguration with wrong URLs
+
+Previously, etcd panics on [membership mis-reconfiguration with wrong URLs](https://github.com/etcd-io/etcd/issues/9173) (v3.2.15 or later returns [error early in client-side](https://github.com/etcd-io/etcd/pull/9174) before etcd server panic).
+
+Recommended way is restore from [snapshot](#snapshotting-the-keyspace). `--force-new-cluster` can be used to overwrite cluster membership while keeping existing application data, but is strongly discouraged because it will panic if other members from previous cluster are still alive. Make sure to save snapshot periodically.

Documentation/op-guide/runtime-configuration.md

@@ -1,8 +1,10 @@
-# Runtime reconfiguration
+---
+title: Runtime reconfiguration
+---
 
 etcd comes with support for incremental runtime reconfiguration, which allows users to update the membership of the cluster at run time.
 
-Reconfiguration requests can only be processed when a majority of cluster members are functioning. It is **highly recommended** to always have a cluster size greater than two in production. It is unsafe to remove a member from a two member cluster. The majority of a two member cluster is also two. If there is a failure during the removal process, the cluster might not able to make progress and need to [restart from majority failure][majority failure].
+Reconfiguration requests can only be processed when a majority of cluster members are functioning. It is **highly recommended** to always have a cluster size greater than two in production. It is unsafe to remove a member from a two member cluster. The majority of a two member cluster is also two. If there is a failure during the removal process, the cluster might not be able to make progress and need to [restart from majority failure][majority failure].
 
 To better understand the design behind runtime reconfiguration, please read [the runtime reconfiguration document][runtime-reconf].
 
@@ -41,7 +43,7 @@ Before making any change, a simple majority (quorum) of etcd members must be ava
 All changes to the cluster must be done sequentially:
 
 * To update a single member peerURLs, issue an update operation
-* To replace a healthy single member, add a new member then remove the old member
+* To replace a healthy single member, remove the old member then add a new member
 * To increase from 3 to 5 members, issue two add operations
 * To decrease from 5 to 3, issue two remove operations
 
@@ -55,9 +57,9 @@ To update the advertise client URLs of a member, simply restart that member with
 
 #### Update advertise peer URLs
 
-To update the advertise peer URLs of a member, first update it explicitly via member command and then restart the member. The additional action is required since updating peer URLs changes the cluster wide configuration and can affect the health of the etcd cluster. 
+To update the advertise peer URLs of a member, first update it explicitly via member command and then restart the member. The additional action is required since updating peer URLs changes the cluster wide configuration and can affect the health of the etcd cluster.
 
-To update the peer URLs, first find the target member's ID. To list all members with `etcdctl`:
+To update the advertise peer URLs, first find the target member's ID. To list all members with `etcdctl`:
 
 ```sh
 $ etcdctl member list
@@ -69,7 +71,7 @@ a8266ecf031671f3: name=node1 peerURLs=http://localhost:23801 clientURLs=http://1
 This example will `update` a8266ecf031671f3 member ID and change its peerURLs value to `http://10.0.1.10:2380`:
 
 ```sh
-$ etcdctl member update a8266ecf031671f3 http://10.0.1.10:2380
+$ etcdctl member update a8266ecf031671f3 --peer-urls=http://10.0.1.10:2380
 Updated member with ID a8266ecf031671f3 in cluster
 ```
 
@@ -100,7 +102,7 @@ Adding a member is a two step process:
 `etcdctl` adds a new member to the cluster by specifying the member's [name][conf-name] and [advertised peer URLs][conf-adv-peer]:
 
 ```sh
-$ etcdctl member add infra3 http://10.0.1.13:2380
+$ etcdctl member add infra3 --peer-urls=http://10.0.1.13:2380
 added member 9bf1b35fc7761a23 to cluster
 
 ETCD_NAME="infra3"

Documentation/op-guide/runtime-reconf-design.md

@@ -1,4 +1,6 @@
-# Design of runtime reconfiguration
+---
+title: Design of runtime reconfiguration
+---
 
 Runtime reconfiguration is one of the hardest and most error prone features in a distributed system, especially in a consensus based system like etcd.
 
@@ -6,17 +8,17 @@ Read on to learn about the design of etcd's runtime reconfiguration commands and
 
 ## Two phase config changes keep the cluster safe
 
-In etcd, every runtime reconfiguration has to go through [two phases][add-member] for safety reasons. For example, to add a member, first inform cluster of new configuration and then start the new member.
+In etcd, every runtime reconfiguration has to go through [two phases][add-member] for safety reasons. For example, to add a member, first inform the cluster of the new configuration and then start the new member.
 
 Phase 1 - Inform cluster of new configuration
 
-To add a member into etcd cluster, make an API call to request a new member to be added to the cluster. This is only way to add a new member into an existing cluster. The API call returns when the cluster agrees on the configuration change.
+To add a member into an etcd cluster, make an API call to request a new member to be added to the cluster. This is the only way to add a new member into an existing cluster. The API call returns when the cluster agrees on the configuration change.
 
 Phase 2 - Start new member
 
-To join the etcd member into the existing cluster, specify the correct `initial-cluster` and set `initial-cluster-state` to `existing`. When the member starts, it will contact the existing cluster first and verify the current cluster configuration matches the expected one specified in `initial-cluster`. When the new member successfully starts, the cluster has reached the expected configuration.
+To join the new etcd member into the existing cluster, specify the correct `initial-cluster` and set `initial-cluster-state` to `existing`. When the member starts, it will contact the existing cluster first and verify the current cluster configuration matches the expected one specified in `initial-cluster`. When the new member successfully starts, the cluster has reached the expected configuration.
 
-By splitting the process into two discrete phases users are forced to be explicit regarding cluster membership changes. This actually gives users more flexibility and makes things easier to reason about. For example, if there is an attempt to add a new member with the same ID as an existing member in an etcd cluster, the action will fail immediately during phase one without impacting the running cluster. Similar protection is provided to prevent adding new members by mistake. If a new etcd member attempts to join the cluster before the cluster has accepted the configuration change,, it will not be accepted by the cluster.
+By splitting the process into two discrete phases users are forced to be explicit regarding cluster membership changes. This actually gives users more flexibility and makes things easier to reason about. For example, if there is an attempt to add a new member with the same ID as an existing member in an etcd cluster, the action will fail immediately during phase one without impacting the running cluster. Similar protection is provided to prevent adding new members by mistake. If a new etcd member attempts to join the cluster before the cluster has accepted the configuration change, it will not be accepted by the cluster.
 
 Without the explicit workflow around cluster membership etcd would be vulnerable to unexpected cluster membership changes. For example, if etcd is running under an init system such as systemd, etcd would be restarted after being removed via the membership API, and attempt to rejoin the cluster on startup. This cycle would continue every time a member is removed via the API and systemd is set to restart etcd after failing, which is unexpected.
 
@@ -26,21 +28,21 @@ We expect runtime reconfiguration to be an infrequent operation. We decided to k
 
 If a cluster permanently loses a majority of its members, a new cluster will need to be started from an old data directory to recover the previous state.
 
-It is entirely possible to force removing the failed members from the existing cluster to recover. However, we decided not to support this method since it bypasses the normal consensus committing phase, which is unsafe. If the member to remove is not actually dead or force removed through different members in the same cluster, etcd will end up with a diverged cluster with same clusterID. This is very dangerous and hard to debug/fix afterwards. 
+It is entirely possible to force removing the failed members from the existing cluster to recover. However, we decided not to support this method since it bypasses the normal consensus committing phase, which is unsafe. If the member to remove is not actually dead or force removed through different members in the same cluster, etcd will end up with a diverged cluster with same clusterID. This is very dangerous and hard to debug/fix afterwards.
 
-With a correct deployment, the possibility of permanent majority lose is very low. But it is a severe enough problem that worth special care. We strongly suggest reading the [disaster recovery documentation][disaster-recovery] and prepare for permanent majority lose before putting etcd into production.
+With a correct deployment, the possibility of permanent majority loss is very low. But it is a severe enough problem that is worth special care. We strongly suggest reading the [disaster recovery documentation][disaster-recovery] and preparing for permanent majority loss before putting etcd into production.
 
 ## Do not use public discovery service for runtime reconfiguration
 
-The public discovery service should only be used for bootstrapping a cluster. To join member into an existing cluster, use runtime reconfiguration API. 
+The public discovery service should only be used for bootstrapping a cluster. To join member into an existing cluster, use the runtime reconfiguration API.
 
-Discovery service is designed for bootstrapping an etcd cluster in the cloud environment, when the IP addresses of all the members are not known beforehand. After successfully bootstrapping a cluster, the IP addresses of all the members are known. Technically, the discovery service should no longer be needed.
+The discovery service is designed for bootstrapping an etcd cluster in a cloud environment, when the IP addresses of all the members are not known beforehand. After successfully bootstrapping a cluster, the IP addresses of all the members are known. Technically, the discovery service should no longer be needed.
 
-It seems that using public discovery service is a convenient way to do runtime reconfiguration, after all discovery service already has all the cluster configuration information. However relying on public discovery service brings troubles: 
+It seems that using public discovery service is a convenient way to do runtime reconfiguration, after all discovery service already has all the cluster configuration information. However relying on public discovery service brings troubles:
 
 1. it introduces external dependencies for the entire life-cycle of the cluster, not just bootstrap time. If there is a network issue between the cluster and public discovery service, the cluster will suffer from it.
- 
-2. public discovery service must reflect correct runtime configuration of the cluster during it life-cycle. It has to provide security mechanism to avoid bad actions, and it is hard. 
+
+2. public discovery service must reflect correct runtime configuration of the cluster during its life-cycle. It has to provide security mechanisms to avoid bad actions, and it is hard.
 
 3. public discovery service has to keep tens of thousands of cluster configurations. Our public discovery service backend is not ready for that workload.
 

Documentation/op-guide/security.md

@@ -1,4 +1,6 @@
-# Security model
+---
+title: Transport security model
+---
 
 etcd supports automatic TLS as well as authentication through client certificates for both clients to server as well as peer (server to server / cluster) communication.
 
@@ -38,6 +40,8 @@ The peer options work the same way as the client-to-server options:
 
 If either a client-to-server or peer certificate is supplied the key must also be set. All of these configuration options are also available through the environment variables, `ETCD_CA_FILE`, `ETCD_PEER_CA_FILE` and so on.
 
+`--cipher-suites`: Comma-separated list of supported TLS cipher suites between server/client and peers (empty will be auto-populated by Go). Available from v3.2.22+, v3.3.7+, and v3.4+.
+
 ## Example 1: Client-to-server transport security with HTTPS
 
 For this, have a CA certificate (`ca.crt`) and signed key pair (`server.crt`, `server.key`) ready.
@@ -122,6 +126,49 @@ And also the response from the server:
 }
 ```
 
+Specify cipher suites to block [weak TLS cipher suites](https://github.com/etcd-io/etcd/issues/8320).
+
+TLS handshake would fail when client hello is requested with invalid cipher suites.
+
+For instance:
+
+```bash
+$ etcd \
+  --cert-file ./server.crt \
+  --key-file ./server.key \
+  --trusted-ca-file ./ca.crt \
+  --cipher-suites TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384
+```
+
+Then, client requests must specify one of the cipher suites specified in the server:
+
+```bash
+# valid cipher suite
+$ curl \
+  --cacert ./ca.crt \
+  --cert ./server.crt \
+  --key ./server.key \
+  -L [CLIENT-URL]/metrics \
+  --ciphers ECDHE-RSA-AES128-GCM-SHA256
+
+# request succeeds
+etcd_server_version{server_version="3.2.22"} 1
+...
+```
+
+```bash
+# invalid cipher suite
+$ curl \
+  --cacert ./ca.crt \
+  --cert ./server.crt \
+  --key ./server.key \
+  -L [CLIENT-URL]/metrics \
+  --ciphers ECDHE-RSA-DES-CBC3-SHA
+
+# request fails with
+(35) error:14094410:SSL routines:ssl3_read_bytes:sslv3 alert handshake failure
+```
+
 ## Example 3: Transport security & client certificates in a cluster
 
 etcd supports the same model as above for **peer communication**, that means the communication between etcd members in a cluster.
@@ -181,6 +228,10 @@ To disable certificate chain checking, invoke curl with the `-k` flag:
 $ curl -k https://127.0.0.1:2379/v2/keys/foo -Xput -d value=bar -v
 ```
 
+## Notes for DNS SRV
+
+Since v3.1.0 (except v3.2.9), discovery SRV bootstrapping authenticates `ServerName` with a root domain name from `--discovery-srv` flag. This is to avoid man-in-the-middle cert attacks, by requiring a certificate to have matching root domain name in its Subject Alternative Name (SAN) field. For instance, `etcd --discovery-srv=etcd.local` will only authenticate peers/clients when the provided certs have root domain `etcd.local` as an entry in Subject Alternative Name (SAN) field
+
 ## Notes for etcd proxy
 
 etcd proxy terminates the TLS from its client if the connection is secure, and uses proxy's own key/cert specified in `--peer-key-file` and `--peer-cert-file` to communicate with etcd members.
@@ -189,6 +240,163 @@ The proxy communicates with etcd members through both the `--advertise-client-ur
 
 When client authentication is enabled for an etcd member, the administrator must ensure that the peer certificate specified in the proxy's `--peer-cert-file` option is valid for that authentication. The proxy's peer certificate must also be valid for peer authentication if peer authentication is enabled.
 
+## Notes for TLS authentication
+
+Since [v3.2.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.2.md#v320-2017-06-09), [TLS certificates get reloaded on every client connection](https://github.com/etcd-io/etcd/pull/7829). This is useful when replacing expiry certs without stopping etcd servers; it can be done by overwriting old certs with new ones. Refreshing certs for every connection should not have too much overhead, but can be improved in the future, with caching layer. Example tests can be found [here](https://github.com/coreos/etcd/blob/b041ce5d514a4b4aaeefbffb008f0c7570a18986/integration/v3_grpc_test.go#L1601-L1757).
+
+Since [v3.2.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.2.md#v320-2017-06-09), [server denies incoming peer certs with wrong IP `SAN`](https://github.com/etcd-io/etcd/pull/7687). For instance, if peer cert contains any IP addresses in Subject Alternative Name (SAN) field, server authenticates a peer only when the remote IP address matches one of those IP addresses. This is to prevent unauthorized endpoints from joining the cluster. For example, peer B's CSR (with `cfssl`) is:
+
+```json
+{
+  "CN": "etcd peer",
+  "hosts": [
+    "*.example.default.svc",
+    "*.example.default.svc.cluster.local",
+    "10.138.0.27"
+  ],
+  "key": {
+    "algo": "rsa",
+    "size": 2048
+  },
+  "names": [
+    {
+      "C": "US",
+      "L": "CA",
+      "ST": "San Francisco"
+    }
+  ]
+}
+```
+
+when peer B's actual IP address is `10.138.0.2`, not `10.138.0.27`. When peer B tries to join the cluster, peer A will reject B with the error `x509: certificate is valid for 10.138.0.27, not 10.138.0.2`, because B's remote IP address does not match the one in Subject Alternative Name (SAN) field.
+
+Since [v3.2.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.2.md#v320-2017-06-09), [server resolves TLS `DNSNames` when checking `SAN`](https://github.com/etcd-io/etcd/pull/7767). For instance, if peer cert contains only DNS names (no IP addresses) in Subject Alternative Name (SAN) field, server authenticates a peer only when forward-lookups (`dig b.com`) on those DNS names have matching IP with the remote IP address. For example, peer B's CSR (with `cfssl`) is:
+
+```json
+{
+  "CN": "etcd peer",
+  "hosts": [
+    "b.com"
+  ],
+```
+
+when peer B's remote IP address is `10.138.0.2`. When peer B tries to join the cluster, peer A looks up the incoming host `b.com` to get the list of IP addresses (e.g. `dig b.com`). And rejects B if the list does not contain the IP `10.138.0.2`, with the error `tls: 10.138.0.2 does not match any of DNSNames ["b.com"]`.
+
+Since [v3.2.2](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.2.md#v322-2017-07-07), [server accepts connections if IP matches, without checking DNS entries](https://github.com/etcd-io/etcd/pull/8223). For instance, if peer cert contains IP addresses and DNS names in Subject Alternative Name (SAN) field, and the remote IP address matches one of those IP addresses, server just accepts connection without further checking the DNS names. For example, peer B's CSR (with `cfssl`) is:
+
+```json
+{
+  "CN": "etcd peer",
+  "hosts": [
+    "invalid.domain",
+    "10.138.0.2"
+  ],
+```
+
+when peer B's remote IP address is `10.138.0.2` and `invalid.domain` is a invalid host. When peer B tries to join the cluster, peer A successfully authenticates B, since Subject Alternative Name (SAN) field has a valid matching IP address. See [issue#8206](https://github.com/etcd-io/etcd/issues/8206) for more detail.
+
+Since [v3.2.5](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.2.md#v325-2017-08-04), [server supports reverse-lookup on wildcard DNS `SAN`](https://github.com/etcd-io/etcd/pull/8281). For instance, if peer cert contains only DNS names (no IP addresses) in Subject Alternative Name (SAN) field, server first reverse-lookups the remote IP address to get a list of names mapping to that address (e.g. `nslookup IPADDR`). Then accepts the connection if those names have a matching name with peer cert's DNS names (either by exact or wildcard match). If none is matched, server forward-lookups each DNS entry in peer cert (e.g. look up `example.default.svc` when the entry is `*.example.default.svc`), and accepts connection only when the host's resolved addresses have the matching IP address with the peer's remote IP address. For example, peer B's CSR (with `cfssl`) is:
+
+```json
+{
+  "CN": "etcd peer",
+  "hosts": [
+    "*.example.default.svc",
+    "*.example.default.svc.cluster.local"
+  ],
+```
+
+when peer B's remote IP address is `10.138.0.2`. When peer B tries to join the cluster, peer A reverse-lookup the IP `10.138.0.2` to get the list of host names. And either exact or wildcard match the host names with peer B's cert DNS names in Subject Alternative Name (SAN) field. If none of reverse/forward lookups worked, it returns an error `"tls: "10.138.0.2" does not match any of DNSNames ["*.example.default.svc","*.example.default.svc.cluster.local"]`. See [issue#8268](https://github.com/etcd-io/etcd/issues/8268) for more detail.
+
+[v3.3.0](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.3.md) adds [`etcd --peer-cert-allowed-cn`](https://github.com/etcd-io/etcd/pull/8616) flag to support [CN(Common Name)-based auth for inter-peer connections](https://github.com/etcd-io/etcd/issues/8262). Kubernetes TLS bootstrapping involves generating dynamic certificates for etcd members and other system components (e.g. API server, kubelet, etc.). Maintaining different CAs for each component provides tighter access control to etcd cluster but often tedious. When `--peer-cert-allowed-cn` flag is specified, node can only join with matching common name even with shared CAs. For example, each member in 3-node cluster is set up with CSRs (with `cfssl`) as below:
+
+```json
+{
+  "CN": "etcd.local",
+  "hosts": [
+    "m1.etcd.local",
+    "127.0.0.1",
+    "localhost"
+  ],
+```
+
+```json
+{
+  "CN": "etcd.local",
+  "hosts": [
+    "m2.etcd.local",
+    "127.0.0.1",
+    "localhost"
+  ],
+```
+
+```json
+{
+  "CN": "etcd.local",
+  "hosts": [
+    "m3.etcd.local",
+    "127.0.0.1",
+    "localhost"
+  ],
+```
+
+Then only peers with matching common names will be authenticated if `--peer-cert-allowed-cn etcd.local` is given. And nodes with different CNs in CSRs or different `--peer-cert-allowed-cn` will be rejected:
+
+```bash
+$ etcd --peer-cert-allowed-cn m1.etcd.local
+
+I | embed: rejected connection from "127.0.0.1:48044" (error "CommonName authentication failed", ServerName "m1.etcd.local")
+I | embed: rejected connection from "127.0.0.1:55702" (error "remote error: tls: bad certificate", ServerName "m3.etcd.local")
+```
+
+Each process should be started with:
+
+```bash
+etcd --peer-cert-allowed-cn etcd.local
+
+I | pkg/netutil: resolving m3.etcd.local:32380 to 127.0.0.1:32380
+I | pkg/netutil: resolving m2.etcd.local:22380 to 127.0.0.1:22380
+I | pkg/netutil: resolving m1.etcd.local:2380 to 127.0.0.1:2380
+I | etcdserver: published {Name:m3 ClientURLs:[https://m3.etcd.local:32379]} to cluster 9db03f09b20de32b
+I | embed: ready to serve client requests
+I | etcdserver: published {Name:m1 ClientURLs:[https://m1.etcd.local:2379]} to cluster 9db03f09b20de32b
+I | embed: ready to serve client requests
+I | etcdserver: published {Name:m2 ClientURLs:[https://m2.etcd.local:22379]} to cluster 9db03f09b20de32b
+I | embed: ready to serve client requests
+I | embed: serving client requests on 127.0.0.1:32379
+I | embed: serving client requests on 127.0.0.1:22379
+I | embed: serving client requests on 127.0.0.1:2379
+```
+
+[v3.2.19](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.2.md) and [v3.3.4](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.3.md) fixes TLS reload when [certificate SAN field only includes IP addresses but no domain names](https://github.com/etcd-io/etcd/issues/9541). For example, a member is set up with CSRs (with `cfssl`) as below:
+
+```json
+{
+  "CN": "etcd.local",
+  "hosts": [
+    "127.0.0.1"
+  ],
+```
+
+In Go, server calls `(*tls.Config).GetCertificate` for TLS reload if and only if server's `(*tls.Config).Certificates` field is not empty, or `(*tls.ClientHelloInfo).ServerName` is not empty with a valid SNI from the client. Previously, etcd always populates `(*tls.Config).Certificates` on the initial client TLS handshake, as non-empty. Thus, client was always expected to supply a matching SNI in order to pass the TLS verification and to trigger `(*tls.Config).GetCertificate` to reload TLS assets.
+
+However, a certificate whose SAN field does [not include any domain names but only IP addresses](https://github.com/etcd-io/etcd/issues/9541) would request `*tls.ClientHelloInfo` with an empty `ServerName` field, thus failing to trigger the TLS reload on initial TLS handshake; this becomes a problem when expired certificates need to be replaced online.
+
+Now, `(*tls.Config).Certificates` is created empty on initial TLS client handshake, first to trigger `(*tls.Config).GetCertificate`, and then to populate rest of the certificates on every new TLS connection, even when client SNI is empty (e.g. cert only includes IPs).
+
+## Notes for Host Whitelist
+
+`etcd --host-whitelist` flag specifies acceptable hostnames from HTTP client requests. Client origin policy protects against ["DNS Rebinding"](https://en.wikipedia.org/wiki/DNS_rebinding) attacks to insecure etcd servers. That is, any website can simply create an authorized DNS name, and direct DNS to `"localhost"` (or any other address). Then, all HTTP endpoints of etcd server listening on `"localhost"` becomes accessible, thus vulnerable to DNS rebinding attacks. See [CVE-2018-5702](https://bugs.chromium.org/p/project-zero/issues/detail?id=1447#c2) for more detail.
+
+Client origin policy works as follows:
+
+1. If client connection is secure via HTTPS, allow any hostnames.
+2. If client connection is not secure and `"HostWhitelist"` is not empty, only allow HTTP requests whose Host field is listed in whitelist.
+
+Note that the client origin policy is enforced whether authentication is enabled or not, for tighter controls.
+
+By default, `etcd --host-whitelist` and `embed.Config.HostWhitelist` are set *empty* to allow all hostnames. Note that when specifying hostnames, loopback addresses are not added automatically. To allow loopback interfaces, add them to whitelist manually (e.g. `"localhost"`, `"127.0.0.1"`, etc.).
+
 ## Frequently asked questions
 
 ### I'm seeing a SSLv3 alert handshake failure when using TLS client authentication?

Documentation/op-guide/supported-platform.md

@@ -1,12 +1,14 @@
-## Supported platforms
+---
+title: Supported systems
+---
 
-### Current support
+## Current support
 
-The following table lists etcd support status for common architectures and operating systems,
+The following table lists etcd support status for common architectures and operating systems:
 
 | Architecture | Operating System | Status       | Maintainers                 |
 | ------------ | ---------------- | ------------ | --------------------------- |
-| amd64        | Darwin           | Experimental | etcd maintainers            | 
+| amd64        | Darwin           | Experimental | etcd maintainers            |
 | amd64        | Linux            | Stable       | etcd maintainers            |
 | amd64        | Windows          | Experimental |                             |
 | arm64        | Linux            | Experimental | @glevand                    |
@@ -14,11 +16,11 @@ The following table lists etcd support status for common architectures and opera
 | 386          | Linux            | Unstable     |                             |
 | ppc64le      | Linux            | Stable       | etcd maintainers, @mkumatag |
 
-* etcd-maintainers are listed in https://github.com/coreos/etcd/blob/master/MAINTAINERS.
+* etcd-maintainers are listed in https://github.com/etcd-io/etcd/blob/master/MAINTAINERS.
 
 Experimental platforms appear to work in practice and have some platform specific code in etcd, but do not fully conform to the stable support policy. Unstable platforms have been lightly tested, but less than experimental. Unlisted architecture and operating system pairs are currently unsupported; caveat emptor.
 
-### Supporting a new platform
+## Supporting a new system platform
 
 For etcd to officially support a new platform as stable, a few requirements are necessary to ensure acceptable quality:
 
@@ -28,7 +30,7 @@ For etcd to officially support a new platform as stable, a few requirements are
 4. Set up CI (TravisCI, SemaphoreCI or Jenkins) for running integration tests; etcd must pass intensive tests.
 5. (Optional) Set up a functional testing cluster; an etcd cluster should survive stress testing.
 
-### 32-bit and other unsupported systems
+## 32-bit and other unsupported systems
 
 etcd has known issues on 32-bit systems due to a bug in the Go runtime. See the [Go issue][go-issue] and [atomic package][go-atomic] for more information.
 

Documentation/op-guide/v2-migration.md

@@ -1,4 +1,6 @@
-# Migrate applications from using API v2 to API v3
+---
+title: Migrate applications from using API v2 to API v3
+---
 
 The data store v2 is still accessible from the API v2 after upgrading to etcd3. Thus, it will work as before and require no application changes. With etcd 3, applications use the new grpc API v3 to access the mvcc store, which provides more features and improved performance. The mvcc store and the old store v2 are separate and isolated; writes to the store v2 will not affect the mvcc store and, similarly, writes to the mvcc store will not affect the store v2.
 
@@ -6,7 +8,7 @@ Migrating an application from the API v2 to the API v3 involves two steps: 1) mi
 
 ## Migrate client library
 
-API v3 is different from API v2, thus application developers need to use a new client library to send requests to etcd API v3. The documentation of the client v3 is available at https://godoc.org/github.com/coreos/etcd/clientv3. 
+API v3 is different from API v2, thus application developers need to use a new client library to send requests to etcd API v3. The documentation of the client v3 is available at https://godoc.org/github.com/coreos/etcd/clientv3.
 
 There are some notable differences between API v2 and API v3:
 
@@ -38,13 +40,17 @@ Second, migrate the v2 keys into v3 with the [migrate][migrate_command] (`ETCDCT
 
 Restart the etcd members and everything should just work.
 
+For etcd v3.3+, run `ETCDCTL_API=3 etcdctl endpoint hashkv --cluster` to ensure key-value stores are consistent post migration.
+
+**Warn**: When v2 store has expiring TTL keys and migrate command intends to preserve TTLs, migration may be inconsistent with the last committed v2 state when run on any member with a raft index less than the last leader's raft index.
+
 ### Online migration
 
 If the application cannot tolerate any downtime, then it must migrate online. The implementation of online migration will vary from application to application but the overall idea is the same.
 
 First, write application code using the v3 API. The application must support two modes: a migration mode and a normal mode. The application starts in migration mode. When running in migration mode, the application reads keys using the v3 API first, and, if it cannot find the key, it retries with the API v2. In normal mode, the application only reads keys using the v3 API. The application writes keys over the API v3 in both modes. To acknowledge a switch from migration mode to normal mode, the application watches on a switch mode key. When switch key’s value turns to `true`, the application switches over from migration mode to normal mode.
 
-Second, start a background job to migrate data from the store v2 to the mvcc store by reading keys from the API v2 and writing keys to the API v3. 
+Second, start a background job to migrate data from the store v2 to the mvcc store by reading keys from the API v2 and writing keys to the API v3.
 
 After finishing data migration, the background job writes `true` into the switch mode key to notify the application that it may switch modes.
 

Documentation/op-guide/versioning.md

@@ -1,6 +1,8 @@
-## Versioning
+---
+title: Versioning
+---
 
-### Service versioning
+## Service versioning
 
 etcd uses [semantic versioning](http://semver.org)
 New minor versions may add additional features to the API.
@@ -11,7 +13,7 @@ Get the running etcd cluster version with `etcdctl`:
 ETCDCTL_API=3 etcdctl --endpoints=127.0.0.1:2379 endpoint status
 ```
 
-### API versioning
+## API versioning
 
 The `v3` API responses should not change after the 3.0.0 release but new features will be added over time.
 

Documentation/platforms/_index.md

@@ -0,0 +1,3 @@
+---
+title: Platforms
+---

Documentation/platforms/aws.md

@@ -1,4 +1,6 @@
-## Introduction
+---
+title: Amazon Web Services
+---
 
 This guide assumes operational knowledge of Amazon Web Services (AWS), specifically Amazon Elastic Compute Cloud (EC2). This guide provides an introduction to design considerations when designing an etcd deployment on AWS EC2 and how AWS specific features may be utilized in that context.
 
@@ -6,7 +8,7 @@ This guide assumes operational knowledge of Amazon Web Services (AWS), specifica
 
 As a critical building block for distributed systems it is crucial to perform adequate capacity planning in order to support the intended cluster workload. As a highly available and strongly consistent data store increasing the number of nodes in an etcd cluster will generally affect performance adversely. This makes sense intuitively, as more nodes means more members for the leader to coordinate state across. The most direct way to increase throughput and decrease latency of an etcd cluster is allocate more disk I/O, network I/O, CPU, and memory to cluster members. In the event it is impossible to temporarily divert incoming requests to the cluster, scaling the EC2 instances which comprise the etcd cluster members one at a time may improve performance. It is, however, best to avoid bottlenecks through capacity planning.
 
-The etcd team has produced a [hardware recommendation guide]( ../op-guide/hardware.md) which is very useful for “ballparking” how many nodes and what instance type are necessary for a cluster.
+The etcd team has produced a [hardware recommendation guide](../op-guide/hardware.md) which is very useful for “ballparking” how many nodes and what instance type are necessary for a cluster.
 
 AWS provides a service for creating groups of EC2 instances which are dynamically sized to match load on the instances. Using an Auto Scaling Group ([ASG](http://docs.aws.amazon.com/autoscaling/latest/userguide/AutoScalingGroup.html)) to dynamically scale an etcd cluster is not recommended for several reasons including:
 

Documentation/platforms/container-linux-systemd.md

@@ -1,4 +1,6 @@
-# Run etcd on Container Linux with systemd
+---
+title: Container Linux with systemd
+---
 
 The following guide shows how to run etcd with [systemd][systemd-docs] under [Container Linux][container-linux-docs].
 
@@ -134,13 +136,13 @@ etcd:
   initial_cluster_state:       new
   client_cert_auth:            true
   trusted_ca_file:             /etc/ssl/certs/etcd-root-ca.pem
-  cert-file:                   /etc/ssl/certs/s1.pem
-  key-file:                    /etc/ssl/certs/s1-key.pem
-  peer-client-cert-auth:       true
-  peer-trusted-ca-file:        /etc/ssl/certs/etcd-root-ca.pem
-  peer-cert-file:              /etc/ssl/certs/s1.pem
-  peer-key-file:               /etc/ssl/certs/s1-key.pem
-  auto-compaction-retention:   1
+  cert_file:                   /etc/ssl/certs/s1.pem
+  key_file:                    /etc/ssl/certs/s1-key.pem
+  peer_client_cert_auth:       true
+  peer_trusted_ca_file:        /etc/ssl/certs/etcd-root-ca.pem
+  peer_cert_file:              /etc/ssl/certs/s1.pem
+  peer_key_file:               /etc/ssl/certs/s1-key.pem
+  auto_compaction_retention:   1
 ```
 
 ```

Documentation/platforms/freebsd.md

@@ -1,4 +1,6 @@
-# FreeBSD
+---
+title: FreeBSD
+---
 
 Starting with version 0.1.2 both etcd and etcdctl have been ported to FreeBSD and can be installed either via packages or ports system. Their versions have been recently updated to 0.2.0 so now etcd and etcdctl can be enjoyed on FreeBSD 10.0 (RC4 as of now) and 9.x, where they have been tested. They might also work when installed from ports on earlier versions of FreeBSD, but it is untested; caveat emptor.
 

Documentation/production-users.md

@@ -1,4 +1,6 @@
-# Production users
+---
+title: Production users
+---
 
 This document tracks people and use cases for etcd in production. By creating a list of production use cases we hope to build a community of advisors that we can reach out to with experience using various etcd applications, operation environments, and cluster sizes. The etcd development team may reach out periodically to check-in on how etcd is working in the field and update this list.
 
@@ -79,9 +81,9 @@ Radius Intelligence uses Kubernetes running CoreOS to containerize and scale int
 
 PD(Placement Driver) is the central controller in the TiDB cluster. It saves the cluster meta information, schedule the data, allocate the global unique timestamp for the distributed transaction, etc. It embeds etcd to supply high availability and auto failover.
 
-## Canal
+## Huawei
 
-- *Application*: system configuration for overlay network
+- *Application*: System configuration for overlay network (Canal)
 - *Launched*: June 2016
 - *Cluster Size*: 3 members for each cluster
 - *Order of Data Size*: kilobytes
@@ -237,3 +239,12 @@ At [Branch][branch], we use kubernetes heavily as our core microservice platform
 - *Environment*: Bare Metal
 - *Backups*: None, all data is considered ephemeral.
 
+## Transwarp
+
+- *Application*: Transwarp Data Cloud, Transwarp Operating System, Transwarp Data Hub, Sophon
+- *Launched*: January 2016
+- *Cluster Size*: Multiple clusters, multiple sizes
+- *Order of Data Size*: Megabytes
+- *Operator*: Trasnwarp Operating System
+- *Environment*: Bare Metal, Container
+- *Backups*: backup scripts

Documentation/reporting_bugs.md

@@ -1,4 +1,6 @@
-# Reporting bugs
+---
+title: Reporting bugs
+---
 
 If any part of the etcd project has bugs or documentation mistakes, please let us know by [opening an issue][etcd-issue]. We treat bugs and mistakes very seriously and believe no issue is too small. Before creating a bug report, please check that an issue reporting the same problem does not already exist.
 
@@ -41,5 +43,5 @@ $ sudo journalctl -u etcd2
 
 Due to an upstream systemd bug, journald may miss the last few log lines when its processes exit. If journalctl says etcd stopped without fatal or panic message, try `sudo journalctl -f -t etcd2` to get full log.
 
-[etcd-issue]: https://github.com/coreos/etcd/issues/new
+[etcd-issue]: https://github.com/etcd-io/etcd/issues/new
 [filing-good-bugs]: http://fantasai.inkedblade.net/style/talks/filing-good-bugs/

Documentation/rfc/_index.md

@@ -1,4 +1,6 @@
-# Overview
+---
+title: etcd v3 API
+---
 
 The etcd v3 API is designed to give users a more efficient and cleaner abstraction compared to etcd v2. There are a number of semantic and protocol changes in this new API. For an overview [see Xiang Li's video](https://youtu.be/J5AioGtEPeQ?t=211).
 
@@ -52,6 +54,7 @@ the size in the future a little bit or make it configurable.
 ## Examples
 
 ### Put a key (foo=bar)
+
 ```
 // A put is always successful
 Put( PutRequest { key = foo, value = bar } )
@@ -207,5 +210,5 @@ WatchResponse {
 
 ```
 
-[api-protobuf]: https://github.com/coreos/etcd/blob/release-2.3/etcdserver/etcdserverpb/rpc.proto
-[kv-protobuf]: https://github.com/coreos/etcd/blob/release-2.3/storage/storagepb/kv.proto
+[api-protobuf]: https://github.com/etcd-io/etcd/blob/master/etcdserver/etcdserverpb/rpc.proto
+[kv-protobuf]: https://github.com/etcd-io/etcd/blob/master/mvcc/mvccpb/kv.proto

Documentation/rfc/v3api.md

@@ -1,211 +0,0 @@
-# Overview
-
-The etcd v3 API is designed to give users a more efficient and cleaner abstraction compared to etcd v2. There are a number of semantic and protocol changes in this new API. For an overview [see Xiang Li's video](https://youtu.be/J5AioGtEPeQ?t=211).
-
-To prove out the design of the v3 API the team has also built [a number of example recipes](https://github.com/coreos/etcd/tree/master/contrib/recipes), there is a [video discussing these recipes too](https://www.youtube.com/watch?v=fj-2RY-3yVU&feature=youtu.be&t=590).
-
-# Design
-
-1. Flatten binary key-value space
-    
-2. Keep the event history until compaction
-    - access to old version of keys
-    - user controlled history compaction
-    
-3. Support range query
-    - Pagination support with limit argument
-    - Support consistency guarantee across multiple range queries
-    
-4. Replace TTL key with Lease
-    - more efficient/ low cost keep alive
-    - a logical group of TTL keys
-    
-5. Replace CAS/CAD with multi-object Txn
-    - MUCH MORE powerful and flexible
-    
-6. Support efficient watching with multiple ranges
-
-7. RPC API supports the completed set of APIs. 
-    - more efficient than JSON/HTTP
-    - additional txn/lease support
-
-8. HTTP API supports a subset of APIs.
-    - easy for people to try out etcd
-    - easy for people to write simple etcd application
-
-
-## Notes
-
-### Request Size Limitation
-
-The max request size is around 1MB. Since etcd replicates requests in a streaming fashion, a very large
-request might block other requests for a long time. The use case for etcd is to store small configuration
-values, so we prevent user from submitting large requests. This also applies to Txn requests. We might loosen
-the size in the future a little bit or make it configurable.
-
-## Protobuf Defined API
-
-[api protobuf][api-protobuf]
-
-[kv protobuf][kv-protobuf]
-
-## Examples
-
-### Put a key (foo=bar)
-```
-// A put is always successful
-Put( PutRequest { key = foo, value = bar } )
-
-PutResponse { 
-    cluster_id = 0x1000,
-    member_id = 0x1,
-    revision = 1,
-    raft_term = 0x1,
-}
-```
-
-### Get a key (assume we have foo=bar)
-```
-Get ( RangeRequest { key = foo } )
-
-RangeResponse {
-    cluster_id = 0x1000,
-    member_id = 0x1,
-    revision = 1,
-    raft_term = 0x1,
-    kvs = {
-      {
-          key = foo,
-          value = bar,
-          create_revision = 1,
-          mod_revision = 1,
-          version = 1;
-      },
-    },
-}
-```
-
-### Range over a key space (assume we have foo0=bar0… foo100=bar100)
-```
-Range ( RangeRequest { key = foo, end_key = foo80, limit = 30  } )
-
-RangeResponse {
-    cluster_id = 0x1000,
-    member_id = 0x1,
-    revision = 100,
-    raft_term = 0x1,
-    kvs = {
-      {
-          key = foo0,
-          value = bar0,
-          create_revision = 1,
-          mod_revision = 1,
-          version = 1;
-      },
-         ...,
-      {
-          key = foo30,
-          value = bar30,
-          create_revision = 30,
-          mod_revision = 30,
-          version = 1;
-      },
-    },
-}
-```
-
-### Finish a txn (assume we have foo0=bar0, foo1=bar1)
-```
-Txn(TxnRequest {
-    // mod_revision of foo0 is equal to 1, mod_revision of foo1 is greater than 1
-    compare = {
-        {compareType = equal, key = foo0, mod_revision = 1}, 
-        {compareType = greater, key = foo1, mod_revision = 1}}
-    },
-    // if the comparison succeeds, put foo2 = bar2
-    success = {PutRequest { key = foo2, value = success }},
-    // if the comparison fails, put foo2=fail
-    failure = {PutRequest { key = foo2, value = failure }},
-)
-
-TxnResponse {
-    cluster_id = 0x1000,
-    member_id = 0x1,
-    revision = 3,
-    raft_term = 0x1,
-    succeeded = true,
-    responses = {
-      // response of PUT foo2=success
-      {
-            cluster_id = 0x1000,
-            member_id = 0x1,
-            revision = 3,
-            raft_term = 0x1,
-        }
-    }
-}
-```
-
-### Watch on a key/range
-
-```
-Watch( WatchRequest{
-           key = foo,
-           end_key = fop, // prefix foo
-           start_revision = 20,
-           end_revision = 10000,
-           // server decided notification frequency
-           progress_notification = true,
-       } 
-       … // this can be a watch request stream
-      )
-
-// put (foo0=bar0) event at 3
-WatchResponse {
-    cluster_id = 0x1000,
-    member_id = 0x1,
-    revision = 3,
-    raft_term = 0x1,
-    event_type = put,
-    kv = {
-              key = foo0,
-              value = bar0,
-              create_revision = 1,
-              mod_revision = 1,
-              version = 1;
-          },
-    }
-    …
-    
-    // a notification at 2000
-    WatchResponse {
-        cluster_id = 0x1000,
-        member_id = 0x1,
-        revision = 2000,
-        raft_term = 0x1,
-        // nil event as notification
-    }
-    
-    … 
-    
-    // put (foo0=bar3000) event at 3000
-    WatchResponse {
-        cluster_id = 0x1000,
-        member_id = 0x1,
-        revision = 3000,
-        raft_term = 0x1,
-        event_type = put,
-        kv = {
-                key = foo0,
-                value = bar3000,
-                create_revision = 1,
-                mod_revision = 3000,
-                version = 2;
-          },
-    }
-    …
-    
-```
-
-[api-protobuf]: https://github.com/coreos/etcd/blob/master/etcdserver/etcdserverpb/rpc.proto
-[kv-protobuf]: https://github.com/coreos/etcd/blob/master/mvcc/mvccpb/kv.proto

Documentation/tuning.md

@@ -1,4 +1,6 @@
-# Tuning
+---
+title: Tuning
+---
 
 The default settings in etcd should work well for installations on a local network where the average network latency is low. However, when using etcd across multiple data centers or over networks with high latency, the heartbeat interval and election timeout settings may need tuning.
 
@@ -71,12 +73,12 @@ dropped MsgAppResp to 247ae21ff9436b2d since streamMsg's sending buffer is full
 
 These errors may be resolved by prioritizing etcd's peer traffic over its client traffic. On Linux, peer traffic can be prioritized by using the traffic control mechanism:
 
-```
+```sh
 tc qdisc add dev eth0 root handle 1: prio bands 3
 tc filter add dev eth0 parent 1: protocol ip prio 1 u32 match ip sport 2380 0xffff flowid 1:1
 tc filter add dev eth0 parent 1: protocol ip prio 1 u32 match ip dport 2380 0xffff flowid 1:1
-tc filter add dev eth0 parent 1: protocol ip prio 2 u32 match ip sport 2739 0xffff flowid 1:1
-tc filter add dev eth0 parent 1: protocol ip prio 2 u32 match ip dport 2739 0xffff flowid 1:1
+tc filter add dev eth0 parent 1: protocol ip prio 2 u32 match ip sport 2379 0xffff flowid 1:1
+tc filter add dev eth0 parent 1: protocol ip prio 2 u32 match ip dport 2379 0xffff flowid 1:1
 ```
 
 [ping]: https://en.wikipedia.org/wiki/Ping_(networking_utility)

Documentation/upgrades/_index.md

@@ -0,0 +1,3 @@
+---
+title: Upgrading
+---

Documentation/upgrades/upgrade_3_0.md

@@ -1,4 +1,6 @@
-## Upgrade etcd from 2.3 to 3.0
+---
+title: Upgrade etcd from 2.3 to 3.0
+---
 
 In the general case, upgrading from etcd 2.3 to 3.0 can be a zero-downtime, rolling upgrade:
  - one by one, stop the etcd v2.3 processes and replace them with etcd v3.0 processes
@@ -8,6 +10,8 @@ Before [starting an upgrade](#upgrade-procedure), read through the rest of this
 
 ### Upgrade checklists
 
+**NOTE:** When [migrating from v2 with no v3 data](https://github.com/etcd-io/etcd/issues/9480), etcd server v3.2+ panics when etcd restores from existing snapshots but no v3 `ETCD_DATA_DIR/member/snap/db` file. This happens when the server had migrated from v2 with no previous v3 data. This also prevents accidental v3 data loss (e.g. `db` file might have been moved). etcd requires that post v3 migration can only happen with v3 data. Do not upgrade to newer v3 versions until v3.0 server contains v3 data.
+
 #### Upgrade requirements
 
 To upgrade an existing etcd deployment to 3.0, the running cluster must be 2.3 or greater. If it's before 2.3, please upgrade to [2.3](https://github.com/coreos/etcd/releases/tag/v2.3.8) before upgrading to 3.0.
@@ -122,8 +126,8 @@ $ ETCDCTL_API=3 etcdctl endpoint health
 
 ## Known Issues
 
-- etcd < v3.1 does not work properly if built with Go > v1.7. See [Issue 6951](https://github.com/coreos/etcd/issues/6951) for additional information.
+- etcd < v3.1 does not work properly if built with Go > v1.7. See [Issue 6951](https://github.com/etcd-io/etcd/issues/6951) for additional information.
 - If an error such as `transport: http2Client.notifyError got notified that the client transport was broken unexpected EOF.` shows up in the etcd server logs, be sure etcd is a pre-built release or built with (etcd v3.1+ & go v1.7+) or (etcd <v3.1 & go v1.6.x).
-- Adding a v3 node to v2.3 cluster during upgrades is not supported and could trigger panics. See [Issue 7249](https://github.com/coreos/etcd/issues/7429) for additional information. Mixed versions of etcd members are only allowed during v3 migration. Finish upgrades before making any membership changes.
+- Adding a v3 node to v2.3 cluster during upgrades is not supported and could trigger panics. See [Issue 7249](https://github.com/etcd-io/etcd/issues/7429) for additional information. Mixed versions of etcd members are only allowed during v3 migration. Finish upgrades before making any membership changes.
 
 [etcd-contact]: https://groups.google.com/forum/#!forum/etcd-dev

Documentation/upgrades/upgrade_3_1.md

@@ -1,4 +1,6 @@
-## Upgrade etcd from 3.0 to 3.1
+---
+title: Upgrade etcd from 3.0 to 3.1
+---
 
 In the general case, upgrading from etcd 3.0 to 3.1 can be a zero-downtime, rolling upgrade:
  - one by one, stop the etcd v3.0 processes and replace them with etcd v3.1 processes
@@ -8,6 +10,17 @@ Before [starting an upgrade](#upgrade-procedure), read through the rest of this
 
 ### Upgrade checklists
 
+**NOTE:** When [migrating from v2 with no v3 data](https://github.com/etcd-io/etcd/issues/9480), etcd server v3.2+ panics when etcd restores from existing snapshots but no v3 `ETCD_DATA_DIR/member/snap/db` file. This happens when the server had migrated from v2 with no previous v3 data. This also prevents accidental v3 data loss (e.g. `db` file might have been moved). etcd requires that post v3 migration can only happen with v3 data. Do not upgrade to newer v3 versions until v3.0 server contains v3 data.
+
+#### Monitoring
+
+Following metrics from v3.0.x have been deprecated in favor of [go-grpc-prometheus](https://github.com/grpc-ecosystem/go-grpc-prometheus):
+
+- `etcd_grpc_requests_total`
+- `etcd_grpc_requests_failed_total`
+- `etcd_grpc_active_streams`
+- `etcd_grpc_unary_requests_duration_seconds`
+
 #### Upgrade requirements
 
 To upgrade an existing etcd deployment to 3.1, the running cluster must be 3.0 or greater. If it's before 3.0, please [upgrade to 3.0](upgrade_3_0.md) before upgrading to 3.1.

Documentation/upgrades/upgrade_3_2.md

@@ -1,4 +1,6 @@
-## Upgrade etcd from 3.1 to 3.2
+---
+title: Upgrade etcd from 3.1 to 3.2
+---
 
 In the general case, upgrading from etcd 3.1 to 3.2 can be a zero-downtime, rolling upgrade:
  - one by one, stop the etcd v3.1 processes and replace them with etcd v3.2 processes
@@ -6,11 +8,171 @@ In the general case, upgrading from etcd 3.1 to 3.2 can be a zero-downtime, roll
 
 Before [starting an upgrade](#upgrade-procedure), read through the rest of this guide to prepare.
 
-### Client upgrade checklists
+### Upgrade checklists
 
-3.2 introduces two breaking changes.
+**NOTE:** When [migrating from v2 with no v3 data](https://github.com/etcd-io/etcd/issues/9480), etcd server v3.2+ panics when etcd restores from existing snapshots but no v3 `ETCD_DATA_DIR/member/snap/db` file. This happens when the server had migrated from v2 with no previous v3 data. This also prevents accidental v3 data loss (e.g. `db` file might have been moved). etcd requires that post v3 migration can only happen with v3 data. Do not upgrade to newer v3 versions until v3.0 server contains v3 data.
 
-Previously, `clientv3.Lease.TimeToLive` API returned `lease.ErrLeaseNotFound` on non-existent lease ID. 3.2 instead returns TTL=-1 in its response and no error (see [#7305](https://github.com/coreos/etcd/pull/7305)).
+Highlighted breaking changes in 3.2.
+
+#### Changed default `snapshot-count` value
+
+Higher `--snapshot-count` holds more Raft entries in memory until snapshot, thus causing [recurrent higher memory usage](https://github.com/kubernetes/kubernetes/issues/60589#issuecomment-371977156). Since leader retains latest Raft entries for longer, a slow follower has more time to catch up before leader snapshot. `--snapshot-count` is a tradeoff between higher memory usage and better availabilities of slow followers.
+
+Since v3.2, the default value of `--snapshot-count` has [changed from from 10,000 to 100,000](https://github.com/etcd-io/etcd/pull/7160).
+
+#### Changed gRPC dependency (>=3.2.10)
+
+3.2.10 or later now requires [grpc/grpc-go](https://github.com/grpc/grpc-go/releases) `v1.7.5` (<=3.2.9 requires `v1.2.1`).
+
+##### Deprecated `grpclog.Logger`
+
+`grpclog.Logger` has been deprecated in favor of [`grpclog.LoggerV2`](https://github.com/grpc/grpc-go/blob/master/grpclog/loggerv2.go). `clientv3.Logger` is now `grpclog.LoggerV2`.
+
+Before
+
+```go
+import "github.com/coreos/etcd/clientv3"
+clientv3.SetLogger(log.New(os.Stderr, "grpc: ", 0))
+```
+
+After
+
+```go
+import "github.com/coreos/etcd/clientv3"
+import "google.golang.org/grpc/grpclog"
+clientv3.SetLogger(grpclog.NewLoggerV2(os.Stderr, os.Stderr, os.Stderr))
+
+// log.New above cannot be used (not implement grpclog.LoggerV2 interface)
+```
+
+##### Deprecated `grpc.ErrClientConnTimeout`
+
+Previously, `grpc.ErrClientConnTimeout` error is returned on client dial time-outs. 3.2 instead returns `context.DeadlineExceeded` (see [#8504](https://github.com/etcd-io/etcd/issues/8504)).
+
+Before
+
+```go
+// expect dial time-out on ipv4 blackhole
+_, err := clientv3.New(clientv3.Config{
+    Endpoints:   []string{"http://254.0.0.1:12345"},
+    DialTimeout: 2 * time.Second
+})
+if err == grpc.ErrClientConnTimeout {
+	// handle errors
+}
+```
+
+After
+
+```go
+_, err := clientv3.New(clientv3.Config{
+    Endpoints:   []string{"http://254.0.0.1:12345"},
+    DialTimeout: 2 * time.Second
+})
+if err == context.DeadlineExceeded {
+	// handle errors
+}
+```
+
+#### Changed maximum request size limits (>=3.2.10)
+
+3.2.10 and 3.2.11 allow custom request size limits in server side. >=3.2.12 allows custom request size limits for both server and **client side**. In previous versions(v3.2.10, v3.2.11), client response size was limited to only 4 MiB.
+
+Server-side request limits can be configured with `--max-request-bytes` flag:
+
+```bash
+# limits request size to 1.5 KiB
+etcd --max-request-bytes 1536
+
+# client writes exceeding 1.5 KiB will be rejected
+etcdctl put foo [LARGE VALUE...]
+# etcdserver: request is too large
+```
+
+Or configure `embed.Config.MaxRequestBytes` field:
+
+```go
+import "github.com/coreos/etcd/embed"
+import "github.com/coreos/etcd/etcdserver/api/v3rpc/rpctypes"
+
+// limit requests to 5 MiB
+cfg := embed.NewConfig()
+cfg.MaxRequestBytes = 5 * 1024 * 1024
+
+// client writes exceeding 5 MiB will be rejected
+_, err := cli.Put(ctx, "foo", [LARGE VALUE...])
+err == rpctypes.ErrRequestTooLarge
+```
+
+**If not specified, server-side limit defaults to 1.5 MiB**.
+
+Client-side request limits must be configured based on server-side limits.
+
+```bash
+# limits request size to 1 MiB
+etcd --max-request-bytes 1048576
+```
+
+```go
+import "github.com/coreos/etcd/clientv3"
+
+cli, _ := clientv3.New(clientv3.Config{
+    Endpoints: []string{"127.0.0.1:2379"},
+    MaxCallSendMsgSize: 2 * 1024 * 1024,
+    MaxCallRecvMsgSize: 3 * 1024 * 1024,
+})
+
+
+// client writes exceeding "--max-request-bytes" will be rejected from etcd server
+_, err := cli.Put(ctx, "foo", strings.Repeat("a", 1*1024*1024+5))
+err == rpctypes.ErrRequestTooLarge
+
+
+// client writes exceeding "MaxCallSendMsgSize" will be rejected from client-side
+_, err = cli.Put(ctx, "foo", strings.Repeat("a", 5*1024*1024))
+err.Error() == "rpc error: code = ResourceExhausted desc = grpc: trying to send message larger than max (5242890 vs. 2097152)"
+
+
+// some writes under limits
+for i := range []int{0,1,2,3,4} {
+    _, err = cli.Put(ctx, fmt.Sprintf("foo%d", i), strings.Repeat("a", 1*1024*1024-500))
+    if err != nil {
+        panic(err)
+    }
+}
+// client reads exceeding "MaxCallRecvMsgSize" will be rejected from client-side
+_, err = cli.Get(ctx, "foo", clientv3.WithPrefix())
+err.Error() == "rpc error: code = ResourceExhausted desc = grpc: received message larger than max (5240509 vs. 3145728)"
+```
+
+**If not specified, client-side send limit defaults to 2 MiB (1.5 MiB + gRPC overhead bytes) and receive limit to `math.MaxInt32`**. Please see [clientv3 godoc](https://godoc.org/github.com/coreos/etcd/clientv3#Config) for more detail.
+
+#### Changed raw gRPC client wrappers
+
+3.2.12 or later changes the function signatures of `clientv3` gRPC client wrapper. This change was needed to support [custom `grpc.CallOption` on message size limits](https://github.com/etcd-io/etcd/pull/9047).
+
+Before and after
+
+```diff
+-func NewKVFromKVClient(remote pb.KVClient) KV {
++func NewKVFromKVClient(remote pb.KVClient, c *Client) KV {
+
+-func NewClusterFromClusterClient(remote pb.ClusterClient) Cluster {
++func NewClusterFromClusterClient(remote pb.ClusterClient, c *Client) Cluster {
+
+-func NewLeaseFromLeaseClient(remote pb.LeaseClient, keepAliveTimeout time.Duration) Lease {
++func NewLeaseFromLeaseClient(remote pb.LeaseClient, c *Client, keepAliveTimeout time.Duration) Lease {
+
+-func NewMaintenanceFromMaintenanceClient(remote pb.MaintenanceClient) Maintenance {
++func NewMaintenanceFromMaintenanceClient(remote pb.MaintenanceClient, c *Client) Maintenance {
+
+-func NewWatchFromWatchClient(wc pb.WatchClient) Watcher {
++func NewWatchFromWatchClient(wc pb.WatchClient, c *Client) Watcher {
+```
+
+#### Changed `clientv3.Lease.TimeToLive` API
+
+Previously, `clientv3.Lease.TimeToLive` API returned `lease.ErrLeaseNotFound` on non-existent lease ID. 3.2 instead returns TTL=-1 in its response and no error (see [#7305](https://github.com/etcd-io/etcd/pull/7305)).
 
 Before
 
@@ -30,6 +192,8 @@ resp.TTL == -1
 err == nil
 ```
 
+#### Moved `clientv3.NewFromConfigFile` to `clientv3.yaml.NewConfig`
+
 `clientv3.NewFromConfigFile` is moved to `yaml.NewConfig`.
 
 Before
@@ -46,6 +210,12 @@ import clientv3yaml "github.com/coreos/etcd/clientv3/yaml"
 clientv3yaml.NewConfig
 ```
 
+#### Change in `--listen-peer-urls` and `--listen-client-urls`
+
+3.2 now rejects domains names for `--listen-peer-urls` and `--listen-client-urls` (3.1 only prints out warnings), since domain name is invalid for network interface binding. Make sure that those URLs are properly formated as `scheme://IP:port`.
+
+See [issue #6336](https://github.com/etcd-io/etcd/issues/6336) for more contexts.
+
 ### Server upgrade checklists
 
 #### Upgrade requirements

Documentation/upgrades/upgrade_3_3.md

@@ -0,0 +1,541 @@
+---
+title: Upgrade etcd from 3.2 to 3.3
+---
+
+In the general case, upgrading from etcd 3.2 to 3.3 can be a zero-downtime, rolling upgrade:
+ - one by one, stop the etcd v3.2 processes and replace them with etcd v3.3 processes
+ - after running all v3.3 processes, new features in v3.3 are available to the cluster
+
+Before [starting an upgrade](#upgrade-procedure), read through the rest of this guide to prepare.
+
+### Upgrade checklists
+
+**NOTE:** When [migrating from v2 with no v3 data](https://github.com/etcd-io/etcd/issues/9480), etcd server v3.2+ panics when etcd restores from existing snapshots but no v3 `ETCD_DATA_DIR/member/snap/db` file. This happens when the server had migrated from v2 with no previous v3 data. This also prevents accidental v3 data loss (e.g. `db` file might have been moved). etcd requires that post v3 migration can only happen with v3 data. Do not upgrade to newer v3 versions until v3.0 server contains v3 data.
+
+Highlighted breaking changes in 3.3.
+
+#### Changed value type of `etcd --auto-compaction-retention` flag to `string`
+
+Changed `--auto-compaction-retention` flag to [accept string values](https://github.com/etcd-io/etcd/pull/8563) with [finer granularity](https://github.com/etcd-io/etcd/issues/8503). Now that `--auto-compaction-retention` accepts string values, etcd configuration YAML file `auto-compaction-retention` field must be changed to `string` type. Previously, `--config-file etcd.config.yaml` can have `auto-compaction-retention: 24` field, now must be `auto-compaction-retention: "24"` or `auto-compaction-retention: "24h"`. If configured as `--auto-compaction-mode periodic --auto-compaction-retention "24h"`, the time duration value for `--auto-compaction-retention` flag must be valid for [`time.ParseDuration`](https://golang.org/pkg/time/#ParseDuration) function in Go.
+
+```diff
+# etcd.config.yaml
++auto-compaction-mode: periodic
+-auto-compaction-retention: 24
++auto-compaction-retention: "24"
++# Or
++auto-compaction-retention: "24h"
+```
+
+#### Changed `etcdserver.EtcdServer.ServerConfig` to `*etcdserver.EtcdServer.ServerConfig`
+
+`etcdserver.EtcdServer` has changed the type of its member field `*etcdserver.ServerConfig` to `etcdserver.ServerConfig`. And `etcdserver.NewServer` now takes `etcdserver.ServerConfig`, instead of `*etcdserver.ServerConfig`.
+
+Before and after (e.g. [k8s.io/kubernetes/test/e2e_node/services/etcd.go](https://github.com/kubernetes/kubernetes/blob/release-1.8/test/e2e_node/services/etcd.go#L50-L55))
+
+```diff
+import "github.com/coreos/etcd/etcdserver"
+
+type EtcdServer struct {
+	*etcdserver.EtcdServer
+-	config *etcdserver.ServerConfig
++	config etcdserver.ServerConfig
+}
+
+func NewEtcd(dataDir string) *EtcdServer {
+-	config := &etcdserver.ServerConfig{
++	config := etcdserver.ServerConfig{
+		DataDir: dataDir,
+        ...
+	}
+	return &EtcdServer{config: config}
+}
+
+func (e *EtcdServer) Start() error {
+	var err error
+	e.EtcdServer, err = etcdserver.NewServer(e.config)
+    ...
+```
+
+#### Added `embed.Config.LogOutput` struct
+
+**Note that this field has been renamed to `embed.Config.LogOutputs` in `[]string` type in v3.4. Please see [v3.4 upgrade guide](https://github.com/etcd-io/etcd/blob/master/Documentation/upgrades/upgrade_3_4.md) for more details.**
+
+Field `LogOutput` is added to `embed.Config`:
+
+```diff
+package embed
+
+type Config struct {
+ 	Debug bool `json:"debug"`
+ 	LogPkgLevels string `json:"log-package-levels"`
++	LogOutput string `json:"log-output"`
+ 	...
+```
+
+Before gRPC server warnings were logged in etcdserver.
+
+```
+WARNING: 2017/11/02 11:35:51 grpc: addrConn.resetTransport failed to create client transport: connection error: desc = "transport: Error while dialing dial tcp: operation was canceled"; Reconnecting to {localhost:2379 <nil>}
+WARNING: 2017/11/02 11:35:51 grpc: addrConn.resetTransport failed to create client transport: connection error: desc = "transport: Error while dialing dial tcp: operation was canceled"; Reconnecting to {localhost:2379 <nil>}
+```
+
+From v3.3, gRPC server logs are disabled by default.
+
+**Note that `embed.Config.SetupLogging` method has been deprecated in v3.4. Please see [v3.4 upgrade guide](https://github.com/etcd-io/etcd/blob/master/Documentation/upgrades/upgrade_3_4.md) for more details.**
+
+```go
+import "github.com/coreos/etcd/embed"
+
+cfg := &embed.Config{Debug: false}
+cfg.SetupLogging()
+```
+
+Set `embed.Config.Debug` field to `true` to enable gRPC server logs.
+
+#### Changed `/health` endpoint response
+
+Previously, `[endpoint]:[client-port]/health` returned manually marshaled JSON value. 3.3 now defines [`etcdhttp.Health`](https://godoc.org/github.com/coreos/etcd/etcdserver/api/etcdhttp#Health) struct.
+
+Note that in v3.3.0-rc.0, v3.3.0-rc.1, and v3.3.0-rc.2, `etcdhttp.Health` has boolean type `"health"` and `"errors"` fields. For backward compatibilities, we reverted `"health"` field to `string` type and removed `"errors"` field. Further health information will be provided in separate APIs.
+
+```bash
+$ curl http://localhost:2379/health
+{"health":"true"}
+```
+
+#### Changed gRPC gateway HTTP endpoints (replaced `/v3alpha` with `/v3beta`)
+
+Before
+
+```bash
+curl -L http://localhost:2379/v3alpha/kv/put \
+  -X POST -d '{"key": "Zm9v", "value": "YmFy"}'
+```
+
+After
+
+```bash
+curl -L http://localhost:2379/v3beta/kv/put \
+  -X POST -d '{"key": "Zm9v", "value": "YmFy"}'
+```
+
+Requests to `/v3alpha` endpoints will redirect to `/v3beta`, and `/v3alpha` will be removed in 3.4 release.
+
+#### Changed maximum request size limits
+
+3.3 now allows custom request size limits for both server and **client side**. In previous versions(v3.2.10, v3.2.11), client response size was limited to only 4 MiB.
+
+Server-side request limits can be configured with `--max-request-bytes` flag:
+
+```bash
+# limits request size to 1.5 KiB
+etcd --max-request-bytes 1536
+
+# client writes exceeding 1.5 KiB will be rejected
+etcdctl put foo [LARGE VALUE...]
+# etcdserver: request is too large
+```
+
+Or configure `embed.Config.MaxRequestBytes` field:
+
+```go
+import "github.com/coreos/etcd/embed"
+import "github.com/coreos/etcd/etcdserver/api/v3rpc/rpctypes"
+
+// limit requests to 5 MiB
+cfg := embed.NewConfig()
+cfg.MaxRequestBytes = 5 * 1024 * 1024
+
+// client writes exceeding 5 MiB will be rejected
+_, err := cli.Put(ctx, "foo", [LARGE VALUE...])
+err == rpctypes.ErrRequestTooLarge
+```
+
+**If not specified, server-side limit defaults to 1.5 MiB**.
+
+Client-side request limits must be configured based on server-side limits.
+
+```bash
+# limits request size to 1 MiB
+etcd --max-request-bytes 1048576
+```
+
+```go
+import "github.com/coreos/etcd/clientv3"
+
+cli, _ := clientv3.New(clientv3.Config{
+    Endpoints: []string{"127.0.0.1:2379"},
+    MaxCallSendMsgSize: 2 * 1024 * 1024,
+    MaxCallRecvMsgSize: 3 * 1024 * 1024,
+})
+
+
+// client writes exceeding "--max-request-bytes" will be rejected from etcd server
+_, err := cli.Put(ctx, "foo", strings.Repeat("a", 1*1024*1024+5))
+err == rpctypes.ErrRequestTooLarge
+
+
+// client writes exceeding "MaxCallSendMsgSize" will be rejected from client-side
+_, err = cli.Put(ctx, "foo", strings.Repeat("a", 5*1024*1024))
+err.Error() == "rpc error: code = ResourceExhausted desc = grpc: trying to send message larger than max (5242890 vs. 2097152)"
+
+
+// some writes under limits
+for i := range []int{0,1,2,3,4} {
+    _, err = cli.Put(ctx, fmt.Sprintf("foo%d", i), strings.Repeat("a", 1*1024*1024-500))
+    if err != nil {
+        panic(err)
+    }
+}
+// client reads exceeding "MaxCallRecvMsgSize" will be rejected from client-side
+_, err = cli.Get(ctx, "foo", clientv3.WithPrefix())
+err.Error() == "rpc error: code = ResourceExhausted desc = grpc: received message larger than max (5240509 vs. 3145728)"
+```
+
+**If not specified, client-side send limit defaults to 2 MiB (1.5 MiB + gRPC overhead bytes) and receive limit to `math.MaxInt32`**. Please see [clientv3 godoc](https://godoc.org/github.com/coreos/etcd/clientv3#Config) for more detail.
+
+#### Changed raw gRPC client wrapper function signatures
+
+3.3 changes the function signatures of `clientv3` gRPC client wrapper. This change was needed to support [custom `grpc.CallOption` on message size limits](https://github.com/etcd-io/etcd/pull/9047).
+
+Before and after
+
+```diff
+-func NewKVFromKVClient(remote pb.KVClient) KV {
++func NewKVFromKVClient(remote pb.KVClient, c *Client) KV {
+
+-func NewClusterFromClusterClient(remote pb.ClusterClient) Cluster {
++func NewClusterFromClusterClient(remote pb.ClusterClient, c *Client) Cluster {
+
+-func NewLeaseFromLeaseClient(remote pb.LeaseClient, keepAliveTimeout time.Duration) Lease {
++func NewLeaseFromLeaseClient(remote pb.LeaseClient, c *Client, keepAliveTimeout time.Duration) Lease {
+
+-func NewMaintenanceFromMaintenanceClient(remote pb.MaintenanceClient) Maintenance {
++func NewMaintenanceFromMaintenanceClient(remote pb.MaintenanceClient, c *Client) Maintenance {
+
+-func NewWatchFromWatchClient(wc pb.WatchClient) Watcher {
++func NewWatchFromWatchClient(wc pb.WatchClient, c *Client) Watcher {
+```
+
+#### Changed clientv3 `Snapshot` API error type
+
+Previously, clientv3 `Snapshot` API returned raw [`grpc/*status.statusError`] type error. v3.3 now translates those errors to corresponding public error types, to be consistent with other APIs.
+
+Before
+
+```go
+import "context"
+
+// reading snapshot with canceled context should error out
+ctx, cancel := context.WithCancel(context.Background())
+rc, _ := cli.Snapshot(ctx)
+cancel()
+_, err := io.Copy(f, rc)
+err.Error() == "rpc error: code = Canceled desc = context canceled"
+
+// reading snapshot with deadline exceeded should error out
+ctx, cancel = context.WithTimeout(context.Background(), time.Second)
+defer cancel()
+rc, _ = cli.Snapshot(ctx)
+time.Sleep(2 * time.Second)
+_, err = io.Copy(f, rc)
+err.Error() == "rpc error: code = DeadlineExceeded desc = context deadline exceeded"
+```
+
+After
+
+```go
+import "context"
+
+// reading snapshot with canceled context should error out
+ctx, cancel := context.WithCancel(context.Background())
+rc, _ := cli.Snapshot(ctx)
+cancel()
+_, err := io.Copy(f, rc)
+err == context.Canceled
+
+// reading snapshot with deadline exceeded should error out
+ctx, cancel = context.WithTimeout(context.Background(), time.Second)
+defer cancel()
+rc, _ = cli.Snapshot(ctx)
+time.Sleep(2 * time.Second)
+_, err = io.Copy(f, rc)
+err == context.DeadlineExceeded
+```
+
+#### Changed `etcdctl lease timetolive` command output
+
+Previously, `lease timetolive LEASE_ID` command on expired lease prints `-1s` for remaining seconds. 3.3 now outputs clearer messages.
+
+Before
+
+
+```bash
+lease 2d8257079fa1bc0c granted with TTL(0s), remaining(-1s)
+```
+
+After
+
+```bash
+lease 2d8257079fa1bc0c already expired
+```
+
+#### Changed `golang.org/x/net/context` imports
+
+`clientv3` has deprecated `golang.org/x/net/context`. If a project vendors `golang.org/x/net/context` in other code (e.g. etcd generated protocol buffer code) and imports `github.com/coreos/etcd/clientv3`, it requires Go 1.9+ to compile.
+
+Before
+
+```go
+import "golang.org/x/net/context"
+cli.Put(context.Background(), "f", "v")
+```
+
+After
+
+```go
+import "context"
+cli.Put(context.Background(), "f", "v")
+```
+
+#### Changed gRPC dependency
+
+3.3 now requires [grpc/grpc-go](https://github.com/grpc/grpc-go/releases) `v1.7.5`.
+
+##### Deprecated `grpclog.Logger`
+
+`grpclog.Logger` has been deprecated in favor of [`grpclog.LoggerV2`](https://github.com/grpc/grpc-go/blob/master/grpclog/loggerv2.go). `clientv3.Logger` is now `grpclog.LoggerV2`.
+
+Before
+
+```go
+import "github.com/coreos/etcd/clientv3"
+clientv3.SetLogger(log.New(os.Stderr, "grpc: ", 0))
+```
+
+After
+
+```go
+import "github.com/coreos/etcd/clientv3"
+import "google.golang.org/grpc/grpclog"
+clientv3.SetLogger(grpclog.NewLoggerV2(os.Stderr, os.Stderr, os.Stderr))
+
+// log.New above cannot be used (not implement grpclog.LoggerV2 interface)
+```
+
+##### Deprecated `grpc.ErrClientConnTimeout`
+
+Previously, `grpc.ErrClientConnTimeout` error is returned on client dial time-outs. 3.3 instead returns `context.DeadlineExceeded` (see [#8504](https://github.com/etcd-io/etcd/issues/8504)).
+
+Before
+
+```go
+// expect dial time-out on ipv4 blackhole
+_, err := clientv3.New(clientv3.Config{
+    Endpoints:   []string{"http://254.0.0.1:12345"},
+    DialTimeout: 2 * time.Second
+})
+if err == grpc.ErrClientConnTimeout {
+	// handle errors
+}
+```
+
+After
+
+```go
+_, err := clientv3.New(clientv3.Config{
+    Endpoints:   []string{"http://254.0.0.1:12345"},
+    DialTimeout: 2 * time.Second
+})
+if err == context.DeadlineExceeded {
+	// handle errors
+}
+```
+
+#### Changed official container registry
+
+etcd now uses [`gcr.io/etcd-development/etcd`](https://gcr.io/etcd-development/etcd) as a primary container registry, and [`quay.io/coreos/etcd`](https://quay.io/coreos/etcd) as secondary.
+
+Before
+
+```bash
+docker pull quay.io/coreos/etcd:v3.2.5
+```
+
+After
+
+```bash
+docker pull gcr.io/etcd-development/etcd:v3.3.0
+```
+
+### Upgrades to >= v3.3.14
+
+[v3.3.14](https://github.com/etcd-io/etcd/releases/tag/v3.3.14) had to include some features from 3.4, while trying to minimize the difference between client balancer implementation. This release fixes ["kube-apiserver 1.13.x refuses to work when first etcd-server is not available" (kubernetes#72102)](https://github.com/kubernetes/kubernetes/issues/72102).
+
+`grpc.ErrClientConnClosing` has been [deprecated in gRPC >= 1.10](https://github.com/grpc/grpc-go/pull/1854).
+
+```diff
+import (
++	"go.etcd.io/etcd/clientv3"
+
+	"google.golang.org/grpc"
++	"google.golang.org/grpc/codes"
++	"google.golang.org/grpc/status"
+)
+
+_, err := kvc.Get(ctx, "a")
+-if err == grpc.ErrClientConnClosing {
++if clientv3.IsConnCanceled(err) {
+
+// or
++s, ok := status.FromError(err)
++if ok {
++  if s.Code() == codes.Canceled
+```
+
+[The new client balancer](https://github.com/etcd-io/etcd/blob/master/Documentation/learning/design-client.md) uses an asynchronous resolver to pass endpoints to the gRPC dial function. As a result, [v3.3.14](https://github.com/etcd-io/etcd/releases/tag/v3.3.14) or later requires `grpc.WithBlock` dial option to wait until the underlying connection is up.
+
+```diff
+import (
+	"time"
+	"go.etcd.io/etcd/clientv3"
++	"google.golang.org/grpc"
+)
+
++// "grpc.WithBlock()" to block until the underlying connection is up
+ccfg := clientv3.Config{
+  Endpoints:            []string{"localhost:2379"},
+  DialTimeout:          time.Second,
++ DialOptions:          []grpc.DialOption{grpc.WithBlock()},
+  DialKeepAliveTime:    time.Second,
+  DialKeepAliveTimeout: 500 * time.Millisecond,
+}
+```
+
+Please see [CHANGELOG](https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.3.md) for a full list of changes.
+
+### Server upgrade checklists
+
+#### Upgrade requirements
+
+To upgrade an existing etcd deployment to 3.3, the running cluster must be 3.2 or greater. If it's before 3.2, please [upgrade to 3.2](upgrade_3_2.md) before upgrading to 3.3.
+
+Also, to ensure a smooth rolling upgrade, the running cluster must be healthy. Check the health of the cluster by using the `etcdctl endpoint health` command before proceeding.
+
+#### Preparation
+
+Before upgrading etcd, always test the services relying on etcd in a staging environment before deploying the upgrade to the production environment.
+
+Before beginning, [backup the etcd data](../op-guide/maintenance.md#snapshot-backup). Should something go wrong with the upgrade, it is possible to use this backup to [downgrade](#downgrade) back to existing etcd version. Please note that the `snapshot` command only backs up the v3 data. For v2 data, see [backing up v2 datastore](../v2/admin_guide.md#backing-up-the-datastore).
+
+#### Mixed versions
+
+While upgrading, an etcd cluster supports mixed versions of etcd members, and operates with the protocol of the lowest common version. The cluster is only considered upgraded once all of its members are upgraded to version 3.3. Internally, etcd members negotiate with each other to determine the overall cluster version, which controls the reported version and the supported features.
+
+#### Limitations
+
+Note: If the cluster only has v3 data and no v2 data, it is not subject to this limitation.
+
+If the cluster is serving a v2 data set larger than 50MB, each newly upgraded member may take up to two minutes to catch up with the existing cluster. Check the size of a recent snapshot to estimate the total data size. In other words, it is safest to wait for 2 minutes between upgrading each member.
+
+For a much larger total data size, 100MB or more , this one-time process might take even more time. Administrators of very large etcd clusters of this magnitude can feel free to contact the [etcd team][etcd-contact] before upgrading, and we'll be happy to provide advice on the procedure.
+
+#### Downgrade
+
+If all members have been upgraded to v3.3, the cluster will be upgraded to v3.3, and downgrade from this completed state is **not possible**. If any single member is still v3.2, however, the cluster and its operations remains "v3.2", and it is possible from this mixed cluster state to return to using a v3.2 etcd binary on all members.
+
+Please [backup the data directory](../op-guide/maintenance.md#snapshot-backup) of all etcd members to make downgrading the cluster possible even after it has been completely upgraded.
+
+### Upgrade procedure
+
+This example shows how to upgrade a 3-member v3.2 ectd cluster running on a local machine.
+
+#### 1. Check upgrade requirements
+
+Is the cluster healthy and running v3.2.x?
+
+```
+$ ETCDCTL_API=3 etcdctl endpoint health --endpoints=localhost:2379,localhost:22379,localhost:32379
+localhost:2379 is healthy: successfully committed proposal: took = 6.600684ms
+localhost:22379 is healthy: successfully committed proposal: took = 8.540064ms
+localhost:32379 is healthy: successfully committed proposal: took = 8.763432ms
+
+$ curl http://localhost:2379/version
+{"etcdserver":"3.2.7","etcdcluster":"3.2.0"}
+```
+
+#### 2. Stop the existing etcd process
+
+When each etcd process is stopped, expected errors will be logged by other cluster members. This is normal since a cluster member connection has been (temporarily) broken:
+
+```
+14:13:31.491746 I | raft: c89feb932daef420 [term 3] received MsgTimeoutNow from 6d4f535bae3ab960 and starts an election to get leadership.
+14:13:31.491769 I | raft: c89feb932daef420 became candidate at term 4
+14:13:31.491788 I | raft: c89feb932daef420 received MsgVoteResp from c89feb932daef420 at term 4
+14:13:31.491797 I | raft: c89feb932daef420 [logterm: 3, index: 9] sent MsgVote request to 6d4f535bae3ab960 at term 4
+14:13:31.491805 I | raft: c89feb932daef420 [logterm: 3, index: 9] sent MsgVote request to 9eda174c7df8a033 at term 4
+14:13:31.491815 I | raft: raft.node: c89feb932daef420 lost leader 6d4f535bae3ab960 at term 4
+14:13:31.524084 I | raft: c89feb932daef420 received MsgVoteResp from 6d4f535bae3ab960 at term 4
+14:13:31.524108 I | raft: c89feb932daef420 [quorum:2] has received 2 MsgVoteResp votes and 0 vote rejections
+14:13:31.524123 I | raft: c89feb932daef420 became leader at term 4
+14:13:31.524136 I | raft: raft.node: c89feb932daef420 elected leader c89feb932daef420 at term 4
+14:13:31.592650 W | rafthttp: lost the TCP streaming connection with peer 6d4f535bae3ab960 (stream MsgApp v2 reader)
+14:13:31.592825 W | rafthttp: lost the TCP streaming connection with peer 6d4f535bae3ab960 (stream Message reader)
+14:13:31.693275 E | rafthttp: failed to dial 6d4f535bae3ab960 on stream Message (dial tcp [::1]:2380: getsockopt: connection refused)
+14:13:31.693289 I | rafthttp: peer 6d4f535bae3ab960 became inactive
+14:13:31.936678 W | rafthttp: lost the TCP streaming connection with peer 6d4f535bae3ab960 (stream Message writer)
+```
+
+It's a good idea at this point to [backup the etcd data](../op-guide/maintenance.md#snapshot-backup) to provide a downgrade path should any problems occur:
+
+```
+$ etcdctl snapshot save backup.db
+```
+
+#### 3. Drop-in etcd v3.3 binary and start the new etcd process
+
+The new v3.3 etcd will publish its information to the cluster:
+
+```
+14:14:25.363225 I | etcdserver: published {Name:s1 ClientURLs:[http://localhost:2379]} to cluster a9ededbffcb1b1f1
+```
+
+Verify that each member, and then the entire cluster, becomes healthy with the new v3.3 etcd binary:
+
+```
+$ ETCDCTL_API=3 /etcdctl endpoint health --endpoints=localhost:2379,localhost:22379,localhost:32379
+localhost:22379 is healthy: successfully committed proposal: took = 5.540129ms
+localhost:32379 is healthy: successfully committed proposal: took = 7.321771ms
+localhost:2379 is healthy: successfully committed proposal: took = 10.629901ms
+```
+
+Upgraded members will log warnings like the following until the entire cluster is upgraded. This is expected and will cease after all etcd cluster members are upgraded to v3.3:
+
+```
+14:15:17.071804 W | etcdserver: member c89feb932daef420 has a higher version 3.3.0
+14:15:21.073110 W | etcdserver: the local etcd version 3.2.7 is not up-to-date
+14:15:21.073142 W | etcdserver: member 6d4f535bae3ab960 has a higher version 3.3.0
+14:15:21.073157 W | etcdserver: the local etcd version 3.2.7 is not up-to-date
+14:15:21.073164 W | etcdserver: member c89feb932daef420 has a higher version 3.3.0
+```
+
+#### 4. Repeat step 2 to step 3 for all other members
+
+#### 5. Finish
+
+When all members are upgraded, the cluster will report upgrading to 3.3 successfully:
+
+```
+14:15:54.536901 N | etcdserver/membership: updated the cluster version from 3.2 to 3.3
+14:15:54.537035 I | etcdserver/api: enabled capabilities for version 3.3
+```
+
+```
+$ ETCDCTL_API=3 /etcdctl endpoint health --endpoints=localhost:2379,localhost:22379,localhost:32379
+localhost:2379 is healthy: successfully committed proposal: took = 2.312897ms
+localhost:22379 is healthy: successfully committed proposal: took = 2.553476ms
+localhost:32379 is healthy: successfully committed proposal: took = 2.517902ms
+```
+
+[etcd-contact]: https://groups.google.com/forum/#!forum/etcd-dev

Documentation/upgrades/upgrade_3_5.md

@@ -0,0 +1,343 @@
+---
+title: Upgrade etcd from 3.4 to 3.5
+---
+
+In the general case, upgrading from etcd 3.4 to 3.5 can be a zero-downtime, rolling upgrade:
+ - one by one, stop the etcd v3.4 processes and replace them with etcd v3.5 processes
+ - after running all v3.5 processes, new features in v3.5 are available to the cluster
+
+Before [starting an upgrade](#upgrade-procedure), read through the rest of this guide to prepare.
+
+
+
+### Upgrade checklists
+
+**NOTE:** When [migrating from v2 with no v3 data](https://github.com/etcd-io/etcd/issues/9480), etcd server v3.2+ panics when etcd restores from existing snapshots but no v3 `ETCD_DATA_DIR/member/snap/db` file. This happens when the server had migrated from v2 with no previous v3 data. This also prevents accidental v3 data loss (e.g. `db` file might have been moved). etcd requires that post v3 migration can only happen with v3 data. Do not upgrade to newer v3 versions until v3.0 server contains v3 data.
+
+Highlighted breaking changes in 3.5.
+
+#### Deprecate `etcd_debugging_mvcc_db_total_size_in_bytes` Prometheus metrics
+
+v3.4 promoted `etcd_debugging_mvcc_db_total_size_in_bytes` Prometheus metrics to `etcd_mvcc_db_total_size_in_bytes`, in order to encourage etcd storage monitoring. And v3.5 completely deprcates `etcd_debugging_mvcc_db_total_size_in_bytes`.
+
+```diff
+-etcd_debugging_mvcc_db_total_size_in_bytes
++etcd_mvcc_db_total_size_in_bytes
+```
+
+Note that `etcd_debugging_*` namespace metrics have been marked as experimental. As we improve monitoring guide, we will promote more metrics.
+
+#### Deprecated in `etcd --logger capnslog`
+
+v3.4 defaults to `--logger=zap` in order to support multiple log outputs and structured logging.
+
+**`etcd --logger=capnslog` has been deprecated in v3.5**, and now `--logger=zap` is the default.
+
+```diff
+-etcd --logger=capnslog
++etcd --logger=zap --log-outputs=stderr
+
++# to write logs to stderr and a.log file at the same time
++etcd --logger=zap --log-outputs=stderr,a.log
+```
+
+TODO(add more monitoring guides); v3.4 adds `etcd --logger=zap` support for structured logging and multiple log outputs. Main motivation is to promote automated etcd monitoring, rather than looking back server logs when it starts breaking. Future development will make etcd log as few as possible, and make etcd easier to monitor with metrics and alerts. **`etcd --logger=capnslog` will be deprecated in v3.5.**
+
+#### Deprecated in `etcd --log-output`
+
+v3.4 renamed [`etcd --log-output` to `--log-outputs`](https://github.com/etcd-io/etcd/pull/9624) to support multiple log outputs.
+
+**`etcd --log-output` has been deprecated in v3.5.**
+
+```diff
+-etcd --log-output=stderr
++etcd --log-outputs=stderr
+```
+
+#### Deprecated `etcd --log-package-levels`
+
+**`etcd --log-package-levels` flag for `capnslog` has been deprecated.**
+
+Now, **`etcd --logger=zap`** is the default.
+
+```diff
+-etcd --log-package-levels 'etcdmain=CRITICAL,etcdserver=DEBUG'
++etcd --logger=zap --log-outputs=stderr
+```
+
+#### Deprecated `[CLIENT-URL]/config/local/log`
+
+**`/config/local/log` endpoint is being deprecated in v3.5, as is `etcd --log-package-levels` flag.**
+
+```diff
+-$ curl http://127.0.0.1:2379/config/local/log -XPUT -d '{"Level":"DEBUG"}'
+-# debug logging enabled
+```
+
+#### Changed gRPC gateway HTTP endpoints (deprecated `/v3beta`)
+
+Before
+
+```bash
+curl -L http://localhost:2379/v3beta/kv/put \
+  -X POST -d '{"key": "Zm9v", "value": "YmFy"}'
+```
+
+After
+
+```bash
+curl -L http://localhost:2379/v3/kv/put \
+  -X POST -d '{"key": "Zm9v", "value": "YmFy"}'
+```
+
+`/v3beta` has been removed in 3.5 release.
+
+
+
+### Server upgrade checklists
+
+#### Upgrade requirements
+
+To upgrade an existing etcd deployment to 3.5, the running cluster must be 3.4 or greater. If it's before 3.4, please [upgrade to 3.4](upgrade_3_3.md) before upgrading to 3.5.
+
+Also, to ensure a smooth rolling upgrade, the running cluster must be healthy. Check the health of the cluster by using the `etcdctl endpoint health` command before proceeding.
+
+#### Preparation
+
+Before upgrading etcd, always test the services relying on etcd in a staging environment before deploying the upgrade to the production environment.
+
+Before beginning, [download the snapshot backup](../op-guide/maintenance.md#snapshot-backup). Should something go wrong with the upgrade, it is possible to use this backup to [downgrade](#downgrade) back to existing etcd version. Please note that the `snapshot` command only backs up the v3 data. For v2 data, see [backing up v2 datastore](../v2/admin_guide.md#backing-up-the-datastore).
+
+#### Mixed versions
+
+While upgrading, an etcd cluster supports mixed versions of etcd members, and operates with the protocol of the lowest common version. The cluster is only considered upgraded once all of its members are upgraded to version 3.5. Internally, etcd members negotiate with each other to determine the overall cluster version, which controls the reported version and the supported features.
+
+#### Limitations
+
+Note: If the cluster only has v3 data and no v2 data, it is not subject to this limitation.
+
+If the cluster is serving a v2 data set larger than 50MB, each newly upgraded member may take up to two minutes to catch up with the existing cluster. Check the size of a recent snapshot to estimate the total data size. In other words, it is safest to wait for 2 minutes between upgrading each member.
+
+For a much larger total data size, 100MB or more , this one-time process might take even more time. Administrators of very large etcd clusters of this magnitude can feel free to contact the [etcd team][etcd-contact] before upgrading, and we'll be happy to provide advice on the procedure.
+
+#### Downgrade
+
+If all members have been upgraded to v3.5, the cluster will be upgraded to v3.5, and downgrade from this completed state is **not possible**. If any single member is still v3.4, however, the cluster and its operations remains "v3.4", and it is possible from this mixed cluster state to return to using a v3.4 etcd binary on all members.
+
+Please [download the snapshot backup](../op-guide/maintenance.md#snapshot-backup) to make downgrading the cluster possible even after it has been completely upgraded.
+
+### Upgrade procedure
+
+This example shows how to upgrade a 3-member v3.4 ectd cluster running on a local machine.
+
+#### Step 1: check upgrade requirements
+
+Is the cluster healthy and running v3.4.x?
+
+```bash
+etcdctl --endpoints=localhost:2379,localhost:22379,localhost:32379 endpoint health
+<<COMMENT
+localhost:2379 is healthy: successfully committed proposal: took = 2.118638ms
+localhost:22379 is healthy: successfully committed proposal: took = 3.631388ms
+localhost:32379 is healthy: successfully committed proposal: took = 2.157051ms
+COMMENT
+
+curl http://localhost:2379/version
+<<COMMENT
+{"etcdserver":"3.4.0","etcdcluster":"3.4.0"}
+COMMENT
+
+curl http://localhost:22379/version
+<<COMMENT
+{"etcdserver":"3.4.0","etcdcluster":"3.4.0"}
+COMMENT
+
+curl http://localhost:32379/version
+<<COMMENT
+{"etcdserver":"3.4.0","etcdcluster":"3.4.0"}
+COMMENT
+```
+
+#### Step 2: download snapshot backup from leader
+
+[Download the snapshot backup](../op-guide/maintenance.md#snapshot-backup) to provide a downgrade path should any problems occur.
+
+etcd leader is guaranteed to have the latest application data, thus fetch snapshot from leader:
+
+```bash
+curl -sL http://localhost:2379/metrics | grep etcd_server_is_leader
+<<COMMENT
+# HELP etcd_server_is_leader Whether or not this member is a leader. 1 if is, 0 otherwise.
+# TYPE etcd_server_is_leader gauge
+etcd_server_is_leader 1
+COMMENT
+
+curl -sL http://localhost:22379/metrics | grep etcd_server_is_leader
+<<COMMENT
+etcd_server_is_leader 0
+COMMENT
+
+curl -sL http://localhost:32379/metrics | grep etcd_server_is_leader
+<<COMMENT
+etcd_server_is_leader 0
+COMMENT
+
+etcdctl --endpoints=localhost:2379 snapshot save backup.db
+<<COMMENT
+{"level":"info","ts":1526585787.148433,"caller":"snapshot/v3_snapshot.go:109","msg":"created temporary db file","path":"backup.db.part"}
+{"level":"info","ts":1526585787.1485257,"caller":"snapshot/v3_snapshot.go:120","msg":"fetching snapshot","endpoint":"localhost:2379"}
+{"level":"info","ts":1526585787.1519694,"caller":"snapshot/v3_snapshot.go:133","msg":"fetched snapshot","endpoint":"localhost:2379","took":0.003502721}
+{"level":"info","ts":1526585787.1520295,"caller":"snapshot/v3_snapshot.go:142","msg":"saved","path":"backup.db"}
+Snapshot saved at backup.db
+COMMENT
+```
+
+#### Step 3: stop one existing etcd server
+
+When each etcd process is stopped, expected errors will be logged by other cluster members. This is normal since a cluster member connection has been (temporarily) broken:
+
+```bash
+{"level":"info","ts":1526587281.2001143,"caller":"etcdserver/server.go:2249","msg":"updating cluster version","from":"3.0","to":"3.4"}
+{"level":"info","ts":1526587281.2010646,"caller":"membership/cluster.go:473","msg":"updated cluster version","cluster-id":"7dee9ba76d59ed53","local-member-id":"7339c4e5e833c029","from":"3.0","from":"3.4"}
+{"level":"info","ts":1526587281.2012327,"caller":"api/capability.go:76","msg":"enabled capabilities for version","cluster-version":"3.4"}
+{"level":"info","ts":1526587281.2013083,"caller":"etcdserver/server.go:2272","msg":"cluster version is updated","cluster-version":"3.4"}
+
+
+
+^C{"level":"info","ts":1526587299.0717514,"caller":"osutil/interrupt_unix.go:63","msg":"received signal; shutting down","signal":"interrupt"}
+{"level":"info","ts":1526587299.0718873,"caller":"embed/etcd.go:285","msg":"closing etcd server","name":"s1","data-dir":"/tmp/etcd/s1","advertise-peer-urls":["http://localhost:2380"],"advertise-client-urls":["http://localhost:2379"]}
+{"level":"info","ts":1526587299.0722554,"caller":"etcdserver/server.go:1341","msg":"leadership transfer starting","local-member-id":"7339c4e5e833c029","current-leader-member-id":"7339c4e5e833c029","transferee-member-id":"729934363faa4a24"}
+{"level":"info","ts":1526587299.0723994,"caller":"raft/raft.go:1107","msg":"7339c4e5e833c029 [term 3] starts to transfer leadership to 729934363faa4a24"}
+{"level":"info","ts":1526587299.0724802,"caller":"raft/raft.go:1113","msg":"7339c4e5e833c029 sends MsgTimeoutNow to 729934363faa4a24 immediately as 729934363faa4a24 already has up-to-date log"}
+{"level":"info","ts":1526587299.0737045,"caller":"raft/raft.go:797","msg":"7339c4e5e833c029 [term: 3] received a MsgVote message with higher term from 729934363faa4a24 [term: 4]"}
+{"level":"info","ts":1526587299.0737681,"caller":"raft/raft.go:656","msg":"7339c4e5e833c029 became follower at term 4"}
+{"level":"info","ts":1526587299.073831,"caller":"raft/raft.go:882","msg":"7339c4e5e833c029 [logterm: 3, index: 9, vote: 0] cast MsgVote for 729934363faa4a24 [logterm: 3, index: 9] at term 4"}
+{"level":"info","ts":1526587299.0738947,"caller":"raft/node.go:312","msg":"raft.node: 7339c4e5e833c029 lost leader 7339c4e5e833c029 at term 4"}
+{"level":"info","ts":1526587299.0748374,"caller":"raft/node.go:306","msg":"raft.node: 7339c4e5e833c029 elected leader 729934363faa4a24 at term 4"}
+{"level":"info","ts":1526587299.1726425,"caller":"etcdserver/server.go:1362","msg":"leadership transfer finished","local-member-id":"7339c4e5e833c029","old-leader-member-id":"7339c4e5e833c029","new-leader-member-id":"729934363faa4a24","took":0.100389359}
+{"level":"info","ts":1526587299.1728148,"caller":"rafthttp/peer.go:333","msg":"stopping remote peer","remote-peer-id":"b548c2511513015"}
+{"level":"warn","ts":1526587299.1751974,"caller":"rafthttp/stream.go:291","msg":"closed TCP streaming connection with remote peer","stream-writer-type":"stream MsgApp v2","remote-peer-id":"b548c2511513015"}
+{"level":"warn","ts":1526587299.1752589,"caller":"rafthttp/stream.go:301","msg":"stopped TCP streaming connection with remote peer","stream-writer-type":"stream MsgApp v2","remote-peer-id":"b548c2511513015"}
+{"level":"warn","ts":1526587299.177348,"caller":"rafthttp/stream.go:291","msg":"closed TCP streaming connection with remote peer","stream-writer-type":"stream Message","remote-peer-id":"b548c2511513015"}
+{"level":"warn","ts":1526587299.1774004,"caller":"rafthttp/stream.go:301","msg":"stopped TCP streaming connection with remote peer","stream-writer-type":"stream Message","remote-peer-id":"b548c2511513015"}
+{"level":"info","ts":1526587299.177515,"caller":"rafthttp/pipeline.go:86","msg":"stopped HTTP pipelining with remote peer","local-member-id":"7339c4e5e833c029","remote-peer-id":"b548c2511513015"}
+{"level":"warn","ts":1526587299.1777067,"caller":"rafthttp/stream.go:436","msg":"lost TCP streaming connection with remote peer","stream-reader-type":"stream MsgApp v2","local-member-id":"7339c4e5e833c029","remote-peer-id":"b548c2511513015","error":"read tcp 127.0.0.1:34636->127.0.0.1:32380: use of closed network connection"}
+{"level":"info","ts":1526587299.1778402,"caller":"rafthttp/stream.go:459","msg":"stopped stream reader with remote peer","stream-reader-type":"stream MsgApp v2","local-member-id":"7339c4e5e833c029","remote-peer-id":"b548c2511513015"}
+{"level":"warn","ts":1526587299.1780295,"caller":"rafthttp/stream.go:436","msg":"lost TCP streaming connection with remote peer","stream-reader-type":"stream Message","local-member-id":"7339c4e5e833c029","remote-peer-id":"b548c2511513015","error":"read tcp 127.0.0.1:34634->127.0.0.1:32380: use of closed network connection"}
+{"level":"info","ts":1526587299.1780987,"caller":"rafthttp/stream.go:459","msg":"stopped stream reader with remote peer","stream-reader-type":"stream Message","local-member-id":"7339c4e5e833c029","remote-peer-id":"b548c2511513015"}
+{"level":"info","ts":1526587299.1781602,"caller":"rafthttp/peer.go:340","msg":"stopped remote peer","remote-peer-id":"b548c2511513015"}
+{"level":"info","ts":1526587299.1781986,"caller":"rafthttp/peer.go:333","msg":"stopping remote peer","remote-peer-id":"729934363faa4a24"}
+{"level":"warn","ts":1526587299.1802843,"caller":"rafthttp/stream.go:291","msg":"closed TCP streaming connection with remote peer","stream-writer-type":"stream MsgApp v2","remote-peer-id":"729934363faa4a24"}
+{"level":"warn","ts":1526587299.1803446,"caller":"rafthttp/stream.go:301","msg":"stopped TCP streaming connection with remote peer","stream-writer-type":"stream MsgApp v2","remote-peer-id":"729934363faa4a24"}
+{"level":"warn","ts":1526587299.1824749,"caller":"rafthttp/stream.go:291","msg":"closed TCP streaming connection with remote peer","stream-writer-type":"stream Message","remote-peer-id":"729934363faa4a24"}
+{"level":"warn","ts":1526587299.18255,"caller":"rafthttp/stream.go:301","msg":"stopped TCP streaming connection with remote peer","stream-writer-type":"stream Message","remote-peer-id":"729934363faa4a24"}
+{"level":"info","ts":1526587299.18261,"caller":"rafthttp/pipeline.go:86","msg":"stopped HTTP pipelining with remote peer","local-member-id":"7339c4e5e833c029","remote-peer-id":"729934363faa4a24"}
+{"level":"warn","ts":1526587299.1827736,"caller":"rafthttp/stream.go:436","msg":"lost TCP streaming connection with remote peer","stream-reader-type":"stream MsgApp v2","local-member-id":"7339c4e5e833c029","remote-peer-id":"729934363faa4a24","error":"read tcp 127.0.0.1:51482->127.0.0.1:22380: use of closed network connection"}
+{"level":"info","ts":1526587299.182845,"caller":"rafthttp/stream.go:459","msg":"stopped stream reader with remote peer","stream-reader-type":"stream MsgApp v2","local-member-id":"7339c4e5e833c029","remote-peer-id":"729934363faa4a24"}
+{"level":"warn","ts":1526587299.1830168,"caller":"rafthttp/stream.go:436","msg":"lost TCP streaming connection with remote peer","stream-reader-type":"stream Message","local-member-id":"7339c4e5e833c029","remote-peer-id":"729934363faa4a24","error":"context canceled"}
+{"level":"warn","ts":1526587299.1831107,"caller":"rafthttp/peer_status.go:65","msg":"peer became inactive","peer-id":"729934363faa4a24","error":"failed to read 729934363faa4a24 on stream Message (context canceled)"}
+{"level":"info","ts":1526587299.1831737,"caller":"rafthttp/stream.go:459","msg":"stopped stream reader with remote peer","stream-reader-type":"stream Message","local-member-id":"7339c4e5e833c029","remote-peer-id":"729934363faa4a24"}
+{"level":"info","ts":1526587299.1832306,"caller":"rafthttp/peer.go:340","msg":"stopped remote peer","remote-peer-id":"729934363faa4a24"}
+{"level":"warn","ts":1526587299.1837125,"caller":"rafthttp/http.go:424","msg":"failed to find remote peer in cluster","local-member-id":"7339c4e5e833c029","remote-peer-id-stream-handler":"7339c4e5e833c029","remote-peer-id-from":"b548c2511513015","cluster-id":"7dee9ba76d59ed53"}
+{"level":"warn","ts":1526587299.1840093,"caller":"rafthttp/http.go:424","msg":"failed to find remote peer in cluster","local-member-id":"7339c4e5e833c029","remote-peer-id-stream-handler":"7339c4e5e833c029","remote-peer-id-from":"b548c2511513015","cluster-id":"7dee9ba76d59ed53"}
+{"level":"warn","ts":1526587299.1842315,"caller":"rafthttp/http.go:424","msg":"failed to find remote peer in cluster","local-member-id":"7339c4e5e833c029","remote-peer-id-stream-handler":"7339c4e5e833c029","remote-peer-id-from":"729934363faa4a24","cluster-id":"7dee9ba76d59ed53"}
+{"level":"warn","ts":1526587299.1844475,"caller":"rafthttp/http.go:424","msg":"failed to find remote peer in cluster","local-member-id":"7339c4e5e833c029","remote-peer-id-stream-handler":"7339c4e5e833c029","remote-peer-id-from":"729934363faa4a24","cluster-id":"7dee9ba76d59ed53"}
+{"level":"info","ts":1526587299.2056687,"caller":"embed/etcd.go:473","msg":"stopping serving peer traffic","address":"127.0.0.1:2380"}
+{"level":"info","ts":1526587299.205819,"caller":"embed/etcd.go:480","msg":"stopped serving peer traffic","address":"127.0.0.1:2380"}
+{"level":"info","ts":1526587299.2058413,"caller":"embed/etcd.go:289","msg":"closed etcd server","name":"s1","data-dir":"/tmp/etcd/s1","advertise-peer-urls":["http://localhost:2380"],"advertise-client-urls":["http://localhost:2379"]}
+```
+
+#### Step 4: restart the etcd server with same configuration
+
+Restart the etcd server with same configuration but with the new etcd binary.
+
+```diff
+-etcd-old --name s1 \
++etcd-new --name s1 \
+  --data-dir /tmp/etcd/s1 \
+  --listen-client-urls http://localhost:2379 \
+  --advertise-client-urls http://localhost:2379 \
+  --listen-peer-urls http://localhost:2380 \
+  --initial-advertise-peer-urls http://localhost:2380 \
+  --initial-cluster s1=http://localhost:2380,s2=http://localhost:22380,s3=http://localhost:32380 \
+  --initial-cluster-token tkn \
+  --initial-cluster-state new
+```
+
+The new v3.5 etcd will publish its information to the cluster. At this point, cluster still operates as v3.4 protocol, which is the lowest common version.
+
+> `{"level":"info","ts":1526586617.1647713,"caller":"membership/cluster.go:485","msg":"set initial cluster version","cluster-id":"7dee9ba76d59ed53","local-member-id":"7339c4e5e833c029","cluster-version":"3.0"}`
+
+> `{"level":"info","ts":1526586617.1648536,"caller":"api/capability.go:76","msg":"enabled capabilities for version","cluster-version":"3.0"}`
+
+> `{"level":"info","ts":1526586617.1649303,"caller":"membership/cluster.go:473","msg":"updated cluster version","cluster-id":"7dee9ba76d59ed53","local-member-id":"7339c4e5e833c029","from":"3.0","from":"3.4"}`
+
+> `{"level":"info","ts":1526586617.1649797,"caller":"api/capability.go:76","msg":"enabled capabilities for version","cluster-version":"3.4"}`
+
+> `{"level":"info","ts":1526586617.2107732,"caller":"etcdserver/server.go:1770","msg":"published local member to cluster through raft","local-member-id":"7339c4e5e833c029","local-member-attributes":"{Name:s1 ClientURLs:[http://localhost:2379]}","request-path":"/0/members/7339c4e5e833c029/attributes","cluster-id":"7dee9ba76d59ed53","publish-timeout":7}`
+
+Verify that each member, and then the entire cluster, becomes healthy with the new v3.5 etcd binary:
+
+```bash
+etcdctl endpoint health --endpoints=localhost:2379,localhost:22379,localhost:32379
+<<COMMENT
+localhost:32379 is healthy: successfully committed proposal: took = 2.337471ms
+localhost:22379 is healthy: successfully committed proposal: took = 1.130717ms
+localhost:2379 is healthy: successfully committed proposal: took = 2.124843ms
+COMMENT
+```
+
+Un-upgraded members will log warnings like the following until the entire cluster is upgraded.
+
+This is expected and will cease after all etcd cluster members are upgraded to v3.5:
+
+```
+:41.942121 W | etcdserver: member 7339c4e5e833c029 has a higher version 3.5.0
+:45.945154 W | etcdserver: the local etcd version 3.4.0 is not up-to-date
+```
+
+#### Step 5: repeat *step 3* and *step 4* for rest of the members
+
+When all members are upgraded, the cluster will report upgrading to 3.5 successfully:
+
+Member 1:
+
+> `{"level":"info","ts":1526586949.0920913,"caller":"api/capability.go:76","msg":"enabled capabilities for version","cluster-version":"3.5"}`
+> `{"level":"info","ts":1526586949.0921566,"caller":"etcdserver/server.go:2272","msg":"cluster version is updated","cluster-version":"3.5"}`
+
+Member 2:
+
+> `{"level":"info","ts":1526586949.092117,"caller":"membership/cluster.go:473","msg":"updated cluster version","cluster-id":"7dee9ba76d59ed53","local-member-id":"729934363faa4a24","from":"3.4","from":"3.5"}`
+> `{"level":"info","ts":1526586949.0923078,"caller":"api/capability.go:76","msg":"enabled capabilities for version","cluster-version":"3.5"}`
+
+Member 3:
+
+> `{"level":"info","ts":1526586949.0921423,"caller":"membership/cluster.go:473","msg":"updated cluster version","cluster-id":"7dee9ba76d59ed53","local-member-id":"b548c2511513015","from":"3.4","from":"3.5"}`
+> `{"level":"info","ts":1526586949.0922918,"caller":"api/capability.go:76","msg":"enabled capabilities for version","cluster-version":"3.5"}`
+
+
+```bash
+endpoint health --endpoints=localhost:2379,localhost:22379,localhost:32379
+<<COMMENT
+localhost:2379 is healthy: successfully committed proposal: took = 492.834µs
+localhost:22379 is healthy: successfully committed proposal: took = 1.015025ms
+localhost:32379 is healthy: successfully committed proposal: took = 1.853077ms
+COMMENT
+
+curl http://localhost:2379/version
+<<COMMENT
+{"etcdserver":"3.5.0","etcdcluster":"3.5.0"}
+COMMENT
+
+curl http://localhost:22379/version
+<<COMMENT
+{"etcdserver":"3.5.0","etcdcluster":"3.5.0"}
+COMMENT
+
+curl http://localhost:32379/version
+<<COMMENT
+{"etcdserver":"3.5.0","etcdcluster":"3.5.0"}
+COMMENT
+```
+
+[etcd-contact]: https://groups.google.com/forum/#!forum/etcd-dev

Documentation/upgrades/upgrading-etcd.md

@@ -0,0 +1,26 @@
+---
+title: Upgrading etcd clusters and applications
+---
+
+This section contains documents specific to upgrading etcd clusters and applications.
+
+## Moving from etcd API v2 to API v3
+
+* [Migrate applications from using API v2 to API v3][migrate-apps]
+
+## Upgrading an etcd v3.x cluster
+* [Upgrade etcd from 3.0 to 3.1][upgrade-3-1]
+* [Upgrade etcd from 3.1 to 3.2][upgrade-3-2]
+* [Upgrade etcd from 3.2 to 3.3][upgrade-3-3]
+* [Upgrade etcd from 3.3 to 3.4][upgrade-3-4]
+
+## Upgrading from etcd v2.3
+* [Upgrade a v2.3 cluster to v3.0][upgrade-cluster]
+
+
+[migrate-apps]: ../op-guide/v2-migration.md
+[upgrade-cluster]: upgrade_3_0.md
+[upgrade-3-1]: upgrade_3_1.md
+[upgrade-3-2]: upgrade_3_2.md
+[upgrade-3-3]: upgrade_3_3.md
+[upgrade-3-4]: upgrade_3_4.md

Documentation/v2/04_to_2_snapshot_migration.md

@@ -1,31 +0,0 @@
-# Snapshot Migration
-
-You can migrate a snapshot of your data from a v0.4.9+ cluster into a new etcd 2.2 cluster using a snapshot migration. After snapshot migration, the etcd indexes of your data will change. Many etcd applications rely on these indexes to behave correctly. This operation should only be done while all etcd applications are stopped.
-
-To get started get the newest data snapshot from the 0.4.9+ cluster:
-
-```
-curl http://cluster.example.com:4001/v2/migration/snapshot > backup.snap
-```
-
-Now, import the snapshot into your new cluster:
-
-```
-etcdctl --endpoint new_cluster.example.com import --snap backup.snap
-```
-
-If you have a large amount of data, you can specify more concurrent works to copy data in parallel by using `-c` flag.
-If you have hidden keys to copy, you can use `--hidden` flag to specify. For example fleet uses `/_coreos.com/fleet` so to import those keys use `--hidden /_coreos.com`.
-
-And the data will quickly copy into the new cluster:
-
-```
-entering dir: /
-entering dir: /foo
-entering dir: /foo/bar
-copying key: /foo/bar/1 1
-entering dir: /
-entering dir: /foo2
-entering dir: /foo2/bar2
-copying key: /foo2/bar2/2 2
-```

Documentation/v2/README.md

@@ -1,165 +0,0 @@
-# etcd2
-
-[![Go Report Card](https://goreportcard.com/badge/github.com/coreos/etcd)](https://goreportcard.com/report/github.com/coreos/etcd)
-[![Build Status](https://travis-ci.org/coreos/etcd.svg?branch=master)](https://travis-ci.org/coreos/etcd)
-[![Build Status](https://semaphoreci.com/api/v1/coreos/etcd/branches/master/shields_badge.svg)](https://semaphoreci.com/coreos/etcd)
-[![Docker Repository on Quay.io](https://quay.io/repository/coreos/etcd-git/status "Docker Repository on Quay.io")](https://quay.io/repository/coreos/etcd-git)
-
-**Note**: The `master` branch may be in an *unstable or even broken state* during development. Please use [releases][github-release] instead of the `master` branch in order to get stable binaries.
-
-![etcd Logo](../../logos/etcd-horizontal-color.png)
-
-etcd is a distributed, consistent key-value store for shared configuration and service discovery, with a focus on being:
-
-* *Simple*: curl'able user-facing API (HTTP+JSON)
-* *Secure*: optional SSL client cert authentication
-* *Fast*: benchmarked 1000s of writes/s per instance
-* *Reliable*: properly distributed using Raft
-
-etcd is written in Go and uses the [Raft][raft] consensus algorithm to manage a highly-available replicated log.
-
-etcd is used [in production by many companies](./production-users.md), and the development team stands behind it in critical deployment scenarios, where etcd is frequently teamed with applications such as [Kubernetes][k8s], [fleet][fleet], [locksmith][locksmith], [vulcand][vulcand], and many others.
-
-See [etcdctl][etcdctl] for a simple command line client.
-Or feel free to just use `curl`, as in the examples below.
-
-[raft]: https://raft.github.io/
-[k8s]: http://kubernetes.io/
-[fleet]: https://github.com/coreos/fleet
-[locksmith]: https://github.com/coreos/locksmith
-[vulcand]: https://github.com/vulcand/vulcand
-[etcdctl]: https://github.com/coreos/etcd/tree/master/etcdctl
-
-## Getting Started
-
-### Getting etcd
-
-The easiest way to get etcd is to use one of the pre-built release binaries which are available for OSX, Linux, Windows, AppC (ACI), and Docker. Instructions for using these binaries are on the [GitHub releases page][github-release].
-
-For those wanting to try the very latest version, you can build the latest version of etcd from the `master` branch.
-You will first need [*Go*](https://golang.org/) installed on your machine (version 1.5+ is required).
-All development occurs on `master`, including new features and bug fixes.
-Bug fixes are first targeted at `master` and subsequently ported to release branches, as described in the [branch management][branch-management] guide.
-
-[github-release]: https://github.com/coreos/etcd/releases/
-[branch-management]: branch_management.md
-
-### Running etcd
-
-First start a single-member cluster of etcd:
-
-```sh
-./bin/etcd
-```
-
-This will bring up etcd listening on port 2379 for client communication and on port 2380 for server-to-server communication.
-
-Next, let's set a single key, and then retrieve it:
-
-```
-curl -L http://127.0.0.1:2379/v2/keys/mykey -XPUT -d value="this is awesome"
-curl -L http://127.0.0.1:2379/v2/keys/mykey
-```
-
-You have successfully started an etcd and written a key to the store.
-
-### etcd TCP ports
-
-The [official etcd ports][iana-ports] are 2379 for client requests, and 2380 for peer communication. To maintain compatibility, some etcd configuration and documentation continues to refer to the legacy ports 4001 and 7001, but all new etcd use and discussion should adopt the IANA-assigned ports. The legacy ports 4001 and 7001 will be fully deprecated, and support for their use removed, in future etcd releases.
-
-[iana-ports]: http://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.txt
-
-### Running local etcd cluster
-
-First install [goreman](https://github.com/mattn/goreman), which manages Procfile-based applications.
-
-Our [Procfile script](../../V2Procfile) will set up a local example cluster. You can start it with:
-
-```sh
-goreman start
-```
-
-This will bring up 3 etcd members `infra1`, `infra2` and `infra3` and etcd proxy `proxy`, which runs locally and composes a cluster.
-
-You can write a key to the cluster and retrieve the value back from any member or proxy.
-
-### Next Steps
-
-Now it's time to dig into the full etcd API and other guides.
-
-- Explore the full [API][api].
-- Set up a [multi-machine cluster][clustering].
-- Learn the [config format, env variables and flags][configuration].
-- Find [language bindings and tools][libraries-and-tools].
-- Use TLS to [secure an etcd cluster][security].
-- [Tune etcd][tuning].
-- [Upgrade from 0.4.9+ to 2.2.0][upgrade].
-
-[api]: ./api.md
-[clustering]: ./clustering.md
-[configuration]: ./configuration.md
-[libraries-and-tools]: ./libraries-and-tools.md
-[security]: ./security.md
-[tuning]: ./tuning.md
-[upgrade]: ./04_to_2_snapshot_migration.md
-
-## Contact
-
-- Mailing list: [etcd-dev](https://groups.google.com/forum/?hl=en#!forum/etcd-dev)
-- IRC: #[etcd](irc://irc.freenode.org:6667/#etcd) on freenode.org
-- Planning/Roadmap: [milestones](https://github.com/coreos/etcd/milestones), [roadmap](../../ROADMAP.md)
-- Bugs: [issues](https://github.com/coreos/etcd/issues)
-
-## Contributing
-
-See [CONTRIBUTING](../../CONTRIBUTING.md) for details on submitting patches and the contribution workflow.
-
-## Reporting bugs
-
-See [reporting bugs](reporting_bugs.md) for details about reporting any issue you may encounter.
-
-## Known bugs
-
-[GH518](https://github.com/coreos/etcd/issues/518) is a known bug. Issue is that:
-
-```
-curl http://127.0.0.1:2379/v2/keys/foo -XPUT -d value=bar
-curl http://127.0.0.1:2379/v2/keys/foo -XPUT -d dir=true -d prevExist=true
-```
-
-If the previous node is a key and client tries to overwrite it with `dir=true`, it does not give warnings such as `Not a directory`. Instead, the key is set to empty value.
-
-## Project Details
-
-### Versioning
-
-#### Service Versioning
-
-etcd uses [semantic versioning](http://semver.org)
-New minor versions may add additional features to the API.
-
-You can get the version of etcd by issuing a request to /version:
-
-```sh
-curl -L http://127.0.0.1:2379/version
-```
-
-#### API Versioning
-
-The `v2` API responses should not change after the 2.0.0 release but new features will be added over time.
-
-#### 32-bit and other unsupported systems
-
-etcd has known issues on 32-bit systems due to a bug in the Go runtime. See #[358][358] for more information.
-
-To avoid inadvertently running a possibly unstable etcd server, `etcd` on unsupported architectures will print
-a warning message and immediately exit if the environment variable `ETCD_UNSUPPORTED_ARCH` is not set to
-the target architecture.
-
-Currently only the amd64 architecture is officially supported by `etcd`.
-
-[358]: https://github.com/coreos/etcd/issues/358
-
-### License
-
-etcd is under the Apache 2.0 license. See the [LICENSE](../../LICENSE) file for details.

Documentation/v2/admin_guide.md

@@ -1,312 +0,0 @@
-# Administration
-
-## Data Directory
-
-### Lifecycle
-
-When first started, etcd stores its configuration into a data directory specified by the data-dir configuration parameter.
-Configuration is stored in the write ahead log and includes: the local member ID, cluster ID, and initial cluster configuration.
-The write ahead log and snapshot files are used during member operation and to recover after a restart.
-
-Having a dedicated disk to store wal files can improve the throughput and stabilize the cluster. 
-It is highly recommended to dedicate a wal disk and set `--wal-dir` to point to a directory on that device for a production cluster deployment.
-
-If a member’s data directory is ever lost or corrupted then the user should [remove][remove-a-member] the etcd member from the cluster using `etcdctl` tool.
-
-A user should avoid restarting an etcd member with a data directory from an out-of-date backup.
-Using an out-of-date data directory can lead to inconsistency as the member had agreed to store information via raft then re-joins saying it needs that information again.
-For maximum safety, if an etcd member suffers any sort of data corruption or loss, it must be removed from the cluster.
-Once removed the member can be re-added with an empty data directory.
-
-### Contents
-
-The data directory has two sub-directories in it:
-
-1. wal: write ahead log files are stored here. For details see the [wal package documentation][wal-pkg]
-2. snap: log snapshots are stored here. For details see the [snap package documentation][snap-pkg]
-
-If `--wal-dir` flag is set, etcd will write the write ahead log files to the specified directory instead of data directory.
-
-## Cluster Management
-
-### Lifecycle
-
-If you are spinning up multiple clusters for testing it is recommended that you specify a unique initial-cluster-token for the different clusters.
-This can protect you from cluster corruption in case of mis-configuration because two members started with different cluster tokens will refuse members from each other.
-
-### Monitoring
-
-It is important to monitor your production etcd cluster for healthy information and runtime metrics.
-
-#### Health Monitoring
-
-At lowest level, etcd exposes health information via HTTP at `/health` in JSON format. If it returns `{"health": "true"}`, then the cluster is healthy. Please note the `/health` endpoint is still an experimental one as in etcd 2.2.
-
-```
-$ curl -L http://127.0.0.1:2379/health
-
-{"health": "true"}
-```
-
-You can also use etcdctl to check the cluster-wide health information. It will contact all the members of the cluster and collect the health information for you.
-
-```
-$./etcdctl cluster-health 
-member 8211f1d0f64f3269 is healthy: got healthy result from http://127.0.0.1:12379
-member 91bc3c398fb3c146 is healthy: got healthy result from http://127.0.0.1:22379
-member fd422379fda50e48 is healthy: got healthy result from http://127.0.0.1:32379
-cluster is healthy
-```
-
-#### Runtime Metrics
-
-etcd uses [Prometheus][prometheus] for metrics reporting in the server. You can read more through the runtime metrics [doc][metrics].
-
-### Debugging
-
-Debugging a distributed system can be difficult. etcd provides several ways to make debug
-easier.
-
-#### Enabling Debug Logging
-
-When you want to debug etcd without stopping it, you can enable debug logging at runtime.
-etcd exposes logging configuration at `/config/local/log`.
-
-```
-$ curl http://127.0.0.1:2379/config/local/log -XPUT -d '{"Level":"DEBUG"}'
-$ # debug logging enabled
-$
-$ curl http://127.0.0.1:2379/config/local/log -XPUT -d '{"Level":"INFO"}'
-$ # debug logging disabled
-```
-
-#### Debugging Variables
-
-Debug variables are exposed for real-time debugging purposes. Developers who are familiar with etcd can utilize these variables to debug unexpected behavior. etcd exposes debug variables via HTTP at `/debug/vars` in JSON format. The debug variables contains
-`cmdline`, `file_descriptor_limit`, `memstats` and `raft.status`.
-
-`cmdline` is the command line arguments passed into etcd.
-
-`file_descriptor_limit` is the max number of file descriptors etcd can utilize.
-
-`memstats` is explained in detail in the [Go runtime documentation][golang-memstats].
-
-`raft.status` is useful when you want to debug low level raft issues if you are familiar with raft internals. In most cases, you do not need to check `raft.status`.
-
-```json
-{
-"cmdline": ["./etcd"],
-"file_descriptor_limit": 0,
-"memstats": {"Alloc":4105744,"TotalAlloc":42337320,"Sys":12560632,"...":"..."},
-"raft.status": {"id":"ce2a822cea30bfca","term":5,"vote":"ce2a822cea30bfca","commit":23509,"lead":"ce2a822cea30bfca","raftState":"StateLeader","progress":{"ce2a822cea30bfca":{"match":23509,"next":23510,"state":"ProgressStateProbe"}}}
-}
-```
-
-### Optimal Cluster Size
-
-The recommended etcd cluster size is 3, 5 or 7, which is decided by the fault tolerance requirement. A 7-member cluster can provide enough fault tolerance in most cases. While larger cluster provides better fault tolerance the write performance reduces since data needs to be replicated to more machines.
-
-#### Fault Tolerance Table
-
-It is recommended to have an odd number of members in a cluster. Having an odd cluster size doesn't change the number needed for majority, but you gain a higher tolerance for failure by adding the extra member. You can see this in practice when comparing even and odd sized clusters:
-
-| Cluster Size | Majority   | Failure Tolerance |
-|--------------|------------|-------------------|
-| 1 | 1 | 0 |
-| 2 | 2 | 0 |
-| 3 | 2 | **1** |
-| 4 | 3 | 1 |
-| 5 | 3 | **2** |
-| 6 | 4 | 2 |
-| 7 | 4 | **3** |
-| 8 | 5 | 3 |
-| 9 | 5 | **4** |
-
-As you can see, adding another member to bring the size of cluster up to an odd size is always worth it. During a network partition, an odd number of members also guarantees that there will almost always be a majority of the cluster that can continue to operate and be the source of truth when the partition ends.
-
-#### Changing Cluster Size
-
-After your cluster is up and running, adding or removing members is done via [runtime reconfiguration][runtime-reconfig], which allows the cluster to be modified without downtime. The `etcdctl` tool has `member list`, `member add` and `member remove` commands to complete this process.
-
-### Member Migration
-
-When there is a scheduled machine maintenance or retirement, you might want to migrate an etcd member to another machine without losing the data and changing the member ID.
-
-The data directory contains all the data to recover a member to its point-in-time state. To migrate a member:
-
-* Stop the member process.
-* Copy the data directory of the now-idle member to the new machine.
-* Update the peer URLs for the replaced member to reflect the new machine according to the [runtime reconfiguration instructions][update-a-member].
-* Start etcd on the new machine, using the same configuration and the copy of the data directory.
-
-This example will walk you through the process of migrating the infra1 member to a new machine:
-
-|Name|Peer URL|
-|------|--------------|
-|infra0|10.0.1.10:2380|
-|infra1|10.0.1.11:2380|
-|infra2|10.0.1.12:2380|
-
-```sh
-$ export ETCDCTL_ENDPOINT=http://10.0.1.10:2379,http://10.0.1.11:2379,http://10.0.1.12:2379
-```
-
-```sh
-$ etcdctl member list
-84194f7c5edd8b37: name=infra0 peerURLs=http://10.0.1.10:2380 clientURLs=http://127.0.0.1:2379,http://10.0.1.10:2379
-b4db3bf5e495e255: name=infra1 peerURLs=http://10.0.1.11:2380 clientURLs=http://127.0.0.1:2379,http://10.0.1.11:2379
-bc1083c870280d44: name=infra2 peerURLs=http://10.0.1.12:2380 clientURLs=http://127.0.0.1:2379,http://10.0.1.12:2379
-```
-
-#### Stop the member etcd process
-
-```sh
-$ ssh 10.0.1.11
-```
-
-```sh
-$ kill `pgrep etcd`
-```
-
-#### Copy the data directory of the now-idle member to the new machine
-
-```
-$ tar -cvzf infra1.etcd.tar.gz %data_dir%
-```
-
-```sh
-$ scp infra1.etcd.tar.gz 10.0.1.13:~/
-```
-
-#### Update the peer URLs for that member to reflect the new machine
-
-```sh
-$ curl http://10.0.1.10:2379/v2/members/b4db3bf5e495e255 -XPUT \
--H "Content-Type: application/json" -d '{"peerURLs":["http://10.0.1.13:2380"]}'
-```
-
-Or use `etcdctl member update` command
-
-```sh
-$ etcdctl member update b4db3bf5e495e255 http://10.0.1.13:2380
-```
-
-#### Start etcd on the new machine, using the same configuration and the copy of the data directory
-
-```sh
-$ ssh 10.0.1.13
-```
-
-```sh
-$ tar -xzvf infra1.etcd.tar.gz -C %data_dir%
-```
-
-```
-etcd -name infra1 \
--listen-peer-urls http://10.0.1.13:2380 \
--listen-client-urls http://10.0.1.13:2379,http://127.0.0.1:2379 \
--advertise-client-urls http://10.0.1.13:2379,http://127.0.0.1:2379
-```
-
-### Disaster Recovery
-
-etcd is designed to be resilient to machine failures. An etcd cluster can automatically recover from any number of temporary failures (for example, machine reboots), and a cluster of N members can tolerate up to _(N-1)/2_ permanent failures (where a member can no longer access the cluster, due to hardware failure or disk corruption). However, in extreme circumstances, a cluster might permanently lose enough members such that quorum is irrevocably lost. For example, if a three-node cluster suffered two simultaneous and unrecoverable machine failures, it would be normally impossible for the cluster to restore quorum and continue functioning.
-
-To recover from such scenarios, etcd provides functionality to backup and restore the datastore and recreate the cluster without data loss.
-
-#### Backing up the datastore
-
-**Note:** Windows users must stop etcd before running the backup command.
-
-The first step of the recovery is to backup the data directory and wal directory, if stored separately, on a functioning etcd node. To do this, use the `etcdctl backup` command, passing in the original data (and wal) directory used by etcd. For example:
-
-```sh
-    etcdctl backup \
-      --data-dir %data_dir% \
-      [--wal-dir %wal_dir%] \
-      --backup-dir %backup_data_dir%
-      [--backup-wal-dir %backup_wal_dir%]
-```
-
-This command will rewrite some of the metadata contained in the backup (specifically, the node ID and cluster ID), which means that the node will lose its former identity. In order to recreate a cluster from the backup, you will need to start a new, single-node cluster. The metadata is rewritten to prevent the new node from inadvertently being joined onto an existing cluster.
-
-#### Restoring a backup
-
-To restore a backup using the procedure created above, start etcd with the `-force-new-cluster` option and pointing to the backup directory. This will initialize a new, single-member cluster with the default advertised peer URLs, but preserve the entire contents of the etcd data store. Continuing from the previous example:
-
-```sh
-    etcd \
-      -data-dir=%backup_data_dir% \
-      [-wal-dir=%backup_wal_dir%] \
-      -force-new-cluster \
-      ...
-```
-
-Now etcd should be available on this node and serving the original datastore.
-
-Once you have verified that etcd has started successfully, shut it down and move the data and wal, if stored separately, back to the previous location (you may wish to make another copy as well to be safe):
-
-```sh
-    pkill etcd
-    rm -fr %data_dir%
-    rm -fr %wal_dir%
-    mv %backup_data_dir% %data_dir%
-    mv %backup_wal_dir% %wal_dir%
-    etcd \
-      -data-dir=%data_dir% \
-      [-wal-dir=%wal_dir%] \
-      ...
-```
-
-#### Restoring the cluster
-
-Now that the node is running successfully, [change its advertised peer URLs][update-a-member], as the `--force-new-cluster` option has set the peer URL to the default listening on localhost.
-
-You can then add more nodes to the cluster and restore resiliency. See the [add a new member][add-a-member] guide for more details.
-
-**Note:** If you are trying to restore your cluster using old failed etcd nodes, please make sure you have stopped old etcd instances and removed their old data directories specified by the data-dir configuration parameter.
-
-### Client Request Timeout
-
-etcd sets different timeouts for various types of client requests. The timeout value is not tunable now, which will be improved soon (https://github.com/coreos/etcd/issues/2038).
-
-#### Get requests
-
-Timeout is not set for get requests, because etcd serves the result locally in a non-blocking way.
-
-**Note**: QuorumGet request is a different type, which is mentioned in the following sections.
-
-#### Watch requests
-
-Timeout is not set for watch requests. etcd will not stop a watch request until client cancels it, or the connection is broken.
-
-#### Delete, Put, Post, QuorumGet requests
-
-The default timeout is 5 seconds. It should be large enough to allow all key modifications if the majority of cluster is functioning.
-
-If the request times out, it indicates two possibilities:
-
-1. the server the request sent to was not functioning at that time.
-2. the majority of the cluster is not functioning.
-
-If timeout happens several times continuously, administrators should check status of cluster and resolve it as soon as possible.
-
-### Best Practices
-
-#### Maximum OS threads
-
-By default, etcd uses the default configuration of the Go 1.4 runtime, which means that at most one operating system thread will be used to execute code simultaneously. (Note that this default behavior [has changed in Go 1.5][golang1.5-runtime]).
-
-When using etcd in heavy-load scenarios on machines with multiple cores it will usually be desirable to increase the number of threads that etcd can utilize. To do this, simply set the environment variable GOMAXPROCS to the desired number when starting etcd. For more information on this variable, see the [Go runtime documentation][golang-runtime].
-
-[add-a-member]: runtime-configuration.md#add-a-new-member
-[golang1.5-runtime]: https://golang.org/doc/go1.5#runtime
-[golang-memstats]: https://golang.org/pkg/runtime/#MemStats
-[golang-runtime]: https://golang.org/pkg/runtime
-[metrics]: metrics.md
-[prometheus]: http://prometheus.io/
-[remove-a-member]: runtime-configuration.md#remove-a-member
-[runtime-reconfig]: runtime-configuration.md#cluster-reconfiguration-operations
-[snap-pkg]: http://godoc.org/github.com/coreos/etcd/snap
-[update-a-member]: runtime-configuration.md#update-a-member
-[wal-pkg]: http://godoc.org/github.com/coreos/etcd/wal

Documentation/v2/api_v3.md

@@ -1,92 +0,0 @@
-# etcd3 API
-
-TODO: API doc
-
-## Data Model
-
-etcd is designed to reliably store infrequently updated data and provide reliable watch queries. etcd exposes previous versions of key-value pairs to support inexpensive snapshots and watch history events (“time travel queries”). A persistent, multi-version, concurrency-control data model is a good fit for these use cases.
-
-etcd stores data in a multiversion [persistent][persistent-ds] key-value store. The persistent key-value store preserves the previous version of a key-value pair when its value is superseded with new data. The key-value store is effectively immutable; its operations do not update the structure in-place, but instead always generates a new updated structure. All past versions of keys are still accessible and watchable after modification. To prevent the data store from growing indefinitely over time from maintaining old versions, the store may be compacted to shed the oldest versions of superseded data.
-
-### Logical View
-
-The store’s logical view is a flat binary key space. The key space has a lexically sorted index on byte string keys so range queries are inexpensive.
-
-The key space maintains multiple revisions. Each atomic mutative operation (e.g., a transaction operation may contain multiple operations) creates a new revision on the key space. All data held by previous revisions remains unchanged. Old versions of key can still be accessed through previous revisions. Likewise, revisions are indexed as well; ranging over revisions with watchers is efficient. If the store is compacted to recover space, revisions before the compact revision will be removed.
-
-A key’s lifetime spans a generation. Each key may have one or multiple generations. Creating a key increments the generation of that key, starting at 1 if the key never existed. Deleting a key generates a key tombstone, concluding the key’s current generation. Each modification of a key creates a new version of the key. Once a compaction happens, any generation ended before the given revision will be removed and values set before the compaction revision except the latest one will be removed.
-
-### Physical View
-
-etcd stores the physical data as key-value pairs in a persistent [b+tree][b+tree]. Each revision of the store’s state only contains the delta from its previous revision to be efficient. A single revision may correspond to multiple keys in the tree.
-
-The key of key-value pair is a 3-tuple (major, sub, type). Major is the store revision holding the key. Sub differentiates among  keys within the same revision. Type is an optional suffix for special value (e.g., `t` if the value contains a tombstone). The value of the key-value pair contains the modification from previous revision, thus one delta from previous revision. The b+tree is ordered by key in lexical byte-order. Ranged lookups over revision deltas are fast; this enables quickly finding modifications from one specific revision to another. Compaction removes out-of-date keys-value pairs.
-
-etcd also keeps a secondary in-memory [btree][btree] index to speed up range queries over keys. The keys in the btree index are the keys of the store exposed to user. The value is a pointer to the modification of the persistent b+tree. Compaction removes dead pointers.
-
-## KV API Guarantees
-
-etcd is a consistent and durable key value store with mini-transaction(TODO: link to txn doc when we have it) support. The key value store is exposed through the KV APIs. etcd tries to ensure the strongest consistency and durability guarantees for a distributed system. This specification enumerates the KV API guarantees made by etcd.
-
-### APIs to consider
-
-* Read APIs
-    * range
-    * watch
-* Write APIs
-    * put
-    * delete
-* Combination (read-modify-write) APIs
-    * txn
-
-### etcd Specific Definitions
-
-#### operation completed
-
-An etcd operation is considered complete when it is committed through consensus, and therefore “executed” -- permanently stored -- by the etcd storage engine. The client knows an operation is completed when it receives a response from the etcd server. Note that the client may be uncertain about the status of an operation if it times out, or there is a network disruption between the client and the etcd member. etcd may also abort operations when there is a leader election. etcd does not send `abort` responses to  clients’ outstanding requests in this event.
-
-#### revision
-
-An etcd operation that modifies the key value store is assigned with a single increasing revision. A transaction operation might modify the key value store multiple times, but only one revision is assigned. The revision attribute of a key value pair that modified by the operation has the same value as the revision of the operation. The revision can be used as a logical clock for key value store. A key value pair that has a larger revision is modified after a key value pair with a smaller revision. Two key value pairs that have the same revision are modified by an operation "concurrently".
-
-### Guarantees Provided
-
-#### Atomicity
-
-All API requests are atomic; an operation either completes entirely or not at all. For watch requests, all events generated by one operation will be in one watch response. Watch never observes partial events for a single operation.
-
-#### Consistency
-
-All API calls ensure [sequential consistency][seq_consistency], the strongest consistency guarantee available from distributed systems. No matter which etcd member server a client makes requests to, a client reads the same events in the same order. If two members complete the same number of operations, the state of the two members is consistent.
-
-For watch operations, etcd guarantees to return the same value for the same key across all members for the same revision. For range operations, etcd has a similar guarantee for [linearized][Linearizability] access; serialized access may be behind the quorum state, so that the later revision is not yet available.
-
-As with all distributed systems, it is impossible for etcd to ensure [strict consistency][strict_consistency]. etcd does not guarantee that it will return to a read the “most recent” value (as measured by a wall clock when a request is completed) available on any cluster member.
-
-#### Isolation
-
-etcd ensures [serializable isolation][serializable_isolation], which is the highest isolation level available in distributed systems. Read operations will never observe any intermediate data.
-
-#### Durability
-
-Any completed operations are durable. All accessible data is also durable data. A read will never return data that has not been made durable.
-
-#### Linearizability
-
-Linearizability (also known as Atomic Consistency or External Consistency) is a consistency level between strict consistency and sequential consistency.
-
-For linearizability, suppose each operation receives a timestamp from a loosely synchronized global clock. Operations are linearized if and only if they always complete as though they were executed in a sequential order and each operation appears to complete in the order specified by the program. Likewise, if an operation’s timestamp precedes another, that operation must also precede the other operation in the sequence.
-
-For example, consider a client completing a write at time point 1 (*t1*). A client issuing a read at *t2* (for *t2* > *t1*) should receive a value at least as recent as the previous write, completed at *t1*. However, the read might actually complete only by *t3*, and the returned value, current at *t2* when the read began, might be "stale" by *t3*.
-
-etcd does not ensure linearizability for watch operations. Users are expected to verify the revision of watch responses to ensure correct ordering.
-
-etcd ensures linearizability for all other operations by default. Linearizability comes with a cost, however, because linearized requests must go through the Raft consensus process. To obtain lower latencies and higher throughput for read requests, clients can configure a request’s consistency mode to `serializable`, which may access stale data with respect to quorum, but removes the performance penalty of linearized accesses' reliance on live consensus.
-
-[persistent-ds]: https://en.wikipedia.org/wiki/Persistent_data_structure
-[btree]: https://en.wikipedia.org/wiki/B-tree
-[b+tree]: https://en.wikipedia.org/wiki/B%2B_tree
-[seq_consistency]: https://en.wikipedia.org/wiki/Consistency_model#Sequential_consistency
-[strict_consistency]: https://en.wikipedia.org/wiki/Consistency_model#Strict_consistency
-[serializable_isolation]: https://en.wikipedia.org/wiki/Isolation_(database_systems)#Serializable
-[Linearizability]: #linearizability

Documentation/v2/auth_api.md

@@ -1,511 +0,0 @@
-# v2 Auth and Security
-
-## etcd Resources 
-There are three types of resources in etcd
-
-1. permission resources: users and roles in the user store
-2. key-value resources: key-value pairs in the key-value store
-3. settings resources: security settings, auth settings, and dynamic etcd cluster settings (election/heartbeat)
-
-### Permission Resources 
-
-#### Users
-A user is an identity to be authenticated. Each user can have multiple roles. The user has a capability (such as reading or writing) on the resource if one of the roles has that capability.
-
-A user named `root` is required before authentication can be enabled, and it always has the ROOT role. The ROOT role can be granted to multiple users, but `root` is required for recovery purposes.
-
-#### Roles
-Each role has exact one associated Permission List. An permission list exists for each permission on key-value resources. 
-
-The special static ROOT (named `root`) role has a full permissions on all key-value resources, the permission to manage user resources and settings resources. Only the ROOT role has the permission to manage user resources and modify settings resources. The ROOT role is built-in and does not need to be created.
-
-There is also a special GUEST role, named 'guest'. These are the permissions given to unauthenticated requests to etcd. This role will be created automatically, and by default allows access to the full keyspace due to backward compatibility. (etcd did not previously authenticate any actions.). This role can be modified by a ROOT role holder at any time, to reduce the capabilities of unauthenticated users.
-
-#### Permissions
-
-There are two types of permissions, `read` and `write`. All management and settings require the ROOT role.
-
-A Permission List is a list of allowed patterns for that particular permission (read or write). Only ALLOW prefixes are supported. DENY becomes more complicated and is TBD.
-
-### Key-Value Resources
-A key-value resource is a key-value pairs in the store. Given a list of matching patterns, permission for any given key in a request is granted if any of the patterns in the list match.
-
-Only prefixes or exact keys are supported. A prefix permission string ends in `*`. 
-A permission on `/foo` is for that exact key or directory, not its children or recursively. `/foo*` is a prefix that matches `/foo` recursively, and all keys thereunder, and keys with that prefix (eg. `/foobar`. Contrast to the prefix `/foo/*`). `*` alone is permission on the full keyspace. 
-
-### Settings Resources
-
-Specific settings for the cluster as a whole. This can include adding and removing cluster members, enabling or disabling authentication, replacing certificates, and any other dynamic configuration by the administrator (holder of the ROOT role).
-
-## v2 Auth
-
-### Basic Auth
-We only support [Basic Auth][basic-auth] for the first version. Client needs to attach the basic auth to the HTTP Authorization Header.
-
-### Authorization field for operations
-Added to requests to /v2/keys, /v2/auth
-Add code 401 Unauthorized to the set of responses from the v2 API
-Authorization: Basic {encoded string}
-
-### Future Work
-Other types of auth can be considered for the future (eg, signed certs, public keys) but the `Authorization:` header allows for other such types
-
-### Things out of Scope for etcd Permissions
-
-* Pluggable AUTH backends like LDAP (other Authorization tokens generated by LDAP et al may be a possibility)
-* Very fine-grained access controls (eg: users modifying keys outside work hours)
-
-
-
-## API endpoints
-
-An Error JSON corresponds to:
-{
-  "name": "ErrErrorName",
-  "description" : "The longer helpful description of the error."
-}
-
-#### Enable and Disable Authentication
-        
-**Get auth status**
-
-GET  /v2/auth/enable
-
-    Sent Headers:
-    Possible Status Codes:
-        200 OK
-    200 Body:
-        {
-          "enabled": true
-        }
-
-
-**Enable auth**
-
-PUT  /v2/auth/enable
-
-    Sent Headers:
-    Put Body: (empty)
-    Possible Status Codes:
-        200 OK
-        400 Bad Request (if root user has not been created)
-        409 Conflict (already enabled)
-    200 Body: (empty)
-
-**Disable auth**
-
-DELETE  /v2/auth/enable
-
-    Sent Headers:
-        Authorization: Basic <RootAuthString>
-    Possible Status Codes:
-        200 OK
-        401 Unauthorized (if not a root user)
-        409 Conflict (already disabled)
-    200 Body: (empty)
-
-
-#### Users
-
-The User JSON object is formed as follows:
-
-```
-{
-  "user": "userName",
-  "password": "password",
-  "roles": [
-    "role1",
-    "role2"
-  ],
-  "grant": [],
-  "revoke": []
-}
-```
-
-Password is only passed when necessary.
-
-**Get a List of Users**
-
-GET/HEAD  /v2/auth/users
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Possible Status Codes:
-        200 OK
-        401 Unauthorized
-    200 Headers:
-        Content-type: application/json
-    200 Body:
-        {
-          "users": [
-            {
-              "user": "alice",
-              "roles": [
-                {
-                  "role": "root",
-                  "permissions": {
-                    "kv": {
-                      "read": ["/*"],
-                      "write": ["/*"]
-                    }
-                  }
-                }
-              ]
-            },
-            {
-              "user": "bob",
-              "roles": [
-                {
-                  "role": "guest",
-                  "permissions": {
-                    "kv": {
-                      "read": ["/*"],
-                      "write": ["/*"]
-                    }
-                  }
-                }
-              ]
-            }
-          ]
-        }
-
-**Get User Details**
-
-GET/HEAD  /v2/auth/users/alice
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Possible Status Codes:
-        200 OK
-        401 Unauthorized
-        404 Not Found
-    200 Headers:
-        Content-type: application/json
-    200 Body:
-        {
-          "user" : "alice",
-          "roles" : [
-            {
-              "role": "fleet",
-              "permissions" : {
-                "kv" : {
-                  "read": [ "/fleet/" ],
-                  "write": [ "/fleet/" ]
-                }
-              }
-            },
-            {
-              "role": "etcd",
-              "permissions" : {
-                "kv" : {
-                  "read": [ "/*" ],
-                  "write": [ "/*" ]
-                }
-              }
-            }
-          ]
-        }
-
-**Create Or Update A User**
-
-A user can be created with initial roles, if filled in. However, no roles are required; only the username and password fields
-
-PUT  /v2/auth/users/charlie
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Put Body:
-        JSON struct, above, matching the appropriate name 
-          * Starting password and roles when creating. 
-          * Grant/Revoke/Password filled in when updating (to grant roles, revoke roles, or change the password).
-    Possible Status Codes:
-        200 OK
-        201 Created
-        400 Bad Request
-        401 Unauthorized
-        404 Not Found (update non-existent users)
-        409 Conflict (when granting duplicated roles or revoking non-existent roles)
-    200 Headers:
-        Content-type: application/json
-    200 Body:
-        JSON state of the user
-
-**Remove A User**
-
-DELETE  /v2/auth/users/charlie
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Possible Status Codes:
-        200 OK
-        401 Unauthorized
-        403 Forbidden (remove root user when auth is enabled)
-        404 Not Found
-    200 Headers:
-    200 Body: (empty)
-
-#### Roles
-
-A full role structure may look like this. A Permission List structure is used for the "permissions", "grant", and "revoke" keys.
-```
-{
-  "role" : "fleet",
-  "permissions" : {
-    "kv" : {
-      "read" : [ "/fleet/" ],
-      "write": [ "/fleet/" ]
-    }
-  },
-  "grant" : {"kv": {...}},
-  "revoke": {"kv": {...}}
-}
-```
-
-**Get Role Details**
-
-GET/HEAD  /v2/auth/roles/fleet
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Possible Status Codes:
-        200 OK
-        401 Unauthorized
-        404 Not Found
-    200 Headers:
-        Content-type: application/json
-    200 Body:
-        {
-          "role" : "fleet",
-          "permissions" : {
-            "kv" : {
-              "read": [ "/fleet/" ],
-              "write": [ "/fleet/" ]
-            }
-          }
-        }
-
-**Get a list of Roles**
-
-GET/HEAD  /v2/auth/roles
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Possible Status Codes:
-        200 OK
-        401 Unauthorized
-    200 Headers:
-        Content-type: application/json
-    200 Body:
-        {
-          "roles": [
-            {
-              "role": "fleet",
-              "permissions": {
-                "kv": {
-                  "read": ["/fleet/"],
-                  "write": ["/fleet/"]
-                }
-              }
-            },
-            {
-              "role": "etcd",
-              "permissions": {
-                "kv": {
-                  "read": ["/*"],
-                  "write": ["/*"]
-                }
-              }
-            },
-            {
-              "role": "quay",
-              "permissions": {
-                "kv": {
-                  "read": ["/*"],
-                  "write": ["/*"]
-                }
-              }
-            }
-          ]
-        }
-
-**Create Or Update A Role**
-
-PUT  /v2/auth/roles/rkt
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Put Body:
-        Initial desired JSON state, including the role name for verification and:
-          * Starting permission set if creating
-          * Granted/Revoked permission set if updating
-    Possible Status Codes:
-        200 OK
-        201 Created
-        400 Bad Request
-        401 Unauthorized
-        404 Not Found (update non-existent roles)
-        409 Conflict (when granting duplicated permission or revoking non-existent permission)
-    200 Body: 
-        JSON state of the role
-
-**Remove A Role**
-
-DELETE  /v2/auth/roles/rkt
-
-    Sent Headers:
-        Authorization: Basic <BasicAuthString>
-    Possible Status Codes:
-        200 OK
-        401 Unauthorized
-        403 Forbidden (remove root)
-        404 Not Found
-    200 Headers:
-    200 Body: (empty)
-
-
-## Example Workflow
-
-Let's walk through an example to show two tenants (applications, in our case) using etcd permissions.
-
-### Create root role
-
-```
-PUT  /v2/auth/users/root
-    Put Body:
-        {"user" : "root", "password": "betterRootPW!"}
-```
-
-### Enable auth
-
-```
-PUT  /v2/auth/enable
-```
-
-### Modify guest role (revoke write permission)
-
-```
-PUT  /v2/auth/roles/guest
-    Headers:
-        Authorization: Basic <root:betterRootPW!>
-    Put Body:
-        {
-          "role" : "guest",
-          "revoke" : {
-            "kv" : {
-              "write": [
-                "/*"
-              ]
-            }
-          }
-        }
-```
-
-
-### Create Roles for the Applications
-
-Create the rkt role fully specified:
-
-```
-PUT /v2/auth/roles/rkt
-    Headers:
-        Authorization: Basic <root:betterRootPW!>
-    Body:
-        {
-          "role" : "rkt",
-          "permissions" : {
-            "kv": {
-              "read": [
-                "/rkt/*"
-              ],
-              "write": [
-                "/rkt/*"
-              ]
-            }
-          }
-        }
-```
-
-But let's make fleet just a basic role for now:
-
-```
-PUT /v2/auth/roles/fleet
-    Headers:
-      Authorization: Basic <root:betterRootPW!>
-    Body:
-        {
-          "role" : "fleet"
-        }
-```
-
-### Optional: Grant some permissions to the roles
-
-Well, we finally figured out where we want fleet to live. Let's fix it.
-(Note that we avoided this in the rkt case. So this step is optional.)
-
-
-```
-PUT /v2/auth/roles/fleet
-    Headers:
-        Authorization: Basic <root:betterRootPW!>
-    Put Body:
-        {
-          "role" : "fleet",
-          "grant" : {
-            "kv" : {
-              "read": [
-                "/rkt/fleet",
-                "/fleet/*"
-              ]
-            }
-          }
-        }
-```
-
-### Create Users
-
-Same as before, let's use rocket all at once and fleet separately
-
-```
-PUT /v2/auth/users/rktuser
-    Headers:
-        Authorization: Basic <root:betterRootPW!>
-    Body:
-        {"user" : "rktuser", "password" : "rktpw", "roles" : ["rkt"]}
-```
-
-```
-PUT /v2/auth/users/fleetuser
-    Headers:
-        Authorization: Basic <root:betterRootPW!>
-    Body:
-        {"user" : "fleetuser", "password" : "fleetpw"}
-```
-
-### Optional: Grant Roles to Users
-
-Likewise, let's explicitly grant fleetuser access.
-
-```
-PUT /v2/auth/users/fleetuser
-    Headers:
-        Authorization: Basic <root:betterRootPW!>
-    Body:
-        {"user": "fleetuser", "grant": ["fleet"]}
-```
-
-#### Start to use fleetuser and rktuser
-
-
-For example:
-
-```
-PUT /v2/keys/rkt/RktData
-    Headers:
-        Authorization: Basic <rktuser:rktpw>
-    Body:
-        value=launch
-```
-
-Reads and writes outside the prefixes granted will fail with a 401 Unauthorized.
-
-[basic-auth]: https://en.wikipedia.org/wiki/Basic_access_authentication

Documentation/v2/authentication.md

@@ -1,180 +0,0 @@
-# Authentication Guide
-
-## Overview
-
-Authentication -- having users and roles in etcd -- was added in etcd 2.1. This guide will help you set up basic authentication in etcd.
-
-etcd before 2.1 was a completely open system; anyone with access to the API could change keys. In order to preserve backward compatibility and upgradability, this feature is off by default.
-
-For a full discussion of the RESTful API, see [the authentication API documentation][auth-api]
-
-## Special Users and Roles
-
-There is one special user, `root`, and there are two special roles, `root` and `guest`.
-
-### User `root`
-
-User `root` must be created before security can be activated. It has the `root` role and allows for the changing of anything inside etcd. The idea behind the `root` user is for recovery purposes -- a password is generated and stored somewhere -- and the root role is granted to the administrator accounts on the system. In the future, for troubleshooting and recovery, we will need to assume some access to the system, and future documentation will assume this root user (though anyone with the role will suffice). 
-
-### Role `root`
-
-Role `root` cannot be modified, but it may be granted to any user. Having access via the root role not only allows global read-write access (as was the case before 2.1) but allows modification of the authentication policy and all administrative things, like modifying the cluster membership.
-
-### Role `guest`
-
-The `guest` role defines the permissions granted to any request that does not provide an authentication. This will be created on security activation (if it doesn't already exist) to have full access to all keys, as was true in etcd 2.0. It may be modified at any time, and cannot be removed.
-
-## Working with users
-
-The `user` subcommand for `etcdctl` handles all things having to do with user accounts.
-
-A listing of users can be found with
-
-```
-$ etcdctl user list
-```
-
-Creating a user is as easy as
-
-```
-$ etcdctl user add myusername
-```
-
-And there will be prompt for a new password.
-
-Roles can be granted and revoked for a user with
-
-```
-$ etcdctl user grant myusername -roles foo,bar,baz
-$ etcdctl user revoke myusername -roles bar,baz
-```
-
-We can look at this user with
-
-```
-$ etcdctl user get myusername
-```
-
-And the password for a user can be changed with
-
-```
-$ etcdctl user passwd myusername
-```
-
-Which will prompt again for a new password.
-
-To delete an account, there's always
-```
-$ etcdctl user remove myusername
-```
-
-
-## Working with roles
-
-The `role` subcommand for `etcdctl` handles all things having to do with access controls for particular roles, as were granted to individual users.
-
-A listing of roles can be found with
-
-```
-$ etcdctl role list
-```
-
-A new role can be created with
-
-```
-$ etcdctl role add myrolename
-```
-
-A role has no password; we are merely defining a new set of access rights.
-
-Roles are granted access to various parts of the keyspace, a single path at a time.
-
-Reading a path is simple; if the path ends in `*`, that key **and all keys prefixed with it**, are granted to holders of this role. If it does not end in `*`, only that key and that key alone is granted.
-
-Access can be granted as either read, write, or both, as in the following examples:
-
-```
-# Give read access to keys under the /foo directory
-$ etcdctl role grant myrolename -path '/foo/*' -read
-
-# Give write-only access to the key at /foo/bar
-$ etcdctl role grant myrolename -path '/foo/bar' -write
-
-# Give full access to keys under /pub
-$ etcdctl role grant myrolename -path '/pub/*' -readwrite
-```
-
-Beware that 
-
-```
-# Give full access to keys under /pub??
-$ etcdctl role grant myrolename -path '/pub*' -readwrite
-```
-
-Without the slash may include keys under `/publishing`, for example. To do both, grant `/pub` and `/pub/*`
-
-To see what's granted, we can look at the role at any time:
-
-```
-$ etcdctl role get myrolename
-```
-
-Revocation of permissions is done the same logical way:
-
-```
-$ etcdctl role revoke myrolename -path '/foo/bar' -write
-```
-
-As is removing a role entirely
-
-```
-$ etcdctl role remove myrolename
-```
-
-## Enabling authentication
-
-The minimal steps to enabling auth are as follows. The administrator can set up users and roles before or after enabling authentication, as a matter of preference. 
-
-Make sure the root user is created:
-
-```
-$ etcdctl user add root 
-New password:
-```
-
-And enable authentication
-
-```
-$ etcdctl auth enable
-```
-
-After this, etcd is running with authentication enabled. To disable it for any reason, use the reciprocal command:
-
-```
-$ etcdctl -u root:rootpw auth disable
-```
-
-It would also be good to check what guests (unauthenticated users) are allowed to do:
-```
-$ etcdctl -u root:rootpw role get guest
-```
-
-And modify this role appropriately, depending on your policies.
-
-## Using `etcdctl` to authenticate
-
-`etcdctl` supports a similar flag as `curl` for authentication.
-
-```
-$ etcdctl -u user:password get foo
-```
-
-or if you prefer to be prompted:
-
-```
-$ etcdctl -u user get foo
-```
-
-Otherwise, all `etcdctl` commands remain the same. Users and roles can still be created and modified, but require authentication by a user with the root role.
-
-[auth-api]: auth_api.md

Documentation/v2/backward_compatibility.md

@@ -1,72 +0,0 @@
-# Backward Compatibility
-
-The main goal of etcd 2.0 release is to improve cluster safety around bootstrapping and dynamic reconfiguration. To do this, we deprecated the old error-prone APIs and provide a new set of APIs.
-
-The other main focus of this release was a more reliable Raft implementation, but as this change is internal it should not have any notable effects to users.
-
-## Command Line Flags Changes
-
-The major flag changes are to mostly related to bootstrapping. The `initial-*` flags provide an improved way to specify the required criteria to start the cluster. The advertised URLs now support a list of values instead of a single value, which allows etcd users to gracefully migrate to the new set of IANA-assigned ports (2379/client and 2380/peers) while maintaining backward compatibility with the old ports.
-
- - `-addr` is replaced by `-advertise-client-urls`.
- - `-bind-addr` is replaced by `-listen-client-urls`.
- - `-peer-addr` is replaced by `-initial-advertise-peer-urls`.
- - `-peer-bind-addr` is replaced by `-listen-peer-urls`.
- - `-peers` is replaced by `-initial-cluster`.
- - `-peers-file` is replaced by `-initial-cluster`.
- - `-peer-heartbeat-interval` is replaced by `-heartbeat-interval`.
- - `-peer-election-timeout` is replaced by `-election-timeout`.
-
-The documentation of new command line flags can be found at
-https://github.com/coreos/etcd/blob/master/Documentation/v2/configuration.md.
-
-## Data Directory Naming
-
-The default data dir location has changed from {$hostname}.etcd to {name}.etcd.
-
-## Key-Value API
-
-### Read consistency flag
-
-The consistent flag for read operations is removed in etcd 2.0.0. The normal read operations provides the same consistency guarantees with the 0.4.6 read operations with consistent flag set.
-
-The read consistency guarantees are:
-
-The consistent read guarantees the sequential consistency within one client that talks to one etcd server. Read/Write from one client to one etcd member should be observed in order. If one client write a value to an etcd server successfully, it should be able to get the value out of the server immediately.
-
-Each etcd member will proxy the request to leader and only return the result to user after the result is applied on the local member. Thus after the write succeed, the user is guaranteed to see the value on the member it sent the request to.
-
-Reads do not provide linearizability. If you want linearizable read, you need to set quorum option to true.
-
-**Previous behavior**
-
-We added an option for a consistent read in the old version of etcd since etcd 0.x redirects the write request to the leader. When the user get back the result from the leader, the member it sent the request to originally might not apply the write request yet. With the consistent flag set to true, the client will always send read request to the leader. So one client should be able to see its last write when consistent=true is enabled. There is no order guarantees among different clients.
-
-
-## Standby
-
-etcd 0.4’s standby mode has been deprecated. [Proxy mode][proxymode] is introduced to solve a subset of problems standby was solving.
-
-Standby mode was intended for large clusters that had a subset of the members acting in the consensus process. Overall this process was too magical and allowed for operators to back themselves into a corner.
-
-Proxy mode in 2.0 will provide similar functionality, and with improved control over which machines act as proxies due to the operator specifically configuring them. Proxies also support read only or read/write modes for increased security and durability.
-
-[proxymode]: proxy.md
-
-## Discovery Service
-
-A size key needs to be provided inside a [discovery token][discoverytoken].
-
-[discoverytoken]: clustering.md#custom-etcd-discovery-service
-
-## HTTP Admin API
-
-`v2/admin` on peer url and `v2/keys/_etcd` are unified under the new [v2/members API][members-api] to better explain which machines are part of an etcd cluster, and to simplify the keyspace for all your use cases.
-
-[members-api]: members_api.md
-
-## HTTP Key Value API
-- The follower can now transparently proxy write requests to the leader. Clients will no longer see 307 redirections to the leader from etcd.
-
-- Expiration time is in UTC instead of local time.
-

Documentation/v2/benchmarks/README.md

@@ -1,18 +0,0 @@
-# Benchmarks
-
-etcd benchmarks will be published regularly and tracked for each release below:
-
-- [etcd v2.1.0-alpha][2.1]
-- [etcd v2.2.0-rc][2.2]
-- [etcd v3 demo][3.0]
-
-# Memory Usage Benchmarks
-
-It records expected memory usage in different scenarios.
-
-- [etcd v2.2.0-rc][2.2-mem]
-
-[2.1]: etcd-2-1-0-alpha-benchmarks.md
-[2.2]: etcd-2-2-0-rc-benchmarks.md
-[2.2-mem]: etcd-2-2-0-rc-memory-benchmarks.md
-[3.0]: etcd-3-demo-benchmarks.md

Documentation/v2/benchmarks/etcd-2-1-0-alpha-benchmarks.md

@@ -1,52 +0,0 @@
-## Physical machines
-
-GCE n1-highcpu-2 machine type
-
-- 1x dedicated local SSD mounted under /var/lib/etcd
-- 1x dedicated slow disk for the OS
-- 1.8 GB memory
-- 2x CPUs
-- etcd version 2.1.0 alpha
-
-## etcd Cluster
-
-3 etcd members, each runs on a single machine
-
-## Testing
-
-Bootstrap another machine and use the [boom HTTP benchmark tool][boom] to send requests to each etcd member. Check the [benchmark hacking guide][hack-benchmark] for detailed instructions.
-
-## Performance
-
-### reading one single key
-
-| key size in bytes | number of clients | target etcd server | read QPS | 90th Percentile Latency (ms) |
-|-------------------|-------------------|--------------------|----------|---------------|
-| 64                | 1                 | leader only        | 1534     | 0.7        |
-| 64                | 64                | leader only        | 10125    | 9.1      |
-| 64                | 256               | leader only        | 13892    | 27.1      |
-| 256               | 1                 | leader only        | 1530     | 0.8       |
-| 256               | 64                | leader only        | 10106    | 10.1      |
-| 256               | 256               | leader only        | 14667    | 27.0      |
-| 64                | 64                | all servers        | 24200    | 3.9      |
-| 64                | 256               | all servers        | 33300    | 11.8      |
-| 256               | 64                | all servers        | 24800    | 3.9      |
-| 256               | 256               | all servers        | 33000    | 11.5      |
-
-### writing one single key
-
-| key size in bytes | number of clients | target etcd server | write QPS | 90th Percentile Latency (ms) |
-|-------------------|-------------------|--------------------|-----------|---------------|
-| 64                | 1                 | leader only        | 60        | 21.4 |
-| 64                | 64                | leader only        | 1742      | 46.8 |
-| 64                | 256               | leader only        | 3982      | 90.5 |
-| 256               | 1                 | leader only        | 58        | 20.3 |
-| 256               | 64                | leader only        | 1770      | 47.8 |
-| 256               | 256               | leader only        | 4157      | 105.3 |
-| 64                | 64                | all servers        | 1028      | 123.4 |
-| 64                | 256               | all servers        | 3260      | 123.8 |
-| 256               | 64                | all servers        | 1033      | 121.5 |
-| 256               | 256               | all servers        | 3061      | 119.3 |
-
-[boom]: https://github.com/rakyll/boom
-[hack-benchmark]: ../../../hack/benchmark/

Documentation/v2/benchmarks/etcd-2-2-0-benchmarks.md

@@ -1,72 +0,0 @@
-# Benchmarking etcd v2.2.0
-
-## Physical Machines
-
-GCE n1-highcpu-2 machine type
-
-- 1x dedicated local SSD mounted as etcd data directory
-- 1x dedicated slow disk for the OS
-- 1.8 GB memory
-- 2x CPUs
-
-## etcd Cluster
-
-3 etcd 2.2.0 members, each runs on a single machine.
-
-Detailed versions:
-
-```
-etcd Version: 2.2.0
-Git SHA: e4561dd
-Go Version: go1.5
-Go OS/Arch: linux/amd64
-```
-
-## Testing
-
-Bootstrap another machine, outside of the etcd cluster, and run the [`boom` HTTP benchmark tool][boom] with a connection reuse patch to send requests to each etcd cluster member. See the [benchmark instructions][hack] for the patch and the steps to reproduce our procedures.
-
-The performance is calulated through results of 100 benchmark rounds.
-
-## Performance
-
-### Single Key Read Performance
-
-| key size in bytes | number of clients | target etcd server | average read QPS | read QPS stddev | average 90th Percentile Latency (ms) | latency stddev |
-|-------------------|-------------------|--------------------|------------------|-----------------|--------------------------------------|----------------|
-| 64 | 1 | leader only | 2303 | 200 | 0.49 | 0.06 |
-| 64 | 64 | leader only | 15048 | 685 | 7.60 | 0.46 |
-| 64 | 256 | leader only | 14508 | 434 | 29.76 | 1.05 |
-| 256 | 1 | leader only | 2162 | 214 | 0.52 | 0.06 |
-| 256 | 64 | leader only | 14789 | 792 | 7.69| 0.48 |
-| 256 | 256 | leader only | 14424 | 512 | 29.92 | 1.42 |
-| 64 | 64 | all servers | 45752 | 2048 | 2.47 | 0.14 |
-| 64 | 256 | all servers | 46592 | 1273 | 10.14 | 0.59 |
-| 256 | 64 | all servers | 45332 | 1847 | 2.48| 0.12 |
-| 256 | 256 | all servers | 46485 | 1340 | 10.18 | 0.74 |
-
-### Single Key Write Performance
-
-| key size in bytes | number of clients | target etcd server | average write QPS | write QPS stddev | average 90th Percentile Latency (ms) | latency stddev |
-|-------------------|-------------------|--------------------|------------------|-----------------|--------------------------------------|----------------|
-| 64 | 1 | leader only | 55 | 4 | 24.51 | 13.26 |
-| 64 | 64 | leader only | 2139 | 125 | 35.23 | 3.40 |
-| 64 | 256 | leader only | 4581 | 581 | 70.53 | 10.22 |
-| 256 | 1 | leader only | 56 | 4 | 22.37| 4.33 |
-| 256 | 64 | leader only | 2052 | 151 | 36.83 | 4.20 |
-| 256 | 256 | leader only | 4442 | 560 | 71.59 | 10.03 |
-| 64 | 64 | all servers | 1625 | 85 | 58.51 | 5.14 |
-| 64 | 256 | all servers | 4461 | 298 | 89.47 | 36.48 |
-| 256 | 64 | all servers | 1599 | 94 | 60.11| 6.43 |
-| 256 | 256 | all servers | 4315 | 193 | 88.98 | 7.01 |
-
-## Performance Changes
-
-- Because etcd now records metrics for each API call, read QPS performance seems to see a minor decrease in most scenarios. This minimal performance impact was judged a reasonable investment for the breadth of monitoring and debugging information returned.
-
-- Write QPS to cluster leaders seems to be increased by a small margin. This is because the main loop and entry apply loops were decoupled in the etcd raft logic, eliminating several blocks between them.
-
-- Write QPS to all members seems to be increased by a significant margin, because followers now receive the latest commit index sooner, and commit proposals more quickly.
-
-[boom]: https://github.com/rakyll/boom
-[hack]: ../../../hack/benchmark/

Documentation/v2/benchmarks/etcd-2-2-0-rc-benchmarks.md

@@ -1,72 +0,0 @@
-## Physical machines
-
-GCE n1-highcpu-2 machine type
-
-- 1x dedicated local SSD mounted under /var/lib/etcd
-- 1x dedicated slow disk for the OS
-- 1.8 GB memory
-- 2x CPUs
-
-## etcd Cluster
-
-3 etcd 2.2.0-rc members, each runs on a single machine.
-
-Detailed versions:
-
-```
-etcd Version: 2.2.0-alpha.1+git
-Git SHA: 59a5a7e
-Go Version: go1.4.2
-Go OS/Arch: linux/amd64
-```
-
-Also, we use 3 etcd 2.1.0 alpha-stage members to form cluster to get base performance. etcd's commit head is at [c7146bd5][c7146bd5], which is the same as the one that we use in [etcd 2.1 benchmark][etcd-2.1-benchmark].
-
-## Testing
-
-Bootstrap another machine and use the [boom HTTP benchmark tool][boom] to send requests to each etcd member. Check the [benchmark hacking guide][hack-benchmark] for detailed instructions.
-
-## Performance
-
-### reading one single key
-
-| key size in bytes | number of clients | target etcd server | read QPS | 90th Percentile Latency (ms) |
-|-------------------|-------------------|--------------------|----------|---------------|
-| 64                | 1                 | leader only        | 2804 (-5%) | 0.4 (+0%) |
-| 64                | 64                | leader only        | 17816 (+0%) | 5.7 (-6%) |
-| 64                | 256               | leader only        | 18667 (-6%) | 20.4 (+2%) |
-| 256               | 1                 | leader only        | 2181 (-15%) | 0.5 (+25%) |
-| 256               | 64                | leader only        | 17435 (-7%) | 6.0 (+9%) |
-| 256               | 256               | leader only        | 18180 (-8%) | 21.3 (+3%) |
-| 64                | 64                | all servers        | 46965 (-4%) | 2.1 (+0%) |
-| 64                | 256               | all servers        | 55286 (-6%) | 7.4 (+6%) |
-| 256               | 64                | all servers        | 46603 (-6%) | 2.1 (+5%) |
-| 256               | 256               | all servers        | 55291 (-6%) | 7.3 (+4%) |
-
-### writing one single key
-
-| key size in bytes | number of clients | target etcd server | write QPS | 90th Percentile Latency (ms) |
-|-------------------|-------------------|--------------------|-----------|---------------|
-| 64                | 1                 | leader only        | 76 (+22%)  | 19.4 (-15%) |
-| 64                | 64                | leader only        | 2461 (+45%) | 31.8 (-32%) |
-| 64                | 256               | leader only        | 4275 (+1%) | 69.6 (-10%) |
-| 256               | 1                 | leader only        | 64 (+20%)  | 16.7 (-30%) |
-| 256               | 64                | leader only        | 2385 (+30%) | 31.5 (-19%) |
-| 256               | 256               | leader only        | 4353 (-3%) | 74.0 (+9%) |
-| 64                | 64                | all servers        | 2005 (+81%) | 49.8 (-55%) |
-| 64                | 256               | all servers        | 4868 (+35%) | 81.5 (-40%) |
-| 256               | 64                | all servers        | 1925 (+72%) | 47.7 (-59%) |
-| 256               | 256               | all servers        | 4975 (+36%) | 70.3 (-36%) |
-
-### performance changes explanation
-
-- read QPS in most scenarios is decreased by 5~8%. The reason is that etcd records store metrics for each store operation. The metrics is important for monitoring and debugging, so this is acceptable.
-
-- write QPS to leader is increased by 20~30%. This is because we decouple raft main loop and entry apply loop, which avoids them blocking each other.
-
-- write QPS to all servers is increased by 30~80% because follower could receive latest commit index earlier and commit proposals faster.
-
-[boom]: https://github.com/rakyll/boom
-[c7146bd5]: https://github.com/coreos/etcd/commits/c7146bd5f2c73716091262edc638401bb8229144
-[etcd-2.1-benchmark]: etcd-2-1-0-alpha-benchmarks.md
-[hack-benchmark]: ../../../hack/benchmark/

Documentation/v2/benchmarks/etcd-2-2-0-rc-memory-benchmarks.md

@@ -1,47 +0,0 @@
-## Physical machine
-
-GCE n1-standard-2 machine type
-
-- 1x dedicated local SSD mounted under /var/lib/etcd
-- 1x dedicated slow disk for the OS
-- 7.5 GB memory
-- 2x CPUs
-
-## etcd
-
-```
-etcd Version: 2.2.0-rc.0+git
-Git SHA: 103cb5c
-Go Version: go1.5
-Go OS/Arch: linux/amd64
-```
-
-## Testing
-
-Start 3-member etcd cluster, each of which uses 2 cores.
-
-The length of key name is always 64 bytes, which is a reasonable length of average key bytes.
-
-## Memory Maximal Usage
-
-- etcd may use maximal memory if one follower is dead and the leader keeps sending snapshots.
-- `max RSS` is the maximal memory usage recorded in 3 runs.
-
-| value bytes | key number  | data size(MB) | max RSS(MB) | max RSS/data rate on leader |
-|-------------|-------------|---------------|-------------|-----------------------------|
-| 128  | 50000  | 6 | 433 | 72x |
-| 128  | 100000 | 12 | 659 | 54x |
-| 128  | 200000 | 24 | 1466 | 61x |
-| 1024 | 50000  | 48 | 1253 | 26x |
-| 1024 | 100000 | 96 | 2344 | 24x |
-| 1024 | 200000 | 192 | 4361 | 22x |
-
-## Data Size Threshold
-
-- When etcd reaches data size threshold, it may trigger leader election easily and drop part of proposals.
-- At most cases, etcd cluster should work smoothly if it doesn't hit the threshold. If it doesn't work well due to insufficient resources, you need to decrease its data size.
-
-| value bytes | key number limitation | suggested data size threshold(MB) | consumed RSS(MB) |
-|-------------|-----------------------|-----------------------------------|------------------|
-| 128 | 400K | 48 | 2400 |
-| 1024 | 300K | 292 | 6500 |

Documentation/v2/benchmarks/etcd-3-demo-benchmarks.md

@@ -1,42 +0,0 @@
-## Physical machines
-
-GCE n1-highcpu-2 machine type
-
-- 1x dedicated local SSD mounted under /var/lib/etcd
-- 1x dedicated slow disk for the OS
-- 1.8 GB memory
-- 2x CPUs
-- etcd version 2.2.0
-
-## etcd Cluster
-
-1 etcd member running in v3 demo mode
-
-## Testing
-
-Use [etcd v3 benchmark tool][etcd-v3-benchmark].
-
-## Performance
-
-### reading one single key
-
-| key size in bytes | number of clients | read QPS | 90th Percentile Latency (ms) |
-|-------------------|-------------------|----------|---------------|
-| 256               | 1                 | 2716  | 0.4      |
-| 256               | 64                | 16623 | 6.1      |
-| 256               | 256               | 16622 | 21.7     |
-
-The performance is nearly the same as the one with empty server handler.
-
-### reading one single key after putting
-
-| key size in bytes | number of clients | read QPS | 90th Percentile Latency (ms) |
-|-------------------|-------------------|----------|---------------|
-| 256               | 1                 | 2269  | 0.5      |
-| 256               | 64                | 13582 | 8.6      |
-| 256               | 256               | 13262 | 47.5     |
-
-The performance with empty server handler is not affected by one put. So the
-performance downgrade should be caused by storage package.
-
-[etcd-v3-benchmark]: ../../../tools/benchmark/