version: bump up to 3.1.14

Automated cherry pick of #9587

.travis.yml

@@ -1,10 +1,12 @@
-dist: trusty
 language: go
 go_import_path: github.com/coreos/etcd
-sudo: false
+
+sudo: required
+
+services: docker
 
 go:
-  - 1.7.5
+- 1.8.7
 
 notifications:
   on_success: never
@@ -12,41 +14,84 @@ notifications:
 
 env:
   matrix:
-   - TARGET=amd64
-   - TARGET=arm64
-   - TARGET=arm
-   - TARGET=386
-   - TARGET=ppc64le
+  - TARGET=linux-amd64-build
+  - TARGET=linux-amd64-unit
+  - TARGET=linux-amd64-integration
+  - TARGET=linux-amd64-functional
+  - TARGET=linux-386-build
+  - TARGET=linux-386-unit
+  - TARGET=darwin-amd64-build
+  - TARGET=windows-amd64-build
+  - TARGET=linux-arm-build
+  - TARGET=linux-arm64-build
+  - TARGET=linux-ppc64le-build
 
 matrix:
   fast_finish: true
-  allow_failures:
-    - go: tip
-  exclude:
-  - go: tip
-    env: TARGET=arm
-  - go: tip
-    env: TARGET=arm64
-  - go: tip
-    env: TARGET=386
-  - go: tip
-    env: TARGET=ppc64le
 
-# disable godep restore override
+before_install:
+- if [[ $TRAVIS_GO_VERSION == 1.* ]]; then docker pull gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION}; fi
+
 install:
- - pushd cmd/etcd && go get -t -v ./... && popd
+- pushd cmd/etcd && go get -t -v ./... && popd
 
 script:
+ - echo "TRAVIS_GO_VERSION=${TRAVIS_GO_VERSION}"
  - >
     case "${TARGET}" in
-      amd64)
-        GOARCH=amd64 ./test
+      linux-amd64-build)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GOARCH=amd64 PASSES='build' ./test"
         ;;
-      386)
-        GOARCH=386 PASSES="build unit" ./test
+      linux-amd64-unit)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GOARCH=amd64 PASSES='unit' ./test"
         ;;
-      *)
-        # test building out of gopath
-        GO_BUILD_FLAGS="-a -v" GOPATH="" GOARCH="${TARGET}" ./build
+      linux-amd64-integration)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GOARCH=amd64 PASSES='integration' ./test"
+        ;;
+      linux-amd64-functional)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "./build && GOARCH=amd64 PASSES='functional' ./test"
+        ;;
+      linux-386-build)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GOARCH=386 PASSES='build' ./test"
+        ;;
+      linux-386-unit)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GOARCH=386 PASSES='unit' ./test"
+        ;;
+      darwin-amd64-build)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GO_BUILD_FLAGS='-v' GOOS=darwin GOARCH=amd64 ./build"
+        ;;
+      windows-amd64-build)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GO_BUILD_FLAGS='-v' GOOS=windows GOARCH=amd64 ./build"
+        ;;
+      linux-arm-build)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GO_BUILD_FLAGS='-v' GOARCH=arm ./build"
+        ;;
+      linux-arm64-build)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GO_BUILD_FLAGS='-v' GOARCH=arm64 ./build"
+        ;;
+      linux-ppc64le-build)
+        docker run --rm \
+          --volume=`pwd`:/go/src/github.com/coreos/etcd gcr.io/etcd-development/etcd-test:go${TRAVIS_GO_VERSION} \
+          /bin/bash -c "GO_BUILD_FLAGS='-v' GOARCH=ppc64le ./build"
         ;;
     esac

Dockerfile-test

@@ -0,0 +1,57 @@
+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/wadey/gocovmerge \
+  && go get -v -u github.com/gordonklaus/ineffassign \
+  && /tmp/install-marker.sh amd64 \
+  && rm -f /tmp/install-marker.sh \
+  && curl -s https://codecov.io/bash >/codecov \
+  && chmod 700 /codecov

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

@@ -49,4 +49,4 @@ Bootstrap another machine and use the [hey HTTP benchmark tool][hey] to send req
 | 256               | 256               | all servers        | 3061      | 119.3 |
 
 [hey]: https://github.com/rakyll/hey
-[hack-benchmark]: /hack/benchmark/
+[hack-benchmark]: https://github.com/coreos/etcd/tree/master/hack/benchmark

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

@@ -69,4 +69,4 @@ Bootstrap another machine and use the [hey HTTP benchmark tool][hey] to send req
 [hey]: https://github.com/rakyll/hey
 [c7146bd5]: https://github.com/coreos/etcd/commits/c7146bd5f2c73716091262edc638401bb8229144
 [etcd-2.1-benchmark]: etcd-2-1-0-alpha-benchmarks.md
-[hack-benchmark]: /hack/benchmark/
+[hack-benchmark]: ../../hack/benchmark/

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

@@ -39,4 +39,4 @@ The performance is nearly the same as the one with empty server handler.
 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/
+[etcd-v3-benchmark]: ../../tools/benchmark/

Documentation/dev-internal/logging.md

@@ -3,7 +3,7 @@
 etcd uses the [capnslog][capnslog] library for logging application output categorized into *levels*. A log message's level is determined according to these conventions:
 
 * Error: Data has been lost, a request has failed for a bad reason, or a required resource has been lost
-  * Examples: 
+  * Examples:
     * A failure to allocate disk space for WAL
 
 * Warning: (Hopefully) Temporary conditions that may cause errors, but may work fine. A replica disappearing (that may reconnect) is a warning.
@@ -26,4 +26,4 @@ etcd uses the [capnslog][capnslog] library for logging application output catego
     * Send a normal message to a remote peer
     * Write a log entry to disk
 
-[capnslog]: [https://github.com/coreos/pkg/tree/master/capnslog]
+[capnslog]: https://github.com/coreos/pkg/tree/master/capnslog

Documentation/op-guide/clustering.md

@@ -475,5 +475,5 @@ 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
-[tls-setup]: /hack/tls-setup
+[tls-setup]: ../../hack/tls-setup
 [gateway]: gateway.md

Documentation/op-guide/configuration.md

@@ -286,7 +286,7 @@ Follow the instructions when using these flags.
 [build-cluster]: clustering.md#static
 [reconfig]: runtime-configuration.md
 [discovery]: clustering.md#discovery
-[iana-ports]: https://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.xhtml?search=etcd
+[iana-ports]: http://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.txt
 [proxy]: ../v2/proxy.md
 [restore]: ../v2/admin_guide.md#restoring-a-backup
 [security]: security.md

Documentation/op-guide/grpc_proxy.md

@@ -36,9 +36,9 @@ watch key A ^     ^ watch key A    |
 
 To effectively coalesce multiple client watchers into a single watcher, the gRPC proxy coalesces new `c-watchers` into an existing `s-watcher` when possible. This coalesced `s-watcher` may be out of sync with the etcd server due to network delays or buffered undelivered events. When the watch revision is unspecified, the gRPC proxy will not guarantee the `c-watcher` will start watching from the most recent store revision. For example, if a client watches from an etcd server with revision 1000, that watcher will begin at revision 1000. If a client watches from the gRPC proxy, may begin watching from revision 990.
 
-Similar limitations apply to cancellation. When the watcher is cancelled, the etcd server’s revision may be greater than the cancellation response revision. 
+Similar limitations apply to cancellation. When the watcher is cancelled, the etcd server’s revision may be greater than the cancellation response revision.
 
-These two limitations should not cause problems for most use cases. In the future, there may be additional options to force the watcher to bypass the gRPC proxy for more accurate revision responses. 
+These two limitations should not cause problems for most use cases. In the future, there may be additional options to force the watcher to bypass the gRPC proxy for more accurate revision responses.
 
 ## Scalable lease API
 
@@ -75,3 +75,4 @@ $ ETCDCTL_API=3 ./etcdctl --endpoints=127.0.0.1:2379 get foo
 foo
 bar
 ```
+

Documentation/op-guide/security.md

@@ -219,6 +219,6 @@ Make sure to sign the certificates with a Subject Name the member's public IP ad
 The certificate needs to be signed for the member's FQDN in its Subject Name, use Subject Alternative Names (short IP SANs) to add the IP address. The `etcd-ca` tool provides `--domain=` option for its `new-cert` command, and openssl can make [it][alt-name] too.
 
 [cfssl]: https://github.com/cloudflare/cfssl
-[tls-setup]: /hack/tls-setup
+[tls-setup]: ../../hack/tls-setup
 [tls-guide]: https://github.com/coreos/docs/blob/master/os/generate-self-signed-certificates.md
 [alt-name]: http://wiki.cacert.org/FAQ/subjectAltName

Documentation/production-users.md

@@ -50,7 +50,7 @@ Radius Intelligence uses Kubernetes running CoreOS to containerize and scale int
 
 ## Vonage
 
-- *Application*: system configuration for microservices, scheduling, locks (future - service discovery) 
+- *Application*: system configuration for microservices, scheduling, locks (future - service discovery)
 - *Launched*: August 2015
 - *Cluster Size*: 2 clusters of 5 members in 2 DCs, n local proxies 1-to-1 with microservice, (ssl and SRV look up)
 - *Order of Data Size*: kilobytes
@@ -60,3 +60,148 @@ Radius Intelligence uses Kubernetes running CoreOS to containerize and scale int
 
 [teamcity]: https://www.jetbrains.com/teamcity/
 [raoofm]:https://github.com/raoofm
+
+## Qiniu Cloud
+
+- *Application*: system configuration for microservices, distributed locks
+- *Launched*: Jan. 2016
+- *Cluster Size*: 3 members each with several clusters
+- *Order of Data Size*: kilobytes
+- *Operator*: Pandora, chenchao@qiniu.com
+- *Environment*: Baremetal
+- *Backups*: None, all data can be recreated if necessary
+
+## QingCloud
+
+- *Application*: [QingCloud][qingcloud] appcenter cluster for service discovery as [metad][metad] backend.
+- *Launched*: December 2016
+- *Cluster Size*: 1 cluster of 3 members per user.
+- *Order of Data Size*: kilobytes
+- *Operator*: [yunify][yunify]
+- *Environment*: QingCloud IaaS
+- *Backups*: None, all data can be recreated if necessary.
+
+[metad]:https://github.com/yunify/metad
+[yunify]:https://github.com/yunify
+[qingcloud]:https://qingcloud.com/
+
+
+## Yandex
+
+- *Application*: system configuration for services, service discovery
+- *Launched*: March 2016
+- *Cluster Size*: 3 clusters of 5 members
+- *Order of Data Size*: several gigabytes
+- *Operator*: Yandex; [nekto0n][nekto0n]
+- *Environment*: Bare Metal
+- *Backups*: None
+
+[nekto0n]:https://github.com/nekto0n
+
+## Tencent Games
+
+- *Application*: Meta data and configuration data for service discovery, Kubernetes, etc.
+- *Launched*: Jan. 2015
+- *Cluster Size*: 3 members each with 10s of clusters
+- *Order of Data Size*: 10s of Megabytes
+- *Operator*: Tencent Game Operations Department
+- *Environment*: Baremetal
+- *Backups*: Periodic sync to backup server
+
+In Tencent games, we use Docker and Kubernetes to deploy and run our applications, and use etcd to save meta data for service discovery, Kubernetes, etc.
+
+## Hyper.sh
+
+- *Application*: Kubernetes, distributed locks, etc.
+- *Launched*: April 2016
+- *Cluster Size*: 1 cluster of 3 members
+- *Order of Data Size*: 10s of MB
+- *Operator*: Hyper.sh
+- *Environment*: Baremetal
+- *Backups*: None, all data can be recreated if necessary.
+
+In [hyper.sh][hyper.sh], the container service is backed by [hypernetes][hypernetes], a multi-tenant kubernetes distro. Moreover, we use etcd to coordinate the multiple manage services and store global meta data.
+
+[hypernetes]:https://github.com/hyperhq/hypernetes
+[Hyper.sh]:https://www.hyper.sh
+
+## Meitu
+- *Application*: system configuration for services, service discovery, kubernetes in test environment
+- *Launched*: October 2015
+- *Cluster Size*: 1 cluster of 3 members
+- *Order of Data Size*: megabytes
+- *Operator*: Meitu, hxj@meitu.com, [shafreeck][shafreeck]
+- *Environment*: Bare Metal
+- *Backups*: None, all data can be recreated if necessary.
+
+[shafreeck]:https://github.com/shafreeck
+
+## Grab
+- *Application*: system configuration for services, service discovery
+- *Launched*: June 2016
+- *Cluster Size*: 1 cluster of 7 members
+- *Order of Data Size*: megabytes
+- *Operator*: Grab, [taxitan][taxitan], [reterVision][reterVision]
+- *Environment*: AWS
+- *Backups*: None, all data can be recreated if necessary.
+
+[taxitan]:https://github.com/taxitan
+[reterVision]:https://github.com/reterVision
+
+## DaoCloud.io
+
+- *Application*: container management
+- *Launched*: Sep. 2015
+- *Cluster Size*: 1000+ deployments, each deployment contains a 3 node cluster.
+- *Order of Data Size*: 100s of Megabytes
+- *Operator*: daocloud.io
+- *Environment*: Baremetal and virtual machines
+- *Backups*: None, all data can be recreated if necessary.
+
+In [DaoCloud][DaoCloud], we use Docker and Swarm to deploy and run our applications, and we use etcd to save metadata for service discovery.
+
+[DaoCloud]:https://www.daocloud.io
+
+## Branch.io
+
+- *Application*: Kubernetes
+- *Launched*: April 2016
+- *Cluster Size*: Multiple clusters, multiple sizes
+- *Order of Data Size*: 100s of Megabytes
+- *Operator*: branch.io
+- *Environment*: AWS, Kubernetes
+- *Backups*: EBS volume backups
+
+At [Branch][branch], we use kubernetes heavily as our core microservice platform for staging and production.
+
+[branch]: https://branch.io
+
+## Baidu Waimai
+
+- *Application*: SkyDNS, Kubernetes, UDC, CMDB and other distributed systems
+- *Launched*: April. 2016
+- *Cluster Size*: 3 clusters of 5 members
+- *Order of Data Size*: several gigabytes
+- *Operator*: Baidu Waimai Operations Department
+- *Environment*: CentOS 6.5
+- *Backups*: backup scripts
+
+## Salesforce.com
+
+- *Application*: Kubernetes
+- *Launched*: Jan 2017
+- *Cluster Size*: Multiple clusters of 3 members
+- *Order of Data Size*: 100s of Megabytes
+- *Operator*: Salesforce.com (krmayankk@github)
+- *Environment*: BareMetal
+- *Backups*: None, all data can be recreated
+
+## Hosted Graphite
+
+- *Application*: Service discovery, locking, ephemeral application data
+- *Launched*: January 2017
+- *Cluster Size*: 2 clusters of 7 members
+- *Order of Data Size*: Megabytes
+- *Operator*: Hosted Graphite (sre@hostedgraphite.com)
+- *Environment*: Bare Metal
+- *Backups*: None, all data is considered ephemeral.

Documentation/reporting_bugs.md

@@ -1,6 +1,6 @@
 # Reporting bugs
 
-If any part of the etcd project has bugs or documentation mistakes, please let us know by [opening an issue][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.
+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.
 
 To make the bug report accurate and easy to understand, please try to create bug reports that are:
 

Documentation/upgrades/upgrade_3_0.md

@@ -8,9 +8,11 @@ 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/coreos/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/v2.3.0) before upgrading to 3.0.
+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.
 
 Also, to ensure a smooth rolling upgrade, the running cluster must be healthy. Check the health of the cluster by using the `etcdctl cluster-health` command before proceeding.
 
@@ -52,7 +54,7 @@ member 8211f1d0f64f3269 is healthy: got healthy result from http://localhost:123
 cluster is healthy
 
 $ curl http://localhost:2379/version
-{"etcdserver":"2.3.x","etcdcluster":"2.3.0"}
+{"etcdserver":"2.3.x","etcdcluster":"2.3.8"}
 ```
 
 #### 2. Stop the existing etcd process
@@ -116,4 +118,14 @@ $ ETCDCTL_API=3 etcdctl endpoint health
 127.0.0.1:22379 is healthy: successfully committed proposal: took = 18.513301ms
 ```
 
+## Further considerations
+
+- etcdctl environment variables have been updated. If `ETCDCTL_API=2 etcdctl cluster-health` works properly but `ETCDCTL_API=3 etcdctl endpoints health` responds with `Error:  grpc: timed out when dialing`, be sure to use the [new variable names](https://github.com/coreos/etcd/tree/master/etcdctl#etcdctl).
+
+## 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.
+- 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.
+
 [etcd-contact]: https://groups.google.com/forum/#!forum/etcd-dev

Documentation/upgrades/upgrade_3_1.md

@@ -8,9 +8,20 @@ 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/coreos/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](https://github.com/coreos/etcd/releases/tag/v3.0.16) before upgrading to 3.1.
+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.
 
 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.
 

Documentation/upgrades/upgrade_3_2.md

@@ -0,0 +1,338 @@
+## 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
+ - after running all v3.2 processes, new features in v3.2 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/coreos/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 3.2.
+
+#### Change in default `snapshot-count` value
+
+The default value of `--snapshot-count` has [changed from from 10,000 to 100,000](https://github.com/coreos/etcd/pull/7160). Higher snapshot count means it holds Raft entries in memory for longer before discarding old entries. It is a trade-off between less frequent snapshotting and [higher memory usage](https://github.com/kubernetes/kubernetes/issues/60589#issuecomment-371977156). Higher `--snapshot-count` will be manifested with higher memory usage, while retaining more Raft entries helps with the availabilities of slow followers: leader is still able to replicate its logs to followers, rather than forcing followers to rebuild its stores from leader snapshots.
+
+#### Change in 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`).
+
+##### Deprecate `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)
+```
+
+##### Deprecate `grpc.ErrClientConnTimeout`
+
+Previously, `grpc.ErrClientConnTimeout` error is returned on client dial time-outs. 3.2 instead returns `context.DeadlineExceeded` (see [#8504](https://github.com/coreos/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
+}
+```
+
+#### Change in 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.
+
+#### Change in 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/coreos/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 {
+```
+
+#### Change in `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/coreos/etcd/pull/7305)).
+
+Before
+
+```go
+// when leaseID does not exist
+resp, err := TimeToLive(ctx, leaseID)
+resp == nil
+err == lease.ErrLeaseNotFound
+```
+
+After
+
+```go
+// when leaseID does not exist
+resp, err := TimeToLive(ctx, leaseID)
+resp.TTL == -1
+err == nil
+```
+
+#### Change in `clientv3.NewFromConfigFile`
+
+`clientv3.NewFromConfigFile` is moved to `yaml.NewConfig`.
+
+Before
+
+```go
+import "github.com/coreos/etcd/clientv3"
+clientv3.NewFromConfigFile
+```
+
+After
+
+```go
+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/coreos/etcd/issues/6336) for more contexts.
+
+### Server upgrade checklists
+
+#### Upgrade requirements
+
+To upgrade an existing etcd deployment to 3.2, the running cluster must be 3.1 or greater. If it's before 3.1, please [upgrade to 3.1](upgrade_3_1.md) before upgrading to 3.2.
+
+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 3.2. 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 v3.2, the cluster will be upgraded to v3.2, and downgrade from this completed state is **not possible**. If any single member is still v3.1, however, the cluster and its operations remains "v3.1", and it is possible from this mixed cluster state to return to using a v3.1 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 v3.1 ectd cluster running on a local machine.
+
+#### 1. Check upgrade requirements
+
+Is the cluster healthy and running v3.1.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":"3.1.7","etcdcluster":"3.1.0"}
+```
+
+#### 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:
+
+```
+2017-04-27 14:13:31.491746 I | raft: c89feb932daef420 [term 3] received MsgTimeoutNow from 6d4f535bae3ab960 and starts an election to get leadership.
+2017-04-27 14:13:31.491769 I | raft: c89feb932daef420 became candidate at term 4
+2017-04-27 14:13:31.491788 I | raft: c89feb932daef420 received MsgVoteResp from c89feb932daef420 at term 4
+2017-04-27 14:13:31.491797 I | raft: c89feb932daef420 [logterm: 3, index: 9] sent MsgVote request to 6d4f535bae3ab960 at term 4
+2017-04-27 14:13:31.491805 I | raft: c89feb932daef420 [logterm: 3, index: 9] sent MsgVote request to 9eda174c7df8a033 at term 4
+2017-04-27 14:13:31.491815 I | raft: raft.node: c89feb932daef420 lost leader 6d4f535bae3ab960 at term 4
+2017-04-27 14:13:31.524084 I | raft: c89feb932daef420 received MsgVoteResp from 6d4f535bae3ab960 at term 4
+2017-04-27 14:13:31.524108 I | raft: c89feb932daef420 [quorum:2] has received 2 MsgVoteResp votes and 0 vote rejections
+2017-04-27 14:13:31.524123 I | raft: c89feb932daef420 became leader at term 4
+2017-04-27 14:13:31.524136 I | raft: raft.node: c89feb932daef420 elected leader c89feb932daef420 at term 4
+2017-04-27 14:13:31.592650 W | rafthttp: lost the TCP streaming connection with peer 6d4f535bae3ab960 (stream MsgApp v2 reader)
+2017-04-27 14:13:31.592825 W | rafthttp: lost the TCP streaming connection with peer 6d4f535bae3ab960 (stream Message reader)
+2017-04-27 14:13:31.693275 E | rafthttp: failed to dial 6d4f535bae3ab960 on stream Message (dial tcp [::1]:2380: getsockopt: connection refused)
+2017-04-27 14:13:31.693289 I | rafthttp: peer 6d4f535bae3ab960 became inactive
+2017-04-27 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 v3.2 binary and start the new etcd process
+
+The new v3.2 etcd will publish its information to the cluster:
+
+```
+2017-04-27 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 v3.2 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 v3.2:
+
+```
+2017-04-27 14:15:17.071804 W | etcdserver: member c89feb932daef420 has a higher version 3.2.0
+2017-04-27 14:15:21.073110 W | etcdserver: the local etcd version 3.1.7 is not up-to-date
+2017-04-27 14:15:21.073142 W | etcdserver: member 6d4f535bae3ab960 has a higher version 3.2.0
+2017-04-27 14:15:21.073157 W | etcdserver: the local etcd version 3.1.7 is not up-to-date
+2017-04-27 14:15:21.073164 W | etcdserver: member c89feb932daef420 has a higher version 3.2.0
+```
+
+#### 4. Repeat step 2 to step 3 for all other members
+
+#### 5. Finish
+
+When all members are upgraded, the cluster will report upgrading to 3.2 successfully:
+
+```
+2017-04-27 14:15:54.536901 N | etcdserver/membership: updated the cluster version from 3.1 to 3.2
+2017-04-27 14:15:54.537035 I | etcdserver/api: enabled capabilities for version 3.2
+```
+
+```
+$ 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_3.md

@@ -0,0 +1,476 @@
+## 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/coreos/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.
+
+#### Change in `etcdserver.EtcdServer` struct
+
+`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)
+    ...
+```
+
+#### Change in `embed.EtcdServer` struct
+
+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.
+
+```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.
+
+#### Change in `/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"}
+```
+
+#### Change in 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.
+
+#### Change in 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.
+
+#### Change in raw gRPC client wrappers
+
+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/coreos/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 {
+```
+
+#### Change in 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
+```
+
+#### Change in `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
+```
+
+#### Change in `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")
+```
+
+#### Change in gRPC dependency
+
+3.3 now requires [grpc/grpc-go](https://github.com/grpc/grpc-go/releases) `v1.7.5`.
+
+##### Deprecate `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)
+```
+
+##### Deprecate `grpc.ErrClientConnTimeout`
+
+Previously, `grpc.ErrClientConnTimeout` error is returned on client dial time-outs. 3.3 instead returns `context.DeadlineExceeded` (see [#8504](https://github.com/coreos/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
+}
+```
+
+#### Change in 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
+```
+
+### 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_4.md

@@ -0,0 +1,171 @@
+## Upgrade etcd from 3.3 to 3.4
+
+In the general case, upgrading from etcd 3.3 to 3.4 can be a zero-downtime, rolling upgrade:
+ - one by one, stop the etcd v3.3 processes and replace them with etcd v3.4 processes
+ - after running all v3.4 processes, new features in v3.4 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/coreos/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 3.4.
+
+#### Change in `etcd` flags
+
+`--ca-file` and `--peer-ca-file` flags are deprecated; they have been deprecated since v2.1.
+
+```diff
+-etcd --ca-file ca-client.crt
++etcd --trusted-ca-file ca-client.crt
+```
+
+```diff
+-etcd --peer-ca-file ca-peer.crt
++etcd --peer-trusted-ca-file ca-peer.crt
+```
+
+#### Change in ``pkg/transport`
+
+Deprecated `pkg/transport.TLSInfo.CAFile` field.
+
+```diff
+import "github.com/coreos/etcd/pkg/transport"
+
+tlsInfo := transport.TLSInfo{
+    CertFile: "/tmp/test-certs/test.pem",
+    KeyFile: "/tmp/test-certs/test-key.pem",
+-   CAFile: "/tmp/test-certs/trusted-ca.pem",
++   TrustedCAFile: "/tmp/test-certs/trusted-ca.pem",
+}
+tlsConfig, err := tlsInfo.ClientConfig()
+if err != nil {
+    panic(err)
+}
+```
+
+### Server upgrade checklists
+
+#### Upgrade requirements
+
+To upgrade an existing etcd deployment to 3.4, the running cluster must be 3.3 or greater. If it's before 3.3, please [upgrade to 3.3](upgrade_3_3.md) before upgrading to 3.4.
+
+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 3.4. 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 v3.4, the cluster will be upgraded to v3.4, and downgrade from this completed state is **not possible**. If any single member is still v3.3, however, the cluster and its operations remains "v3.3", and it is possible from this mixed cluster state to return to using a v3.3 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 v3.3 ectd cluster running on a local machine.
+
+#### 1. Check upgrade requirements
+
+Is the cluster healthy and running v3.3.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":"3.3.0","etcdcluster":"3.3.0"}
+```
+
+#### 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 v3.4 binary and start the new etcd process
+
+The new v3.4 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 v3.4 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 v3.4:
+
+```
+14:15:17.071804 W | etcdserver: member c89feb932daef420 has a higher version 3.4.0
+14:15:21.073110 W | etcdserver: the local etcd version 3.3.0 is not up-to-date
+14:15:21.073142 W | etcdserver: member 6d4f535bae3ab960 has a higher version 3.4.0
+14:15:21.073157 W | etcdserver: the local etcd version 3.3.0 is not up-to-date
+14:15:21.073164 W | etcdserver: member c89feb932daef420 has a higher version 3.4.0
+```
+
+#### 4. Repeat step 2 to step 3 for all other members
+
+#### 5. Finish
+
+When all members are upgraded, the cluster will report upgrading to 3.4 successfully:
+
+```
+14:15:54.536901 N | etcdserver/membership: updated the cluster version from 3.3 to 3.4
+14:15:54.537035 I | etcdserver/api: enabled capabilities for version 3.4
+```
+
+```
+$ 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/upgrading-etcd.md

@@ -0,0 +1,19 @@
+# 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]
+
+## 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

Documentation/v2/README.md

@@ -67,13 +67,13 @@ You have successfully started an etcd and written a key to the store.
 
 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]: https://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.xhtml?search=etcd
+[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](./Procfile) will set up a local example cluster. You can start it with:
+Our [Procfile script](../../V2Procfile) will set up a local example cluster. You can start it with:
 
 ```sh
 goreman start
@@ -162,4 +162,4 @@ Currently only the amd64 architecture is officially supported by `etcd`.
 
 ### License
 
-etcd is under the Apache 2.0 license. See the [LICENSE](LICENSE) file for details.
+etcd is under the Apache 2.0 license. See the [LICENSE](../../LICENSE) file for details.

Documentation/v2/api_v3.md

@@ -18,7 +18,7 @@ A key’s lifetime spans a generation. Each key may have one or multiple generat
 
 ### 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.
 
@@ -73,7 +73,7 @@ Any completed operations are durable. All accessible data is also durable data.
 
 #### Linearizability
 
-Linearizability (also known as Atomic Consistency or External Consistency) is a consistency level between strict consistency and sequential consistency. 
+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.
 
@@ -83,10 +83,10 @@ etcd does not ensure linearizability for watch operations. Users are expected to
 
 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]
+[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/backward_compatibility.md

@@ -32,7 +32,7 @@ The consistent flag for read operations is removed in etcd 2.0.0. The normal rea
 
 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. 
+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.
 
@@ -56,6 +56,7 @@ Proxy mode in 2.0 will provide similar functionality, and with improved control
 ## Discovery Service
 
 A size key needs to be provided inside a [discovery token][discoverytoken].
+
 [discoverytoken]: clustering.md#custom-etcd-discovery-service
 
 ## HTTP Admin API

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

@@ -49,4 +49,4 @@ Bootstrap another machine and use the [boom HTTP benchmark tool][boom] to send r
 | 256               | 256               | all servers        | 3061      | 119.3 |
 
 [boom]: https://github.com/rakyll/boom
-[hack-benchmark]: /hack/benchmark/
+[hack-benchmark]: ../../../hack/benchmark/

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

@@ -24,7 +24,7 @@ Go OS/Arch: linux/amd64
 
 ## Testing
 
-Bootstrap another machine, outside of the etcd cluster, and run the [`boom` HTTP benchmark tool](https://github.com/rakyll/boom) 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.
+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.
 
@@ -66,4 +66,7 @@ The performance is calulated through results of 100 benchmark rounds.
 
 - 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.
+- 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

@@ -69,4 +69,4 @@ Bootstrap another machine and use the [boom HTTP benchmark tool][boom] to send r
 [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/
+[hack-benchmark]: ../../../hack/benchmark/

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

@@ -39,4 +39,4 @@ The performance is nearly the same as the one with empty server handler.
 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/
+[etcd-v3-benchmark]: ../../../tools/benchmark/

Documentation/v2/clustering.md

@@ -423,7 +423,7 @@ To make understanding this feature easier, we changed the naming of some flags,
 |-peers      |none      |Deprecated. The --initial-cluster flag provides a similar concept with different semantics. Please read this guide on cluster startup.|
 |-peers-file    |none      |Deprecated. The --initial-cluster flag provides a similar concept with different semantics. Please read this guide on cluster startup.|
 
-[client]: /client
+[client]: ../../client
 [client-discoverer]: https://godoc.org/github.com/coreos/etcd/client#Discoverer
 [conf-adv-client]: configuration.md#-advertise-client-urls
 [conf-listen-client]: configuration.md#-listen-client-urls

Documentation/v2/configuration.md

@@ -234,7 +234,7 @@ The security flags help to [build a secure etcd cluster][security].
 + env variable: ETCD_DEBUG
 
 ### --log-package-levels
-+ Set individual etcd subpackages to specific log levels. An example being `etcdserver=WARNING,security=DEBUG` 
++ Set individual etcd subpackages to specific log levels. An example being `etcdserver=WARNING,security=DEBUG`
 + default: none (INFO for all packages)
 + env variable: ETCD_LOG_PACKAGE_LEVELS
 
@@ -272,7 +272,7 @@ Follow the instructions when using these flags.
 [build-cluster]: clustering.md#static
 [reconfig]: runtime-configuration.md
 [discovery]: clustering.md#discovery
-[iana-ports]: https://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.xhtml?search=etcd
+[iana-ports]: http://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.txt
 [proxy]: proxy.md
 [reconfig]: runtime-configuration.md
 [restore]: admin_guide.md#restoring-a-backup

Documentation/v2/libraries-and-tools.md

@@ -112,7 +112,6 @@
 - [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.
-- [scrz](https://github.com/scrz/scrz) - Container manager, stores configuration in etcd.
 - [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.

Documentation/v2/reporting_bugs.md

@@ -1,6 +1,6 @@
 # Reporting Bugs
 
-If you find bugs or documentation mistakes in the etcd project, please let us know by [opening an issue][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.
+If you find bugs or documentation mistakes in the etcd project, 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.
 
 To make your bug report accurate and easy to understand, please try to create bug reports that are:
 

Documentation/v2/rfc/v3api.md

@@ -7,25 +7,25 @@ To prove out the design of the v3 API the team has also built [a number of examp
 # 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. 
+7. RPC API supports the completed set of APIs.
     - more efficient than JSON/HTTP
     - additional txn/lease support
 
@@ -56,7 +56,7 @@ the size in the future a little bit or make it configurable.
 // A put is always successful
 Put( PutRequest { key = foo, value = bar } )
 
-PutResponse { 
+PutResponse {
     cluster_id = 0x1000,
     member_id = 0x1,
     revision = 1,
@@ -119,7 +119,7 @@ RangeResponse {
 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 = equal, key = foo0, mod_revision = 1},
         {compareType = greater, key = foo1, mod_revision = 1}}
     },
     // if the comparison succeeds, put foo2 = bar2
@@ -156,7 +156,7 @@ Watch( WatchRequest{
            end_revision = 10000,
            // server decided notification frequency
            progress_notification = true,
-       } 
+       }
        … // this can be a watch request stream
       )
 
@@ -176,7 +176,7 @@ WatchResponse {
           },
     }
     …
-    
+
     // a notification at 2000
     WatchResponse {
         cluster_id = 0x1000,
@@ -185,9 +185,9 @@ WatchResponse {
         raft_term = 0x1,
         // nil event as notification
     }
-    
-    … 
-    
+
+    …
+
     // put (foo0=bar3000) event at 3000
     WatchResponse {
         cluster_id = 0x1000,
@@ -204,8 +204,8 @@ WatchResponse {
           },
     }
     …
-    
+
 ```
 
-[api-protobuf]: https://github.com/coreos/etcd/blob/master/etcdserver/etcdserverpb/rpc.proto
-[kv-protobuf]: https://github.com/coreos/etcd/blob/master/storage/storagepb/kv.proto
+[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

Documentation/v2/security.md

@@ -188,6 +188,6 @@ Make sure that you sign your certificates with a Subject Name your member's publ
 If you need your certificate to be signed for your member's FQDN in its Subject Name then you could use Subject Alternative Names (short IP SANs) to add your IP address. The `etcd-ca` tool provides `--domain=` option for its `new-cert` command, and openssl can make [it][alt-name] too.
 
 [cfssl]: https://github.com/cloudflare/cfssl
-[tls-setup]: /hack/tls-setup
+[tls-setup]: ../../hack/tls-setup
 [tls-guide]: https://github.com/coreos/docs/blob/master/os/generate-self-signed-certificates.md
 [alt-name]: http://wiki.cacert.org/FAQ/subjectAltName

Makefile

@@ -0,0 +1,516 @@
+# run from repository root
+
+
+
+# Example:
+#   make build
+#   make clean
+#   make docker-clean
+#   make docker-start
+#   make docker-kill
+#   make docker-remove
+
+.PHONY: build
+build:
+	GO_BUILD_FLAGS="-v" ./build
+	./bin/etcd --version
+	ETCDCTL_API=3 ./bin/etcdctl version
+
+clean:
+	rm -f ./codecov
+	rm -rf ./agent-*
+	rm -rf ./covdir
+	rm -f ./*.log
+	rm -f ./bin/Dockerfile-release
+	rm -rf ./bin/*.etcd
+	rm -rf ./gopath
+	rm -rf ./gopath.proto
+	rm -rf ./release
+	rm -f ./integration/127.0.0.1:* ./integration/localhost:*
+	rm -f ./clientv3/integration/127.0.0.1:* ./clientv3/integration/localhost:*
+	rm -f ./clientv3/ordering/127.0.0.1:* ./clientv3/ordering/localhost:*
+
+docker-clean:
+	docker images
+	docker image prune --force
+
+docker-start:
+	service docker restart
+
+docker-kill:
+	docker kill `docker ps -q` || true
+
+docker-remove:
+	docker rm --force `docker ps -a -q` || true
+	docker rmi --force `docker images -q` || true
+
+
+
+GO_VERSION ?= 1.10.1
+ETCD_VERSION ?= $(shell git rev-parse --short HEAD || echo "GitNotFound")
+
+TEST_SUFFIX = $(shell date +%s | base64 | head -c 15)
+TEST_OPTS ?= PASSES='unit'
+
+TMP_DIR_MOUNT_FLAG = --mount type=tmpfs,destination=/tmp
+ifdef HOST_TMP_DIR
+	TMP_DIR_MOUNT_FLAG = --mount type=bind,source=$(HOST_TMP_DIR),destination=/tmp
+endif
+
+
+
+# Example:
+#   GO_VERSION=1.8.7 make build-docker-test
+#   GO_VERSION=1.9.5 make build-docker-test
+#   make build-docker-test
+#
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   GO_VERSION=1.8.7 make push-docker-test
+#   GO_VERSION=1.9.5 make push-docker-test
+#   make push-docker-test
+#
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   GO_VERSION=1.9.5 make pull-docker-test
+#   make pull-docker-test
+
+build-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./tests/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  --file ./tests/Dockerfile .
+	@mv ./tests/Dockerfile.bak ./tests/Dockerfile
+
+push-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-test:go$(GO_VERSION)
+
+pull-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-test:go$(GO_VERSION)
+
+
+
+# Example:
+#   make build-docker-test
+#   make compile-with-docker-test
+#   make compile-setup-gopath-with-docker-test
+
+compile-with-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker run \
+	  --rm \
+	  --mount type=bind,source=`pwd`,destination=/go/src/github.com/coreos/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "GO_BUILD_FLAGS=-v ./build && ./bin/etcd --version"
+
+compile-setup-gopath-with-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker run \
+	  --rm \
+	  --mount type=bind,source=`pwd`,destination=/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && ETCD_SETUP_GOPATH=1 GO_BUILD_FLAGS=-v ./build && ./bin/etcd --version && rm -rf ./gopath"
+
+
+
+# Example:
+#
+# Local machine:
+#   TEST_OPTS="PASSES='fmt'" make test
+#   TEST_OPTS="PASSES='fmt bom dep compile build unit'" make test
+#   TEST_OPTS="PASSES='build unit release integration_e2e functional'" make test
+#   TEST_OPTS="PASSES='build grpcproxy'" make test
+#
+# Example (test with docker):
+#   make pull-docker-test
+#   TEST_OPTS="PASSES='fmt'" make docker-test
+#   TEST_OPTS="VERBOSE=2 PASSES='unit'" make docker-test
+#
+# Travis CI (test with docker):
+#   TEST_OPTS="PASSES='fmt bom dep compile build unit'" make docker-test
+#
+# Semaphore CI (test with docker):
+#   TEST_OPTS="PASSES='build unit release integration_e2e functional'" make docker-test
+#   HOST_TMP_DIR=/tmp TEST_OPTS="PASSES='build unit release integration_e2e functional'" make docker-test
+#   TEST_OPTS="GOARCH=386 PASSES='build unit integration_e2e'" make docker-test
+#
+# grpc-proxy tests (test with docker):
+#   TEST_OPTS="PASSES='build grpcproxy'" make docker-test
+#   HOST_TMP_DIR=/tmp TEST_OPTS="PASSES='build grpcproxy'" make docker-test
+
+.PHONY: test
+test:
+	$(info TEST_OPTS: $(TEST_OPTS))
+	$(info log-file: test-$(TEST_SUFFIX).log)
+	$(TEST_OPTS) ./test 2>&1 | tee test-$(TEST_SUFFIX).log
+	! egrep "(--- FAIL:|panic: test timed out|appears to have leaked)" -B50 -A10 test-$(TEST_SUFFIX).log
+
+docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	$(info TEST_OPTS: $(TEST_OPTS))
+	$(info log-file: test-$(TEST_SUFFIX).log)
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`,destination=/go/src/github.com/coreos/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "$(TEST_OPTS) ./test 2>&1 | tee test-$(TEST_SUFFIX).log"
+	! egrep "(--- FAIL:|panic: test timed out|appears to have leaked)" -B50 -A10 test-$(TEST_SUFFIX).log
+
+docker-test-coverage:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	$(info log-file: docker-test-coverage-$(TEST_SUFFIX).log)
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`,destination=/go/src/github.com/coreos/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "COVERDIR=covdir PASSES='build build_cov cov' ./test 2>&1 | tee docker-test-coverage-$(TEST_SUFFIX).log && /codecov -t 6040de41-c073-4d6f-bbf8-d89256ef31e1"
+	! egrep "(--- FAIL:|panic: test timed out|appears to have leaked)" -B50 -A10 docker-test-coverage-$(TEST_SUFFIX).log
+
+
+
+# Example:
+#   make compile-with-docker-test
+#   ETCD_VERSION=v3-test make build-docker-release-master
+#   ETCD_VERSION=v3-test make push-docker-release-master
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+
+build-docker-release-master:
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	cp ./Dockerfile-release ./bin/Dockerfile-release
+	docker build \
+	  --tag gcr.io/etcd-development/etcd:$(ETCD_VERSION) \
+	  --file ./bin/Dockerfile-release \
+	  ./bin
+	rm -f ./bin/Dockerfile-release
+
+	docker run \
+	  --rm \
+	  gcr.io/etcd-development/etcd:$(ETCD_VERSION) \
+	  /bin/sh -c "/usr/local/bin/etcd --version && ETCDCTL_API=3 /usr/local/bin/etcdctl version"
+
+push-docker-release-master:
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd:$(ETCD_VERSION)
+
+
+
+# Example:
+#   make build-docker-test
+#   make compile-with-docker-test
+#   make build-docker-static-ip-test
+#
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   make push-docker-static-ip-test
+#
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   make pull-docker-static-ip-test
+#
+#   make docker-static-ip-test-certs-run
+#   make docker-static-ip-test-certs-metrics-proxy-run
+
+build-docker-static-ip-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./tests/docker-static-ip/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION) \
+	  --file ./tests/docker-static-ip/Dockerfile \
+	  ./tests/docker-static-ip
+	@mv ./tests/docker-static-ip/Dockerfile.bak ./tests/docker-static-ip/Dockerfile
+
+push-docker-static-ip-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION)
+
+pull-docker-static-ip-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION)
+
+docker-static-ip-test-certs-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-static-ip/certs,destination=/certs \
+	  gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs/run.sh && rm -rf m*.etcd"
+
+docker-static-ip-test-certs-metrics-proxy-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-static-ip/certs-metrics-proxy,destination=/certs-metrics-proxy \
+	  gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-metrics-proxy/run.sh && rm -rf m*.etcd"
+
+
+
+# Example:
+#   make build-docker-test
+#   make compile-with-docker-test
+#   make build-docker-dns-test
+#
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   make push-docker-dns-test
+#
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   make pull-docker-dns-test
+#
+#   make docker-dns-test-insecure-run
+#   make docker-dns-test-certs-run
+#   make docker-dns-test-certs-gateway-run
+#   make docker-dns-test-certs-wildcard-run
+#   make docker-dns-test-certs-common-name-auth-run
+#   make docker-dns-test-certs-common-name-multi-run
+
+build-docker-dns-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./tests/docker-dns/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  --file ./tests/docker-dns/Dockerfile \
+	  ./tests/docker-dns
+	@mv ./tests/docker-dns/Dockerfile.bak ./tests/docker-dns/Dockerfile
+
+	docker run \
+	  --rm \
+	  --dns 127.0.0.1 \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "/etc/init.d/bind9 start && cat /dev/null >/etc/hosts && dig etcd.local"
+
+push-docker-dns-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION)
+
+pull-docker-dns-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION)
+
+docker-dns-test-insecure-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns/insecure,destination=/insecure \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /insecure/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns/certs,destination=/certs \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-gateway-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns/certs-gateway,destination=/certs-gateway \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-gateway/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-wildcard-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns/certs-wildcard,destination=/certs-wildcard \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-wildcard/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-common-name-auth-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns/certs-common-name-auth,destination=/certs-common-name-auth \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-common-name-auth/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-common-name-multi-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns/certs-common-name-multi,destination=/certs-common-name-multi \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-common-name-multi/run.sh && rm -rf m*.etcd"
+
+
+
+# Example:
+#   make build-docker-test
+#   make compile-with-docker-test
+#   make build-docker-dns-srv-test
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   make push-docker-dns-srv-test
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   make pull-docker-dns-srv-test
+#   make docker-dns-srv-test-certs-run
+#   make docker-dns-srv-test-certs-gateway-run
+#   make docker-dns-srv-test-certs-wildcard-run
+
+build-docker-dns-srv-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./tests/docker-dns-srv/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  --file ./tests/docker-dns-srv/Dockerfile \
+	  ./tests/docker-dns-srv
+	@mv ./tests/docker-dns-srv/Dockerfile.bak ./tests/docker-dns-srv/Dockerfile
+
+	docker run \
+	  --rm \
+	  --dns 127.0.0.1 \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "/etc/init.d/bind9 start && cat /dev/null >/etc/hosts && dig +noall +answer SRV _etcd-client-ssl._tcp.etcd.local && dig +noall +answer SRV _etcd-server-ssl._tcp.etcd.local && dig +noall +answer m1.etcd.local m2.etcd.local m3.etcd.local"
+
+push-docker-dns-srv-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION)
+
+pull-docker-dns-srv-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION)
+
+docker-dns-srv-test-certs-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns-srv/certs,destination=/certs \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs/run.sh && rm -rf m*.etcd"
+
+docker-dns-srv-test-certs-gateway-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns-srv/certs-gateway,destination=/certs-gateway \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-gateway/run.sh && rm -rf m*.etcd"
+
+docker-dns-srv-test-certs-wildcard-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/tests/docker-dns-srv/certs-wildcard,destination=/certs-wildcard \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-wildcard/run.sh && rm -rf m*.etcd"
+
+
+
+# Example:
+#   make build-functional
+#   make build-docker-functional
+#   make push-docker-functional
+#   make pull-docker-functional
+
+build-functional:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	./functional/build
+	./bin/etcd-agent -help || true && \
+	  ./bin/etcd-proxy -help || true && \
+	  ./bin/etcd-runner --help || true && \
+	  ./bin/etcd-tester -help || true
+
+build-docker-functional:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./functional/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-functional:go$(GO_VERSION) \
+	  --file ./functional/Dockerfile \
+	  .
+	@mv ./functional/Dockerfile.bak ./functional/Dockerfile
+
+	docker run \
+	  --rm \
+	  gcr.io/etcd-development/etcd-functional:go$(GO_VERSION) \
+	  /bin/bash -c "./bin/etcd --version && \
+	   ./bin/etcd-failpoints --version && \
+	   ETCDCTL_API=3 ./bin/etcdctl version && \
+	   ./bin/etcd-agent -help || true && \
+	   ./bin/etcd-proxy -help || true && \
+	   ./bin/etcd-runner --help || true && \
+	   ./bin/etcd-tester -help || true && \
+	   ./bin/benchmark --help || true"
+
+push-docker-functional:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-functional:go$(GO_VERSION)
+
+pull-docker-functional:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	docker pull gcr.io/etcd-development/etcd-functional:go$(GO_VERSION)

README.md

@@ -78,7 +78,7 @@ That's it! etcd is now running and serving client requests. For more
 
 The [official etcd ports][iana-ports] are 2379 for client requests, and 2380 for peer communication. 
 
-[iana-ports]: https://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.xhtml?search=etcd
+[iana-ports]: http://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.txt
 
 ### Running a local etcd cluster
 
@@ -136,5 +136,3 @@ See [reporting bugs](Documentation/reporting_bugs.md) for details about reportin
 ### License
 
 etcd is under the Apache 2.0 license. See the [LICENSE](LICENSE) file for details.
-
-

client/integration/client_test.go

@@ -34,7 +34,7 @@ import (
 func TestV2NoRetryEOF(t *testing.T) {
 	defer testutil.AfterTest(t)
 	// generate an EOF response; specify address so appears first in sorted ep list
-	lEOF := integration.NewListenerWithAddr(t, fmt.Sprintf("eof:123.%d.sock", os.Getpid()))
+	lEOF := integration.NewListenerWithAddr(t, fmt.Sprintf("127.0.0.1:%05d", os.Getpid()))
 	defer lEOF.Close()
 	tries := uint32(0)
 	go func() {
@@ -65,8 +65,7 @@ func TestV2NoRetryEOF(t *testing.T) {
 // TestV2NoRetryNoLeader tests destructive api calls won't retry if given an error code.
 func TestV2NoRetryNoLeader(t *testing.T) {
 	defer testutil.AfterTest(t)
-
-	lHttp := integration.NewListenerWithAddr(t, fmt.Sprintf("errHttp:123.%d.sock", os.Getpid()))
+	lHttp := integration.NewListenerWithAddr(t, fmt.Sprintf("127.0.0.1:%05d", os.Getpid()))
 	eh := &errHandler{errCode: http.StatusServiceUnavailable}
 	srv := httptest.NewUnstartedServer(eh)
 	defer lHttp.Close()

clientv3/integration/logger_test.go

@@ -17,5 +17,5 @@ package integration
 import "github.com/coreos/pkg/capnslog"
 
 func init() {
-	capnslog.SetGlobalLogLevel(capnslog.INFO)
+	capnslog.SetGlobalLogLevel(capnslog.CRITICAL)
 }

clientv3/integration/watch_test.go

@@ -347,7 +347,57 @@ func putAndWatch(t *testing.T, wctx *watchctx, key, val string) {
 	}
 }
 
-// TestWatchResumeComapcted checks that the watcher gracefully closes in case
+func TestWatchResumeInitRev(t *testing.T) {
+	defer testutil.AfterTest(t)
+	clus := integration.NewClusterV3(t, &integration.ClusterConfig{Size: 1})
+	defer clus.Terminate(t)
+
+	cli := clus.Client(0)
+	if _, err := cli.Put(context.TODO(), "b", "2"); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := cli.Put(context.TODO(), "a", "3"); err != nil {
+		t.Fatal(err)
+	}
+	// if resume is broken, it'll pick up this key first instead of a=3
+	if _, err := cli.Put(context.TODO(), "a", "4"); err != nil {
+		t.Fatal(err)
+	}
+
+	wch := clus.Client(0).Watch(context.Background(), "a", clientv3.WithRev(1), clientv3.WithCreatedNotify())
+	if resp, ok := <-wch; !ok || resp.Header.Revision != 4 {
+		t.Fatalf("got (%v, %v), expected create notification rev=4", resp, ok)
+	}
+	// pause wch
+	clus.Members[0].DropConnections()
+	clus.Members[0].PauseConnections()
+
+	select {
+	case resp, ok := <-wch:
+		t.Skipf("wch should block, got (%+v, %v); drop not fast enough", resp, ok)
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	// resume wch
+	clus.Members[0].UnpauseConnections()
+
+	select {
+	case resp, ok := <-wch:
+		if !ok {
+			t.Fatal("unexpected watch close")
+		}
+		if len(resp.Events) == 0 {
+			t.Fatal("expected event on watch")
+		}
+		if string(resp.Events[0].Kv.Value) != "3" {
+			t.Fatalf("expected value=3, got event %+v", resp.Events[0])
+		}
+	case <-time.After(5 * time.Second):
+		t.Fatal("watch timed out")
+	}
+}
+
+// TestWatchResumeCompacted checks that the watcher gracefully closes in case
 // that it tries to resume to a revision that's been compacted out of the store.
 // Since the watcher's server restarts with stale data, the watcher will receive
 // either a compaction error or all keys by staying in sync before the compaction

clientv3/watch.go

@@ -616,10 +616,24 @@ func (w *watchGrpcStream) serveSubstream(ws *watcherStream, resumec chan struct{
 					if ws.initReq.createdNotify {
 						ws.outc <- *wr
 					}
+					// once the watch channel is returned, a current revision
+					// watch must resume at the store revision. This is necessary
+					// for the following case to work as expected:
+					//	wch := m1.Watch("a")
+					//	m2.Put("a", "b")
+					//	<-wch
+					// If the revision is only bound on the first observed event,
+					// if wch is disconnected before the Put is issued, then reconnects
+					// after it is committed, it'll miss the Put.
+					if ws.initReq.rev == 0 {
+						nextRev = wr.Header.Revision
+					}
 				}
+			} else {
+				// current progress of watch; <= store revision
+				nextRev = wr.Header.Revision
 			}
 
-			nextRev = wr.Header.Revision
 			if len(wr.Events) > 0 {
 				nextRev = wr.Events[len(wr.Events)-1].Kv.ModRevision + 1
 			}

cmd/vendor/github.com/coreos/bbolt/bolt_386.go

@@ -5,3 +5,6 @@ const maxMapSize = 0x7FFFFFFF // 2GB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0xFFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_amd64.go

@@ -5,3 +5,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_arm.go

@@ -0,0 +1,28 @@
+package bolt
+
+import "unsafe"
+
+// maxMapSize represents the largest mmap size supported by Bolt.
+const maxMapSize = 0x7FFFFFFF // 2GB
+
+// maxAllocSize is the size used when creating array pointers.
+const maxAllocSize = 0xFFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned bool
+
+func init() {
+	// Simple check to see whether this arch handles unaligned load/stores
+	// correctly.
+
+	// ARM9 and older devices require load/stores to be from/to aligned
+	// addresses. If not, the lower 2 bits are cleared and that address is
+	// read in a jumbled up order.
+
+	// See http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka15414.html
+
+	raw := [6]byte{0xfe, 0xef, 0x11, 0x22, 0x22, 0x11}
+	val := *(*uint32)(unsafe.Pointer(uintptr(unsafe.Pointer(&raw)) + 2))
+
+	brokenUnaligned = val != 0x11222211
+}

cmd/vendor/github.com/coreos/bbolt/bolt_arm64.go

@@ -7,3 +7,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_mips64x.go

@@ -0,0 +1,12 @@
+// +build mips64 mips64le
+
+package bolt
+
+// maxMapSize represents the largest mmap size supported by Bolt.
+const maxMapSize = 0x8000000000 // 512GB
+
+// maxAllocSize is the size used when creating array pointers.
+const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_mipsx.go

@@ -1,7 +1,12 @@
+// +build mips mipsle
+
 package bolt
 
 // maxMapSize represents the largest mmap size supported by Bolt.
-const maxMapSize = 0x7FFFFFFF // 2GB
+const maxMapSize = 0x40000000 // 1GB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0xFFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_ppc64.go

@@ -7,3 +7,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_ppc64le.go

@@ -7,3 +7,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_s390x.go

@@ -7,3 +7,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

cmd/vendor/github.com/coreos/bbolt/bolt_unix.go

@@ -13,29 +13,32 @@ import (
 // flock acquires an advisory lock on a file descriptor.
 func flock(db *DB, mode os.FileMode, exclusive bool, timeout time.Duration) error {
 	var t time.Time
+	if timeout != 0 {
+		t = time.Now()
+	}
+	fd := db.file.Fd()
+	flag := syscall.LOCK_NB
+	if exclusive {
+		flag |= syscall.LOCK_EX
+	} else {
+		flag |= syscall.LOCK_SH
+	}
 	for {
-		// If we're beyond our timeout then return an error.
-		// This can only occur after we've attempted a flock once.
-		if t.IsZero() {
-			t = time.Now()
-		} else if timeout > 0 && time.Since(t) > timeout {
-			return ErrTimeout
-		}
-		flag := syscall.LOCK_SH
-		if exclusive {
-			flag = syscall.LOCK_EX
-		}
-
-		// Otherwise attempt to obtain an exclusive lock.
-		err := syscall.Flock(int(db.file.Fd()), flag|syscall.LOCK_NB)
+		// Attempt to obtain an exclusive lock.
+		err := syscall.Flock(int(fd), flag)
 		if err == nil {
 			return nil
 		} else if err != syscall.EWOULDBLOCK {
 			return err
 		}
 
+		// If we timed out then return an error.
+		if timeout != 0 && time.Since(t) > timeout-flockRetryTimeout {
+			return ErrTimeout
+		}
+
 		// Wait for a bit and try again.
-		time.Sleep(50 * time.Millisecond)
+		time.Sleep(flockRetryTimeout)
 	}
 }
 

cmd/vendor/github.com/coreos/bbolt/bolt_unix_solaris.go

@@ -13,34 +13,33 @@ import (
 // flock acquires an advisory lock on a file descriptor.
 func flock(db *DB, mode os.FileMode, exclusive bool, timeout time.Duration) error {
 	var t time.Time
+	if timeout != 0 {
+		t = time.Now()
+	}
+	fd := db.file.Fd()
+	var lockType int16
+	if exclusive {
+		lockType = syscall.F_WRLCK
+	} else {
+		lockType = syscall.F_RDLCK
+	}
 	for {
-		// If we're beyond our timeout then return an error.
-		// This can only occur after we've attempted a flock once.
-		if t.IsZero() {
-			t = time.Now()
-		} else if timeout > 0 && time.Since(t) > timeout {
-			return ErrTimeout
-		}
-		var lock syscall.Flock_t
-		lock.Start = 0
-		lock.Len = 0
-		lock.Pid = 0
-		lock.Whence = 0
-		lock.Pid = 0
-		if exclusive {
-			lock.Type = syscall.F_WRLCK
-		} else {
-			lock.Type = syscall.F_RDLCK
-		}
-		err := syscall.FcntlFlock(db.file.Fd(), syscall.F_SETLK, &lock)
+		// Attempt to obtain an exclusive lock.
+		lock := syscall.Flock_t{Type: lockType}
+		err := syscall.FcntlFlock(fd, syscall.F_SETLK, &lock)
 		if err == nil {
 			return nil
 		} else if err != syscall.EAGAIN {
 			return err
 		}
 
+		// If we timed out then return an error.
+		if timeout != 0 && time.Since(t) > timeout-flockRetryTimeout {
+			return ErrTimeout
+		}
+
 		// Wait for a bit and try again.
-		time.Sleep(50 * time.Millisecond)
+		time.Sleep(flockRetryTimeout)
 	}
 }
 

cmd/vendor/github.com/coreos/bbolt/bolt_windows.go

@@ -59,29 +59,30 @@ func flock(db *DB, mode os.FileMode, exclusive bool, timeout time.Duration) erro
 	db.lockfile = f
 
 	var t time.Time
+	if timeout != 0 {
+		t = time.Now()
+	}
+	fd := f.Fd()
+	var flag uint32 = flagLockFailImmediately
+	if exclusive {
+		flag |= flagLockExclusive
+	}
 	for {
-		// If we're beyond our timeout then return an error.
-		// This can only occur after we've attempted a flock once.
-		if t.IsZero() {
-			t = time.Now()
-		} else if timeout > 0 && time.Since(t) > timeout {
-			return ErrTimeout
-		}
-
-		var flag uint32 = flagLockFailImmediately
-		if exclusive {
-			flag |= flagLockExclusive
-		}
-
-		err := lockFileEx(syscall.Handle(db.lockfile.Fd()), flag, 0, 1, 0, &syscall.Overlapped{})
+		// Attempt to obtain an exclusive lock.
+		err := lockFileEx(syscall.Handle(fd), flag, 0, 1, 0, &syscall.Overlapped{})
 		if err == nil {
 			return nil
 		} else if err != errLockViolation {
 			return err
 		}
 
+		// If we timed oumercit then return an error.
+		if timeout != 0 && time.Since(t) > timeout-flockRetryTimeout {
+			return ErrTimeout
+		}
+
 		// Wait for a bit and try again.
-		time.Sleep(50 * time.Millisecond)
+		time.Sleep(flockRetryTimeout)
 	}
 }
 
@@ -89,7 +90,7 @@ func flock(db *DB, mode os.FileMode, exclusive bool, timeout time.Duration) erro
 func funlock(db *DB) error {
 	err := unlockFileEx(syscall.Handle(db.lockfile.Fd()), 0, 1, 0, &syscall.Overlapped{})
 	db.lockfile.Close()
-	os.Remove(db.path+lockExt)
+	os.Remove(db.path + lockExt)
 	return err
 }
 

cmd/vendor/github.com/coreos/bbolt/bucket.go

@@ -14,13 +14,6 @@ const (
 	MaxValueSize = (1 << 31) - 2
 )
 
-const (
-	maxUint = ^uint(0)
-	minUint = 0
-	maxInt  = int(^uint(0) >> 1)
-	minInt  = -maxInt - 1
-)
-
 const bucketHeaderSize = int(unsafe.Sizeof(bucket{}))
 
 const (
@@ -130,9 +123,17 @@ func (b *Bucket) Bucket(name []byte) *Bucket {
 func (b *Bucket) openBucket(value []byte) *Bucket {
 	var child = newBucket(b.tx)
 
+	// If unaligned load/stores are broken on this arch and value is
+	// unaligned simply clone to an aligned byte array.
+	unaligned := brokenUnaligned && uintptr(unsafe.Pointer(&value[0]))&3 != 0
+
+	if unaligned {
+		value = cloneBytes(value)
+	}
+
 	// If this is a writable transaction then we need to copy the bucket entry.
 	// Read-only transactions can point directly at the mmap entry.
-	if b.tx.writable {
+	if b.tx.writable && !unaligned {
 		child.bucket = &bucket{}
 		*child.bucket = *(*bucket)(unsafe.Pointer(&value[0]))
 	} else {
@@ -167,9 +168,8 @@ func (b *Bucket) CreateBucket(key []byte) (*Bucket, error) {
 	if bytes.Equal(key, k) {
 		if (flags & bucketLeafFlag) != 0 {
 			return nil, ErrBucketExists
-		} else {
-			return nil, ErrIncompatibleValue
 		}
+		return nil, ErrIncompatibleValue
 	}
 
 	// Create empty, inline bucket.
@@ -316,7 +316,12 @@ func (b *Bucket) Delete(key []byte) error {
 
 	// Move cursor to correct position.
 	c := b.Cursor()
-	_, _, flags := c.seek(key)
+	k, _, flags := c.seek(key)
+
+	// Return nil if the key doesn't exist.
+	if !bytes.Equal(key, k) {
+		return nil
+	}
 
 	// Return an error if there is already existing bucket value.
 	if (flags & bucketLeafFlag) != 0 {
@@ -329,6 +334,28 @@ func (b *Bucket) Delete(key []byte) error {
 	return nil
 }
 
+// Sequence returns the current integer for the bucket without incrementing it.
+func (b *Bucket) Sequence() uint64 { return b.bucket.sequence }
+
+// SetSequence updates the sequence number for the bucket.
+func (b *Bucket) SetSequence(v uint64) error {
+	if b.tx.db == nil {
+		return ErrTxClosed
+	} else if !b.Writable() {
+		return ErrTxNotWritable
+	}
+
+	// Materialize the root node if it hasn't been already so that the
+	// bucket will be saved during commit.
+	if b.rootNode == nil {
+		_ = b.node(b.root, nil)
+	}
+
+	// Increment and return the sequence.
+	b.bucket.sequence = v
+	return nil
+}
+
 // NextSequence returns an autoincrementing integer for the bucket.
 func (b *Bucket) NextSequence() (uint64, error) {
 	if b.tx.db == nil {

cmd/vendor/github.com/coreos/bbolt/db.go

@@ -7,8 +7,7 @@ import (
 	"log"
 	"os"
 	"runtime"
-	"runtime/debug"
-	"strings"
+	"sort"
 	"sync"
 	"time"
 	"unsafe"
@@ -23,6 +22,8 @@ const version = 2
 // Represents a marker value to indicate that a file is a Bolt DB.
 const magic uint32 = 0xED0CDAED
 
+const pgidNoFreelist pgid = 0xffffffffffffffff
+
 // IgnoreNoSync specifies whether the NoSync field of a DB is ignored when
 // syncing changes to a file.  This is required as some operating systems,
 // such as OpenBSD, do not have a unified buffer cache (UBC) and writes
@@ -39,6 +40,9 @@ const (
 // default page size for db is set to the OS page size.
 var defaultPageSize = os.Getpagesize()
 
+// The time elapsed between consecutive file locking attempts.
+const flockRetryTimeout = 50 * time.Millisecond
+
 // DB represents a collection of buckets persisted to a file on disk.
 // All data access is performed through transactions which can be obtained through the DB.
 // All the functions on DB will return a ErrDatabaseNotOpen if accessed before Open() is called.
@@ -61,6 +65,11 @@ type DB struct {
 	// THIS IS UNSAFE. PLEASE USE WITH CAUTION.
 	NoSync bool
 
+	// When true, skips syncing freelist to disk. This improves the database
+	// write performance under normal operation, but requires a full database
+	// re-sync during recovery.
+	NoFreelistSync bool
+
 	// When true, skips the truncate call when growing the database.
 	// Setting this to true is only safe on non-ext3/ext4 systems.
 	// Skipping truncation avoids preallocation of hard drive space and
@@ -107,9 +116,11 @@ type DB struct {
 	opened   bool
 	rwtx     *Tx
 	txs      []*Tx
-	freelist *freelist
 	stats    Stats
 
+	freelist     *freelist
+	freelistLoad sync.Once
+
 	pagePool sync.Pool
 
 	batchMu sync.Mutex
@@ -148,14 +159,17 @@ func (db *DB) String() string {
 // If the file does not exist then it will be created automatically.
 // Passing in nil options will cause Bolt to open the database with the default options.
 func Open(path string, mode os.FileMode, options *Options) (*DB, error) {
-	var db = &DB{opened: true}
-
+	db := &DB{
+		opened: true,
+	}
 	// Set default options if no options are provided.
 	if options == nil {
 		options = DefaultOptions
 	}
+	db.NoSync = options.NoSync
 	db.NoGrowSync = options.NoGrowSync
 	db.MmapFlags = options.MmapFlags
+	db.NoFreelistSync = options.NoFreelistSync
 
 	// Set default values for later DB operations.
 	db.MaxBatchSize = DefaultMaxBatchSize
@@ -184,6 +198,7 @@ func Open(path string, mode os.FileMode, options *Options) (*DB, error) {
 	// The database file is locked using the shared lock (more than one process may
 	// hold a lock at the same time) otherwise (options.ReadOnly is set).
 	if err := flock(db, mode, !db.readOnly, options.Timeout); err != nil {
+		db.lockfile = nil // make 'unused' happy. TODO: rework locks
 		_ = db.close()
 		return nil, err
 	}
@@ -191,6 +206,11 @@ func Open(path string, mode os.FileMode, options *Options) (*DB, error) {
 	// Default values for test hooks
 	db.ops.writeAt = db.file.WriteAt
 
+	if db.pageSize = options.PageSize; db.pageSize == 0 {
+		// Set the default page size to the OS page size.
+		db.pageSize = defaultPageSize
+	}
+
 	// Initialize the database if it doesn't exist.
 	if info, err := db.file.Stat(); err != nil {
 		return nil, err
@@ -202,20 +222,21 @@ func Open(path string, mode os.FileMode, options *Options) (*DB, error) {
 	} else {
 		// Read the first meta page to determine the page size.
 		var buf [0x1000]byte
-		if _, err := db.file.ReadAt(buf[:], 0); err == nil {
-			m := db.pageInBuffer(buf[:], 0).meta()
-			if err := m.validate(); err != nil {
-				// If we can't read the page size, we can assume it's the same
-				// as the OS -- since that's how the page size was chosen in the
-				// first place.
-				//
-				// If the first page is invalid and this OS uses a different
-				// page size than what the database was created with then we
-				// are out of luck and cannot access the database.
-				db.pageSize = os.Getpagesize()
-			} else {
+		// If we can't read the page size, but can read a page, assume
+		// it's the same as the OS or one given -- since that's how the
+		// page size was chosen in the first place.
+		//
+		// If the first page is invalid and this OS uses a different
+		// page size than what the database was created with then we
+		// are out of luck and cannot access the database.
+		//
+		// TODO: scan for next page
+		if bw, err := db.file.ReadAt(buf[:], 0); err == nil && bw == len(buf) {
+			if m := db.pageInBuffer(buf[:], 0).meta(); m.validate() == nil {
 				db.pageSize = int(m.pageSize)
 			}
+		} else {
+			return nil, ErrInvalid
 		}
 	}
 
@@ -232,14 +253,50 @@ func Open(path string, mode os.FileMode, options *Options) (*DB, error) {
 		return nil, err
 	}
 
-	// Read in the freelist.
-	db.freelist = newFreelist()
-	db.freelist.read(db.page(db.meta().freelist))
+	if db.readOnly {
+		return db, nil
+	}
+
+	db.loadFreelist()
+
+	// Flush freelist when transitioning from no sync to sync so
+	// NoFreelistSync unaware boltdb can open the db later.
+	if !db.NoFreelistSync && !db.hasSyncedFreelist() {
+		tx, err := db.Begin(true)
+		if tx != nil {
+			err = tx.Commit()
+		}
+		if err != nil {
+			_ = db.close()
+			return nil, err
+		}
+	}
 
 	// Mark the database as opened and return.
 	return db, nil
 }
 
+// loadFreelist reads the freelist if it is synced, or reconstructs it
+// by scanning the DB if it is not synced. It assumes there are no
+// concurrent accesses being made to the freelist.
+func (db *DB) loadFreelist() {
+	db.freelistLoad.Do(func() {
+		db.freelist = newFreelist()
+		if !db.hasSyncedFreelist() {
+			// Reconstruct free list by scanning the DB.
+			db.freelist.readIDs(db.freepages())
+		} else {
+			// Read free list from freelist page.
+			db.freelist.read(db.page(db.meta().freelist))
+		}
+		db.stats.FreePageN = len(db.freelist.ids)
+	})
+}
+
+func (db *DB) hasSyncedFreelist() bool {
+	return db.meta().freelist != pgidNoFreelist
+}
+
 // mmap opens the underlying memory-mapped file and initializes the meta references.
 // minsz is the minimum size that the new mmap can be.
 func (db *DB) mmap(minsz int) error {
@@ -341,9 +398,6 @@ func (db *DB) mmapSize(size int) (int, error) {
 
 // init creates a new database file and initializes its meta pages.
 func (db *DB) init() error {
-	// Set the page size to the OS page size.
-	db.pageSize = os.Getpagesize()
-
 	// Create two meta pages on a buffer.
 	buf := make([]byte, db.pageSize*4)
 	for i := 0; i < 2; i++ {
@@ -526,21 +580,36 @@ func (db *DB) beginRWTx() (*Tx, error) {
 	t := &Tx{writable: true}
 	t.init(db)
 	db.rwtx = t
+	db.freePages()
+	return t, nil
+}
 
-	// Free any pages associated with closed read-only transactions.
-	var minid txid = 0xFFFFFFFFFFFFFFFF
-	for _, t := range db.txs {
-		if t.meta.txid < minid {
-			minid = t.meta.txid
-		}
+// freePages releases any pages associated with closed read-only transactions.
+func (db *DB) freePages() {
+	// Free all pending pages prior to earliest open transaction.
+	sort.Sort(txsById(db.txs))
+	minid := txid(0xFFFFFFFFFFFFFFFF)
+	if len(db.txs) > 0 {
+		minid = db.txs[0].meta.txid
 	}
 	if minid > 0 {
 		db.freelist.release(minid - 1)
 	}
-
-	return t, nil
+	// Release unused txid extents.
+	for _, t := range db.txs {
+		db.freelist.releaseRange(minid, t.meta.txid-1)
+		minid = t.meta.txid + 1
+	}
+	db.freelist.releaseRange(minid, txid(0xFFFFFFFFFFFFFFFF))
+	// Any page both allocated and freed in an extent is safe to release.
 }
 
+type txsById []*Tx
+
+func (t txsById) Len() int           { return len(t) }
+func (t txsById) Swap(i, j int)      { t[i], t[j] = t[j], t[i] }
+func (t txsById) Less(i, j int) bool { return t[i].meta.txid < t[j].meta.txid }
+
 // removeTx removes a transaction from the database.
 func (db *DB) removeTx(tx *Tx) {
 	// Release the read lock on the mmap.
@@ -552,7 +621,10 @@ func (db *DB) removeTx(tx *Tx) {
 	// Remove the transaction.
 	for i, t := range db.txs {
 		if t == tx {
-			db.txs = append(db.txs[:i], db.txs[i+1:]...)
+			last := len(db.txs) - 1
+			db.txs[i] = db.txs[last]
+			db.txs[last] = nil
+			db.txs = db.txs[:last]
 			break
 		}
 	}
@@ -630,11 +702,7 @@ func (db *DB) View(fn func(*Tx) error) error {
 		return err
 	}
 
-	if err := t.Rollback(); err != nil {
-		return err
-	}
-
-	return nil
+	return t.Rollback()
 }
 
 // Batch calls fn as part of a batch. It behaves similar to Update,
@@ -823,7 +891,7 @@ func (db *DB) meta() *meta {
 }
 
 // allocate returns a contiguous block of memory starting at a given page.
-func (db *DB) allocate(count int) (*page, error) {
+func (db *DB) allocate(txid txid, count int) (*page, error) {
 	// Allocate a temporary buffer for the page.
 	var buf []byte
 	if count == 1 {
@@ -835,7 +903,7 @@ func (db *DB) allocate(count int) (*page, error) {
 	p.overflow = uint32(count - 1)
 
 	// Use pages from the freelist if they are available.
-	if p.id = db.freelist.allocate(count); p.id != 0 {
+	if p.id = db.freelist.allocate(txid, count); p.id != 0 {
 		return p, nil
 	}
 
@@ -890,6 +958,38 @@ func (db *DB) IsReadOnly() bool {
 	return db.readOnly
 }
 
+func (db *DB) freepages() []pgid {
+	tx, err := db.beginTx()
+	defer func() {
+		err = tx.Rollback()
+		if err != nil {
+			panic("freepages: failed to rollback tx")
+		}
+	}()
+	if err != nil {
+		panic("freepages: failed to open read only tx")
+	}
+
+	reachable := make(map[pgid]*page)
+	nofreed := make(map[pgid]bool)
+	ech := make(chan error)
+	go func() {
+		for e := range ech {
+			panic(fmt.Sprintf("freepages: failed to get all reachable pages (%v)", e))
+		}
+	}()
+	tx.checkBucket(&tx.root, reachable, nofreed, ech)
+	close(ech)
+
+	var fids []pgid
+	for i := pgid(2); i < db.meta().pgid; i++ {
+		if _, ok := reachable[i]; !ok {
+			fids = append(fids, i)
+		}
+	}
+	return fids
+}
+
 // Options represents the options that can be set when opening a database.
 type Options struct {
 	// Timeout is the amount of time to wait to obtain a file lock.
@@ -900,6 +1000,10 @@ type Options struct {
 	// Sets the DB.NoGrowSync flag before memory mapping the file.
 	NoGrowSync bool
 
+	// Do not sync freelist to disk. This improves the database write performance
+	// under normal operation, but requires a full database re-sync during recovery.
+	NoFreelistSync bool
+
 	// Open database in read-only mode. Uses flock(..., LOCK_SH |LOCK_NB) to
 	// grab a shared lock (UNIX).
 	ReadOnly bool
@@ -916,6 +1020,14 @@ type Options struct {
 	// If initialMmapSize is smaller than the previous database size,
 	// it takes no effect.
 	InitialMmapSize int
+
+	// PageSize overrides the default OS page size.
+	PageSize int
+
+	// NoSync sets the initial value of DB.NoSync. Normally this can just be
+	// set directly on the DB itself when returned from Open(), but this option
+	// is useful in APIs which expose Options but not the underlying DB.
+	NoSync bool
 }
 
 // DefaultOptions represent the options used if nil options are passed into Open().
@@ -952,15 +1064,11 @@ func (s *Stats) Sub(other *Stats) Stats {
 	diff.PendingPageN = s.PendingPageN
 	diff.FreeAlloc = s.FreeAlloc
 	diff.FreelistInuse = s.FreelistInuse
-	diff.TxN = other.TxN - s.TxN
+	diff.TxN = s.TxN - other.TxN
 	diff.TxStats = s.TxStats.Sub(&other.TxStats)
 	return diff
 }
 
-func (s *Stats) add(other *Stats) {
-	s.TxStats.add(&other.TxStats)
-}
-
 type Info struct {
 	Data     uintptr
 	PageSize int
@@ -999,7 +1107,8 @@ func (m *meta) copy(dest *meta) {
 func (m *meta) write(p *page) {
 	if m.root.root >= m.pgid {
 		panic(fmt.Sprintf("root bucket pgid (%d) above high water mark (%d)", m.root.root, m.pgid))
-	} else if m.freelist >= m.pgid {
+	} else if m.freelist >= m.pgid && m.freelist != pgidNoFreelist {
+		// TODO: reject pgidNoFreeList if !NoFreelistSync
 		panic(fmt.Sprintf("freelist pgid (%d) above high water mark (%d)", m.freelist, m.pgid))
 	}
 
@@ -1026,11 +1135,3 @@ func _assert(condition bool, msg string, v ...interface{}) {
 		panic(fmt.Sprintf("assertion failed: "+msg, v...))
 	}
 }
-
-func warn(v ...interface{})              { fmt.Fprintln(os.Stderr, v...) }
-func warnf(msg string, v ...interface{}) { fmt.Fprintf(os.Stderr, msg+"\n", v...) }
-
-func printstack() {
-	stack := strings.Join(strings.Split(string(debug.Stack()), "\n")[2:], "\n")
-	fmt.Fprintln(os.Stderr, stack)
-}

cmd/vendor/github.com/coreos/bbolt/freelist.go

@@ -6,25 +6,40 @@ import (
 	"unsafe"
 )
 
+// txPending holds a list of pgids and corresponding allocation txns
+// that are pending to be freed.
+type txPending struct {
+	ids              []pgid
+	alloctx          []txid // txids allocating the ids
+	lastReleaseBegin txid   // beginning txid of last matching releaseRange
+}
+
 // freelist represents a list of all pages that are available for allocation.
 // It also tracks pages that have been freed but are still in use by open transactions.
 type freelist struct {
-	ids     []pgid          // all free and available free page ids.
-	pending map[txid][]pgid // mapping of soon-to-be free page ids by tx.
-	cache   map[pgid]bool   // fast lookup of all free and pending page ids.
+	ids     []pgid              // all free and available free page ids.
+	allocs  map[pgid]txid       // mapping of txid that allocated a pgid.
+	pending map[txid]*txPending // mapping of soon-to-be free page ids by tx.
+	cache   map[pgid]bool       // fast lookup of all free and pending page ids.
 }
 
 // newFreelist returns an empty, initialized freelist.
 func newFreelist() *freelist {
 	return &freelist{
-		pending: make(map[txid][]pgid),
+		allocs:  make(map[pgid]txid),
+		pending: make(map[txid]*txPending),
 		cache:   make(map[pgid]bool),
 	}
 }
 
 // size returns the size of the page after serialization.
 func (f *freelist) size() int {
-	return pageHeaderSize + (int(unsafe.Sizeof(pgid(0))) * f.count())
+	n := f.count()
+	if n >= 0xFFFF {
+		// The first element will be used to store the count. See freelist.write.
+		n++
+	}
+	return pageHeaderSize + (int(unsafe.Sizeof(pgid(0))) * n)
 }
 
 // count returns count of pages on the freelist
@@ -40,27 +55,26 @@ func (f *freelist) free_count() int {
 // pending_count returns count of pending pages
 func (f *freelist) pending_count() int {
 	var count int
-	for _, list := range f.pending {
-		count += len(list)
+	for _, txp := range f.pending {
+		count += len(txp.ids)
 	}
 	return count
 }
 
-// all returns a list of all free ids and all pending ids in one sorted list.
-func (f *freelist) all() []pgid {
-	m := make(pgids, 0)
-
-	for _, list := range f.pending {
-		m = append(m, list...)
+// copyall copies into dst a list of all free ids and all pending ids in one sorted list.
+// f.count returns the minimum length required for dst.
+func (f *freelist) copyall(dst []pgid) {
+	m := make(pgids, 0, f.pending_count())
+	for _, txp := range f.pending {
+		m = append(m, txp.ids...)
 	}
-
 	sort.Sort(m)
-	return pgids(f.ids).merge(m)
+	mergepgids(dst, f.ids, m)
 }
 
 // allocate returns the starting page id of a contiguous list of pages of a given size.
 // If a contiguous block cannot be found then 0 is returned.
-func (f *freelist) allocate(n int) pgid {
+func (f *freelist) allocate(txid txid, n int) pgid {
 	if len(f.ids) == 0 {
 		return 0
 	}
@@ -93,7 +107,7 @@ func (f *freelist) allocate(n int) pgid {
 			for i := pgid(0); i < pgid(n); i++ {
 				delete(f.cache, initial+i)
 			}
-
+			f.allocs[initial] = txid
 			return initial
 		}
 
@@ -110,28 +124,73 @@ func (f *freelist) free(txid txid, p *page) {
 	}
 
 	// Free page and all its overflow pages.
-	var ids = f.pending[txid]
+	txp := f.pending[txid]
+	if txp == nil {
+		txp = &txPending{}
+		f.pending[txid] = txp
+	}
+	allocTxid, ok := f.allocs[p.id]
+	if ok {
+		delete(f.allocs, p.id)
+	} else if (p.flags & freelistPageFlag) != 0 {
+		// Freelist is always allocated by prior tx.
+		allocTxid = txid - 1
+	}
+
 	for id := p.id; id <= p.id+pgid(p.overflow); id++ {
 		// Verify that page is not already free.
 		if f.cache[id] {
 			panic(fmt.Sprintf("page %d already freed", id))
 		}
-
 		// Add to the freelist and cache.
-		ids = append(ids, id)
+		txp.ids = append(txp.ids, id)
+		txp.alloctx = append(txp.alloctx, allocTxid)
 		f.cache[id] = true
 	}
-	f.pending[txid] = ids
 }
 
 // release moves all page ids for a transaction id (or older) to the freelist.
 func (f *freelist) release(txid txid) {
 	m := make(pgids, 0)
-	for tid, ids := range f.pending {
+	for tid, txp := range f.pending {
 		if tid <= txid {
 			// Move transaction's pending pages to the available freelist.
 			// Don't remove from the cache since the page is still free.
-			m = append(m, ids...)
+			m = append(m, txp.ids...)
+			delete(f.pending, tid)
+		}
+	}
+	sort.Sort(m)
+	f.ids = pgids(f.ids).merge(m)
+}
+
+// releaseRange moves pending pages allocated within an extent [begin,end] to the free list.
+func (f *freelist) releaseRange(begin, end txid) {
+	if begin > end {
+		return
+	}
+	var m pgids
+	for tid, txp := range f.pending {
+		if tid < begin || tid > end {
+			continue
+		}
+		// Don't recompute freed pages if ranges haven't updated.
+		if txp.lastReleaseBegin == begin {
+			continue
+		}
+		for i := 0; i < len(txp.ids); i++ {
+			if atx := txp.alloctx[i]; atx < begin || atx > end {
+				continue
+			}
+			m = append(m, txp.ids[i])
+			txp.ids[i] = txp.ids[len(txp.ids)-1]
+			txp.ids = txp.ids[:len(txp.ids)-1]
+			txp.alloctx[i] = txp.alloctx[len(txp.alloctx)-1]
+			txp.alloctx = txp.alloctx[:len(txp.alloctx)-1]
+			i--
+		}
+		txp.lastReleaseBegin = begin
+		if len(txp.ids) == 0 {
 			delete(f.pending, tid)
 		}
 	}
@@ -142,12 +201,29 @@ func (f *freelist) release(txid txid) {
 // rollback removes the pages from a given pending tx.
 func (f *freelist) rollback(txid txid) {
 	// Remove page ids from cache.
-	for _, id := range f.pending[txid] {
-		delete(f.cache, id)
+	txp := f.pending[txid]
+	if txp == nil {
+		return
 	}
-
-	// Remove pages from pending list.
+	var m pgids
+	for i, pgid := range txp.ids {
+		delete(f.cache, pgid)
+		tx := txp.alloctx[i]
+		if tx == 0 {
+			continue
+		}
+		if tx != txid {
+			// Pending free aborted; restore page back to alloc list.
+			f.allocs[pgid] = tx
+		} else {
+			// Freed page was allocated by this txn; OK to throw away.
+			m = append(m, pgid)
+		}
+	}
+	// Remove pages from pending list and mark as free if allocated by txid.
 	delete(f.pending, txid)
+	sort.Sort(m)
+	f.ids = pgids(f.ids).merge(m)
 }
 
 // freed returns whether a given page is in the free list.
@@ -157,6 +233,9 @@ func (f *freelist) freed(pgid pgid) bool {
 
 // read initializes the freelist from a freelist page.
 func (f *freelist) read(p *page) {
+	if (p.flags & freelistPageFlag) == 0 {
+		panic(fmt.Sprintf("invalid freelist page: %d, page type is %s", p.id, p.typ()))
+	}
 	// If the page.count is at the max uint16 value (64k) then it's considered
 	// an overflow and the size of the freelist is stored as the first element.
 	idx, count := 0, int(p.count)
@@ -169,7 +248,7 @@ func (f *freelist) read(p *page) {
 	if count == 0 {
 		f.ids = nil
 	} else {
-		ids := ((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[idx:count]
+		ids := ((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[idx : idx+count]
 		f.ids = make([]pgid, len(ids))
 		copy(f.ids, ids)
 
@@ -181,27 +260,33 @@ func (f *freelist) read(p *page) {
 	f.reindex()
 }
 
+// read initializes the freelist from a given list of ids.
+func (f *freelist) readIDs(ids []pgid) {
+	f.ids = ids
+	f.reindex()
+}
+
 // write writes the page ids onto a freelist page. All free and pending ids are
 // saved to disk since in the event of a program crash, all pending ids will
 // become free.
 func (f *freelist) write(p *page) error {
 	// Combine the old free pgids and pgids waiting on an open transaction.
-	ids := f.all()
 
 	// Update the header flag.
 	p.flags |= freelistPageFlag
 
 	// The page.count can only hold up to 64k elements so if we overflow that
 	// number then we handle it by putting the size in the first element.
-	if len(ids) == 0 {
-		p.count = uint16(len(ids))
-	} else if len(ids) < 0xFFFF {
-		p.count = uint16(len(ids))
-		copy(((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[:], ids)
+	lenids := f.count()
+	if lenids == 0 {
+		p.count = uint16(lenids)
+	} else if lenids < 0xFFFF {
+		p.count = uint16(lenids)
+		f.copyall(((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[:])
 	} else {
 		p.count = 0xFFFF
-		((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[0] = pgid(len(ids))
-		copy(((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[1:], ids)
+		((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[0] = pgid(lenids)
+		f.copyall(((*[maxAllocSize]pgid)(unsafe.Pointer(&p.ptr)))[1:])
 	}
 
 	return nil
@@ -213,8 +298,8 @@ func (f *freelist) reload(p *page) {
 
 	// Build a cache of only pending pages.
 	pcache := make(map[pgid]bool)
-	for _, pendingIDs := range f.pending {
-		for _, pendingID := range pendingIDs {
+	for _, txp := range f.pending {
+		for _, pendingID := range txp.ids {
 			pcache[pendingID] = true
 		}
 	}
@@ -236,12 +321,12 @@ func (f *freelist) reload(p *page) {
 
 // reindex rebuilds the free cache based on available and pending free lists.
 func (f *freelist) reindex() {
-	f.cache = make(map[pgid]bool)
+	f.cache = make(map[pgid]bool, len(f.ids))
 	for _, id := range f.ids {
 		f.cache[id] = true
 	}
-	for _, pendingIDs := range f.pending {
-		for _, pendingID := range pendingIDs {
+	for _, txp := range f.pending {
+		for _, pendingID := range txp.ids {
 			f.cache[pendingID] = true
 		}
 	}

cmd/vendor/github.com/coreos/bbolt/node.go

@@ -365,7 +365,7 @@ func (n *node) spill() error {
 		}
 
 		// Allocate contiguous space for the node.
-		p, err := tx.allocate((node.size() / tx.db.pageSize) + 1)
+		p, err := tx.allocate((node.size() + tx.db.pageSize - 1) / tx.db.pageSize)
 		if err != nil {
 			return err
 		}

cmd/vendor/github.com/coreos/bbolt/page.go

@@ -145,12 +145,33 @@ func (a pgids) merge(b pgids) pgids {
 	// Return the opposite slice if one is nil.
 	if len(a) == 0 {
 		return b
-	} else if len(b) == 0 {
+	}
+	if len(b) == 0 {
 		return a
 	}
+	merged := make(pgids, len(a)+len(b))
+	mergepgids(merged, a, b)
+	return merged
+}
 
-	// Create a list to hold all elements from both lists.
-	merged := make(pgids, 0, len(a)+len(b))
+// mergepgids copies the sorted union of a and b into dst.
+// If dst is too small, it panics.
+func mergepgids(dst, a, b pgids) {
+	if len(dst) < len(a)+len(b) {
+		panic(fmt.Errorf("mergepgids bad len %d < %d + %d", len(dst), len(a), len(b)))
+	}
+	// Copy in the opposite slice if one is nil.
+	if len(a) == 0 {
+		copy(dst, b)
+		return
+	}
+	if len(b) == 0 {
+		copy(dst, a)
+		return
+	}
+
+	// Merged will hold all elements from both lists.
+	merged := dst[:0]
 
 	// Assign lead to the slice with a lower starting value, follow to the higher value.
 	lead, follow := a, b
@@ -172,7 +193,5 @@ func (a pgids) merge(b pgids) pgids {
 	}
 
 	// Append what's left in follow.
-	merged = append(merged, follow...)
-
-	return merged
+	_ = append(merged, follow...)
 }

cmd/vendor/github.com/coreos/bbolt/tx.go

@@ -126,10 +126,7 @@ func (tx *Tx) DeleteBucket(name []byte) error {
 // the error is returned to the caller.
 func (tx *Tx) ForEach(fn func(name []byte, b *Bucket) error) error {
 	return tx.root.ForEach(func(k, v []byte) error {
-		if err := fn(k, tx.root.Bucket(k)); err != nil {
-			return err
-		}
-		return nil
+		return fn(k, tx.root.Bucket(k))
 	})
 }
 
@@ -169,28 +166,18 @@ func (tx *Tx) Commit() error {
 	// Free the old root bucket.
 	tx.meta.root.root = tx.root.root
 
-	opgid := tx.meta.pgid
-
-	// Free the freelist and allocate new pages for it. This will overestimate
-	// the size of the freelist but not underestimate the size (which would be bad).
-	tx.db.freelist.free(tx.meta.txid, tx.db.page(tx.meta.freelist))
-	p, err := tx.allocate((tx.db.freelist.size() / tx.db.pageSize) + 1)
-	if err != nil {
-		tx.rollback()
-		return err
+	// Free the old freelist because commit writes out a fresh freelist.
+	if tx.meta.freelist != pgidNoFreelist {
+		tx.db.freelist.free(tx.meta.txid, tx.db.page(tx.meta.freelist))
 	}
-	if err := tx.db.freelist.write(p); err != nil {
-		tx.rollback()
-		return err
-	}
-	tx.meta.freelist = p.id
 
-	// If the high water mark has moved up then attempt to grow the database.
-	if tx.meta.pgid > opgid {
-		if err := tx.db.grow(int(tx.meta.pgid+1) * tx.db.pageSize); err != nil {
-			tx.rollback()
+	if !tx.db.NoFreelistSync {
+		err := tx.commitFreelist()
+		if err != nil {
 			return err
 		}
+	} else {
+		tx.meta.freelist = pgidNoFreelist
 	}
 
 	// Write dirty pages to disk.
@@ -235,6 +222,31 @@ func (tx *Tx) Commit() error {
 	return nil
 }
 
+func (tx *Tx) commitFreelist() error {
+	// Allocate new pages for the new free list. This will overestimate
+	// the size of the freelist but not underestimate the size (which would be bad).
+	opgid := tx.meta.pgid
+	p, err := tx.allocate((tx.db.freelist.size() / tx.db.pageSize) + 1)
+	if err != nil {
+		tx.rollback()
+		return err
+	}
+	if err := tx.db.freelist.write(p); err != nil {
+		tx.rollback()
+		return err
+	}
+	tx.meta.freelist = p.id
+	// If the high water mark has moved up then attempt to grow the database.
+	if tx.meta.pgid > opgid {
+		if err := tx.db.grow(int(tx.meta.pgid+1) * tx.db.pageSize); err != nil {
+			tx.rollback()
+			return err
+		}
+	}
+
+	return nil
+}
+
 // Rollback closes the transaction and ignores all previous updates. Read-only
 // transactions must be rolled back and not committed.
 func (tx *Tx) Rollback() error {
@@ -305,7 +317,11 @@ func (tx *Tx) WriteTo(w io.Writer) (n int64, err error) {
 	if err != nil {
 		return 0, err
 	}
-	defer func() { _ = f.Close() }()
+	defer func() {
+		if cerr := f.Close(); err == nil {
+			err = cerr
+		}
+	}()
 
 	// Generate a meta page. We use the same page data for both meta pages.
 	buf := make([]byte, tx.db.pageSize)
@@ -333,7 +349,7 @@ func (tx *Tx) WriteTo(w io.Writer) (n int64, err error) {
 	}
 
 	// Move past the meta pages in the file.
-	if _, err := f.Seek(int64(tx.db.pageSize*2), os.SEEK_SET); err != nil {
+	if _, err := f.Seek(int64(tx.db.pageSize*2), io.SeekStart); err != nil {
 		return n, fmt.Errorf("seek: %s", err)
 	}
 
@@ -344,7 +360,7 @@ func (tx *Tx) WriteTo(w io.Writer) (n int64, err error) {
 		return n, err
 	}
 
-	return n, f.Close()
+	return n, nil
 }
 
 // CopyFile copies the entire database to file at the given path.
@@ -379,9 +395,14 @@ func (tx *Tx) Check() <-chan error {
 }
 
 func (tx *Tx) check(ch chan error) {
+	// Force loading free list if opened in ReadOnly mode.
+	tx.db.loadFreelist()
+
 	// Check if any pages are double freed.
 	freed := make(map[pgid]bool)
-	for _, id := range tx.db.freelist.all() {
+	all := make([]pgid, tx.db.freelist.count())
+	tx.db.freelist.copyall(all)
+	for _, id := range all {
 		if freed[id] {
 			ch <- fmt.Errorf("page %d: already freed", id)
 		}
@@ -392,8 +413,10 @@ func (tx *Tx) check(ch chan error) {
 	reachable := make(map[pgid]*page)
 	reachable[0] = tx.page(0) // meta0
 	reachable[1] = tx.page(1) // meta1
-	for i := uint32(0); i <= tx.page(tx.meta.freelist).overflow; i++ {
-		reachable[tx.meta.freelist+pgid(i)] = tx.page(tx.meta.freelist)
+	if tx.meta.freelist != pgidNoFreelist {
+		for i := uint32(0); i <= tx.page(tx.meta.freelist).overflow; i++ {
+			reachable[tx.meta.freelist+pgid(i)] = tx.page(tx.meta.freelist)
+		}
 	}
 
 	// Recursively check buckets.
@@ -451,7 +474,7 @@ func (tx *Tx) checkBucket(b *Bucket, reachable map[pgid]*page, freed map[pgid]bo
 
 // allocate returns a contiguous block of memory starting at a given page.
 func (tx *Tx) allocate(count int) (*page, error) {
-	p, err := tx.db.allocate(count)
+	p, err := tx.db.allocate(tx.meta.txid, count)
 	if err != nil {
 		return nil, err
 	}

e2e/etcd_release_upgrade_test.go

@@ -23,6 +23,7 @@ import (
 
 	"github.com/coreos/etcd/pkg/fileutil"
 	"github.com/coreos/etcd/pkg/testutil"
+	"github.com/coreos/etcd/version"
 )
 
 // TestReleaseUpgrade ensures that changes to master branch does not affect
@@ -53,7 +54,7 @@ func TestReleaseUpgrade(t *testing.T) {
 	// so there's a window at boot time where it doesn't have V3rpcCapability enabled
 	// poll /version until etcdcluster is >2.3.x before making v3 requests
 	for i := 0; i < 7; i++ {
-		if err = cURLGet(epc, cURLReq{endpoint: "/version", expected: `"etcdcluster":"3.0`}); err != nil {
+		if err = cURLGet(epc, cURLReq{endpoint: "/version", expected: `"etcdcluster":"` + version.Cluster(version.Version)}); err != nil {
 			t.Logf("#%d: v3 is not ready yet (%v)", i, err)
 			time.Sleep(time.Second)
 			continue

embed/config.go

@@ -80,8 +80,38 @@ type Config struct {
 	// TickMs is the number of milliseconds between heartbeat ticks.
 	// TODO: decouple tickMs and heartbeat tick (current heartbeat tick = 1).
 	// make ticks a cluster wide configuration.
-	TickMs            uint  `json:"heartbeat-interval"`
-	ElectionMs        uint  `json:"election-timeout"`
+	TickMs     uint `json:"heartbeat-interval"`
+	ElectionMs uint `json:"election-timeout"`
+
+	// InitialElectionTickAdvance is true, then local member fast-forwards
+	// election ticks to speed up "initial" leader election trigger. This
+	// benefits the case of larger election ticks. For instance, cross
+	// datacenter deployment may require longer election timeout of 10-second.
+	// If true, local node does not need wait up to 10-second. Instead,
+	// forwards its election ticks to 8-second, and have only 2-second left
+	// before leader election.
+	//
+	// Major assumptions are that:
+	//  - cluster has no active leader thus advancing ticks enables faster
+	//    leader election, or
+	//  - cluster already has an established leader, and rejoining follower
+	//    is likely to receive heartbeats from the leader after tick advance
+	//    and before election timeout.
+	//
+	// However, when network from leader to rejoining follower is congested,
+	// and the follower does not receive leader heartbeat within left election
+	// ticks, disruptive election has to happen thus affecting cluster
+	// availabilities.
+	//
+	// Disabling this would slow down initial bootstrap process for cross
+	// datacenter deployments. Make your own tradeoffs by configuring
+	// --initial-election-tick-advance at the cost of slow initial bootstrap.
+	//
+	// If single-node, it advances ticks regardless.
+	//
+	// See https://github.com/coreos/etcd/issues/9333 for more detail.
+	InitialElectionTickAdvance bool `json:"initial-election-tick-advance"`
+
 	QuotaBackendBytes int64 `json:"quota-backend-bytes"`
 
 	// clustering
@@ -152,13 +182,14 @@ func NewConfig() *Config {
 	lcurl, _ := url.Parse(DefaultListenClientURLs)
 	acurl, _ := url.Parse(DefaultAdvertiseClientURLs)
 	cfg := &Config{
-		CorsInfo:            &cors.CORSInfo{},
-		MaxSnapFiles:        DefaultMaxSnapshots,
-		MaxWalFiles:         DefaultMaxWALs,
-		Name:                DefaultName,
-		SnapCount:           etcdserver.DefaultSnapCount,
-		TickMs:              100,
-		ElectionMs:          1000,
+		CorsInfo:                   &cors.CORSInfo{},
+		MaxSnapFiles:               DefaultMaxSnapshots,
+		MaxWalFiles:                DefaultMaxWALs,
+		Name:                       DefaultName,
+		SnapCount:                  etcdserver.DefaultSnapCount,
+		TickMs:                     100,
+		ElectionMs:                 1000,
+		InitialElectionTickAdvance: true,
 		LPUrls:              []url.URL{*lpurl},
 		LCUrls:              []url.URL{*lcurl},
 		APUrls:              []url.URL{*apurl},

embed/etcd.go

@@ -97,27 +97,28 @@ func StartEtcd(inCfg *Config) (e *Etcd, err error) {
 	}
 
 	srvcfg := &etcdserver.ServerConfig{
-		Name:                    cfg.Name,
-		ClientURLs:              cfg.ACUrls,
-		PeerURLs:                cfg.APUrls,
-		DataDir:                 cfg.Dir,
-		DedicatedWALDir:         cfg.WalDir,
-		SnapCount:               cfg.SnapCount,
-		MaxSnapFiles:            cfg.MaxSnapFiles,
-		MaxWALFiles:             cfg.MaxWalFiles,
-		InitialPeerURLsMap:      urlsmap,
-		InitialClusterToken:     token,
-		DiscoveryURL:            cfg.Durl,
-		DiscoveryProxy:          cfg.Dproxy,
-		NewCluster:              cfg.IsNewCluster(),
-		ForceNewCluster:         cfg.ForceNewCluster,
-		PeerTLSInfo:             cfg.PeerTLSInfo,
-		TickMs:                  cfg.TickMs,
-		ElectionTicks:           cfg.ElectionTicks(),
-		AutoCompactionRetention: cfg.AutoCompactionRetention,
-		QuotaBackendBytes:       cfg.QuotaBackendBytes,
-		StrictReconfigCheck:     cfg.StrictReconfigCheck,
-		ClientCertAuthEnabled:   cfg.ClientTLSInfo.ClientCertAuth,
+		Name:                       cfg.Name,
+		ClientURLs:                 cfg.ACUrls,
+		PeerURLs:                   cfg.APUrls,
+		DataDir:                    cfg.Dir,
+		DedicatedWALDir:            cfg.WalDir,
+		SnapCount:                  cfg.SnapCount,
+		MaxSnapFiles:               cfg.MaxSnapFiles,
+		MaxWALFiles:                cfg.MaxWalFiles,
+		InitialPeerURLsMap:         urlsmap,
+		InitialClusterToken:        token,
+		DiscoveryURL:               cfg.Durl,
+		DiscoveryProxy:             cfg.Dproxy,
+		NewCluster:                 cfg.IsNewCluster(),
+		ForceNewCluster:            cfg.ForceNewCluster,
+		PeerTLSInfo:                cfg.PeerTLSInfo,
+		TickMs:                     cfg.TickMs,
+		ElectionTicks:              cfg.ElectionTicks(),
+		InitialElectionTickAdvance: cfg.InitialElectionTickAdvance,
+		AutoCompactionRetention:    cfg.AutoCompactionRetention,
+		QuotaBackendBytes:          cfg.QuotaBackendBytes,
+		StrictReconfigCheck:        cfg.StrictReconfigCheck,
+		ClientCertAuthEnabled:      cfg.ClientTLSInfo.ClientCertAuth,
 	}
 
 	if e.Server, err = etcdserver.NewServer(srvcfg); err != nil {

etcdctl/README.md

@@ -949,7 +949,7 @@ RPC: RoleGrantPermission
 
 #### Ouptut
 
-`Role <role name> updated`. 
+`Role <role name> updated`.
 
 #### Examples
 

etcdctl/READMEv2.md

@@ -336,6 +336,6 @@ etcdctl is under the Apache 2.0 license. See the [LICENSE][license] file for det
 [authentication]: ../Documentation/v2/authentication.md
 [etcd]: https://github.com/coreos/etcd
 [github-release]: https://github.com/coreos/etcd/releases/
-[license]: https://github.com/coreos/etcdctl/blob/master/LICENSE
+[license]: ../LICENSE
 [semver]: http://semver.org/
 [username-flag]: #--username--u

etcdctl/ctlv3/command/lease_command.go

@@ -67,7 +67,7 @@ func leaseGrantCommandFunc(cmd *cobra.Command, args []string) {
 	if err != nil {
 		ExitWithError(ExitError, fmt.Errorf("failed to grant lease (%v)\n", err))
 	}
-	fmt.Printf("lease %016x granted with TTL(%ds)\n", resp.ID, resp.TTL)
+	display.Grant(*resp)
 }
 
 // NewLeaseRevokeCommand returns the cobra command for "lease revoke".
@@ -90,12 +90,12 @@ func leaseRevokeCommandFunc(cmd *cobra.Command, args []string) {
 
 	id := leaseFromArgs(args[0])
 	ctx, cancel := commandCtx(cmd)
-	_, err := mustClientFromCmd(cmd).Revoke(ctx, id)
+	resp, err := mustClientFromCmd(cmd).Revoke(ctx, id)
 	cancel()
 	if err != nil {
 		ExitWithError(ExitError, fmt.Errorf("failed to revoke lease (%v)\n", err))
 	}
-	fmt.Printf("lease %016x revoked\n", id)
+	display.Revoke(id, *resp)
 }
 
 var timeToLiveKeys bool
@@ -154,9 +154,12 @@ func leaseKeepAliveCommandFunc(cmd *cobra.Command, args []string) {
 	}
 
 	for resp := range respc {
-		fmt.Printf("lease %016x keepalived with TTL(%d)\n", resp.ID, resp.TTL)
+		display.KeepAlive(*resp)
+	}
+
+	if _, ok := (display).(*simplePrinter); ok {
+		fmt.Printf("lease %016x expired or revoked.\n", id)
 	}
-	fmt.Printf("lease %016x expired or revoked.\n", id)
 }
 
 func leaseFromArgs(arg string) v3.LeaseID {

etcdctl/ctlv3/command/printer.go

@@ -32,6 +32,9 @@ type printer interface {
 	Txn(v3.TxnResponse)
 	Watch(v3.WatchResponse)
 
+	Grant(r v3.LeaseGrantResponse)
+	Revoke(id v3.LeaseID, r v3.LeaseRevokeResponse)
+	KeepAlive(r v3.LeaseKeepAliveResponse)
 	TimeToLive(r v3.LeaseTimeToLiveResponse, keys bool)
 
 	MemberAdd(v3.MemberAddResponse)
@@ -81,13 +84,18 @@ type printerRPC struct {
 	p func(interface{})
 }
 
-func (p *printerRPC) Del(r v3.DeleteResponse)                            { p.p((*pb.DeleteRangeResponse)(&r)) }
-func (p *printerRPC) Get(r v3.GetResponse)                               { p.p((*pb.RangeResponse)(&r)) }
-func (p *printerRPC) Put(r v3.PutResponse)                               { p.p((*pb.PutResponse)(&r)) }
-func (p *printerRPC) Txn(r v3.TxnResponse)                               { p.p((*pb.TxnResponse)(&r)) }
-func (p *printerRPC) Watch(r v3.WatchResponse)                           { p.p(&r) }
+func (p *printerRPC) Del(r v3.DeleteResponse)  { p.p((*pb.DeleteRangeResponse)(&r)) }
+func (p *printerRPC) Get(r v3.GetResponse)     { p.p((*pb.RangeResponse)(&r)) }
+func (p *printerRPC) Put(r v3.PutResponse)     { p.p((*pb.PutResponse)(&r)) }
+func (p *printerRPC) Txn(r v3.TxnResponse)     { p.p((*pb.TxnResponse)(&r)) }
+func (p *printerRPC) Watch(r v3.WatchResponse) { p.p(&r) }
+
+func (p *printerRPC) Grant(r v3.LeaseGrantResponse)                      { p.p(r) }
+func (p *printerRPC) Revoke(id v3.LeaseID, r v3.LeaseRevokeResponse)     { p.p(r) }
+func (p *printerRPC) KeepAlive(r v3.LeaseKeepAliveResponse)              { p.p(r) }
 func (p *printerRPC) TimeToLive(r v3.LeaseTimeToLiveResponse, keys bool) { p.p(&r) }
-func (p *printerRPC) MemberAdd(r v3.MemberAddResponse)                   { p.p((*pb.MemberAddResponse)(&r)) }
+
+func (p *printerRPC) MemberAdd(r v3.MemberAddResponse) { p.p((*pb.MemberAddResponse)(&r)) }
 func (p *printerRPC) MemberRemove(id uint64, r v3.MemberRemoveResponse) {
 	p.p((*pb.MemberRemoveResponse)(&r))
 }

etcdctl/ctlv3/command/printer_fields.go

@@ -92,6 +92,22 @@ func (p *fieldsPrinter) Watch(resp v3.WatchResponse) {
 	}
 }
 
+func (p *fieldsPrinter) Grant(r v3.LeaseGrantResponse) {
+	p.hdr(r.ResponseHeader)
+	fmt.Println(`"ID" :`, r.ID)
+	fmt.Println(`"TTL" :`, r.TTL)
+}
+
+func (p *fieldsPrinter) Revoke(id v3.LeaseID, r v3.LeaseRevokeResponse) {
+	p.hdr(r.Header)
+}
+
+func (p *fieldsPrinter) KeepAlive(r v3.LeaseKeepAliveResponse) {
+	p.hdr(r.ResponseHeader)
+	fmt.Println(`"ID" :`, r.ID)
+	fmt.Println(`"TTL" :`, r.TTL)
+}
+
 func (p *fieldsPrinter) TimeToLive(r v3.LeaseTimeToLiveResponse, keys bool) {
 	p.hdr(r.ResponseHeader)
 	fmt.Println(`"ID" :`, r.ID)

etcdctl/ctlv3/command/printer_simple.go

@@ -79,6 +79,18 @@ func (s *simplePrinter) Watch(resp v3.WatchResponse) {
 	}
 }
 
+func (s *simplePrinter) Grant(resp v3.LeaseGrantResponse) {
+	fmt.Printf("lease %016x granted with TTL(%ds)\n", resp.ID, resp.TTL)
+}
+
+func (p *simplePrinter) Revoke(id v3.LeaseID, r v3.LeaseRevokeResponse) {
+	fmt.Printf("lease %016x revoked\n", id)
+}
+
+func (p *simplePrinter) KeepAlive(resp v3.LeaseKeepAliveResponse) {
+	fmt.Printf("lease %016x keepalived with TTL(%d)\n", resp.ID, resp.TTL)
+}
+
 func (s *simplePrinter) TimeToLive(resp v3.LeaseTimeToLiveResponse, keys bool) {
 	txt := fmt.Sprintf("lease %016x granted with TTL(%ds), remaining(%ds)", resp.ID, resp.GrantedTTL, resp.TTL)
 	if keys {

etcdctl/ctlv3/command/snapshot_command.go

@@ -27,7 +27,7 @@ import (
 	"reflect"
 	"strings"
 
-	"github.com/boltdb/bolt"
+	bolt "github.com/coreos/bbolt"
 	"github.com/coreos/etcd/etcdserver"
 	"github.com/coreos/etcd/etcdserver/etcdserverpb"
 	"github.com/coreos/etcd/etcdserver/membership"

etcdmain/config.go

@@ -134,6 +134,7 @@ func newConfig() *config {
 	fs.Uint64Var(&cfg.SnapCount, "snapshot-count", cfg.SnapCount, "Number of committed transactions to trigger a snapshot to disk.")
 	fs.UintVar(&cfg.TickMs, "heartbeat-interval", cfg.TickMs, "Time (in milliseconds) of a heartbeat interval.")
 	fs.UintVar(&cfg.ElectionMs, "election-timeout", cfg.ElectionMs, "Time (in milliseconds) for an election to timeout.")
+	fs.BoolVar(&cfg.InitialElectionTickAdvance, "initial-election-tick-advance", cfg.InitialElectionTickAdvance, "Whether to fast-forward initial election ticks on boot for faster election.")
 	fs.Int64Var(&cfg.QuotaBackendBytes, "quota-backend-bytes", cfg.QuotaBackendBytes, "Raise alarms when backend size exceeds the given quota. 0 means use the default quota.")
 
 	// clustering

etcdmain/help.go

@@ -48,6 +48,8 @@ member flags:
 		time (in milliseconds) of a heartbeat interval.
 	--election-timeout '1000'
 		time (in milliseconds) for an election to timeout. See tuning documentation for details.
+	--initial-election-tick-advance 'true'
+		whether to fast-forward initial election ticks on boot for faster election.
 	--listen-peer-urls 'http://localhost:2380'
 		list of URLs to listen on for peer traffic.
 	--listen-client-urls 'http://localhost:2379'

etcdserver/config.go

@@ -48,8 +48,38 @@ type ServerConfig struct {
 	ForceNewCluster     bool
 	PeerTLSInfo         transport.TLSInfo
 
-	TickMs           uint
-	ElectionTicks    int
+	TickMs        uint
+	ElectionTicks int
+
+	// InitialElectionTickAdvance is true, then local member fast-forwards
+	// election ticks to speed up "initial" leader election trigger. This
+	// benefits the case of larger election ticks. For instance, cross
+	// datacenter deployment may require longer election timeout of 10-second.
+	// If true, local node does not need wait up to 10-second. Instead,
+	// forwards its election ticks to 8-second, and have only 2-second left
+	// before leader election.
+	//
+	// Major assumptions are that:
+	//  - cluster has no active leader thus advancing ticks enables faster
+	//    leader election, or
+	//  - cluster already has an established leader, and rejoining follower
+	//    is likely to receive heartbeats from the leader after tick advance
+	//    and before election timeout.
+	//
+	// However, when network from leader to rejoining follower is congested,
+	// and the follower does not receive leader heartbeat within left election
+	// ticks, disruptive election has to happen thus affecting cluster
+	// availabilities.
+	//
+	// Disabling this would slow down initial bootstrap process for cross
+	// datacenter deployments. Make your own tradeoffs by configuring
+	// --initial-election-tick-advance at the cost of slow initial bootstrap.
+	//
+	// If single-node, it advances ticks regardless.
+	//
+	// See https://github.com/coreos/etcd/issues/9333 for more detail.
+	InitialElectionTickAdvance bool
+
 	BootstrapTimeout time.Duration
 
 	AutoCompactionRetention int

etcdserver/metrics.go

@@ -28,6 +28,12 @@ var (
 		Name:      "has_leader",
 		Help:      "Whether or not a leader exists. 1 is existence, 0 is not.",
 	})
+	isLeader = prometheus.NewGauge(prometheus.GaugeOpts{
+		Namespace: "etcd",
+		Subsystem: "server",
+		Name:      "is_leader",
+		Help:      "Whether or not this member is a leader. 1 if is, 0 otherwise.",
+	})
 	leaderChanges = prometheus.NewCounter(prometheus.CounterOpts{
 		Namespace: "etcd",
 		Subsystem: "server",
@@ -62,6 +68,7 @@ var (
 
 func init() {
 	prometheus.MustRegister(hasLeader)
+	prometheus.MustRegister(isLeader)
 	prometheus.MustRegister(leaderChanges)
 	prometheus.MustRegister(proposalsCommitted)
 	prometheus.MustRegister(proposalsApplied)

etcdserver/raft.go

@@ -95,6 +95,8 @@ type raftNode struct {
 	lead  uint64
 
 	mu sync.Mutex
+
+	tickMu sync.Mutex
 	// last lead elected time
 	lt time.Time
 
@@ -129,6 +131,13 @@ type raftNode struct {
 	done    chan struct{}
 }
 
+// raft.Node does not have locks in Raft package
+func (r *raftNode) tick() {
+	r.tickMu.Lock()
+	r.Tick()
+	r.tickMu.Unlock()
+}
+
 // start prepares and starts raftNode in a new goroutine. It is no longer safe
 // to modify the fields after it has been started.
 func (r *raftNode) start(rh *raftReadyHandler) {
@@ -144,7 +153,7 @@ func (r *raftNode) start(rh *raftReadyHandler) {
 		for {
 			select {
 			case <-r.ticker:
-				r.Tick()
+				r.tick()
 			case rd := <-r.Ready():
 				if rd.SoftState != nil {
 					if lead := atomic.LoadUint64(&r.lead); rd.SoftState.Lead != raft.None && lead != rd.SoftState.Lead {
@@ -162,6 +171,11 @@ func (r *raftNode) start(rh *raftReadyHandler) {
 
 					atomic.StoreUint64(&r.lead, rd.SoftState.Lead)
 					islead = rd.RaftState == raft.StateLeader
+					if islead {
+						isLeader.Set(1)
+					} else {
+						isLeader.Set(0)
+					}
 					rh.updateLeadership()
 				}
 
@@ -321,13 +335,13 @@ func (r *raftNode) resumeSending() {
 	p.Resume()
 }
 
-// advanceTicksForElection advances ticks to the node for fast election.
-// This reduces the time to wait for first leader election if bootstrapping the whole
-// cluster, while leaving at least 1 heartbeat for possible existing leader
-// to contact it.
-func advanceTicksForElection(n raft.Node, electionTicks int) {
-	for i := 0; i < electionTicks-1; i++ {
-		n.Tick()
+// advanceTicks advances ticks of Raft node.
+// This can be used for fast-forwarding election
+// ticks in multi data-center deployments, thus
+// speeding up election process.
+func (r *raftNode) advanceTicks(ticks int) {
+	for i := 0; i < ticks; i++ {
+		r.tick()
 	}
 }
 
@@ -368,8 +382,7 @@ func startNode(cfg *ServerConfig, cl *membership.RaftCluster, ids []types.ID) (i
 	raftStatusMu.Lock()
 	raftStatus = n.Status
 	raftStatusMu.Unlock()
-	advanceTicksForElection(n, c.ElectionTick)
-	return
+	return id, n, s, w
 }
 
 func restartNode(cfg *ServerConfig, snapshot *raftpb.Snapshot) (types.ID, *membership.RaftCluster, raft.Node, *raft.MemoryStorage, *wal.WAL) {
@@ -402,7 +415,6 @@ func restartNode(cfg *ServerConfig, snapshot *raftpb.Snapshot) (types.ID, *membe
 	raftStatusMu.Lock()
 	raftStatus = n.Status
 	raftStatusMu.Unlock()
-	advanceTicksForElection(n, c.ElectionTick)
 	return id, cl, n, s, w
 }
 

etcdserver/server.go

@@ -506,11 +506,55 @@ func NewServer(cfg *ServerConfig) (srv *EtcdServer, err error) {
 	return srv, nil
 }
 
+func (s *EtcdServer) adjustTicks() {
+	clusterN := len(s.cluster.Members())
+
+	// single-node fresh start, or single-node recovers from snapshot
+	if clusterN == 1 {
+		ticks := s.Cfg.ElectionTicks - 1
+		plog.Infof("%s as single-node; fast-forwarding %d ticks (election ticks %d)", s.ID(), ticks, s.Cfg.ElectionTicks)
+		s.r.advanceTicks(ticks)
+		return
+	}
+
+	if !s.Cfg.InitialElectionTickAdvance {
+		plog.Infof("skipping initial election tick advance (election tick %d)", s.Cfg.ElectionTicks)
+		return
+	}
+
+	// retry up to "rafthttp.ConnReadTimeout", which is 5-sec
+	// until peer connection reports; otherwise:
+	// 1. all connections failed, or
+	// 2. no active peers, or
+	// 3. restarted single-node with no snapshot
+	// then, do nothing, because advancing ticks would have no effect
+	waitTime := rafthttp.ConnReadTimeout
+	itv := 50 * time.Millisecond
+	for i := int64(0); i < int64(waitTime/itv); i++ {
+		select {
+		case <-time.After(itv):
+		case <-s.stopping:
+			return
+		}
+
+		peerN := s.r.transport.ActivePeers()
+		if peerN > 1 {
+			// multi-node received peer connection reports
+			// adjust ticks, in case slow leader message receive
+			ticks := s.Cfg.ElectionTicks - 2
+			plog.Infof("%s initialzed peer connection; fast-forwarding %d ticks (election ticks %d) with %d active peer(s)", s.ID(), ticks, s.Cfg.ElectionTicks, peerN)
+			s.r.advanceTicks(ticks)
+			return
+		}
+	}
+}
+
 // Start prepares and starts server in a new goroutine. It is no longer safe to
 // modify a server's fields after it has been sent to Start.
 // It also starts a goroutine to publish its server information.
 func (s *EtcdServer) Start() {
 	s.start()
+	s.goAttach(func() { s.adjustTicks() })
 	s.goAttach(func() { s.publish(s.Cfg.ReqTimeout()) })
 	s.goAttach(s.purgeFile)
 	s.goAttach(func() { monitorFileDescriptor(s.stopping) })
@@ -608,7 +652,7 @@ type raftReadyHandler struct {
 }
 
 func (s *EtcdServer) run() {
-	snap, err := s.r.raftStorage.Snapshot()
+	snapshot, err := s.r.raftStorage.Snapshot()
 	if err != nil {
 		plog.Panicf("get snapshot from raft storage error: %v", err)
 	}
@@ -666,10 +710,10 @@ func (s *EtcdServer) run() {
 	// asynchronously accept apply packets, dispatch progress in-order
 	sched := schedule.NewFIFOScheduler()
 	ep := etcdProgress{
-		confState: snap.Metadata.ConfState,
-		snapi:     snap.Metadata.Index,
-		appliedt:  snap.Metadata.Term,
-		appliedi:  snap.Metadata.Index,
+		confState: snapshot.Metadata.ConfState,
+		snapi:     snapshot.Metadata.Index,
+		appliedt:  snapshot.Metadata.Term,
+		appliedi:  snapshot.Metadata.Index,
 	}
 
 	defer func() {
@@ -1253,9 +1297,14 @@ func (s *EtcdServer) apply(es []raftpb.Entry, confState *raftpb.ConfState) (appl
 		case raftpb.EntryNormal:
 			s.applyEntryNormal(&e)
 		case raftpb.EntryConfChange:
+			// set the consistent index of current executing entry
+			if e.Index > s.consistIndex.ConsistentIndex() {
+				s.consistIndex.setConsistentIndex(e.Index)
+			}
 			var cc raftpb.ConfChange
 			pbutil.MustUnmarshal(&cc, e.Data)
 			removedSelf, err := s.applyConfChange(cc, confState)
+			s.setAppliedIndex(e.Index)
 			shouldStop = shouldStop || removedSelf
 			s.w.Trigger(cc.ID, err)
 		default:

etcdserver/util_test.go

@@ -83,6 +83,7 @@ func (s *nopTransporterWithActiveTime) RemovePeer(id types.ID)              {}
 func (s *nopTransporterWithActiveTime) RemoveAllPeers()                     {}
 func (s *nopTransporterWithActiveTime) UpdatePeer(id types.ID, us []string) {}
 func (s *nopTransporterWithActiveTime) ActiveSince(id types.ID) time.Time   { return s.activeMap[id] }
+func (s *nopTransporterWithActiveTime) ActivePeers() int                    { return 0 }
 func (s *nopTransporterWithActiveTime) Stop()                               {}
 func (s *nopTransporterWithActiveTime) Pause()                              {}
 func (s *nopTransporterWithActiveTime) Resume()                             {}

glide.lock

@@ -1,5 +1,5 @@
-hash: ca3c895fa60c9ca9f53408202fb7643705f9960212d342967ed0da8e93606cc4
-updated: 2017-01-18T10:26:48.990115455-08:00
+hash: 8a2307db167c2f9bc511956fbec0a4400bc38db103603fc6a87bb179ac853bf5
+updated: 2017-11-21T11:36:36.822426751-08:00
 imports:
 - name: github.com/beorn7/perks
   version: 4c0e84591b9aa9e6dcfdf3e020114cd81f89d5f9
@@ -7,10 +7,10 @@ imports:
   - quantile
 - name: github.com/bgentry/speakeasy
   version: 36e9cfdd690967f4f690c6edcc9ffacd006014a0
-- name: github.com/boltdb/bolt
-  version: 583e8937c61f1af6513608ccc75c97b6abdf4ff9
 - name: github.com/cockroachdb/cmux
   version: 112f0506e7743d64a6eb8fedbcff13d9979bbf92
+- name: github.com/coreos/bbolt
+  version: 32c383e75ce054674c53b5a07e55de85332aee14
 - name: github.com/coreos/go-semver
   version: 568e959cd89871e61434c1143528d9162da89ef2
   subpackages:
@@ -74,7 +74,7 @@ imports:
   subpackages:
   - prometheus
 - name: github.com/prometheus/client_model
-  version: fa8ad6fec33561be4280a8f0514318c79d7f6cb6
+  version: 6f3806018612930941127f2a7c6c453ba2c527d2
   subpackages:
   - go
 - name: github.com/prometheus/common

glide.yaml

@@ -2,8 +2,8 @@ package: github.com/coreos/etcd
 import:
 - package: github.com/bgentry/speakeasy
   version: 36e9cfdd690967f4f690c6edcc9ffacd006014a0
-- package: github.com/boltdb/bolt
-  version: v1.3.0
+- package: github.com/coreos/bbolt
+  version: v1.3.1-coreos.5
 - package: github.com/cockroachdb/cmux
   version: 112f0506e7743d64a6eb8fedbcff13d9979bbf92
 - package: github.com/coreos/go-semver
@@ -48,9 +48,21 @@ import:
 - package: github.com/olekukonko/tablewriter
   version: cca8bbc0798408af109aaaa239cbd2634846b340
 - package: github.com/prometheus/client_golang
-  version: v0.8.0
+  version: c5b7fccd204277076155f10851dad72b76a49317
   subpackages:
   - prometheus
+- package: github.com/prometheus/client_model
+  version: 6f3806018612930941127f2a7c6c453ba2c527d2
+  subpackages:
+  - go
+- package: github.com/prometheus/common
+  version: 195bde7883f7c39ea62b0d92ab7359b5327065cb
+  subpackages:
+  - expfmt
+  - internal/bitbucket.org/ww/goautoneg
+  - model
+- package: github.com/prometheus/procfs
+  version: fcdb11ccb4389efb1b210b7ffb623ab71c5fdd60
 - package: github.com/spf13/cobra
   version: 1c44ec8d3f1552cac48999f9306da23c4d8a288b
 - package: github.com/spf13/pflag
@@ -102,4 +114,22 @@ import:
   subpackages:
   - assert
 - package: github.com/karlseguin/ccache
-  version: v2.0.2
+  version: a2d62155777b39595c825ed3824279e642a5db3c
+- package: github.com/beorn7/perks
+  version: 4c0e84591b9aa9e6dcfdf3e020114cd81f89d5f9
+- package: github.com/cpuguy83/go-md2man
+  version: a65d4d2de4d5f7c74868dfa9b202a3c8be315aaa
+- package: github.com/matttproud/golang_protobuf_extensions
+  version: c12348ce28de40eed0136aa2b644d0ee0650e56c
+  subpackages:
+  - pbutil
+- package: github.com/russross/blackfriday
+  version: 5f33e7b7878355cd2b7e6b8eefc48a5472c69f70
+- package: github.com/mattn/go-runewidth
+  version: 737072b4e32b7a5018b4a7125da8d12de90e8045
+- package: github.com/shurcooL/sanitized_anchor_name
+  version: 1dba4b3954bc059efc3991ec364f9f9a35f597d2
+- package: golang.org/x/sys
+  version: 478fcf54317e52ab69f40bb4c7a1520288d7f7ea
+  subpackages:
+  - unix

hack/benchmark/bench.sh

@@ -1,8 +1,8 @@
 #!/bin/bash -e
 
-leader=http://10.240.201.15:2379
+leader=http://localhost:2379
 # assume three servers
-servers=( http://10.240.201.15:2379 http://10.240.212.209:2379 http://10.240.95.3:2379 )
+servers=( http://localhost:2379 http://localhost:22379 http://localhost:32379 )
 
 keyarray=( 64 256 )
 

hack/insta-discovery/README.md

@@ -1 +1 @@
-Starts a cluster via the discovery service on your local machine. Useful for testing.
+Starts a cluster via the discovery service locally. Useful for testing.

hack/patch/README.md

@@ -0,0 +1,37 @@
+# ./hack/patch/cherrypick.sh
+
+Handles cherry-picks of PR(s) from etcd master to a stable etcd release branch automatically.
+
+## Setup
+
+Set the `UPSTREAM_REMOTE` and `FORK_REMOTE` environment variables.
+`UPSTREAM_REMOTE` should be set to git remote name of `github.com/coreos/etcd`,
+and `FORK_REMOTE` should be set to the git remote name of the forked etcd
+repo (`github.com/${github-username}/etcd`). Use `git remotes -v` to
+look up the git remote names. If etcd has not been forked, create
+one on github.com and register it locally with `git remote add ...`.
+
+
+```
+export UPSTREAM_REMOTE=origin
+export FORK_REMOTE=${github-username}
+export GITHUB_USER=${github-username}
+```
+
+Next, install hub from https://github.com/github/hub
+
+## Usage
+
+To cherry pick PR 12345 onto release-3.2 and propose is as a PR, run:
+
+```sh
+./hack/patch/cherrypick.sh ${UPSTREAM_REMOTE}/release-3.2 12345
+```
+
+To cherry pick 12345 then 56789 and propose them togther as a single PR, run:
+
+```
+./hack/patch/cherrypick.sh ${UPSTREAM_REMOTE}/release-3.2 12345 56789
+```
+
+

hack/patch/cherrypick.sh

@@ -0,0 +1,229 @@
+#!/usr/bin/env bash
+
+# Based on github.com/kubernetes/kubernetes/blob/v1.8.2/hack/cherry_pick_pull.sh
+
+# Checkout a PR from GitHub. (Yes, this is sitting in a Git tree. How
+# meta.) Assumes you care about pulls from remote "upstream" and
+# checks thems out to a branch named:
+#  automated-cherry-pick-of-<pr>-<target branch>-<timestamp>
+
+set -o errexit
+set -o nounset
+set -o pipefail
+
+declare -r ETCD_ROOT="$(dirname "${BASH_SOURCE}")/../.."
+cd "${ETCD_ROOT}"
+
+declare -r STARTINGBRANCH=$(git symbolic-ref --short HEAD)
+declare -r REBASEMAGIC="${ETCD_ROOT}/.git/rebase-apply"
+DRY_RUN=${DRY_RUN:-""}
+REGENERATE_DOCS=${REGENERATE_DOCS:-""}
+UPSTREAM_REMOTE=${UPSTREAM_REMOTE:-upstream}
+FORK_REMOTE=${FORK_REMOTE:-origin}
+
+if [[ -z ${GITHUB_USER:-} ]]; then
+  echo "Please export GITHUB_USER=<your-user> (or GH organization, if that's where your fork lives)"
+  exit 1
+fi
+
+if ! which hub > /dev/null; then
+  echo "Can't find 'hub' tool in PATH, please install from https://github.com/github/hub"
+  exit 1
+fi
+
+if [[ "$#" -lt 2 ]]; then
+  echo "${0} <remote branch> <pr-number>...: cherry pick one or more <pr> onto <remote branch> and leave instructions for proposing pull request"
+  echo
+  echo "  Checks out <remote branch> and handles the cherry-pick of <pr> (possibly multiple) for you."
+  echo "  Examples:"
+  echo "    $0 upstream/release-3.14 12345        # Cherry-picks PR 12345 onto upstream/release-3.14 and proposes that as a PR."
+  echo "    $0 upstream/release-3.14 12345 56789  # Cherry-picks PR 12345, then 56789 and proposes the combination as a single PR."
+  echo
+  echo "  Set the DRY_RUN environment var to skip git push and creating PR."
+  echo "  This is useful for creating patches to a release branch without making a PR."
+  echo "  When DRY_RUN is set the script will leave you in a branch containing the commits you cherry-picked."
+  echo
+  echo "  Set the REGENERATE_DOCS environment var to regenerate documentation for the target branch after picking the specified commits."
+  echo "  This is useful when picking commits containing changes to API documentation."
+  echo
+  echo " Set UPSTREAM_REMOTE (default: upstream) and FORK_REMOTE (default: origin)"
+  echo " To override the default remote names to what you have locally."
+  exit 2
+fi
+
+if git_status=$(git status --porcelain --untracked=no 2>/dev/null) && [[ -n "${git_status}" ]]; then
+  echo "!!! Dirty tree. Clean up and try again."
+  exit 1
+fi
+
+if [[ -e "${REBASEMAGIC}" ]]; then
+  echo "!!! 'git rebase' or 'git am' in progress. Clean up and try again."
+  exit 1
+fi
+
+declare -r BRANCH="$1"
+shift 1
+declare -r PULLS=( "$@" )
+
+function join { local IFS="$1"; shift; echo "$*"; }
+declare -r PULLDASH=$(join - "${PULLS[@]/#/#}") # Generates something like "#12345-#56789"
+declare -r PULLSUBJ=$(join " " "${PULLS[@]/#/#}") # Generates something like "#12345 #56789"
+
+echo "+++ Updating remotes..."
+git remote update "${UPSTREAM_REMOTE}" "${FORK_REMOTE}"
+
+if ! git log -n1 --format=%H "${BRANCH}" >/dev/null 2>&1; then
+  echo "!!! '${BRANCH}' not found. The second argument should be something like ${UPSTREAM_REMOTE}/release-0.21."
+  echo "    (In particular, it needs to be a valid, existing remote branch that I can 'git checkout'.)"
+  exit 1
+fi
+
+declare -r NEWBRANCHREQ="automated-cherry-pick-of-${PULLDASH}" # "Required" portion for tools.
+declare -r NEWBRANCH="$(echo "${NEWBRANCHREQ}-${BRANCH}" | sed 's/\//-/g')"
+declare -r NEWBRANCHUNIQ="${NEWBRANCH}-$(date +%s)"
+echo "+++ Creating local branch ${NEWBRANCHUNIQ}"
+
+cleanbranch=""
+prtext=""
+gitamcleanup=false
+function return_to_kansas {
+  if [[ "${gitamcleanup}" == "true" ]]; then
+    echo
+    echo "+++ Aborting in-progress git am."
+    git am --abort >/dev/null 2>&1 || true
+  fi
+
+  # return to the starting branch and delete the PR text file
+  if [[ -z "${DRY_RUN}" ]]; then
+    echo
+    echo "+++ Returning you to the ${STARTINGBRANCH} branch and cleaning up."
+    git checkout -f "${STARTINGBRANCH}" >/dev/null 2>&1 || true
+    if [[ -n "${cleanbranch}" ]]; then
+      git branch -D "${cleanbranch}" >/dev/null 2>&1 || true
+    fi
+    if [[ -n "${prtext}" ]]; then
+      rm "${prtext}"
+    fi
+  fi
+}
+trap return_to_kansas EXIT
+
+SUBJECTS=()
+function make-a-pr() {
+  local rel="$(basename "${BRANCH}")"
+  echo
+  echo "+++ Creating a pull request on GitHub at ${GITHUB_USER}:${NEWBRANCH}"
+
+  # This looks like an unnecessary use of a tmpfile, but it avoids
+  # https://github.com/github/hub/issues/976 Otherwise stdin is stolen
+  # when we shove the heredoc at hub directly, tickling the ioctl
+  # crash.
+  prtext="$(mktemp -t prtext.XXXX)" # cleaned in return_to_kansas
+  cat >"${prtext}" <<EOF
+Automated cherry pick of ${PULLSUBJ}
+
+Cherry pick of ${PULLSUBJ} on ${rel}.
+
+$(printf '%s\n' "${SUBJECTS[@]}")
+EOF
+
+  hub pull-request -F "${prtext}" -h "${GITHUB_USER}:${NEWBRANCH}" -b "coreos:${rel}"
+}
+
+git checkout -b "${NEWBRANCHUNIQ}" "${BRANCH}"
+cleanbranch="${NEWBRANCHUNIQ}"
+
+gitamcleanup=true
+for pull in "${PULLS[@]}"; do
+  echo "+++ Downloading patch to /tmp/${pull}.patch (in case you need to do this again)"
+  curl -o "/tmp/${pull}.patch" -sSL "http://github.com/coreos/etcd/pull/${pull}.patch"
+  echo
+  echo "+++ About to attempt cherry pick of PR. To reattempt:"
+  echo "  $ git am -3 /tmp/${pull}.patch"
+  echo
+  git am -3 "/tmp/${pull}.patch" || {
+    conflicts=false
+    while unmerged=$(git status --porcelain | grep ^U) && [[ -n ${unmerged} ]] \
+      || [[ -e "${REBASEMAGIC}" ]]; do
+      conflicts=true # <-- We should have detected conflicts once
+      echo
+      echo "+++ Conflicts detected:"
+      echo
+      (git status --porcelain | grep ^U) || echo "!!! None. Did you git am --continue?"
+      echo
+      echo "+++ Please resolve the conflicts in another window (and remember to 'git add / git am --continue')"
+      read -p "+++ Proceed (anything but 'y' aborts the cherry-pick)? [y/n] " -r
+      echo
+      if ! [[ "${REPLY}" =~ ^[yY]$ ]]; then
+        echo "Aborting." >&2
+        exit 1
+      fi
+    done
+
+    if [[ "${conflicts}" != "true" ]]; then
+      echo "!!! git am failed, likely because of an in-progress 'git am' or 'git rebase'"
+      exit 1
+    fi
+  }
+
+  # set the subject
+  subject=$(grep -m 1 "^Subject" "/tmp/${pull}.patch" | sed -e 's/Subject: \[PATCH//g' | sed 's/.*] //')
+  SUBJECTS+=("#${pull}: ${subject}")
+
+  # remove the patch file from /tmp
+  rm -f "/tmp/${pull}.patch"
+done
+gitamcleanup=false
+
+# Re-generate docs (if needed)
+if [[ -n "${REGENERATE_DOCS}" ]]; then
+  echo
+  echo "Regenerating docs..."
+  if ! hack/generate-docs.sh; then
+    echo
+    echo "hack/generate-docs.sh FAILED to complete."
+    exit 1
+  fi
+fi
+
+if [[ -n "${DRY_RUN}" ]]; then
+  echo "!!! Skipping git push and PR creation because you set DRY_RUN."
+  echo "To return to the branch you were in when you invoked this script:"
+  echo
+  echo "  git checkout ${STARTINGBRANCH}"
+  echo
+  echo "To delete this branch:"
+  echo
+  echo "  git branch -D ${NEWBRANCHUNIQ}"
+  exit 0
+fi
+
+if git remote -v | grep ^${FORK_REMOTE} | grep etcd/etcd.git; then
+  echo "!!! You have ${FORK_REMOTE} configured as your etcd/etcd.git"
+  echo "This isn't normal. Leaving you with push instructions:"
+  echo
+  echo "+++ First manually push the branch this script created:"
+  echo
+  echo "  git push REMOTE ${NEWBRANCHUNIQ}:${NEWBRANCH}"
+  echo
+  echo "where REMOTE is your personal fork (maybe ${UPSTREAM_REMOTE}? Consider swapping those.)."
+  echo "OR consider setting UPSTREAM_REMOTE and FORK_REMOTE to different values."
+  echo
+  make-a-pr
+  cleanbranch=""
+  exit 0
+fi
+
+echo
+echo "+++ I'm about to do the following to push to GitHub (and I'm assuming ${FORK_REMOTE} is your personal fork):"
+echo
+echo "  git push ${FORK_REMOTE} ${NEWBRANCHUNIQ}:${NEWBRANCH}"
+echo
+read -p "+++ Proceed (anything but 'y' aborts the cherry-pick)? [y/n] " -r
+if ! [[ "${REPLY}" =~ ^[yY]$ ]]; then
+  echo "Aborting." >&2
+  exit 1
+fi
+
+git push "${FORK_REMOTE}" -f "${NEWBRANCHUNIQ}:${NEWBRANCH}"
+make-a-pr

hack/scripts-dev/Makefile

@@ -0,0 +1,499 @@
+# run from repository root
+
+
+
+# Example:
+#   make build -f ./hack/scripts-dev/Makefile
+#   make clean -f ./hack/scripts-dev/Makefile
+#   make clean-docker -f ./hack/scripts-dev/Makefile
+#   make restart-docker -f ./hack/scripts-dev/Makefile
+#   make delete-docker-images -f ./hack/scripts-dev/Makefile
+
+.PHONY: build
+build:
+	GO_BUILD_FLAGS="-v" ./build
+	./bin/etcd --version
+	ETCDCTL_API=3 ./bin/etcdctl version
+
+clean:
+	rm -f ./codecov
+	rm -rf ./agent-*
+	rm -rf ./covdir
+	rm -f ./*.log
+	rm -f ./bin/Dockerfile-release
+	rm -rf ./bin/*.etcd
+	rm -rf ./gopath
+	rm -rf ./release
+	rm -f ./integration/127.0.0.1:* ./integration/localhost:*
+	rm -f ./clientv3/integration/127.0.0.1:* ./clientv3/integration/localhost:*
+	rm -f ./clientv3/ordering/127.0.0.1:* ./clientv3/ordering/localhost:*
+
+clean-docker:
+	docker images
+	docker image prune --force
+
+restart-docker:
+	service docker restart
+
+delete-docker-images:
+	docker rm --force $(docker ps -a -q) || true
+	docker rmi --force $(docker images -q) || true
+
+
+
+GO_VERSION ?= 1.10
+ETCD_VERSION ?= $(shell git rev-parse --short HEAD || echo "GitNotFound")
+
+TEST_SUFFIX = $(shell date +%s | base64 | head -c 15)
+TEST_OPTS ?= PASSES='unit'
+
+TMP_DIR_MOUNT_FLAG = --mount type=tmpfs,destination=/tmp
+ifdef HOST_TMP_DIR
+	TMP_DIR_MOUNT_FLAG = --mount type=bind,source=$(HOST_TMP_DIR),destination=/tmp
+endif
+
+
+
+# Example:
+#   GO_VERSION=1.8.7 make build-docker-test -f ./hack/scripts-dev/Makefile
+#   make build-docker-test -f ./hack/scripts-dev/Makefile
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   GO_VERSION=1.8.7 make push-docker-test -f ./hack/scripts-dev/Makefile
+#   make push-docker-test -f ./hack/scripts-dev/Makefile
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   GO_VERSION=1.8.7 make pull-docker-test -f ./hack/scripts-dev/Makefile
+#   make pull-docker-test -f ./hack/scripts-dev/Makefile
+
+build-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./Dockerfile-test
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  --file ./Dockerfile-test .
+	@mv ./Dockerfile-test.bak ./Dockerfile-test
+
+push-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-test:go$(GO_VERSION)
+
+pull-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-test:go$(GO_VERSION)
+
+
+
+# Example:
+#   make build-docker-test -f ./hack/scripts-dev/Makefile
+#   make compile-with-docker-test -f ./hack/scripts-dev/Makefile
+#   make compile-setup-gopath-with-docker-test -f ./hack/scripts-dev/Makefile
+
+compile-with-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker run \
+	  --rm \
+	  --mount type=bind,source=`pwd`,destination=/go/src/github.com/coreos/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "GO_BUILD_FLAGS=-v ./build && ./bin/etcd --version"
+
+compile-setup-gopath-with-docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker run \
+	  --rm \
+	  --mount type=bind,source=`pwd`,destination=/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && ETCD_SETUP_GOPATH=1 GO_BUILD_FLAGS=-v ./build && ./bin/etcd --version && rm -rf ./gopath"
+
+
+
+# Example:
+#
+# Local machine:
+#   TEST_OPTS="PASSES='fmt'" make test -f ./hack/scripts-dev/Makefile
+#   TEST_OPTS="PASSES='fmt bom dep compile build unit'" make test -f ./hack/scripts-dev/Makefile
+#   TEST_OPTS="PASSES='build unit release integration_e2e functional'" make test -f ./hack/scripts-dev/Makefile
+#   TEST_OPTS="PASSES='build grpcproxy'" make test -f ./hack/scripts-dev/Makefile
+#
+# Example (test with docker):
+#   make pull-docker-test -f ./hack/scripts-dev/Makefile
+#   TEST_OPTS="PASSES='fmt'" make docker-test -f ./hack/scripts-dev/Makefile
+#   TEST_OPTS="VERBOSE=2 PASSES='unit'" make docker-test -f ./hack/scripts-dev/Makefile
+#
+# Travis CI (test with docker):
+#   TEST_OPTS="PASSES='fmt bom dep compile build unit'" make docker-test -f ./hack/scripts-dev/Makefile
+#
+# Semaphore CI (test with docker):
+#   TEST_OPTS="PASSES='build unit release integration_e2e functional'" make docker-test -f ./hack/scripts-dev/Makefile
+#   HOST_TMP_DIR=/tmp TEST_OPTS="PASSES='build unit release integration_e2e functional'" make docker-test -f ./hack/scripts-dev/Makefile
+#   TEST_OPTS="GOARCH=386 PASSES='build unit integration_e2e'" make docker-test -f ./hack/scripts-dev/Makefile
+#
+# grpc-proxy tests (test with docker):
+#   TEST_OPTS="PASSES='build grpcproxy'" make docker-test -f ./hack/scripts-dev/Makefile
+#   HOST_TMP_DIR=/tmp TEST_OPTS="PASSES='build grpcproxy'" make docker-test -f ./hack/scripts-dev/Makefile
+
+.PHONY: test
+test:
+	$(info TEST_OPTS: $(TEST_OPTS))
+	$(info log-file: test-$(TEST_SUFFIX).log)
+	$(TEST_OPTS) ./test 2>&1 | tee test-$(TEST_SUFFIX).log
+	! egrep "(--- FAIL:|panic: test timed out|appears to have leaked)" -B50 -A10 test-$(TEST_SUFFIX).log
+
+docker-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	$(info TEST_OPTS: $(TEST_OPTS))
+	$(info log-file: test-$(TEST_SUFFIX).log)
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`,destination=/go/src/github.com/coreos/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "$(TEST_OPTS) ./test 2>&1 | tee test-$(TEST_SUFFIX).log"
+	! egrep "(--- FAIL:|panic: test timed out|appears to have leaked)" -B50 -A10 test-$(TEST_SUFFIX).log
+
+docker-test-coverage:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	$(info log-file: docker-test-coverage-$(TEST_SUFFIX).log)
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`,destination=/go/src/github.com/coreos/etcd \
+	  gcr.io/etcd-development/etcd-test:go$(GO_VERSION) \
+	  /bin/bash -c "COVERDIR=covdir PASSES='build build_cov cov' ./test 2>&1 | tee docker-test-coverage-$(TEST_SUFFIX).log && /codecov -t 6040de41-c073-4d6f-bbf8-d89256ef31e1"
+	! egrep "(--- FAIL:|panic: test timed out|appears to have leaked)" -B50 -A10 docker-test-coverage-$(TEST_SUFFIX).log
+
+
+
+# Example:
+#   make compile-with-docker-test -f ./hack/scripts-dev/Makefile
+#   ETCD_VERSION=v3-test make build-docker-release-master -f ./hack/scripts-dev/Makefile
+#   ETCD_VERSION=v3-test make push-docker-release-master -f ./hack/scripts-dev/Makefile
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+
+build-docker-release-master:
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	cp ./Dockerfile-release ./bin/Dockerfile-release
+	docker build \
+	  --tag gcr.io/etcd-development/etcd:$(ETCD_VERSION) \
+	  --file ./bin/Dockerfile-release \
+	  ./bin
+	rm -f ./bin/Dockerfile-release
+
+	docker run \
+	  --rm \
+	  gcr.io/etcd-development/etcd:$(ETCD_VERSION) \
+	  /bin/sh -c "/usr/local/bin/etcd --version && ETCDCTL_API=3 /usr/local/bin/etcdctl version"
+
+push-docker-release-master:
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd:$(ETCD_VERSION)
+
+
+
+# Example:
+#   make build-docker-test -f ./hack/scripts-dev/Makefile
+#   make compile-with-docker-test -f ./hack/scripts-dev/Makefile
+#   make build-docker-static-ip-test -f ./hack/scripts-dev/Makefile
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   make push-docker-static-ip-test -f ./hack/scripts-dev/Makefile
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   make pull-docker-static-ip-test -f ./hack/scripts-dev/Makefile
+#   make docker-static-ip-test-certs-run -f ./hack/scripts-dev/Makefile
+#   make docker-static-ip-test-certs-metrics-proxy-run -f ./hack/scripts-dev/Makefile
+
+build-docker-static-ip-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./hack/scripts-dev/docker-static-ip/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION) \
+	  --file ./hack/scripts-dev/docker-static-ip/Dockerfile \
+	  ./hack/scripts-dev/docker-static-ip
+	@mv ./hack/scripts-dev/docker-static-ip/Dockerfile.bak ./hack/scripts-dev/docker-static-ip/Dockerfile
+
+push-docker-static-ip-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION)
+
+pull-docker-static-ip-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION)
+
+docker-static-ip-test-certs-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-static-ip/certs,destination=/certs \
+	  gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs/run.sh && rm -rf m*.etcd"
+
+docker-static-ip-test-certs-metrics-proxy-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-static-ip/certs-metrics-proxy,destination=/certs-metrics-proxy \
+	  gcr.io/etcd-development/etcd-static-ip-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-metrics-proxy/run.sh && rm -rf m*.etcd"
+
+
+
+# Example:
+#   make build-docker-test -f ./hack/scripts-dev/Makefile
+#   make compile-with-docker-test -f ./hack/scripts-dev/Makefile
+#   make build-docker-dns-test -f ./hack/scripts-dev/Makefile
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   make push-docker-dns-test -f ./hack/scripts-dev/Makefile
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   make pull-docker-dns-test -f ./hack/scripts-dev/Makefile
+#   make docker-dns-test-insecure-run -f ./hack/scripts-dev/Makefile
+#   make docker-dns-test-certs-run -f ./hack/scripts-dev/Makefile
+#   make docker-dns-test-certs-gateway-run -f ./hack/scripts-dev/Makefile
+#   make docker-dns-test-certs-wildcard-run -f ./hack/scripts-dev/Makefile
+#   make docker-dns-test-certs-common-name-auth-run -f ./hack/scripts-dev/Makefile
+#   make docker-dns-test-certs-common-name-multi-run -f ./hack/scripts-dev/Makefile
+
+build-docker-dns-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./hack/scripts-dev/docker-dns/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  --file ./hack/scripts-dev/docker-dns/Dockerfile \
+	  ./hack/scripts-dev/docker-dns
+	@mv ./hack/scripts-dev/docker-dns/Dockerfile.bak ./hack/scripts-dev/docker-dns/Dockerfile
+
+	docker run \
+	  --rm \
+	  --dns 127.0.0.1 \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "/etc/init.d/bind9 start && cat /dev/null >/etc/hosts && dig etcd.local"
+
+push-docker-dns-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION)
+
+pull-docker-dns-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION)
+
+docker-dns-test-insecure-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns/insecure,destination=/insecure \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /insecure/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns/certs,destination=/certs \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-gateway-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns/certs-gateway,destination=/certs-gateway \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-gateway/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-wildcard-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns/certs-wildcard,destination=/certs-wildcard \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-wildcard/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-common-name-auth-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns/certs-common-name-auth,destination=/certs-common-name-auth \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-common-name-auth/run.sh && rm -rf m*.etcd"
+
+docker-dns-test-certs-common-name-multi-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns/certs-common-name-multi,destination=/certs-common-name-multi \
+	  gcr.io/etcd-development/etcd-dns-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-common-name-multi/run.sh && rm -rf m*.etcd"
+
+
+
+# Example:
+#   make build-docker-test -f ./hack/scripts-dev/Makefile
+#   make compile-with-docker-test -f ./hack/scripts-dev/Makefile
+#   make build-docker-dns-srv-test -f ./hack/scripts-dev/Makefile
+#   gcloud docker -- login -u _json_key -p "$(cat /etc/gcp-key-etcd-development.json)" https://gcr.io
+#   make push-docker-dns-srv-test -f ./hack/scripts-dev/Makefile
+#   gsutil -m acl ch -u allUsers:R -r gs://artifacts.etcd-development.appspot.com
+#   make pull-docker-dns-srv-test -f ./hack/scripts-dev/Makefile
+#   make docker-dns-srv-test-certs-run -f ./hack/scripts-dev/Makefile
+#   make docker-dns-srv-test-certs-gateway-run -f ./hack/scripts-dev/Makefile
+#   make docker-dns-srv-test-certs-wildcard-run -f ./hack/scripts-dev/Makefile
+
+build-docker-dns-srv-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./hack/scripts-dev/docker-dns-srv/Dockerfile
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  --file ./hack/scripts-dev/docker-dns-srv/Dockerfile \
+	  ./hack/scripts-dev/docker-dns-srv
+	@mv ./hack/scripts-dev/docker-dns-srv/Dockerfile.bak ./hack/scripts-dev/docker-dns-srv/Dockerfile
+
+	docker run \
+	  --rm \
+	  --dns 127.0.0.1 \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "/etc/init.d/bind9 start && cat /dev/null >/etc/hosts && dig +noall +answer SRV _etcd-client-ssl._tcp.etcd.local && dig +noall +answer SRV _etcd-server-ssl._tcp.etcd.local && dig +noall +answer m1.etcd.local m2.etcd.local m3.etcd.local"
+
+push-docker-dns-srv-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION)
+
+pull-docker-dns-srv-test:
+	$(info GO_VERSION: $(GO_VERSION))
+	docker pull gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION)
+
+docker-dns-srv-test-certs-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns-srv/certs,destination=/certs \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs/run.sh && rm -rf m*.etcd"
+
+docker-dns-srv-test-certs-gateway-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns-srv/certs-gateway,destination=/certs-gateway \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-gateway/run.sh && rm -rf m*.etcd"
+
+docker-dns-srv-test-certs-wildcard-run:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info HOST_TMP_DIR: $(HOST_TMP_DIR))
+	$(info TMP_DIR_MOUNT_FLAG: $(TMP_DIR_MOUNT_FLAG))
+	docker run \
+	  --rm \
+	  --tty \
+	  --dns 127.0.0.1 \
+	  $(TMP_DIR_MOUNT_FLAG) \
+	  --mount type=bind,source=`pwd`/bin,destination=/etcd \
+	  --mount type=bind,source=`pwd`/hack/scripts-dev/docker-dns-srv/certs-wildcard,destination=/certs-wildcard \
+	  gcr.io/etcd-development/etcd-dns-srv-test:go$(GO_VERSION) \
+	  /bin/bash -c "cd /etcd && /certs-wildcard/run.sh && rm -rf m*.etcd"
+
+
+
+# Example:
+#   make build-etcd-test-proxy -f ./hack/scripts-dev/Makefile
+
+build-etcd-test-proxy:
+	go build -v -o ./bin/etcd-test-proxy ./tools/etcd-test-proxy
+
+
+
+# Example:
+#   make build-docker-functional-tester -f ./hack/scripts-dev/Makefile
+#   make push-docker-functional-tester -f ./hack/scripts-dev/Makefile
+#   make pull-docker-functional-tester -f ./hack/scripts-dev/Makefile
+
+build-docker-functional-tester:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	@sed -i.bak 's|REPLACE_ME_GO_VERSION|$(GO_VERSION)|g' ./Dockerfile-functional-tester
+	docker build \
+	  --tag gcr.io/etcd-development/etcd-functional-tester:go$(GO_VERSION) \
+	  --file ./Dockerfile-functional-tester \
+	  .
+	@mv ./Dockerfile-functional-tester.bak ./Dockerfile-functional-tester
+
+	docker run \
+	  --rm \
+	  gcr.io/etcd-development/etcd-functional-tester:go$(GO_VERSION) \
+	  /bin/bash -c "/etcd --version && \
+	   /etcd-failpoints --version && \
+	   ETCDCTL_API=3 /etcdctl version && \
+	   /etcd-agent -help || true && \
+	   /etcd-tester -help || true && \
+	   /etcd-runner --help || true && \
+	   /benchmark --help || true && \
+	   /etcd-test-proxy -help || true"
+
+push-docker-functional-tester:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	gcloud docker -- push gcr.io/etcd-development/etcd-functional-tester:go$(GO_VERSION)
+
+pull-docker-functional-tester:
+	$(info GO_VERSION: $(GO_VERSION))
+	$(info ETCD_VERSION: $(ETCD_VERSION))
+	docker pull gcr.io/etcd-development/etcd-functional-tester:go$(GO_VERSION)

hack/scripts-dev/README

@@ -0,0 +1 @@
+scripts for etcd development

hack/scripts-dev/docker-dns-srv/Dockerfile

@@ -0,0 +1,44 @@
+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 \
+  tar \
+  git \
+  netcat \
+  bind9 \
+  dnsutils \
+  && 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 \
+  && go get -v -u github.com/mattn/goreman
+
+RUN mkdir -p /var/bind /etc/bind
+RUN chown root:bind /var/bind /etc/bind
+
+ADD named.conf etcd.zone rdns.zone /etc/bind/
+RUN chown root:bind /etc/bind/named.conf /etc/bind/etcd.zone /etc/bind/rdns.zone
+ADD resolv.conf /etc/resolv.conf

hack/scripts-dev/docker-dns-srv/certs-gateway/Procfile

@@ -0,0 +1,7 @@
+etcd1: ./etcd --name m1 --data-dir /tmp/m1.data --listen-client-urls https://127.0.0.1:2379 --advertise-client-urls https://m1.etcd.local:2379 --listen-peer-urls https://127.0.0.1:2380 --initial-advertise-peer-urls=https://m1.etcd.local:2380 --initial-cluster-token tkn --discovery-srv=etcd.local --initial-cluster-state new --peer-cert-file=/certs-gateway/server.crt --peer-key-file=/certs-gateway/server.key.insecure --peer-trusted-ca-file=/certs-gateway/ca.crt --peer-client-cert-auth --cert-file=/certs-gateway/server.crt --key-file=/certs-gateway/server.key.insecure --trusted-ca-file=/certs-gateway/ca.crt --client-cert-auth
+
+etcd2: ./etcd --name m2 --data-dir /tmp/m2.data --listen-client-urls https://127.0.0.1:22379 --advertise-client-urls https://m2.etcd.local:22379 --listen-peer-urls https://127.0.0.1:22380 --initial-advertise-peer-urls=https://m2.etcd.local:22380 --initial-cluster-token tkn --discovery-srv=etcd.local --initial-cluster-state new --peer-cert-file=/certs-gateway/server.crt --peer-key-file=/certs-gateway/server.key.insecure --peer-trusted-ca-file=/certs-gateway/ca.crt --peer-client-cert-auth --cert-file=/certs-gateway/server.crt --key-file=/certs-gateway/server.key.insecure --trusted-ca-file=/certs-gateway/ca.crt --client-cert-auth
+
+etcd3: ./etcd --name m3 --data-dir /tmp/m3.data --listen-client-urls https://127.0.0.1:32379 --advertise-client-urls https://m3.etcd.local:32379 --listen-peer-urls https://127.0.0.1:32380 --initial-advertise-peer-urls=https://m3.etcd.local:32380 --initial-cluster-token tkn --discovery-srv=etcd.local --initial-cluster-state new --peer-cert-file=/certs-gateway/server.crt --peer-key-file=/certs-gateway/server.key.insecure --peer-trusted-ca-file=/certs-gateway/ca.crt --peer-client-cert-auth --cert-file=/certs-gateway/server.crt --key-file=/certs-gateway/server.key.insecure --trusted-ca-file=/certs-gateway/ca.crt --client-cert-auth
+
+gateway: ./etcd gateway start --discovery-srv etcd.local --trusted-ca-file /certs-gateway/ca.crt --listen-addr 127.0.0.1:23790

hack/scripts-dev/docker-dns-srv/certs-gateway/ca-csr.json

@@ -0,0 +1,19 @@
+{
+  "key": {
+    "algo": "rsa",
+    "size": 2048
+  },
+  "names": [
+    {
+      "O": "etcd",
+      "OU": "etcd Security",
+      "L": "San Francisco",
+      "ST": "California",
+      "C": "USA"
+    }
+  ],
+  "CN": "ca",
+  "ca": {
+    "expiry": "87600h"
+  }
+}

hack/scripts-dev/docker-dns-srv/certs-gateway/ca.crt

@@ -0,0 +1,22 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----

hack/scripts-dev/docker-dns-srv/certs-gateway/gencert.json

@@ -0,0 +1,13 @@
+{
+  "signing": {
+    "default": {
+        "usages": [
+          "signing",
+          "key encipherment",
+          "server auth",
+          "client auth"
+        ],
+        "expiry": "87600h"
+    }
+  }
+}

hack/scripts-dev/docker-dns-srv/certs-gateway/gencerts.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+if ! [[ "$0" =~ "./gencerts.sh" ]]; then
+	echo "must be run from 'fixtures'"
+	exit 255
+fi
+
+if ! which cfssl; then
+	echo "cfssl is not installed"
+	exit 255
+fi
+
+cfssl gencert --initca=true ./ca-csr.json | cfssljson --bare ./ca
+mv ca.pem ca.crt
+openssl x509 -in ca.crt -noout -text
+
+# generate wildcard certificates DNS: *.etcd.local
+cfssl gencert \
+    --ca ./ca.crt \
+    --ca-key ./ca-key.pem \
+    --config ./gencert.json \
+    ./server-ca-csr.json | cfssljson --bare ./server
+mv server.pem server.crt
+mv server-key.pem server.key.insecure
+
+rm -f *.csr *.pem *.stderr *.txt

hack/scripts-dev/docker-dns-srv/certs-gateway/run.sh

@@ -0,0 +1,47 @@
+#!/bin/sh
+rm -rf /tmp/m1.data /tmp/m2.data /tmp/m3.data
+
+/etc/init.d/bind9 start
+
+# get rid of hosts so go lookup won't resolve 127.0.0.1 to localhost
+cat /dev/null >/etc/hosts
+
+goreman -f /certs-gateway/Procfile start &
+
+# TODO: remove random sleeps
+sleep 7s
+
+ETCDCTL_API=3 ./etcdctl \
+  --cacert=/certs-gateway/ca.crt \
+  --cert=/certs-gateway/server.crt \
+  --key=/certs-gateway/server.key.insecure \
+  --discovery-srv etcd.local \
+  endpoint health --cluster
+
+ETCDCTL_API=3 ./etcdctl \
+  --cacert=/certs-gateway/ca.crt \
+  --cert=/certs-gateway/server.crt \
+  --key=/certs-gateway/server.key.insecure \
+  --discovery-srv etcd.local \
+  put abc def
+
+ETCDCTL_API=3 ./etcdctl \
+  --cacert=/certs-gateway/ca.crt \
+  --cert=/certs-gateway/server.crt \
+  --key=/certs-gateway/server.key.insecure \
+  --discovery-srv etcd.local \
+  get abc
+
+ETCDCTL_API=3 ./etcdctl \
+  --cacert=/certs-gateway/ca.crt \
+  --cert=/certs-gateway/server.crt \
+  --key=/certs-gateway/server.key.insecure \
+  --endpoints=127.0.0.1:23790 \
+  put ghi jkl
+
+ETCDCTL_API=3 ./etcdctl \
+  --cacert=/certs-gateway/ca.crt \
+  --cert=/certs-gateway/server.crt \
+  --key=/certs-gateway/server.key.insecure \
+  --endpoints=127.0.0.1:23790 \
+  get ghi

hack/scripts-dev/docker-dns-srv/certs-gateway/server-ca-csr.json

@@ -0,0 +1,23 @@
+{
+  "key": {
+    "algo": "rsa",
+    "size": 2048
+  },
+  "names": [
+    {
+      "O": "etcd",
+      "OU": "etcd Security",
+      "L": "San Francisco",
+      "ST": "California",
+      "C": "USA"
+    }
+  ],
+  "hosts": [
+    "m1.etcd.local",
+    "m2.etcd.local",
+    "m3.etcd.local",
+    "etcd.local",
+    "127.0.0.1",
+    "localhost"
+  ]
+}

hack/scripts-dev/docker-dns-srv/certs-gateway/server.crt

@@ -0,0 +1,25 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----

hack/scripts-dev/docker-dns-srv/certs-gateway/server.key.insecure

@@ -0,0 +1,27 @@
+-----BEGIN RSA PRIVATE KEY-----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+-----END RSA PRIVATE KEY-----

hack/scripts-dev/docker-dns-srv/certs-wildcard/Procfile

@@ -0,0 +1,5 @@
+etcd1: ./etcd --name m1 --data-dir /tmp/m1.data --listen-client-urls https://127.0.0.1:2379 --advertise-client-urls https://m1.etcd.local:2379 --listen-peer-urls https://127.0.0.1:2380 --initial-advertise-peer-urls=https://m1.etcd.local:2380 --initial-cluster-token tkn --discovery-srv=etcd.local --initial-cluster-state new --peer-cert-file=/certs-wildcard/server.crt --peer-key-file=/certs-wildcard/server.key.insecure --peer-trusted-ca-file=/certs-wildcard/ca.crt --peer-client-cert-auth --cert-file=/certs-wildcard/server.crt --key-file=/certs-wildcard/server.key.insecure --trusted-ca-file=/certs-wildcard/ca.crt --client-cert-auth
+
+etcd2: ./etcd --name m2 --data-dir /tmp/m2.data --listen-client-urls https://127.0.0.1:22379 --advertise-client-urls https://m2.etcd.local:22379 --listen-peer-urls https://127.0.0.1:22380 --initial-advertise-peer-urls=https://m2.etcd.local:22380 --initial-cluster-token tkn --discovery-srv=etcd.local --initial-cluster-state new --peer-cert-file=/certs-wildcard/server.crt --peer-key-file=/certs-wildcard/server.key.insecure --peer-trusted-ca-file=/certs-wildcard/ca.crt --peer-client-cert-auth --cert-file=/certs-wildcard/server.crt --key-file=/certs-wildcard/server.key.insecure --trusted-ca-file=/certs-wildcard/ca.crt --client-cert-auth
+
+etcd3: ./etcd --name m3 --data-dir /tmp/m3.data --listen-client-urls https://127.0.0.1:32379 --advertise-client-urls https://m3.etcd.local:32379 --listen-peer-urls https://127.0.0.1:32380 --initial-advertise-peer-urls=https://m3.etcd.local:32380 --initial-cluster-token tkn --discovery-srv=etcd.local --initial-cluster-state new --peer-cert-file=/certs-wildcard/server.crt --peer-key-file=/certs-wildcard/server.key.insecure --peer-trusted-ca-file=/certs-wildcard/ca.crt --peer-client-cert-auth --cert-file=/certs-wildcard/server.crt --key-file=/certs-wildcard/server.key.insecure --trusted-ca-file=/certs-wildcard/ca.crt --client-cert-auth

hack/scripts-dev/docker-dns-srv/certs-wildcard/ca-csr.json

@@ -0,0 +1,19 @@
+{
+  "key": {
+    "algo": "rsa",
+    "size": 2048
+  },
+  "names": [
+    {
+      "O": "etcd",
+      "OU": "etcd Security",
+      "L": "San Francisco",
+      "ST": "California",
+      "C": "USA"
+    }
+  ],
+  "CN": "ca",
+  "ca": {
+    "expiry": "87600h"
+  }
+}