Merge branch 'jk/pack-bitmap'

Borrow the bitmap index into packfiles from JGit to speed up
enumeration of objects involved in a commit range without having to
fully traverse the history.

* jk/pack-bitmap: (26 commits)
  ewah: unconditionally ntohll ewah data
  ewah: support platforms that require aligned reads
  read-cache: use get_be32 instead of hand-rolled ntoh_l
  block-sha1: factor out get_be and put_be wrappers
  do not discard revindex when re-preparing packfiles
  pack-bitmap: implement optional name_hash cache
  t/perf: add tests for pack bitmaps
  t: add basic bitmap functionality tests
  count-objects: recognize .bitmap in garbage-checking
  repack: consider bitmaps when performing repacks
  repack: handle optional files created by pack-objects
  repack: turn exts array into array-of-struct
  repack: stop using magic number for ARRAY_SIZE(exts)
  pack-objects: implement bitmap writing
  rev-list: add bitmap mode to speed up object lists
  pack-objects: use bitmaps when packing objects
  pack-objects: split add_object_entry
  pack-bitmap: add support for bitmap indexes
  documentation: add documentation for the bitmap format
  ewah: compressed bitmap implementation
  ...
This commit is contained in:
Junio C Hamano
2014-02-27 14:01:48 -08:00
33 changed files with 4735 additions and 275 deletions

57
t/perf/p5310-pack-bitmaps.sh Executable file
View File

@ -0,0 +1,57 @@
#!/bin/sh
test_description='Tests pack performance using bitmaps'
. ./perf-lib.sh
test_perf_large_repo
# note that we do everything through config,
# since we want to be able to compare bitmap-aware
# git versus non-bitmap git
test_expect_success 'setup bitmap config' '
git config pack.writebitmaps true &&
git config pack.writebitmaphashcache true
'
test_perf 'repack to disk' '
git repack -ad
'
test_perf 'simulated clone' '
git pack-objects --stdout --all </dev/null >/dev/null
'
test_perf 'simulated fetch' '
have=$(git rev-list HEAD~100 -1) &&
{
echo HEAD &&
echo ^$have
} | git pack-objects --revs --stdout >/dev/null
'
test_expect_success 'create partial bitmap state' '
# pick a commit to represent the repo tip in the past
cutoff=$(git rev-list HEAD~100 -1) &&
orig_tip=$(git rev-parse HEAD) &&
# now kill off all of the refs and pretend we had
# just the one tip
rm -rf .git/logs .git/refs/* .git/packed-refs
git update-ref HEAD $cutoff
# and then repack, which will leave us with a nice
# big bitmap pack of the "old" history, and all of
# the new history will be loose, as if it had been pushed
# up incrementally and exploded via unpack-objects
git repack -Ad
# and now restore our original tip, as if the pushes
# had happened
git update-ref HEAD $orig_tip
'
test_perf 'partial bitmap' '
git pack-objects --stdout --all </dev/null >/dev/null
'
test_done

139
t/t5310-pack-bitmaps.sh Executable file
View File

@ -0,0 +1,139 @@
#!/bin/sh
test_description='exercise basic bitmap functionality'
. ./test-lib.sh
test_expect_success 'setup repo with moderate-sized history' '
for i in $(test_seq 1 10); do
test_commit $i
done &&
git checkout -b other HEAD~5 &&
for i in $(test_seq 1 10); do
test_commit side-$i
done &&
git checkout master &&
blob=$(echo tagged-blob | git hash-object -w --stdin) &&
git tag tagged-blob $blob &&
git config pack.writebitmaps true &&
git config pack.writebitmaphashcache true
'
test_expect_success 'full repack creates bitmaps' '
git repack -ad &&
ls .git/objects/pack/ | grep bitmap >output &&
test_line_count = 1 output
'
test_expect_success 'rev-list --test-bitmap verifies bitmaps' '
git rev-list --test-bitmap HEAD
'
rev_list_tests() {
state=$1
test_expect_success "counting commits via bitmap ($state)" '
git rev-list --count HEAD >expect &&
git rev-list --use-bitmap-index --count HEAD >actual &&
test_cmp expect actual
'
test_expect_success "counting partial commits via bitmap ($state)" '
git rev-list --count HEAD~5..HEAD >expect &&
git rev-list --use-bitmap-index --count HEAD~5..HEAD >actual &&
test_cmp expect actual
'
test_expect_success "counting non-linear history ($state)" '
git rev-list --count other...master >expect &&
git rev-list --use-bitmap-index --count other...master >actual &&
test_cmp expect actual
'
test_expect_success "enumerate --objects ($state)" '
git rev-list --objects --use-bitmap-index HEAD >tmp &&
cut -d" " -f1 <tmp >tmp2 &&
sort <tmp2 >actual &&
git rev-list --objects HEAD >tmp &&
cut -d" " -f1 <tmp >tmp2 &&
sort <tmp2 >expect &&
test_cmp expect actual
'
test_expect_success "bitmap --objects handles non-commit objects ($state)" '
git rev-list --objects --use-bitmap-index HEAD tagged-blob >actual &&
grep $blob actual
'
}
rev_list_tests 'full bitmap'
test_expect_success 'clone from bitmapped repository' '
git clone --no-local --bare . clone.git &&
git rev-parse HEAD >expect &&
git --git-dir=clone.git rev-parse HEAD >actual &&
test_cmp expect actual
'
test_expect_success 'setup further non-bitmapped commits' '
for i in $(test_seq 1 10); do
test_commit further-$i
done
'
rev_list_tests 'partial bitmap'
test_expect_success 'fetch (partial bitmap)' '
git --git-dir=clone.git fetch origin master:master &&
git rev-parse HEAD >expect &&
git --git-dir=clone.git rev-parse HEAD >actual &&
test_cmp expect actual
'
test_expect_success 'incremental repack cannot create bitmaps' '
test_commit more-1 &&
test_must_fail git repack -d
'
test_expect_success 'incremental repack can disable bitmaps' '
test_commit more-2 &&
git repack -d --no-write-bitmap-index
'
test_expect_success 'full repack, reusing previous bitmaps' '
git repack -ad &&
ls .git/objects/pack/ | grep bitmap >output &&
test_line_count = 1 output
'
test_expect_success 'fetch (full bitmap)' '
git --git-dir=clone.git fetch origin master:master &&
git rev-parse HEAD >expect &&
git --git-dir=clone.git rev-parse HEAD >actual &&
test_cmp expect actual
'
test_lazy_prereq JGIT '
type jgit
'
test_expect_success JGIT 'we can read jgit bitmaps' '
git clone . compat-jgit &&
(
cd compat-jgit &&
rm -f .git/objects/pack/*.bitmap &&
jgit gc &&
git rev-list --test-bitmap HEAD
)
'
test_expect_success JGIT 'jgit can read our bitmaps' '
git clone . compat-us &&
(
cd compat-us &&
git repack -adb &&
# jgit gc will barf if it does not like our bitmaps
jgit gc
)
'
test_done