mirror of
https://github.com/git/git.git
synced 2024-11-01 06:47:52 +01:00
905f27b86a
The usual way to do a full repack (and what is done by git-gc) is to run "repack -Ad --unpack-unreachable=<when>", which will loosen any unreachable objects newer than "<when>", and drop any older ones. This is a safer alternative to "repack -ad", because "<when>" becomes a grace period during which we will not drop any new objects that are about to be referenced. However, it isn't perfectly safe. It's always possible that a process is about to reference an old object. Even if that process were to take care to update the timestamp on the object, there is no atomicity with a simultaneously running "repack" process. So while unlikely, there is a small race wherein we may drop an object that is in the process of being referenced. If you do automated repacking on a large number of active repositories, you may hit it eventually, and the result is a corrupted repository. It would be nice to fix that race in the long run, but it's complicated. In the meantime, there is a much simpler strategy for automated repository maintenance: do not drop objects at all. We already have a "--keep-unreachable" option in pack-objects; we just need to plumb it through from git-repack. Note that this _isn't_ plumbed through from git-gc, so at this point it's strictly a tool for people doing their own advanced repository maintenance strategy. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
140 lines
4 KiB
Bash
Executable file
140 lines
4 KiB
Bash
Executable file
#!/bin/sh
|
|
|
|
test_description='git repack works correctly'
|
|
|
|
. ./test-lib.sh
|
|
|
|
fsha1=
|
|
csha1=
|
|
tsha1=
|
|
|
|
test_expect_success '-A with -d option leaves unreachable objects unpacked' '
|
|
echo content > file1 &&
|
|
git add . &&
|
|
test_tick &&
|
|
git commit -m initial_commit &&
|
|
# create a transient branch with unique content
|
|
git checkout -b transient_branch &&
|
|
echo more content >> file1 &&
|
|
# record the objects created in the database for file, commit, tree
|
|
fsha1=$(git hash-object file1) &&
|
|
test_tick &&
|
|
git commit -a -m more_content &&
|
|
csha1=$(git rev-parse HEAD^{commit}) &&
|
|
tsha1=$(git rev-parse HEAD^{tree}) &&
|
|
git checkout master &&
|
|
echo even more content >> file1 &&
|
|
test_tick &&
|
|
git commit -a -m even_more_content &&
|
|
# delete the transient branch
|
|
git branch -D transient_branch &&
|
|
# pack the repo
|
|
git repack -A -d -l &&
|
|
# verify objects are packed in repository
|
|
test 3 = $(git verify-pack -v -- .git/objects/pack/*.idx |
|
|
egrep "^($fsha1|$csha1|$tsha1) " |
|
|
sort | uniq | wc -l) &&
|
|
git show $fsha1 &&
|
|
git show $csha1 &&
|
|
git show $tsha1 &&
|
|
# now expire the reflog, while keeping reachable ones but expiring
|
|
# unreachables immediately
|
|
test_tick &&
|
|
sometimeago=$(( $test_tick - 10000 )) &&
|
|
git reflog expire --expire=$sometimeago --expire-unreachable=$test_tick --all &&
|
|
# and repack
|
|
git repack -A -d -l &&
|
|
# verify objects are retained unpacked
|
|
test 0 = $(git verify-pack -v -- .git/objects/pack/*.idx |
|
|
egrep "^($fsha1|$csha1|$tsha1) " |
|
|
sort | uniq | wc -l) &&
|
|
git show $fsha1 &&
|
|
git show $csha1 &&
|
|
git show $tsha1
|
|
'
|
|
|
|
compare_mtimes ()
|
|
{
|
|
read tref rest &&
|
|
while read t rest; do
|
|
test "$tref" = "$t" || return 1
|
|
done
|
|
}
|
|
|
|
test_expect_success '-A without -d option leaves unreachable objects packed' '
|
|
fsha1path=$(echo "$fsha1" | sed -e "s|\(..\)|\1/|") &&
|
|
fsha1path=".git/objects/$fsha1path" &&
|
|
csha1path=$(echo "$csha1" | sed -e "s|\(..\)|\1/|") &&
|
|
csha1path=".git/objects/$csha1path" &&
|
|
tsha1path=$(echo "$tsha1" | sed -e "s|\(..\)|\1/|") &&
|
|
tsha1path=".git/objects/$tsha1path" &&
|
|
git branch transient_branch $csha1 &&
|
|
git repack -a -d -l &&
|
|
test ! -f "$fsha1path" &&
|
|
test ! -f "$csha1path" &&
|
|
test ! -f "$tsha1path" &&
|
|
test 1 = $(ls -1 .git/objects/pack/pack-*.pack | wc -l) &&
|
|
packfile=$(ls .git/objects/pack/pack-*.pack) &&
|
|
git branch -D transient_branch &&
|
|
test_tick &&
|
|
git repack -A -l &&
|
|
test ! -f "$fsha1path" &&
|
|
test ! -f "$csha1path" &&
|
|
test ! -f "$tsha1path" &&
|
|
git show $fsha1 &&
|
|
git show $csha1 &&
|
|
git show $tsha1
|
|
'
|
|
|
|
test_expect_success 'unpacked objects receive timestamp of pack file' '
|
|
tmppack=".git/objects/pack/tmp_pack" &&
|
|
ln "$packfile" "$tmppack" &&
|
|
git repack -A -l -d &&
|
|
test-chmtime -v +0 "$tmppack" "$fsha1path" "$csha1path" "$tsha1path" \
|
|
> mtimes &&
|
|
compare_mtimes < mtimes
|
|
'
|
|
|
|
test_expect_success 'do not bother loosening old objects' '
|
|
obj1=$(echo one | git hash-object -w --stdin) &&
|
|
obj2=$(echo two | git hash-object -w --stdin) &&
|
|
pack1=$(echo $obj1 | git pack-objects .git/objects/pack/pack) &&
|
|
pack2=$(echo $obj2 | git pack-objects .git/objects/pack/pack) &&
|
|
git prune-packed &&
|
|
git cat-file -p $obj1 &&
|
|
git cat-file -p $obj2 &&
|
|
test-chmtime =-86400 .git/objects/pack/pack-$pack2.pack &&
|
|
git repack -A -d --unpack-unreachable=1.hour.ago &&
|
|
git cat-file -p $obj1 &&
|
|
test_must_fail git cat-file -p $obj2
|
|
'
|
|
|
|
test_expect_success 'keep packed objects found only in index' '
|
|
echo my-unique-content >file &&
|
|
git add file &&
|
|
git commit -m "make it reachable" &&
|
|
git gc &&
|
|
git reset HEAD^ &&
|
|
git reflog expire --expire=now --all &&
|
|
git add file &&
|
|
test-chmtime =-86400 .git/objects/pack/* &&
|
|
git gc --prune=1.hour.ago &&
|
|
git cat-file blob :file
|
|
'
|
|
|
|
test_expect_success 'repack -k keeps unreachable packed objects' '
|
|
# create packed-but-unreachable object
|
|
sha1=$(echo unreachable-packed | git hash-object -w --stdin) &&
|
|
pack=$(echo $sha1 | git pack-objects .git/objects/pack/pack) &&
|
|
git prune-packed &&
|
|
|
|
# -k should keep it
|
|
git repack -adk &&
|
|
git cat-file -p $sha1 &&
|
|
|
|
# and double check that without -k it would have been removed
|
|
git repack -ad &&
|
|
test_must_fail git cat-file -p $sha1
|
|
'
|
|
|
|
test_done
|