git/t/t7701-repack-unpack-unreachable.sh
Jeff King c90f9e13ab repack: pack objects mentioned by the index
When we pack all objects, we use only the objects reachable
from references and reflogs. This misses any objects which
are reachable from the index, but not yet referenced.

By itself this isn't a big deal; the objects can remain
loose until they are actually used in a commit. However, it
does create a problem when we drop packed but unreachable
objects. We try to optimize out the writing of objects that
we will immediately prune, which means we must follow the
same rules as prune in determining what is reachable. And
prune uses the index for this purpose.

This is rather uncommon in practice, as objects in the index
would not usually have been packed in the first place. But
it could happen in a sequence like:

  1. You make a commit on a branch that references blob X.

  2. You repack, moving X into the pack.

  3. You delete the branch (and its reflog), so that X is
     unreferenced.

  4. You "git add" blob X so that it is now referenced only
     by the index.

  5. You repack again with git-gc. The pack-objects we
     invoke will see that X is neither referenced nor
     recent and not bother loosening it.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-10-19 15:07:07 -07:00

125 lines
3.6 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" = "$t" || break
done
}
test_expect_success '-A without -d option leaves unreachable objects packed' '
fsha1path=$(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_done