1
0
mirror of https://github.com/git/git.git synced 2024-10-19 14:08:16 +02:00
git/t/t7700-repack.sh
Taylor Blau 197443e80a repack: don't remove .keep packs with --pack-kept-objects
`git repack` supports a `--pack-kept-objects` flag which more or less
translates to whether or not we pass `--honor-pack-keep` down to `git
pack-objects` when assembling a new pack.

This behavior has existed since ee34a2bead (repack: add
`repack.packKeptObjects` config var, 2014-03-03). In that commit, the
documentation was extended to say:

    [...] Note that we still do not delete `.keep` packs after
    `pack-objects` finishes.

Unfortunately, this is not the case when `--pack-kept-objects` is
combined with a `--geometric` repack. When doing a geometric repack, we
include `.keep` packs when enumerating available packs only when
`pack_kept_objects` is set.

So this all works fine when `--no-pack-kept-objects` (or similar) is
given. Kept packs are excluded from the geometric roll-up, so when we go
to delete redundant packs (with `-d`), no `.keep` packs appear "below
the split" in our geometric progression.

But when `--pack-kept-objects` is given, things can go awry. Namely,
when a kept pack is included in the list of packs tracked by the
`pack_geometry` struct *and* part of the pack roll-up, we will delete
the `.keep` pack when we shouldn't.

Note that this *doesn't* result in object corruption, since the `.keep`
pack's objects are still present in the new pack. But the `.keep` pack
itself is removed, which violates our promise from back in ee34a2bead.

But there's more. Because `repack` computes the geometric roll-up
independently from selecting which packs belong in a MIDX (with
`--write-midx`), this can lead to odd behavior. Consider when a `.keep`
pack appears below the geometric split (ie., its objects will be part of
the new pack we generate).

We'll write a MIDX containing the new pack along with the existing
`.keep` pack. But because the `.keep` pack appears below the geometric
split line, we'll (incorrectly) try to remove it. While this doesn't
corrupt the repository, it does cause us to remove the MIDX we just
wrote, since removing that pack would invalidate the new MIDX.

Funny enough, this behavior became far less noticeable after e4d0c11c04
(repack: respect kept objects with '--write-midx -b', 2021-12-20), which
made `pack_kept_objects` be enabled by default only when we were writing
a non-MIDX bitmap.

But e4d0c11c04 didn't resolve this bug, it just made it harder to notice
unless callers explicitly passed `--pack-kept-objects`.

The solution is to avoid trying to remove `.keep` packs during
`--geometric` repacks, even when they appear below the geometric split
line, which is the approach this patch implements.

Co-authored-by: Victoria Dye <vdye@github.com>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-10-17 21:29:23 -07:00

510 lines
14 KiB
Bash
Executable File

#!/bin/sh
test_description='git repack works correctly'
. ./test-lib.sh
. "${TEST_DIRECTORY}/lib-bitmap.sh"
. "${TEST_DIRECTORY}/lib-midx.sh"
. "${TEST_DIRECTORY}/lib-terminal.sh"
commit_and_pack () {
test_commit "$@" 1>&2 &&
incrpackid=$(git pack-objects --all --unpacked --incremental .git/objects/pack/pack </dev/null) &&
echo pack-${incrpackid}.pack
}
test_no_missing_in_packs () {
myidx=$(ls -1 .git/objects/pack/*.idx) &&
test_path_is_file "$myidx" &&
git verify-pack -v alt_objects/pack/*.idx >orig.raw &&
sed -n -e "s/^\($OID_REGEX\).*/\1/p" orig.raw | sort >orig &&
git verify-pack -v $myidx >dest.raw &&
cut -d" " -f1 dest.raw | sort >dest &&
comm -23 orig dest >missing &&
test_must_be_empty missing
}
# we expect $packid and $oid to be defined
test_has_duplicate_object () {
want_duplicate_object="$1"
found_duplicate_object=false
for p in .git/objects/pack/*.idx
do
idx=$(basename $p)
test "pack-$packid.idx" = "$idx" && continue
git verify-pack -v $p >packlist || return $?
if grep "^$oid" packlist
then
found_duplicate_object=true
echo "DUPLICATE OBJECT FOUND"
break
fi
done &&
test "$want_duplicate_object" = "$found_duplicate_object"
}
test_expect_success 'objects in packs marked .keep are not repacked' '
echo content1 >file1 &&
echo content2 >file2 &&
git add . &&
test_tick &&
git commit -m initial_commit &&
# Create two packs
# The first pack will contain all of the objects except one
git rev-list --objects --all >objs &&
grep -v file2 objs | git pack-objects pack &&
# The second pack will contain the excluded object
packid=$(grep file2 objs | git pack-objects pack) &&
>pack-$packid.keep &&
git verify-pack -v pack-$packid.idx >packlist &&
oid=$(head -n 1 packlist | sed -e "s/^\($OID_REGEX\).*/\1/") &&
mv pack-* .git/objects/pack/ &&
git repack -A -d -l &&
git prune-packed &&
test_has_duplicate_object false
'
test_expect_success 'writing bitmaps via command-line can duplicate .keep objects' '
# build on $oid, $packid, and .keep state from previous
GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 git repack -Adbl &&
test_has_duplicate_object true
'
test_expect_success 'writing bitmaps via config can duplicate .keep objects' '
# build on $oid, $packid, and .keep state from previous
GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 \
git -c repack.writebitmaps=true repack -Adl &&
test_has_duplicate_object true
'
test_expect_success 'loose objects in alternate ODB are not repacked' '
mkdir alt_objects &&
echo $(pwd)/alt_objects >.git/objects/info/alternates &&
echo content3 >file3 &&
oid=$(GIT_OBJECT_DIRECTORY=alt_objects git hash-object -w file3) &&
git add file3 &&
test_tick &&
git commit -m commit_file3 &&
git repack -a -d -l &&
git prune-packed &&
test_has_duplicate_object false
'
test_expect_success 'packed obs in alt ODB are repacked even when local repo is packless' '
mkdir alt_objects/pack &&
mv .git/objects/pack/* alt_objects/pack &&
git repack -a &&
test_no_missing_in_packs
'
test_expect_success 'packed obs in alt ODB are repacked when local repo has packs' '
rm -f .git/objects/pack/* &&
echo new_content >>file1 &&
git add file1 &&
test_tick &&
git commit -m more_content &&
git repack &&
git repack -a -d &&
test_no_missing_in_packs
'
test_expect_success 'packed obs in alternate ODB kept pack are repacked' '
# swap the .keep so the commit object is in the pack with .keep
for p in alt_objects/pack/*.pack
do
base_name=$(basename $p .pack) &&
if test_path_is_file alt_objects/pack/$base_name.keep
then
rm alt_objects/pack/$base_name.keep
else
touch alt_objects/pack/$base_name.keep
fi || return 1
done &&
git repack -a -d &&
test_no_missing_in_packs
'
test_expect_success 'packed unreachable obs in alternate ODB are not loosened' '
rm -f alt_objects/pack/*.keep &&
mv .git/objects/pack/* alt_objects/pack/ &&
coid=$(git rev-parse HEAD^{commit}) &&
git reset --hard HEAD^ &&
test_tick &&
git reflog expire --expire=$test_tick --expire-unreachable=$test_tick --all &&
# The pack-objects call on the next line is equivalent to
# git repack -A -d without the call to prune-packed
git pack-objects --honor-pack-keep --non-empty --all --reflog \
--unpack-unreachable </dev/null pack &&
rm -f .git/objects/pack/* &&
mv pack-* .git/objects/pack/ &&
git verify-pack -v -- .git/objects/pack/*.idx >packlist &&
! grep "^$coid " packlist &&
echo >.git/objects/info/alternates &&
test_must_fail git show $coid
'
test_expect_success 'local packed unreachable obs that exist in alternate ODB are not loosened' '
echo $(pwd)/alt_objects >.git/objects/info/alternates &&
echo "$coid" | git pack-objects --non-empty --all --reflog pack &&
rm -f .git/objects/pack/* &&
mv pack-* .git/objects/pack/ &&
# The pack-objects call on the next line is equivalent to
# git repack -A -d without the call to prune-packed
git pack-objects --honor-pack-keep --non-empty --all --reflog \
--unpack-unreachable </dev/null pack &&
rm -f .git/objects/pack/* &&
mv pack-* .git/objects/pack/ &&
git verify-pack -v -- .git/objects/pack/*.idx >packlist &&
! grep "^$coid " &&
echo >.git/objects/info/alternates &&
test_must_fail git show $coid
'
test_expect_success 'objects made unreachable by grafts only are kept' '
test_tick &&
git commit --allow-empty -m "commit 4" &&
H0=$(git rev-parse HEAD) &&
H1=$(git rev-parse HEAD^) &&
H2=$(git rev-parse HEAD^^) &&
echo "$H0 $H2" >.git/info/grafts &&
git reflog expire --expire=$test_tick --expire-unreachable=$test_tick --all &&
git repack -a -d &&
git cat-file -t $H1
'
test_expect_success 'repack --keep-pack' '
test_create_repo keep-pack &&
(
cd keep-pack &&
P1=$(commit_and_pack 1) &&
P2=$(commit_and_pack 2) &&
P3=$(commit_and_pack 3) &&
P4=$(commit_and_pack 4) &&
ls .git/objects/pack/*.pack >old-counts &&
test_line_count = 4 old-counts &&
git repack -a -d --keep-pack $P1 --keep-pack $P4 &&
ls .git/objects/pack/*.pack >new-counts &&
grep -q $P1 new-counts &&
grep -q $P4 new-counts &&
test_line_count = 3 new-counts &&
git fsck
)
'
test_expect_success 'bitmaps are created by default in bare repos' '
git clone --bare .git bare.git &&
rm -f bare.git/objects/pack/*.bitmap &&
GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 \
git -C bare.git repack -ad &&
bitmap=$(ls bare.git/objects/pack/*.bitmap) &&
test_path_is_file "$bitmap"
'
test_expect_success 'incremental repack does not complain' '
git -C bare.git repack -q 2>repack.err &&
test_must_be_empty repack.err
'
test_expect_success 'bitmaps can be disabled on bare repos' '
GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 \
git -c repack.writeBitmaps=false -C bare.git repack -ad &&
bitmap=$(ls bare.git/objects/pack/*.bitmap || :) &&
test -z "$bitmap"
'
test_expect_success 'no bitmaps created if .keep files present' '
pack=$(ls bare.git/objects/pack/*.pack) &&
test_path_is_file "$pack" &&
keep=${pack%.pack}.keep &&
test_when_finished "rm -f \"\$keep\"" &&
>"$keep" &&
GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 \
git -C bare.git repack -ad 2>stderr &&
test_must_be_empty stderr &&
find bare.git/objects/pack/ -type f -name "*.bitmap" >actual &&
test_must_be_empty actual
'
test_expect_success 'auto-bitmaps do not complain if unavailable' '
test_config -C bare.git pack.packSizeLimit 1M &&
blob=$(test-tool genrandom big $((1024*1024)) |
git -C bare.git hash-object -w --stdin) &&
git -C bare.git update-ref refs/tags/big $blob &&
GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 \
git -C bare.git repack -ad 2>stderr &&
test_must_be_empty stderr &&
find bare.git/objects/pack -type f -name "*.bitmap" >actual &&
test_must_be_empty actual
'
objdir=.git/objects
midx=$objdir/pack/multi-pack-index
test_expect_success 'setup for --write-midx tests' '
git init midx &&
(
cd midx &&
git config core.multiPackIndex true &&
test_commit base
)
'
test_expect_success '--write-midx unchanged' '
(
cd midx &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack &&
test_path_is_missing $midx &&
test_path_is_missing $midx-*.bitmap &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack --write-midx &&
test_path_is_file $midx &&
test_path_is_missing $midx-*.bitmap &&
test_midx_consistent $objdir
)
'
test_expect_success '--write-midx with a new pack' '
(
cd midx &&
test_commit loose &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack --write-midx &&
test_path_is_file $midx &&
test_path_is_missing $midx-*.bitmap &&
test_midx_consistent $objdir
)
'
test_expect_success '--write-midx with -b' '
(
cd midx &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack -mb &&
test_path_is_file $midx &&
test_path_is_file $midx-*.bitmap &&
test_midx_consistent $objdir
)
'
test_expect_success '--write-midx with -d' '
(
cd midx &&
test_commit repack &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack -Ad --write-midx &&
test_path_is_file $midx &&
test_path_is_missing $midx-*.bitmap &&
test_midx_consistent $objdir
)
'
test_expect_success 'cleans up MIDX when appropriate' '
(
cd midx &&
test_commit repack-2 &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack -Adb --write-midx &&
checksum=$(midx_checksum $objdir) &&
test_path_is_file $midx &&
test_path_is_file $midx-$checksum.bitmap &&
test_commit repack-3 &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack -Adb --write-midx &&
test_path_is_file $midx &&
test_path_is_missing $midx-$checksum.bitmap &&
test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
test_commit repack-4 &&
GIT_TEST_MULTI_PACK_INDEX=0 git repack -Adb &&
find $objdir/pack -type f -name "multi-pack-index*" >files &&
test_must_be_empty files
)
'
test_expect_success '--write-midx with preferred bitmap tips' '
git init midx-preferred-tips &&
test_when_finished "rm -fr midx-preferred-tips" &&
(
cd midx-preferred-tips &&
test_commit_bulk --message="%s" 103 &&
git log --format="%H" >commits.raw &&
sort <commits.raw >commits &&
git log --format="create refs/tags/%s/%s %H" HEAD >refs &&
git update-ref --stdin <refs &&
git repack --write-midx --write-bitmap-index &&
test_path_is_file $midx &&
test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
test-tool bitmap list-commits | sort >bitmaps &&
comm -13 bitmaps commits >before &&
test_line_count = 1 before &&
rm -fr $midx-$(midx_checksum $objdir).bitmap &&
rm -fr $midx &&
# instead of constructing the snapshot ourselves (c.f., the test
# "write a bitmap with --refs-snapshot (preferred tips)" in
# t5326), mark the missing commit as preferred by adding it to
# the pack.preferBitmapTips configuration.
git for-each-ref --format="%(refname:rstrip=1)" \
--points-at="$(cat before)" >missing &&
git config pack.preferBitmapTips "$(cat missing)" &&
git repack --write-midx --write-bitmap-index &&
test-tool bitmap list-commits | sort >bitmaps &&
comm -13 bitmaps commits >after &&
! test_cmp before after
)
'
# The first argument is expected to be a filename
# and that file should contain the name of a .idx
# file. Send the list of objects in that .idx file
# into stdout.
get_sorted_objects_from_pack () {
git show-index <$(cat "$1") >raw &&
cut -d" " -f2 raw
}
test_expect_success '--write-midx -b packs non-kept objects' '
git init repo &&
test_when_finished "rm -fr repo" &&
(
cd repo &&
# Create a kept pack-file
test_commit base &&
git repack -ad &&
find $objdir/pack -name "*.idx" >before &&
test_line_count = 1 before &&
before_name=$(cat before) &&
>${before_name%.idx}.keep &&
# Create a non-kept pack-file
test_commit other &&
git repack &&
# Create loose objects
test_commit loose &&
# Repack everything
git repack --write-midx -a -b -d &&
# There should be two pack-files now, the
# old, kept pack and the new, non-kept pack.
find $objdir/pack -name "*.idx" | sort >after &&
test_line_count = 2 after &&
find $objdir/pack -name "*.keep" >kept &&
kept_name=$(cat kept) &&
echo ${kept_name%.keep}.idx >kept-idx &&
test_cmp before kept-idx &&
# Get object list from the kept pack.
get_sorted_objects_from_pack before >old.objects &&
# Get object list from the one non-kept pack-file
comm -13 before after >new-pack &&
test_line_count = 1 new-pack &&
get_sorted_objects_from_pack new-pack >new.objects &&
# None of the objects in the new pack should
# exist within the kept pack.
comm -12 old.objects new.objects >shared.objects &&
test_must_be_empty shared.objects
)
'
test_expect_success '--write-midx with --pack-kept-objects' '
git init repo &&
test_when_finished "rm -fr repo" &&
(
cd repo &&
test_commit one &&
test_commit two &&
one="$(echo "one" | git pack-objects --revs $objdir/pack/pack)" &&
two="$(echo "one..two" | git pack-objects --revs $objdir/pack/pack)" &&
keep="$objdir/pack/pack-$one.keep" &&
touch "$keep" &&
git repack --write-midx --write-bitmap-index --geometric=2 -d \
--pack-kept-objects &&
test_path_is_file $keep &&
test_path_is_file $midx &&
test_path_is_file $midx-$(midx_checksum $objdir).bitmap
)
'
test_expect_success TTY '--quiet disables progress' '
test_terminal env GIT_PROGRESS_DELAY=0 \
git -C midx repack -ad --quiet --write-midx 2>stderr &&
test_must_be_empty stderr
'
test_expect_success 'setup for update-server-info' '
git init update-server-info &&
test_commit -C update-server-info message
'
test_server_info_present () {
test_path_is_file update-server-info/.git/objects/info/packs &&
test_path_is_file update-server-info/.git/info/refs
}
test_server_info_missing () {
test_path_is_missing update-server-info/.git/objects/info/packs &&
test_path_is_missing update-server-info/.git/info/refs
}
test_server_info_cleanup () {
rm -f update-server-info/.git/objects/info/packs update-server-info/.git/info/refs &&
test_server_info_missing
}
test_expect_success 'updates server info by default' '
test_server_info_cleanup &&
git -C update-server-info repack &&
test_server_info_present
'
test_expect_success '-n skips updating server info' '
test_server_info_cleanup &&
git -C update-server-info repack -n &&
test_server_info_missing
'
test_expect_success 'repack.updateServerInfo=true updates server info' '
test_server_info_cleanup &&
git -C update-server-info -c repack.updateServerInfo=true repack &&
test_server_info_present
'
test_expect_success 'repack.updateServerInfo=false skips updating server info' '
test_server_info_cleanup &&
git -C update-server-info -c repack.updateServerInfo=false repack &&
test_server_info_missing
'
test_expect_success '-n overrides repack.updateServerInfo=true' '
test_server_info_cleanup &&
git -C update-server-info -c repack.updateServerInfo=true repack -n &&
test_server_info_missing
'
test_done