git/t/t6500-gc.sh

420 lines
12 KiB
Bash
Raw Normal View History

#!/bin/sh
test_description='basic git gc tests
'
. ./test-lib.sh
. "$TEST_DIRECTORY"/lib-terminal.sh
test_expect_success 'setup' '
# do not let the amount of physical memory affects gc
# behavior, make sure we always pack everything to one pack by
# default
git config gc.bigPackThreshold 2g &&
# These are simply values which, when hashed as a blob with a newline,
# produce a hash where the first byte is 0x17 in their respective
# algorithms.
test_oid_cache <<-EOF
obj1 sha1:263
obj1 sha256:34
obj2 sha1:410
obj2 sha256:174
obj3 sha1:523
obj3 sha256:313
obj4 sha1:790
obj4 sha256:481
EOF
'
test_expect_success 'gc empty repository' '
git gc
'
test_expect_success 'gc does not leave behind pid file' '
git gc &&
test_path_is_missing .git/gc.pid
'
test_expect_success 'gc --gobbledegook' '
test_expect_code 129 git gc --nonsense 2>err &&
test_i18ngrep "[Uu]sage: git gc" err
'
test_expect_success 'gc -h with invalid configuration' '
mkdir broken &&
(
cd broken &&
git init &&
echo "[gc] pruneexpire = CORRUPT" >>.git/config &&
test_expect_code 129 git gc -h >usage 2>&1
) &&
test_i18ngrep "[Uu]sage" broken/usage
'
test_expect_success 'gc is not aborted due to a stale symref' '
git init remote &&
(
cd remote &&
test_commit initial &&
git clone . ../client &&
git branch -m develop &&
cd ../client &&
git fetch --prune &&
git gc
)
'
test_expect_success 'gc --keep-largest-pack' '
test_create_repo keep-pack &&
(
cd keep-pack &&
test_commit one &&
test_commit two &&
test_commit three &&
git gc &&
( cd .git/objects/pack && ls *.pack ) >pack-list &&
test_line_count = 1 pack-list &&
cp pack-list base-pack-list &&
test_commit four &&
git repack -d &&
test_commit five &&
git repack -d &&
( cd .git/objects/pack && ls *.pack ) >pack-list &&
test_line_count = 3 pack-list &&
git gc --keep-largest-pack &&
( cd .git/objects/pack && ls *.pack ) >pack-list &&
test_line_count = 2 pack-list &&
awk "/^P /{print \$2}" <.git/objects/info/packs >pack-info &&
test_line_count = 2 pack-info &&
test_path_is_file .git/objects/pack/$(cat base-pack-list) &&
git fsck
)
'
test_expect_success 'pre-auto-gc hook can stop auto gc' '
cat >err.expect <<-\EOF &&
no gc for you
EOF
git init pre-auto-gc-hook &&
test_hook -C pre-auto-gc-hook pre-auto-gc <<-\EOF &&
echo >&2 no gc for you &&
exit 1
EOF
(
cd pre-auto-gc-hook &&
git config gc.auto 3 &&
git config gc.autoDetach false &&
# We need to create two object whose sha1s start with 17
# since this is what git gc counts. As it happens, these
# two blobs will do so.
test_commit "$(test_oid obj1)" &&
test_commit "$(test_oid obj2)" &&
git gc --auto >../out.actual 2>../err.actual
) &&
test_must_be_empty out.actual &&
test_cmp err.expect err.actual &&
cat >err.expect <<-\EOF &&
will gc for you
Auto packing the repository for optimum performance.
See "git help gc" for manual housekeeping.
EOF
test_hook -C pre-auto-gc-hook --clobber pre-auto-gc <<-\EOF &&
echo >&2 will gc for you &&
exit 0
EOF
git -C pre-auto-gc-hook gc --auto >out.actual 2>err.actual &&
test_must_be_empty out.actual &&
test_cmp err.expect err.actual
'
test_expect_success 'auto gc with too many loose objects does not attempt to create bitmaps' '
test_config gc.auto 3 &&
test_config gc.autodetach false &&
test_config pack.writebitmaps true &&
# We need to create two object whose sha1s start with 17
# since this is what git gc counts. As it happens, these
# two blobs will do so.
test_commit "$(test_oid obj1)" &&
test_commit "$(test_oid obj2)" &&
# Our first gc will create a pack; our second will create a second pack
git gc --auto &&
ls .git/objects/pack/pack-*.pack | sort >existing_packs &&
test_commit "$(test_oid obj3)" &&
test_commit "$(test_oid obj4)" &&
git gc --auto 2>err &&
test_i18ngrep ! "^warning:" err &&
ls .git/objects/pack/pack-*.pack | sort >post_packs &&
comm -1 -3 existing_packs post_packs >new &&
comm -2 -3 existing_packs post_packs >del &&
test_line_count = 0 del && # No packs are deleted
test_line_count = 1 new # There is one new pack
'
test_expect_success 'gc --no-quiet' '
GIT_PROGRESS_DELAY=0 git -c gc.writeCommitGraph=true gc --no-quiet >stdout 2>stderr &&
test_must_be_empty stdout &&
test_i18ngrep "Computing commit graph generation numbers" stderr
'
test_expect_success TTY 'with TTY: gc --no-quiet' '
test_terminal env GIT_PROGRESS_DELAY=0 \
git -c gc.writeCommitGraph=true gc --no-quiet >stdout 2>stderr &&
test_must_be_empty stdout &&
test_i18ngrep "Enumerating objects" stderr &&
test_i18ngrep "Computing commit graph generation numbers" stderr
'
test_expect_success 'gc --quiet' '
git -c gc.writeCommitGraph=true gc --quiet >stdout 2>stderr &&
test_must_be_empty stdout &&
test_must_be_empty stderr
'
gc: handle & check gc.reflogExpire config Don't redundantly run "git reflog expire --all" when gc.reflogExpire and gc.reflogExpireUnreachable are set to "never", and die immediately if those configuration valuer are bad. As an earlier "assert lack of early exit" change to the tests for "git reflog expire" shows, an early check of gc.reflogExpire{Unreachable,} isn't wanted in general for "git reflog expire", but it makes sense for "gc" because: 1) Similarly to 8ab5aa4bd8 ("parseopt: handle malformed --expire arguments more nicely", 2018-04-21) we'll now die early if the config variables are set to invalid values. We run "pack-refs" before "reflog expire", which can take a while, only to then die on an invalid gc.reflogExpire{Unreachable,} configuration. 2) Not invoking the command at all means it won't show up in trace output, which makes what's going on more obvious when the two are set to "never". 3) As a later change documents we lock the refs when looping over the refs to expire, even in cases where we end up doing nothing due to this config. For the reasons noted in the earlier "assert lack of early exit" change I don't think it's worth it to bend over backwards in "git reflog expire" itself to carefully detect if we'll really do nothing given the combination of all its possible options and skip that locking, but that's easy to detect here in "gc" where we'll only run "reflog expire" in a relatively simple mode. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-03-28 16:14:34 +00:00
test_expect_success 'gc.reflogExpire{Unreachable,}=never skips "expire" via "gc"' '
test_config gc.reflogExpire never &&
test_config gc.reflogExpireUnreachable never &&
GIT_TRACE=$(pwd)/trace.out git gc &&
# Check that git-pack-refs is run as a sanity check (done via
# gc_before_repack()) but that git-expire is not.
grep -E "^trace: (built-in|exec|run_command): git pack-refs --" trace.out &&
! grep -E "^trace: (built-in|exec|run_command): git reflog expire --" trace.out
'
test_expect_success 'one of gc.reflogExpire{Unreachable,}=never does not skip "expire" via "gc"' '
>trace.out &&
test_config gc.reflogExpire never &&
GIT_TRACE=$(pwd)/trace.out git gc &&
grep -E "^trace: (built-in|exec|run_command): git reflog expire --" trace.out
'
test_expect_success 'gc.repackFilter launches repack with a filter' '
git clone --no-local --bare . bare.git &&
git -C bare.git -c gc.cruftPacks=false gc &&
test_stdout_line_count = 1 ls bare.git/objects/pack/*.pack &&
GIT_TRACE=$(pwd)/trace.out git -C bare.git -c gc.repackFilter=blob:none \
-c repack.writeBitmaps=false -c gc.cruftPacks=false gc &&
test_stdout_line_count = 2 ls bare.git/objects/pack/*.pack &&
grep -E "^trace: (built-in|exec|run_command): git repack .* --filter=blob:none ?.*" trace.out
'
test_expect_success 'gc.repackFilterTo store filtered out objects' '
test_when_finished "rm -rf bare.git filtered.git" &&
git init --bare filtered.git &&
git -C bare.git -c gc.repackFilter=blob:none \
-c gc.repackFilterTo=../filtered.git/objects/pack/pack \
-c repack.writeBitmaps=false -c gc.cruftPacks=false gc &&
test_stdout_line_count = 1 ls bare.git/objects/pack/*.pack &&
test_stdout_line_count = 1 ls filtered.git/objects/pack/*.pack
'
prepare_cruft_history () {
test_commit base &&
test_commit --no-tag foo &&
test_commit --no-tag bar &&
git reset HEAD^^
}
assert_no_cruft_packs () {
find .git/objects/pack -name "*.mtimes" >mtimes &&
test_must_be_empty mtimes
}
for argv in \
builtin/gc.c: make `gc.cruftPacks` enabled by default Back in 5b92477f89 (builtin/gc.c: conditionally avoid pruning objects via loose, 2022-05-20), `git gc` learned the `--cruft` option and `gc.cruftPacks` configuration to opt-in to writing cruft packs when collecting or pruning unreachable objects. Cruft packs were introduced with the merge in a50036da1a (Merge branch 'tb/cruft-packs', 2022-06-03). They address the problem of "loose object explosions", where Git will write out many individual loose objects when there is a large number of unreachable objects that have not yet aged past `--prune=<date>`. Instead of keeping track of those unreachable yet recent objects via their loose object file's mtime, cruft packs collect all unreachable objects into a single pack with a corresponding `*.mtimes` file that acts as a table to store the mtimes of all unreachable objects. This prevents the need to store unreachable objects as loose as they age out of the repository, and avoids the problem of loose object explosions. Beyond avoiding loose object explosions, cruft packs also act as a more efficient mechanism to store unreachable objects as they age out of a repository. This is because pairs of similar unreachable objects serve as delta bases for one another. In 5b92477f89, the feature was introduced as experimental. Since then, GitHub has been running these patches in every repository generating hundreds of millions of cruft packs along the way. The feature is battle-tested, and avoids many pathological cases such as above. Users who either run `git gc` manually, or via `git maintenance` can benefit from having cruft packs. As such, enable cruft pack generation to take place by default (by making `gc.cruftPacks` have the default of "true" rather than "false). Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-04-18 20:40:57 +00:00
"gc" \
"-c gc.cruftPacks=true gc" \
builtin/gc.c: make `gc.cruftPacks` enabled by default Back in 5b92477f89 (builtin/gc.c: conditionally avoid pruning objects via loose, 2022-05-20), `git gc` learned the `--cruft` option and `gc.cruftPacks` configuration to opt-in to writing cruft packs when collecting or pruning unreachable objects. Cruft packs were introduced with the merge in a50036da1a (Merge branch 'tb/cruft-packs', 2022-06-03). They address the problem of "loose object explosions", where Git will write out many individual loose objects when there is a large number of unreachable objects that have not yet aged past `--prune=<date>`. Instead of keeping track of those unreachable yet recent objects via their loose object file's mtime, cruft packs collect all unreachable objects into a single pack with a corresponding `*.mtimes` file that acts as a table to store the mtimes of all unreachable objects. This prevents the need to store unreachable objects as loose as they age out of the repository, and avoids the problem of loose object explosions. Beyond avoiding loose object explosions, cruft packs also act as a more efficient mechanism to store unreachable objects as they age out of a repository. This is because pairs of similar unreachable objects serve as delta bases for one another. In 5b92477f89, the feature was introduced as experimental. Since then, GitHub has been running these patches in every repository generating hundreds of millions of cruft packs along the way. The feature is battle-tested, and avoids many pathological cases such as above. Users who either run `git gc` manually, or via `git maintenance` can benefit from having cruft packs. As such, enable cruft pack generation to take place by default (by making `gc.cruftPacks` have the default of "true" rather than "false). Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-04-18 20:40:57 +00:00
"-c gc.cruftPacks=false gc --cruft"
do
test_expect_success "git $argv generates a cruft pack" '
test_when_finished "rm -fr repo" &&
git init repo &&
(
cd repo &&
prepare_cruft_history &&
git $argv &&
find .git/objects/pack -name "*.mtimes" >mtimes &&
sed -e 's/\.mtimes$/\.pack/g' mtimes >packs &&
test_file_not_empty packs &&
while read pack
do
test_path_is_file "$pack" || return 1
done <packs
)
'
done
for argv in \
builtin/gc.c: make `gc.cruftPacks` enabled by default Back in 5b92477f89 (builtin/gc.c: conditionally avoid pruning objects via loose, 2022-05-20), `git gc` learned the `--cruft` option and `gc.cruftPacks` configuration to opt-in to writing cruft packs when collecting or pruning unreachable objects. Cruft packs were introduced with the merge in a50036da1a (Merge branch 'tb/cruft-packs', 2022-06-03). They address the problem of "loose object explosions", where Git will write out many individual loose objects when there is a large number of unreachable objects that have not yet aged past `--prune=<date>`. Instead of keeping track of those unreachable yet recent objects via their loose object file's mtime, cruft packs collect all unreachable objects into a single pack with a corresponding `*.mtimes` file that acts as a table to store the mtimes of all unreachable objects. This prevents the need to store unreachable objects as loose as they age out of the repository, and avoids the problem of loose object explosions. Beyond avoiding loose object explosions, cruft packs also act as a more efficient mechanism to store unreachable objects as they age out of a repository. This is because pairs of similar unreachable objects serve as delta bases for one another. In 5b92477f89, the feature was introduced as experimental. Since then, GitHub has been running these patches in every repository generating hundreds of millions of cruft packs along the way. The feature is battle-tested, and avoids many pathological cases such as above. Users who either run `git gc` manually, or via `git maintenance` can benefit from having cruft packs. As such, enable cruft pack generation to take place by default (by making `gc.cruftPacks` have the default of "true" rather than "false). Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-04-18 20:40:57 +00:00
"gc --no-cruft" \
"-c gc.cruftPacks=false gc" \
builtin/gc.c: make `gc.cruftPacks` enabled by default Back in 5b92477f89 (builtin/gc.c: conditionally avoid pruning objects via loose, 2022-05-20), `git gc` learned the `--cruft` option and `gc.cruftPacks` configuration to opt-in to writing cruft packs when collecting or pruning unreachable objects. Cruft packs were introduced with the merge in a50036da1a (Merge branch 'tb/cruft-packs', 2022-06-03). They address the problem of "loose object explosions", where Git will write out many individual loose objects when there is a large number of unreachable objects that have not yet aged past `--prune=<date>`. Instead of keeping track of those unreachable yet recent objects via their loose object file's mtime, cruft packs collect all unreachable objects into a single pack with a corresponding `*.mtimes` file that acts as a table to store the mtimes of all unreachable objects. This prevents the need to store unreachable objects as loose as they age out of the repository, and avoids the problem of loose object explosions. Beyond avoiding loose object explosions, cruft packs also act as a more efficient mechanism to store unreachable objects as they age out of a repository. This is because pairs of similar unreachable objects serve as delta bases for one another. In 5b92477f89, the feature was introduced as experimental. Since then, GitHub has been running these patches in every repository generating hundreds of millions of cruft packs along the way. The feature is battle-tested, and avoids many pathological cases such as above. Users who either run `git gc` manually, or via `git maintenance` can benefit from having cruft packs. As such, enable cruft pack generation to take place by default (by making `gc.cruftPacks` have the default of "true" rather than "false). Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-04-18 20:40:57 +00:00
"-c gc.cruftPacks=true gc --no-cruft"
do
test_expect_success "git $argv does not generate a cruft pack" '
test_when_finished "rm -fr repo" &&
git init repo &&
(
cd repo &&
prepare_cruft_history &&
git $argv &&
assert_no_cruft_packs
)
'
done
builtin/gc.c: ignore cruft packs with `--keep-largest-pack` When cruft packs were implemented, we never adjusted the code for `git gc`'s `--keep-largest-pack` and `gc.bigPackThreshold` to ignore cruft packs. This option and configuration option share a common implementation, but including cruft packs is wrong in both cases: - Running `git gc --keep-largest-pack` in a repository where the largest pack is the cruft pack itself will make it impossible for `git gc` to prune objects, since the cruft pack itself is kept. - The same is true for `gc.bigPackThreshold`, if the size of the cruft pack exceeds the limit set by the caller. In the future, it is possible that `gc.bigPackThreshold` could be used to write a separate cruft pack containing any new unreachable objects that entered the repository since the last time a cruft pack was written. There are some complexities to doing so, mainly around handling pruning objects that are in an existing cruft pack that is above the threshold (which would either need to be rewritten, or else delay pruning). Rewriting a substantially similar cruft pack isn't ideal, but it is significantly better than the status-quo. If users have large cruft packs that they don't want to rewrite, they can mark them as `*.keep` packs. But in general, if a repository has a cruft pack that is so large it is slowing down GC's, it should probably be pruned anyway. In the meantime, ignore cruft packs in the common implementation for both of these options, and add a pair of tests to prevent any future regressions here. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-04-18 20:40:38 +00:00
test_expect_success '--keep-largest-pack ignores cruft packs' '
test_when_finished "rm -fr repo" &&
git init repo &&
(
cd repo &&
# Generate a pack for reachable objects (of which there
# are 3), and one for unreachable objects (of which
# there are 6).
prepare_cruft_history &&
git gc --cruft &&
mtimes="$(find .git/objects/pack -type f -name "pack-*.mtimes")" &&
sz="$(test_file_size "${mtimes%.mtimes}.pack")" &&
# Ensure that the cruft pack gets removed (due to
# `--prune=now`) despite it being the largest pack.
git -c gc.bigPackThreshold=$sz gc --cruft --prune=now &&
assert_no_cruft_packs
)
'
test_expect_success 'gc.bigPackThreshold ignores cruft packs' '
test_when_finished "rm -fr repo" &&
git init repo &&
(
cd repo &&
# Generate a pack for reachable objects (of which there
# are 3), and one for unreachable objects (of which
# there are 6).
prepare_cruft_history &&
git gc --cruft &&
# Ensure that the cruft pack gets removed (due to
# `--prune=now`) despite it being the largest pack.
git gc --cruft --prune=now --keep-largest-pack &&
assert_no_cruft_packs
)
'
builtin/repack.c: implement support for `--max-cruft-size` Cruft packs are an alternative mechanism for storing a collection of unreachable objects whose mtimes are recent enough to avoid being pruned out of the repository. When cruft packs were first introduced back in b757353676 (builtin/pack-objects.c: --cruft without expiration, 2022-05-20) and a7d493833f (builtin/pack-objects.c: --cruft with expiration, 2022-05-20), the recommended workflow consisted of: - Repacking periodically, either by packing anything loose in the repository (via `git repack -d`) or producing a geometric sequence of packs (via `git repack --geometric=<d> -d`). - Every so often, splitting the repository into two packs, one cruft to store the unreachable objects, and another non-cruft pack to store the reachable objects. Repositories may (out of band with the above) choose periodically to prune out some unreachable objects which have aged out of the grace period by generating a pack with `--cruft-expiration=<approxidate>`. This allowed repositories to maintain relatively few packs on average, and quarantine unreachable objects together in a cruft pack, avoiding the pitfalls of holding unreachable objects as loose while they age out (for more, see some of the details in 3d89a8c118 (Documentation/technical: add cruft-packs.txt, 2022-05-20)). This all works, but can be costly from an I/O-perspective when frequently repacking a repository that has many unreachable objects. This problem is exacerbated when those unreachable objects are rarely (if every) pruned. Since there is at most one cruft pack in the above scheme, each time we update the cruft pack it must be rewritten from scratch. Because much of the pack is reused, this is a relatively inexpensive operation from a CPU-perspective, but is very costly in terms of I/O since we end up rewriting basically the same pack (plus any new unreachable objects that have entered the repository since the last time a cruft pack was generated). At the time, we decided against implementing more robust support for multiple cruft packs. This patch implements that support which we were lacking. Introduce a new option `--max-cruft-size` which allows repositories to accumulate cruft packs up to a given size, after which point a new generation of cruft packs can accumulate until it reaches the maximum size, and so on. To generate a new cruft pack, the process works like so: - Sort a list of any existing cruft packs in ascending order of pack size. - Starting from the beginning of the list, group cruft packs together while the accumulated size is smaller than the maximum specified pack size. - Combine the objects in these cruft packs together into a new cruft pack, along with any other unreachable objects which have since entered the repository. Once a cruft pack grows beyond the size specified via `--max-cruft-size` the pack is effectively frozen. This limits the I/O churn up to a quadratic function of the value specified by the `--max-cruft-size` option, instead of behaving quadratically in the number of total unreachable objects. When pruning unreachable objects, we bypass the new code paths which combine small cruft packs together, and instead start from scratch, passing in the appropriate `--max-pack-size` down to `pack-objects`, putting it in charge of keeping the resulting set of cruft packs sized correctly. This may seem like further I/O churn, but in practice it isn't so bad. We could prune old cruft packs for whom all or most objects are removed, and then generate a new cruft pack with just the remaining set of objects. But this additional complexity buys us relatively little, because most objects end up being pruned anyway, so the I/O churn is well contained. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-10-03 00:44:32 +00:00
cruft_max_size_opts="git repack -d -l --cruft --cruft-expiration=2.weeks.ago"
test_expect_success 'setup for --max-cruft-size tests' '
git init cruft--max-size &&
(
cd cruft--max-size &&
prepare_cruft_history
)
'
test_expect_success '--max-cruft-size sets appropriate repack options' '
GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size \
gc --cruft --max-cruft-size=1M &&
test_subcommand $cruft_max_size_opts --max-cruft-size=1048576 <trace2.txt
'
test_expect_success 'gc.maxCruftSize sets appropriate repack options' '
GIT_TRACE2_EVENT=$(pwd)/trace2.txt \
git -C cruft--max-size -c gc.maxCruftSize=2M gc --cruft &&
test_subcommand $cruft_max_size_opts --max-cruft-size=2097152 <trace2.txt &&
GIT_TRACE2_EVENT=$(pwd)/trace2.txt \
git -C cruft--max-size -c gc.maxCruftSize=2M gc --cruft \
--max-cruft-size=3M &&
test_subcommand $cruft_max_size_opts --max-cruft-size=3145728 <trace2.txt
'
t6500: wait for detached auto gc at the end of the test script The last test in 't6500-gc', 'background auto gc does not run if gc.log is present and recent but does if it is old', added in a831c06a2 (gc: ignore old gc.log files, 2017-02-10), may sporadically trigger an error message from the test harness: rm: cannot remove 'trash directory.t6500-gc/.git/objects': Directory not empty The test in question ends with executing an auto gc in the backround, which occasionally takes so long that it's still running when 'test_done' is about to remove the trash directory. This 'rm -rf $trash' in the foreground might race with the detached auto gc to create and delete files and directories, and gc might (re-)create a path that 'rm' already visited and removed, triggering the above error message when 'rm' attempts to remove its parent directory. Commit bb05510e5 (t5510: run auto-gc in the foreground, 2016-05-01) fixed the same problem in a different test script by simply disallowing background gc. Unfortunately, what worked there is not applicable here, because the purpose of this test is to check the behavior of a detached auto gc. Make sure that the test doesn't continue before the gc is finished in the background with a clever bit of shell trickery: - Open fd 9 in the shell, to be inherited by the background gc process, because our daemonize() only closes the standard fds 0, 1 and 2. - Duplicate this fd 9 to stdout. - Read 'git gc's stdout, and thus fd 9, through a command substitution. We don't actually care about gc's output, but this construct has two useful properties: - This read blocks until stdout or fd 9 are open. While stdout is closed after the main gc process creates the background process and exits, fd 9 remains open until the backround process exits. - The variable assignment from the command substitution gets its exit status from the command executed within the command substitution, i.e. a failing main gc process will cause the test to fail. Note, that this fd trickery doesn't work on Windows, because due to MSYS limitations the git process only inherits the standard fds 0, 1 and 2 from the shell. Luckily, it doesn't matter in this case, because on Windows daemonize() is basically a noop, thus 'git gc --auto' always runs in the foreground. And since we can now continue the test reliably after the detached gc finished, check that there is only a single packfile left at the end, i.e. that the detached gc actually did what it was supposed to do. Also add a comment at the end of the test script to warn developers of future tests about this issue of long running detached gc processes. Helped-by: Jeff King <peff@peff.net> Helped-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-04-13 10:31:38 +00:00
run_and_wait_for_auto_gc () {
# We read stdout from gc for the side effect of waiting until the
# background gc process exits, closing its fd 9. Furthermore, the
# variable assignment from a command substitution preserves the
# exit status of the main gc process.
# Note: this fd trickery doesn't work on Windows, but there is no
# need to, because on Win the auto gc always runs in the foreground.
doesnt_matter=$(git gc --auto 9>&1)
}
test_expect_success 'background auto gc does not run if gc.log is present and recent but does if it is old' '
test_commit foo &&
test_commit bar &&
git repack &&
test_config gc.autopacklimit 1 &&
test_config gc.autodetach true &&
echo fleem >.git/gc.log &&
gc: do not return error for prior errors in daemonized mode Some build machines started consistently failing to fetch updated source using "repo sync", with error error: The last gc run reported the following. Please correct the root cause and remove /build/.repo/projects/tools/git.git/gc.log. Automatic cleanup will not be performed until the file is removed. warning: There are too many unreachable loose objects; run 'git prune' to remove them. The cause takes some time to describe. In v2.0.0-rc0~145^2 (gc: config option for running --auto in background, 2014-02-08), "git gc --auto" learned to run in the background instead of blocking the invoking command. In this mode, it closed stderr to avoid interleaving output with any subsequent commands, causing warnings like the above to be swallowed; v2.6.3~24^2 (gc: save log from daemonized gc --auto and print it next time, 2015-09-19) addressed that by storing any diagnostic output in .git/gc.log and allowing the next "git gc --auto" run to print it. To avoid wasteful repeated fruitless gcs, when gc.log is present, the subsequent "gc --auto" would die after printing its contents. Most git commands, such as "git fetch", ignore the exit status from "git gc --auto" so all is well at this point: the user gets to see the error message, and the fetch succeeds, without a wasteful additional attempt at an automatic gc. External tools like repo[1], though, do care about the exit status from "git gc --auto". In non-daemonized mode, the exit status is straightforward: if there is an error, it is nonzero, but after a warning like the above, the status is zero. The daemonized mode, as a side effect of the other properties provided, offers a very strange exit code convention: - if no housekeeping was required, the exit status is 0 - the first real run, after forking into the background, returns exit status 0 unconditionally. The parent process has no way to know whether gc will succeed. - if there is any diagnostic output in gc.log, subsequent runs return a nonzero exit status to indicate that gc was not triggered. There's nothing for the calling program to act on on the basis of that error. Use status 0 consistently instead, to indicate that we decided not to run a gc (just like if no housekeeping was required). This way, repo and similar tools can get the benefit of the same behavior as tools like "git fetch" that ignore the exit status from gc --auto. Once the period of time described by gc.pruneExpire elapses, the unreachable loose objects will be removed by "git gc --auto" automatically. [1] https://gerrit-review.googlesource.com/c/git-repo/+/10598/ Reported-by: Andrii Dehtiarov <adehtiarov@google.com> Helped-by: Jeff King <peff@peff.net> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-07-17 06:57:40 +00:00
git gc --auto 2>err &&
test_i18ngrep "^warning:" err &&
test_config gc.logexpiry 5.days &&
test-tool chmtime =-345600 .git/gc.log &&
gc: do not return error for prior errors in daemonized mode Some build machines started consistently failing to fetch updated source using "repo sync", with error error: The last gc run reported the following. Please correct the root cause and remove /build/.repo/projects/tools/git.git/gc.log. Automatic cleanup will not be performed until the file is removed. warning: There are too many unreachable loose objects; run 'git prune' to remove them. The cause takes some time to describe. In v2.0.0-rc0~145^2 (gc: config option for running --auto in background, 2014-02-08), "git gc --auto" learned to run in the background instead of blocking the invoking command. In this mode, it closed stderr to avoid interleaving output with any subsequent commands, causing warnings like the above to be swallowed; v2.6.3~24^2 (gc: save log from daemonized gc --auto and print it next time, 2015-09-19) addressed that by storing any diagnostic output in .git/gc.log and allowing the next "git gc --auto" run to print it. To avoid wasteful repeated fruitless gcs, when gc.log is present, the subsequent "gc --auto" would die after printing its contents. Most git commands, such as "git fetch", ignore the exit status from "git gc --auto" so all is well at this point: the user gets to see the error message, and the fetch succeeds, without a wasteful additional attempt at an automatic gc. External tools like repo[1], though, do care about the exit status from "git gc --auto". In non-daemonized mode, the exit status is straightforward: if there is an error, it is nonzero, but after a warning like the above, the status is zero. The daemonized mode, as a side effect of the other properties provided, offers a very strange exit code convention: - if no housekeeping was required, the exit status is 0 - the first real run, after forking into the background, returns exit status 0 unconditionally. The parent process has no way to know whether gc will succeed. - if there is any diagnostic output in gc.log, subsequent runs return a nonzero exit status to indicate that gc was not triggered. There's nothing for the calling program to act on on the basis of that error. Use status 0 consistently instead, to indicate that we decided not to run a gc (just like if no housekeeping was required). This way, repo and similar tools can get the benefit of the same behavior as tools like "git fetch" that ignore the exit status from gc --auto. Once the period of time described by gc.pruneExpire elapses, the unreachable loose objects will be removed by "git gc --auto" automatically. [1] https://gerrit-review.googlesource.com/c/git-repo/+/10598/ Reported-by: Andrii Dehtiarov <adehtiarov@google.com> Helped-by: Jeff King <peff@peff.net> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-07-17 06:57:40 +00:00
git gc --auto &&
test_config gc.logexpiry 2.days &&
t6500: wait for detached auto gc at the end of the test script The last test in 't6500-gc', 'background auto gc does not run if gc.log is present and recent but does if it is old', added in a831c06a2 (gc: ignore old gc.log files, 2017-02-10), may sporadically trigger an error message from the test harness: rm: cannot remove 'trash directory.t6500-gc/.git/objects': Directory not empty The test in question ends with executing an auto gc in the backround, which occasionally takes so long that it's still running when 'test_done' is about to remove the trash directory. This 'rm -rf $trash' in the foreground might race with the detached auto gc to create and delete files and directories, and gc might (re-)create a path that 'rm' already visited and removed, triggering the above error message when 'rm' attempts to remove its parent directory. Commit bb05510e5 (t5510: run auto-gc in the foreground, 2016-05-01) fixed the same problem in a different test script by simply disallowing background gc. Unfortunately, what worked there is not applicable here, because the purpose of this test is to check the behavior of a detached auto gc. Make sure that the test doesn't continue before the gc is finished in the background with a clever bit of shell trickery: - Open fd 9 in the shell, to be inherited by the background gc process, because our daemonize() only closes the standard fds 0, 1 and 2. - Duplicate this fd 9 to stdout. - Read 'git gc's stdout, and thus fd 9, through a command substitution. We don't actually care about gc's output, but this construct has two useful properties: - This read blocks until stdout or fd 9 are open. While stdout is closed after the main gc process creates the background process and exits, fd 9 remains open until the backround process exits. - The variable assignment from the command substitution gets its exit status from the command executed within the command substitution, i.e. a failing main gc process will cause the test to fail. Note, that this fd trickery doesn't work on Windows, because due to MSYS limitations the git process only inherits the standard fds 0, 1 and 2 from the shell. Luckily, it doesn't matter in this case, because on Windows daemonize() is basically a noop, thus 'git gc --auto' always runs in the foreground. And since we can now continue the test reliably after the detached gc finished, check that there is only a single packfile left at the end, i.e. that the detached gc actually did what it was supposed to do. Also add a comment at the end of the test script to warn developers of future tests about this issue of long running detached gc processes. Helped-by: Jeff King <peff@peff.net> Helped-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-04-13 10:31:38 +00:00
run_and_wait_for_auto_gc &&
ls .git/objects/pack/pack-*.pack >packs &&
test_line_count = 1 packs
'
gc: run pre-detach operations under lock We normally try to avoid having two auto-gc operations run at the same time, because it wastes resources. This was done long ago in 64a99eb47 (gc: reject if another gc is running, unless --force is given, 2013-08-08). When we do a detached auto-gc, we run the ref-related commands _before_ detaching, to avoid confusing lock contention. This was done by 62aad1849 (gc --auto: do not lock refs in the background, 2014-05-25). These two features do not interact well. The pre-detach operations are run before we check the gc.pid lock, meaning that on a busy repository we may run many of them concurrently. Ideally we'd take the lock before spawning any operations, and hold it for the duration of the program. This is tricky, though, with the way the pid-file interacts with the daemonize() process. Other processes will check that the pid recorded in the pid-file still exists. But detaching causes us to fork and continue running under a new pid. So if we take the lock before detaching, the pid-file will have a bogus pid in it. We'd have to go back and update it with the new pid after detaching. We'd also have to play some tricks with the tempfile subsystem to tweak the "owner" field, so that the parent process does not clean it up on exit, but the child process does. Instead, we can do something a bit simpler: take the lock only for the duration of the pre-detach work, then detach, then take it again for the post-detach work. Technically, this means that the post-detach lock could lose to another process doing pre-detach work. But in the long run this works out. That second process would then follow-up by doing post-detach work. Unless it was in turn blocked by a third process doing pre-detach work, and so on. This could in theory go on indefinitely, as the pre-detach work does not repack, and so need_to_gc() will continue to trigger. But in each round we are racing between the pre- and post-detach locks. Eventually, one of the post-detach locks will win the race and complete the full gc. So in the worst case, we may racily repeat the pre-detach work, but we would never do so simultaneously (it would happen via a sequence of serialized race-wins). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-07-11 09:06:35 +00:00
test_expect_success 'background auto gc respects lock for all operations' '
# make sure we run a background auto-gc
test_commit make-pack &&
git repack &&
test_config gc.autopacklimit 1 &&
test_config gc.autodetach true &&
# create a ref whose loose presence we can use to detect a pack-refs run
git update-ref refs/heads/should-be-loose HEAD &&
(ls -1 .git/refs/heads .git/reftable >expect || true) &&
gc: run pre-detach operations under lock We normally try to avoid having two auto-gc operations run at the same time, because it wastes resources. This was done long ago in 64a99eb47 (gc: reject if another gc is running, unless --force is given, 2013-08-08). When we do a detached auto-gc, we run the ref-related commands _before_ detaching, to avoid confusing lock contention. This was done by 62aad1849 (gc --auto: do not lock refs in the background, 2014-05-25). These two features do not interact well. The pre-detach operations are run before we check the gc.pid lock, meaning that on a busy repository we may run many of them concurrently. Ideally we'd take the lock before spawning any operations, and hold it for the duration of the program. This is tricky, though, with the way the pid-file interacts with the daemonize() process. Other processes will check that the pid recorded in the pid-file still exists. But detaching causes us to fork and continue running under a new pid. So if we take the lock before detaching, the pid-file will have a bogus pid in it. We'd have to go back and update it with the new pid after detaching. We'd also have to play some tricks with the tempfile subsystem to tweak the "owner" field, so that the parent process does not clean it up on exit, but the child process does. Instead, we can do something a bit simpler: take the lock only for the duration of the pre-detach work, then detach, then take it again for the post-detach work. Technically, this means that the post-detach lock could lose to another process doing pre-detach work. But in the long run this works out. That second process would then follow-up by doing post-detach work. Unless it was in turn blocked by a third process doing pre-detach work, and so on. This could in theory go on indefinitely, as the pre-detach work does not repack, and so need_to_gc() will continue to trigger. But in each round we are racing between the pre- and post-detach locks. Eventually, one of the post-detach locks will win the race and complete the full gc. So in the worst case, we may racily repeat the pre-detach work, but we would never do so simultaneously (it would happen via a sequence of serialized race-wins). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-07-11 09:06:35 +00:00
# now fake a concurrent gc that holds the lock; we can use our
# shell pid so that it looks valid.
hostname=$(hostname || echo unknown) &&
shell_pid=$$ &&
if test_have_prereq MINGW && test -f /proc/$shell_pid/winpid
then
# In Git for Windows, Bash (actually, the MSYS2 runtime) has a
# different idea of PIDs than git.exe (actually Windows). Use
# the Windows PID in this case.
shell_pid=$(cat /proc/$shell_pid/winpid)
fi &&
printf "%d %s" "$shell_pid" "$hostname" >.git/gc.pid &&
gc: run pre-detach operations under lock We normally try to avoid having two auto-gc operations run at the same time, because it wastes resources. This was done long ago in 64a99eb47 (gc: reject if another gc is running, unless --force is given, 2013-08-08). When we do a detached auto-gc, we run the ref-related commands _before_ detaching, to avoid confusing lock contention. This was done by 62aad1849 (gc --auto: do not lock refs in the background, 2014-05-25). These two features do not interact well. The pre-detach operations are run before we check the gc.pid lock, meaning that on a busy repository we may run many of them concurrently. Ideally we'd take the lock before spawning any operations, and hold it for the duration of the program. This is tricky, though, with the way the pid-file interacts with the daemonize() process. Other processes will check that the pid recorded in the pid-file still exists. But detaching causes us to fork and continue running under a new pid. So if we take the lock before detaching, the pid-file will have a bogus pid in it. We'd have to go back and update it with the new pid after detaching. We'd also have to play some tricks with the tempfile subsystem to tweak the "owner" field, so that the parent process does not clean it up on exit, but the child process does. Instead, we can do something a bit simpler: take the lock only for the duration of the pre-detach work, then detach, then take it again for the post-detach work. Technically, this means that the post-detach lock could lose to another process doing pre-detach work. But in the long run this works out. That second process would then follow-up by doing post-detach work. Unless it was in turn blocked by a third process doing pre-detach work, and so on. This could in theory go on indefinitely, as the pre-detach work does not repack, and so need_to_gc() will continue to trigger. But in each round we are racing between the pre- and post-detach locks. Eventually, one of the post-detach locks will win the race and complete the full gc. So in the worst case, we may racily repeat the pre-detach work, but we would never do so simultaneously (it would happen via a sequence of serialized race-wins). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-07-11 09:06:35 +00:00
# our gc should exit zero without doing anything
run_and_wait_for_auto_gc &&
(ls -1 .git/refs/heads .git/reftable >actual || true) &&
test_cmp expect actual
gc: run pre-detach operations under lock We normally try to avoid having two auto-gc operations run at the same time, because it wastes resources. This was done long ago in 64a99eb47 (gc: reject if another gc is running, unless --force is given, 2013-08-08). When we do a detached auto-gc, we run the ref-related commands _before_ detaching, to avoid confusing lock contention. This was done by 62aad1849 (gc --auto: do not lock refs in the background, 2014-05-25). These two features do not interact well. The pre-detach operations are run before we check the gc.pid lock, meaning that on a busy repository we may run many of them concurrently. Ideally we'd take the lock before spawning any operations, and hold it for the duration of the program. This is tricky, though, with the way the pid-file interacts with the daemonize() process. Other processes will check that the pid recorded in the pid-file still exists. But detaching causes us to fork and continue running under a new pid. So if we take the lock before detaching, the pid-file will have a bogus pid in it. We'd have to go back and update it with the new pid after detaching. We'd also have to play some tricks with the tempfile subsystem to tweak the "owner" field, so that the parent process does not clean it up on exit, but the child process does. Instead, we can do something a bit simpler: take the lock only for the duration of the pre-detach work, then detach, then take it again for the post-detach work. Technically, this means that the post-detach lock could lose to another process doing pre-detach work. But in the long run this works out. That second process would then follow-up by doing post-detach work. Unless it was in turn blocked by a third process doing pre-detach work, and so on. This could in theory go on indefinitely, as the pre-detach work does not repack, and so need_to_gc() will continue to trigger. But in each round we are racing between the pre- and post-detach locks. Eventually, one of the post-detach locks will win the race and complete the full gc. So in the worst case, we may racily repeat the pre-detach work, but we would never do so simultaneously (it would happen via a sequence of serialized race-wins). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-07-11 09:06:35 +00:00
'
t6500: wait for detached auto gc at the end of the test script The last test in 't6500-gc', 'background auto gc does not run if gc.log is present and recent but does if it is old', added in a831c06a2 (gc: ignore old gc.log files, 2017-02-10), may sporadically trigger an error message from the test harness: rm: cannot remove 'trash directory.t6500-gc/.git/objects': Directory not empty The test in question ends with executing an auto gc in the backround, which occasionally takes so long that it's still running when 'test_done' is about to remove the trash directory. This 'rm -rf $trash' in the foreground might race with the detached auto gc to create and delete files and directories, and gc might (re-)create a path that 'rm' already visited and removed, triggering the above error message when 'rm' attempts to remove its parent directory. Commit bb05510e5 (t5510: run auto-gc in the foreground, 2016-05-01) fixed the same problem in a different test script by simply disallowing background gc. Unfortunately, what worked there is not applicable here, because the purpose of this test is to check the behavior of a detached auto gc. Make sure that the test doesn't continue before the gc is finished in the background with a clever bit of shell trickery: - Open fd 9 in the shell, to be inherited by the background gc process, because our daemonize() only closes the standard fds 0, 1 and 2. - Duplicate this fd 9 to stdout. - Read 'git gc's stdout, and thus fd 9, through a command substitution. We don't actually care about gc's output, but this construct has two useful properties: - This read blocks until stdout or fd 9 are open. While stdout is closed after the main gc process creates the background process and exits, fd 9 remains open until the backround process exits. - The variable assignment from the command substitution gets its exit status from the command executed within the command substitution, i.e. a failing main gc process will cause the test to fail. Note, that this fd trickery doesn't work on Windows, because due to MSYS limitations the git process only inherits the standard fds 0, 1 and 2 from the shell. Luckily, it doesn't matter in this case, because on Windows daemonize() is basically a noop, thus 'git gc --auto' always runs in the foreground. And since we can now continue the test reliably after the detached gc finished, check that there is only a single packfile left at the end, i.e. that the detached gc actually did what it was supposed to do. Also add a comment at the end of the test script to warn developers of future tests about this issue of long running detached gc processes. Helped-by: Jeff King <peff@peff.net> Helped-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-04-13 10:31:38 +00:00
# DO NOT leave a detached auto gc process running near the end of the
# test script: it can run long enough in the background to racily
# interfere with the cleanup in 'test_done'.
test_done