git-commit-vandalism/t/t7900-maintenance.sh
Derrick Stolee 252cfb7cb8 maintenance: add loose-objects task
One goal of background maintenance jobs is to allow a user to
disable auto-gc (gc.auto=0) but keep their repository in a clean
state. Without any cleanup, loose objects will clutter the object
database and slow operations. In addition, the loose objects will
take up extra space because they are not stored with deltas against
similar objects.

Create a 'loose-objects' task for the 'git maintenance run' command.
This helps clean up loose objects without disrupting concurrent Git
commands using the following sequence of events:

1. Run 'git prune-packed' to delete any loose objects that exist
   in a pack-file. Concurrent commands will prefer the packed
   version of the object to the loose version. (Of course, there
   are exceptions for commands that specifically care about the
   location of an object. These are rare for a user to run on
   purpose, and we hope a user that has selected background
   maintenance will not be trying to do foreground maintenance.)

2. Run 'git pack-objects' on a batch of loose objects. These
   objects are grouped by scanning the loose object directories in
   lexicographic order until listing all loose objects -or-
   reaching 50,000 objects. This is more than enough if the loose
   objects are created only by a user doing normal development.
   We noticed users with _millions_ of loose objects because VFS
   for Git downloads blobs on-demand when a file read operation
   requires populating a virtual file.

This step is based on a similar step in Scalar [1] and VFS for Git.
[1] https://github.com/microsoft/scalar/blob/master/Scalar.Common/Maintenance/LooseObjectsStep.cs

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-09-25 10:53:04 -07:00

131 lines
4.7 KiB
Bash
Executable File

#!/bin/sh
test_description='git maintenance builtin'
. ./test-lib.sh
GIT_TEST_COMMIT_GRAPH=0
test_expect_success 'help text' '
test_expect_code 129 git maintenance -h 2>err &&
test_i18ngrep "usage: git maintenance run" err &&
test_expect_code 128 git maintenance barf 2>err &&
test_i18ngrep "invalid subcommand: barf" err &&
test_expect_code 129 git maintenance 2>err &&
test_i18ngrep "usage: git maintenance" err
'
test_expect_success 'run [--auto|--quiet]' '
GIT_TRACE2_EVENT="$(pwd)/run-no-auto.txt" \
git maintenance run 2>/dev/null &&
GIT_TRACE2_EVENT="$(pwd)/run-auto.txt" \
git maintenance run --auto 2>/dev/null &&
GIT_TRACE2_EVENT="$(pwd)/run-no-quiet.txt" \
git maintenance run --no-quiet 2>/dev/null &&
test_subcommand git gc --quiet <run-no-auto.txt &&
test_subcommand ! git gc --auto --quiet <run-auto.txt &&
test_subcommand git gc --no-quiet <run-no-quiet.txt
'
test_expect_success 'maintenance.<task>.enabled' '
git config maintenance.gc.enabled false &&
git config maintenance.commit-graph.enabled true &&
GIT_TRACE2_EVENT="$(pwd)/run-config.txt" git maintenance run 2>err &&
test_subcommand ! git gc --quiet <run-config.txt &&
test_subcommand git commit-graph write --split --reachable --no-progress <run-config.txt
'
test_expect_success 'run --task=<task>' '
GIT_TRACE2_EVENT="$(pwd)/run-commit-graph.txt" \
git maintenance run --task=commit-graph 2>/dev/null &&
GIT_TRACE2_EVENT="$(pwd)/run-gc.txt" \
git maintenance run --task=gc 2>/dev/null &&
GIT_TRACE2_EVENT="$(pwd)/run-commit-graph.txt" \
git maintenance run --task=commit-graph 2>/dev/null &&
GIT_TRACE2_EVENT="$(pwd)/run-both.txt" \
git maintenance run --task=commit-graph --task=gc 2>/dev/null &&
test_subcommand ! git gc --quiet <run-commit-graph.txt &&
test_subcommand git gc --quiet <run-gc.txt &&
test_subcommand git gc --quiet <run-both.txt &&
test_subcommand git commit-graph write --split --reachable --no-progress <run-commit-graph.txt &&
test_subcommand ! git commit-graph write --split --reachable --no-progress <run-gc.txt &&
test_subcommand git commit-graph write --split --reachable --no-progress <run-both.txt
'
test_expect_success 'run --task=bogus' '
test_must_fail git maintenance run --task=bogus 2>err &&
test_i18ngrep "is not a valid task" err
'
test_expect_success 'run --task duplicate' '
test_must_fail git maintenance run --task=gc --task=gc 2>err &&
test_i18ngrep "cannot be selected multiple times" err
'
test_expect_success 'run --task=prefetch with no remotes' '
git maintenance run --task=prefetch 2>err &&
test_must_be_empty err
'
test_expect_success 'prefetch multiple remotes' '
git clone . clone1 &&
git clone . clone2 &&
git remote add remote1 "file://$(pwd)/clone1" &&
git remote add remote2 "file://$(pwd)/clone2" &&
git -C clone1 switch -c one &&
git -C clone2 switch -c two &&
test_commit -C clone1 one &&
test_commit -C clone2 two &&
GIT_TRACE2_EVENT="$(pwd)/run-prefetch.txt" git maintenance run --task=prefetch 2>/dev/null &&
fetchargs="--prune --no-tags --no-write-fetch-head --recurse-submodules=no --refmap= --quiet" &&
test_subcommand git fetch remote1 $fetchargs +refs/heads/\\*:refs/prefetch/remote1/\\* <run-prefetch.txt &&
test_subcommand git fetch remote2 $fetchargs +refs/heads/\\*:refs/prefetch/remote2/\\* <run-prefetch.txt &&
test_path_is_missing .git/refs/remotes &&
git log prefetch/remote1/one &&
git log prefetch/remote2/two &&
git fetch --all &&
test_cmp_rev refs/remotes/remote1/one refs/prefetch/remote1/one &&
test_cmp_rev refs/remotes/remote2/two refs/prefetch/remote2/two
'
test_expect_success 'loose-objects task' '
# Repack everything so we know the state of the object dir
git repack -adk &&
# Hack to stop maintenance from running during "git commit"
echo in use >.git/objects/maintenance.lock &&
# Assuming that "git commit" creates at least one loose object
test_commit create-loose-object &&
rm .git/objects/maintenance.lock &&
ls .git/objects >obj-dir-before &&
test_file_not_empty obj-dir-before &&
ls .git/objects/pack/*.pack >packs-before &&
test_line_count = 1 packs-before &&
# The first run creates a pack-file
# but does not delete loose objects.
git maintenance run --task=loose-objects &&
ls .git/objects >obj-dir-between &&
test_cmp obj-dir-before obj-dir-between &&
ls .git/objects/pack/*.pack >packs-between &&
test_line_count = 2 packs-between &&
ls .git/objects/pack/loose-*.pack >loose-packs &&
test_line_count = 1 loose-packs &&
# The second run deletes loose objects
# but does not create a pack-file.
git maintenance run --task=loose-objects &&
ls .git/objects >obj-dir-after &&
cat >expect <<-\EOF &&
info
pack
EOF
test_cmp expect obj-dir-after &&
ls .git/objects/pack/*.pack >packs-after &&
test_cmp packs-between packs-after
'
test_done