maintenance: add pack-refs task

It is valuable to collect loose refs into a more compressed form. This is typically the packed-refs file, although this could be the reftable in the future. Having packed refs can be extremely valuable in repos with many tags or remote branches that are not modified by the local user, but still are necessary for other queries. For instance, with many exploded refs, commands such as git describe --tags --exact-match HEAD can be very slow (multiple seconds). This command in particular is used by terminal prompts to show when a detatched HEAD is pointing to an existing tag, so having it be slow causes significant delays for users. Add a new 'pack-refs' maintenance task. It runs 'git pack-refs --all --prune' to move loose refs into a packed form. For now, that is the packed-refs file, but could adjust to other file formats in the future. This is the first of several sub-tasks of the 'gc' task that could be extracted to their own tasks. In this process, we should not change the behavior of the 'gc' task since that remains the default way to keep repositories maintained. Creating a new task for one of these sub-tasks only provides more customization options for those choosing to not use the 'gc' task. It is certainly possible to have both the 'gc' and 'pack-refs' tasks enabled and run regularly. While they may repeat effort, they do not conflict in a destructive way. The 'auto_condition' function pointer is left NULL for now. We could extend this in the future to have a condition check if pack-refs should be run during 'git maintenance run --auto'. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Derrick Stolee committed Feb 9, 2021 at 13:42 UTC 41abfe15d95ede4c2a047180a6062eac23d8f7d6
3 files changed +35 -4
Documentation/git-maintenance.txt
+6
@@ -145,6 +145,12 @@ incremental-repack::
145 which is a special case that attempts to repack all pack-files
146 into a single pack-file.
147
148 +pack-refs::
149 + The `pack-refs` task collects the loose reference files and
150 + collects them into a single file. This speeds up operations that
151 + need to iterate across many references. See linkgit:git-pack-refs[1]
152 + for more information.
153 +
154 OPTIONS
155 -------
156 --auto::
builtin/gc.c
+17 -4
@@ -54,7 +54,6 @@ static const char *prune_worktrees_expire = "3.months.ago";
54 static unsigned long big_pack_threshold;
55 static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
56
57 -static struct strvec pack_refs_cmd = STRVEC_INIT;
57 static struct strvec reflog = STRVEC_INIT;
58 static struct strvec repack = STRVEC_INIT;
59 static struct strvec prune = STRVEC_INIT;
@@ -163,6 +162,15 @@ static void gc_config(void)
162 git_config(git_default_config, NULL);
163 }
164
165 +struct maintenance_run_opts;
166 +static int maintenance_task_pack_refs(MAYBE_UNUSED struct maintenance_run_opts *opts)
167 +{
168 + struct strvec pack_refs_cmd = STRVEC_INIT;
169 + strvec_pushl(&pack_refs_cmd, "pack-refs", "--all", "--prune", NULL);
170 +
171 + return run_command_v_opt(pack_refs_cmd.v, RUN_GIT_CMD);
172 +}
173 +
174 static int too_many_loose_objects(void)
175 {
176 /*
@@ -518,8 +526,8 @@ static void gc_before_repack(void)
526 if (done++)
527 return;
528
521 - if (pack_refs && run_command_v_opt(pack_refs_cmd.v, RUN_GIT_CMD))
522 - die(FAILED_RUN, pack_refs_cmd.v[0]);
529 + if (pack_refs && maintenance_task_pack_refs(NULL))
530 + die(FAILED_RUN, "pack-refs");
531
532 if (prune_reflogs && run_command_v_opt(reflog.v, RUN_GIT_CMD))
533 die(FAILED_RUN, reflog.v[0]);
@@ -556,7 +564,6 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
564 if (argc == 2 && !strcmp(argv[1], "-h"))
565 usage_with_options(builtin_gc_usage, builtin_gc_options);
566
559 - strvec_pushl(&pack_refs_cmd, "pack-refs", "--all", "--prune", NULL);
567 strvec_pushl(&reflog, "reflog", "expire", "--all", NULL);
568 strvec_pushl(&repack, "repack", "-d", "-l", NULL);
569 strvec_pushl(&prune, "prune", "--expire", NULL);
@@ -1224,6 +1231,7 @@ enum maintenance_task_label {
1231 TASK_INCREMENTAL_REPACK,
1232 TASK_GC,
1233 TASK_COMMIT_GRAPH,
1234 + TASK_PACK_REFS,
1235
1236 /* Leave as final value */
1237 TASK__COUNT
@@ -1255,6 +1263,11 @@ static struct maintenance_task tasks[] = {
1263 maintenance_task_commit_graph,
1264 should_write_commit_graph,
1265 },
1266 + [TASK_PACK_REFS] = {
1267 + "pack-refs",
1268 + maintenance_task_pack_refs,
1269 + NULL,
1270 + },
1271 };
1272
1273 static int compare_tasks_by_selection(const void *a_, const void *b_)
t/t7900-maintenance.sh
+12
@@ -343,6 +343,18 @@ test_expect_success 'maintenance.incremental-repack.auto' '
343 test_subcommand git multi-pack-index write --no-progress <trace-B
344 '
345
346 +test_expect_success 'pack-refs task' '
347 + for n in $(test_seq 1 5)
348 + do
349 + git branch -f to-pack/$n HEAD || return 1
350 + done &&
351 + GIT_TRACE2_EVENT="$(pwd)/pack-refs.txt" \
352 + git maintenance run --task=pack-refs &&
353 + ls .git/refs/heads/ >after &&
354 + test_must_be_empty after &&
355 + test_subcommand git pack-refs --all --prune <pack-refs.txt
356 +'
357 +
358 test_expect_success '--auto and --schedule incompatible' '
359 test_must_fail git maintenance run --auto --schedule=daily 2>err &&
360 test_i18ngrep "at most one" err