Merge branch 'ps/pack-refs-auto'

"git pack-refs" learned the "--auto" option, which is a useful addition to be triggered from "git gc --auto". Acked-by: Karthik Nayak <[email protected]> cf. <CAOLa=ZRAEA7rSUoYL0h-2qfEELdbPHbeGpgBJRqesyhHi9Q6WQ@mail.gmail.com> * ps/pack-refs-auto: builtin/gc: pack refs when using `git maintenance run --auto` builtin/gc: forward git-gc(1)'s `--auto` flag when packing refs t6500: extract objects with "17" prefix builtin/gc: move `struct maintenance_run_opts` builtin/pack-refs: introduce new "--auto" flag builtin/pack-refs: release allocated memory refs/reftable: expose auto compaction via new flag refs: remove `PACK_REFS_ALL` flag refs: move `struct pack_refs_opts` to where it's used t/helper: drop pack-refs wrapper refs/reftable: print errors on compaction failure reftable/stack: gracefully handle failed auto-compaction due to locks reftable/stack: use error codes when locking fails during compaction reftable/error: discern locked/outdated errors reftable/stack: fix error handling in `reftable_stack_init_addition()`
ToBoMi · Apr 9, 2024 · eacfd58 · eacfd58
2 parents a6abdda + 9f6714a
commit eacfd58
Show file tree

Hide file tree

Showing 14 changed files with 308 additions and 125 deletions.
diff --git a/Documentation/git-pack-refs.txt b/Documentation/git-pack-refs.txt
@@ -8,7 +8,7 @@ git-pack-refs - Pack heads and tags for efficient repository access
 SYNOPSIS
 --------
 [verse]
-'git pack-refs' [--all] [--no-prune] [--include <pattern>] [--exclude <pattern>]
+'git pack-refs' [--all] [--no-prune] [--auto] [--include <pattern>] [--exclude <pattern>]
 
 DESCRIPTION
 -----------
@@ -60,6 +60,19 @@ with many branches of historical interests.
 The command usually removes loose refs under `$GIT_DIR/refs`
 hierarchy after packing them.  This option tells it not to.
 
+--auto::
+
+Pack refs as needed depending on the current state of the ref database. The
+behavior depends on the ref format used by the repository and may change in the
+future.
++
+	- "files": No special handling for `--auto` has been implemented.
++
+	- "reftable": Tables are compacted such that they form a geometric
+	  sequence. For two tables N and N+1, where N+1 is newer, this
+	  maintains the property that N is at least twice as big as N+1. Only
+	  tables that violate this property are compacted.
+
 --include <pattern>::
 
 Pack refs based on a `glob(7)` pattern. Repetitions of this option

diff --git a/builtin/gc.c b/builtin/gc.c
@@ -180,13 +180,51 @@ static void gc_config(void)
 	git_config(git_default_config, NULL);
 }
 
-struct maintenance_run_opts;
+enum schedule_priority {
+	SCHEDULE_NONE = 0,
+	SCHEDULE_WEEKLY = 1,
+	SCHEDULE_DAILY = 2,
+	SCHEDULE_HOURLY = 3,
+};
+
+static enum schedule_priority parse_schedule(const char *value)
+{
+	if (!value)
+		return SCHEDULE_NONE;
+	if (!strcasecmp(value, "hourly"))
+		return SCHEDULE_HOURLY;
+	if (!strcasecmp(value, "daily"))
+		return SCHEDULE_DAILY;
+	if (!strcasecmp(value, "weekly"))
+		return SCHEDULE_WEEKLY;
+	return SCHEDULE_NONE;
+}
+
+struct maintenance_run_opts {
+	int auto_flag;
+	int quiet;
+	enum schedule_priority schedule;
+};
+
+static int pack_refs_condition(void)
+{
+	/*
+	 * The auto-repacking logic for refs is handled by the ref backends and
+	 * exposed via `git pack-refs --auto`. We thus always return truish
+	 * here and let the backend decide for us.
+	 */
+	return 1;
+}
+
 static int maintenance_task_pack_refs(MAYBE_UNUSED struct maintenance_run_opts *opts)
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
 
 	cmd.git_cmd = 1;
 	strvec_pushl(&cmd.args, "pack-refs", "--all", "--prune", NULL);
+	if (opts->auto_flag)
+		strvec_push(&cmd.args, "--auto");
+
 	return run_command(&cmd);
 }
 
@@ -547,7 +585,7 @@ static int report_last_gc_error(void)
 	return ret;
 }
 
-static void gc_before_repack(void)
+static void gc_before_repack(struct maintenance_run_opts *opts)
 {
 	/*
 	 * We may be called twice, as both the pre- and
@@ -558,7 +596,7 @@ static void gc_before_repack(void)
 	if (done++)
 		return;
 
-	if (pack_refs && maintenance_task_pack_refs(NULL))
+	if (pack_refs && maintenance_task_pack_refs(opts))
 		die(FAILED_RUN, "pack-refs");
 
 	if (prune_reflogs) {
@@ -574,7 +612,6 @@ static void gc_before_repack(void)
 int cmd_gc(int argc, const char **argv, const char *prefix)
 {
 	int aggressive = 0;
-	int auto_gc = 0;
 	int quiet = 0;
 	int force = 0;
 	const char *name;
@@ -583,6 +620,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 	int keep_largest_pack = -1;
 	timestamp_t dummy;
 	struct child_process rerere_cmd = CHILD_PROCESS_INIT;
+	struct maintenance_run_opts opts = {0};
 
 	struct option builtin_gc_options[] = {
 		OPT__QUIET(&quiet, N_("suppress progress reporting")),
@@ -593,7 +631,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		OPT_MAGNITUDE(0, "max-cruft-size", &max_cruft_size,
 			      N_("with --cruft, limit the size of new cruft packs")),
 		OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
-		OPT_BOOL_F(0, "auto", &auto_gc, N_("enable auto-gc mode"),
+		OPT_BOOL_F(0, "auto", &opts.auto_flag, N_("enable auto-gc mode"),
 			   PARSE_OPT_NOCOMPLETE),
 		OPT_BOOL_F(0, "force", &force,
 			   N_("force running gc even if there may be another gc running"),
@@ -638,7 +676,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 	if (quiet)
 		strvec_push(&repack, "-q");
 
-	if (auto_gc) {
+	if (opts.auto_flag) {
 		/*
 		 * Auto-gc should be least intrusive as possible.
 		 */
@@ -663,7 +701,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 
 			if (lock_repo_for_gc(force, &pid))
 				return 0;
-			gc_before_repack(); /* dies on failure */
+			gc_before_repack(&opts); /* dies on failure */
 			delete_tempfile(&pidfile);
 
 			/*
@@ -688,7 +726,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 
 	name = lock_repo_for_gc(force, &pid);
 	if (name) {
-		if (auto_gc)
+		if (opts.auto_flag)
 			return 0; /* be quiet on --auto */
 		die(_("gc is already running on machine '%s' pid %"PRIuMAX" (use --force if not)"),
 		    name, (uintmax_t)pid);
@@ -703,7 +741,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		atexit(process_log_file_at_exit);
 	}
 
-	gc_before_repack();
+	gc_before_repack(&opts);
 
 	if (!repository_format_precious_objects) {
 		struct child_process repack_cmd = CHILD_PROCESS_INIT;
@@ -758,7 +796,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 					     !quiet && !daemonized ? COMMIT_GRAPH_WRITE_PROGRESS : 0,
 					     NULL);
 
-	if (auto_gc && too_many_loose_objects())
+	if (opts.auto_flag && too_many_loose_objects())
 		warning(_("There are too many unreachable loose objects; "
 			"run 'git prune' to remove them."));
 
@@ -773,26 +811,6 @@ static const char *const builtin_maintenance_run_usage[] = {
 	NULL
 };
 
-enum schedule_priority {
-	SCHEDULE_NONE = 0,
-	SCHEDULE_WEEKLY = 1,
-	SCHEDULE_DAILY = 2,
-	SCHEDULE_HOURLY = 3,
-};
-
-static enum schedule_priority parse_schedule(const char *value)
-{
-	if (!value)
-		return SCHEDULE_NONE;
-	if (!strcasecmp(value, "hourly"))
-		return SCHEDULE_HOURLY;
-	if (!strcasecmp(value, "daily"))
-		return SCHEDULE_DAILY;
-	if (!strcasecmp(value, "weekly"))
-		return SCHEDULE_WEEKLY;
-	return SCHEDULE_NONE;
-}
-
 static int maintenance_opt_schedule(const struct option *opt, const char *arg,
 				    int unset)
 {
@@ -809,12 +827,6 @@ static int maintenance_opt_schedule(const struct option *opt, const char *arg,
 	return 0;
 }
 
-struct maintenance_run_opts {
-	int auto_flag;
-	int quiet;
-	enum schedule_priority schedule;
-};
-
 /* Remember to update object flag allocation in object.h */
 #define SEEN		(1u<<0)
 
@@ -1296,7 +1308,7 @@ static struct maintenance_task tasks[] = {
 	[TASK_PACK_REFS] = {
 		"pack-refs",
 		maintenance_task_pack_refs,
-		NULL,
+		pack_refs_condition,
 	},
 };
 

diff --git a/builtin/pack-refs.c b/builtin/pack-refs.c
@@ -7,24 +7,28 @@
 #include "revision.h"
 
 static char const * const pack_refs_usage[] = {
-	N_("git pack-refs [--all] [--no-prune] [--include <pattern>] [--exclude <pattern>]"),
+	N_("git pack-refs [--all] [--no-prune] [--auto] [--include <pattern>] [--exclude <pattern>]"),
 	NULL
 };
 
 int cmd_pack_refs(int argc, const char **argv, const char *prefix)
 {
-	unsigned int flags = PACK_REFS_PRUNE;
-	static struct ref_exclusions excludes = REF_EXCLUSIONS_INIT;
-	static struct string_list included_refs = STRING_LIST_INIT_NODUP;
-	struct pack_refs_opts pack_refs_opts = { .exclusions = &excludes,
-						 .includes = &included_refs,
-						 .flags = flags };
-	static struct string_list option_excluded_refs = STRING_LIST_INIT_NODUP;
+	struct ref_exclusions excludes = REF_EXCLUSIONS_INIT;
+	struct string_list included_refs = STRING_LIST_INIT_NODUP;
+	struct pack_refs_opts pack_refs_opts = {
+		.exclusions = &excludes,
+		.includes = &included_refs,
+		.flags = PACK_REFS_PRUNE,
+	};
+	struct string_list option_excluded_refs = STRING_LIST_INIT_NODUP;
 	struct string_list_item *item;
+	int pack_all = 0;
+	int ret;
 
 	struct option opts[] = {
-		OPT_BIT(0, "all",   &pack_refs_opts.flags, N_("pack everything"), PACK_REFS_ALL),
+		OPT_BOOL(0, "all",   &pack_all, N_("pack everything")),
 		OPT_BIT(0, "prune", &pack_refs_opts.flags, N_("prune loose refs (default)"), PACK_REFS_PRUNE),
+		OPT_BIT(0, "auto", &pack_refs_opts.flags, N_("auto-pack refs as needed"), PACK_REFS_AUTO),
 		OPT_STRING_LIST(0, "include", pack_refs_opts.includes, N_("pattern"),
 			N_("references to include")),
 		OPT_STRING_LIST(0, "exclude", &option_excluded_refs, N_("pattern"),
@@ -38,11 +42,16 @@ int cmd_pack_refs(int argc, const char **argv, const char *prefix)
 	for_each_string_list_item(item, &option_excluded_refs)
 		add_ref_exclusion(pack_refs_opts.exclusions, item->string);
 
-	if (pack_refs_opts.flags & PACK_REFS_ALL)
+	if (pack_all)
 		string_list_append(pack_refs_opts.includes, "*");
 
 	if (!pack_refs_opts.includes->nr)
 		string_list_append(pack_refs_opts.includes, "refs/tags/*");
 
-	return refs_pack_refs(get_main_ref_store(the_repository), &pack_refs_opts);
+	ret = refs_pack_refs(get_main_ref_store(the_repository), &pack_refs_opts);
+
+	clear_ref_exclusions(&excludes);
+	string_list_clear(&included_refs, 0);
+	string_list_clear(&option_excluded_refs, 0);
+	return ret;
 }
diff --git a/refs.h b/refs.h
@@ -66,12 +66,6 @@ const char *ref_storage_format_to_name(unsigned int ref_storage_format);
 #define RESOLVE_REF_NO_RECURSE 0x02
 #define RESOLVE_REF_ALLOW_BAD_NAME 0x04
 
-struct pack_refs_opts {
-	unsigned int flags;
-	struct ref_exclusions *exclusions;
-	struct string_list *includes;
-};
-
 const char *refs_resolve_ref_unsafe(struct ref_store *refs,
 				    const char *refname,
 				    int resolve_flags,
@@ -428,10 +422,18 @@ void warn_dangling_symrefs(FILE *fp, const char *msg_fmt,
 /*
  * Flags for controlling behaviour of pack_refs()
  * PACK_REFS_PRUNE: Prune loose refs after packing
- * PACK_REFS_ALL:   Pack _all_ refs, not just tags and already packed refs
+ * PACK_REFS_AUTO: Pack refs on a best effort basis. The heuristics and end
+ *                 result are decided by the ref backend. Backends may ignore
+ *                 this flag and fall back to a normal repack.
  */
-#define PACK_REFS_PRUNE 0x0001
-#define PACK_REFS_ALL   0x0002
+#define PACK_REFS_PRUNE (1 << 0)
+#define PACK_REFS_AUTO  (1 << 1)
+
+struct pack_refs_opts {
+	unsigned int flags;
+	struct ref_exclusions *exclusions;
+	struct string_list *includes;
+};
 
 /*
  * Write a packed-refs file for the current repository.

diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c
@@ -1203,9 +1203,16 @@ static int reftable_be_pack_refs(struct ref_store *ref_store,
 	if (!stack)
 		stack = refs->main_stack;
 
-	ret = reftable_stack_compact_all(stack, NULL);
-	if (ret)
+	if (opts->flags & PACK_REFS_AUTO)
+		ret = reftable_stack_auto_compact(stack);
+	else
+		ret = reftable_stack_compact_all(stack, NULL);
+	if (ret < 0) {
+		ret = error(_("unable to compact stack: %s"),
+			    reftable_error_str(ret));
 		goto out;
+	}
+
 	ret = reftable_stack_clean(stack);
 	if (ret)
 		goto out;

diff --git a/reftable/error.c b/reftable/error.c
@@ -22,7 +22,7 @@ const char *reftable_error_str(int err)
 	case REFTABLE_NOT_EXIST_ERROR:
 		return "file does not exist";
 	case REFTABLE_LOCK_ERROR:
-		return "data is outdated";
+		return "data is locked";
 	case REFTABLE_API_ERROR:
 		return "misuse of the reftable API";
 	case REFTABLE_ZLIB_ERROR:
@@ -35,6 +35,8 @@ const char *reftable_error_str(int err)
 		return "invalid refname";
 	case REFTABLE_ENTRY_TOO_BIG_ERROR:
 		return "entry too large";
+	case REFTABLE_OUTDATED_ERROR:
+		return "data concurrently modified";
 	case -1:
 		return "general error";
 	default:

diff --git a/reftable/reftable-error.h b/reftable/reftable-error.h
@@ -25,7 +25,7 @@ enum reftable_error {
 	 */
 	REFTABLE_NOT_EXIST_ERROR = -4,
 
-	/* Trying to write out-of-date data. */
+	/* Trying to access locked data. */
 	REFTABLE_LOCK_ERROR = -5,
 
 	/* Misuse of the API:
@@ -57,6 +57,9 @@ enum reftable_error {
 	/* Entry does not fit. This can happen when writing outsize reflog
 	   messages. */
 	REFTABLE_ENTRY_TOO_BIG_ERROR = -11,
+
+	/* Trying to write out-of-date data. */
+	REFTABLE_OUTDATED_ERROR = -12,
 };
 
 /* convert the numeric error code to a string. The string should not be