git-gc --auto: run "repack -A -d -l" as necessary.

This teaches "git-gc --auto" to consolidate many packs into one
without losing unreachable objects in them by using "repack -A"
when there are too many packfiles that are not marked with *.keep
in the repository.  gc.autopacklimit configuration can be used
to set the maximum number of packs a repository is allowed to
have before this mechanism kicks in.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 66 insertions, 7 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 6b6553d..b0390f8 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -446,6 +446,12 @@ gc.auto::
 	light-weight garbage collection from time to time.  Setting
 	this to 0 disables it.
 
+gc.autopacklimit::
+	When there are more than this many packs that are not
+	marked with `*.keep` file in the repository, `git gc
+	--auto` consolidates them into one larger pack.  Setting
+	this to 0 disables this.
+
 gc.packrefs::
 	`git gc` does not run `git pack-refs` in a bare repository by
 	default so that older dumb-transport clients can still fetch
diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index 40c1ce4..b9d5660 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -47,10 +47,15 @@ OPTIONS
 	With this option, `git gc` checks if there are too many
 	loose objects in the repository and runs
 	gitlink:git-repack[1] with `-d -l` option to pack them.
-	The threshold is set with `gc.auto` configuration
+	The threshold for loose objects is set with `gc.auto` configuration
 	variable, and can be disabled by setting it to 0.  Some
 	Porcelain commands use this after they perform operation
 	that could create many loose objects automatically.
+	Additionally, when there are too many packs are present,
+	they are consolidated into one larger pack by running
+	the `git-repack` command with `-A` option.  The
+	threshold for number of packs is set with
+	`gc.autopacklimit` configuration variable.
 
 Configuration
 -------------
diff --git a/builtin-gc.c b/builtin-gc.c
index 34ce35b..23ad2b6 100644
--- a/builtin-gc.c
+++ b/builtin-gc.c
@@ -21,6 +21,7 @@ static const char builtin_gc_usage[] = "git-gc [--prune] [--aggressive]";
 static int pack_refs = 1;
 static int aggressive_window = -1;
 static int gc_auto_threshold = 6700;
+static int gc_auto_pack_limit = 20;
 
 #define MAX_ADD 10
 static const char *argv_pack_refs[] = {"pack-refs", "--all", "--prune", NULL};
@@ -46,6 +47,10 @@ static int gc_config(const char *var, const char *value)
 		gc_auto_threshold = git_config_int(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "gc.autopacklimit")) {
+		gc_auto_pack_limit = git_config_int(var, value);
+		return 0;
+	}
 	return git_default_config(var, value);
 }
 
@@ -78,6 +83,9 @@ static int too_many_loose_objects(void)
 	int num_loose = 0;
 	int needed = 0;
 
+	if (gc_auto_threshold <= 0)
+		return 0;
+
 	if (sizeof(path) <= snprintf(path, sizeof(path), "%s/17", objdir)) {
 		warning("insanely long object directory %.*s", 50, objdir);
 		return 0;
@@ -100,21 +108,61 @@ static int too_many_loose_objects(void)
 	return needed;
 }
 
+static int too_many_packs(void)
+{
+	struct packed_git *p;
+	int cnt;
+
+	if (gc_auto_pack_limit <= 0)
+		return 0;
+
+	prepare_packed_git();
+	for (cnt = 0, p = packed_git; p; p = p->next) {
+		char path[PATH_MAX];
+		size_t len;
+		int keep;
+
+		if (!p->pack_local)
+			continue;
+		len = strlen(p->pack_name);
+		if (PATH_MAX <= len + 1)
+			continue; /* oops, give up */
+		memcpy(path, p->pack_name, len-5);
+		memcpy(path + len - 5, ".keep", 6);
+		keep = access(p->pack_name, F_OK) && (errno == ENOENT);
+		if (keep)
+			continue;
+		/*
+		 * Perhaps check the size of the pack and count only
+		 * very small ones here?
+		 */
+		cnt++;
+	}
+	return gc_auto_pack_limit <= cnt;
+}
+
 static int need_to_gc(void)
 {
 	int ac = 0;
 
 	/*
-	 * Setting gc.auto to 0 or negative can disable the
-	 * automatic gc
+	 * Setting gc.auto and gc.autopacklimit to 0 or negative can
+	 * disable the automatic gc.
 	 */
-	if (gc_auto_threshold <= 0)
-		return 0;
-
-	if (!too_many_loose_objects())
+	if (gc_auto_threshold <= 0 && gc_auto_pack_limit <= 0)
 		return 0;
 
+	/*
+	 * If there are too many loose objects, but not too many
+	 * packs, we run "repack -d -l".  If there are too many packs,
+	 * we run "repack -A -d -l".  Otherwise we tell the caller
+	 * there is no need.
+	 */
 	argv_repack[ac++] = "repack";
+	if (too_many_packs())
+		argv_repack[ac++] = "-A";
+	else if (!too_many_loose_objects())
+		return 0;
 	argv_repack[ac++] = "-d";
 	argv_repack[ac++] = "-l";
 	argv_repack[ac++] = NULL;