Add --aggressive option to 'git gc'

This option causes 'git gc' to more aggressively optimize the
repository at the cost of taking much more wall clock and CPU time.

Today this option causes git-pack-objects to use --no-use-delta
option, and it allows the --window parameter to be set via the
gc.aggressiveWindow configuration parameter.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Junio C Hamano <junkio@cox.net>

3 files changed, 50 insertions, 3 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index ea434af9d..efcf3019b 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -384,6 +384,11 @@ format.suffix::
 	`.patch`. Use this variable to change that suffix (make sure to
 	include the dot if you want it).
 
+gc.aggressiveWindow::
+	The window size parameter used in the delta compression
+	algorithm used by 'git gc --aggressive'.  This defaults
+	to 10.
+
 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 bc1658434..4ac839f93 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -8,7 +8,7 @@ git-gc - Cleanup unnecessary files and optimize the local repository
 
 SYNOPSIS
 --------
-'git-gc' [--prune]
+'git-gc' [--prune] [--aggressive]
 
 DESCRIPTION
 -----------
@@ -35,6 +35,13 @@ OPTIONS
 	repository at the same time (e.g. never use this option
 	in a cron script).
 
+--aggressive::
+	Usually 'git-gc' runs very quickly while providing good disk
+	space utilization and performance.   This option will cause
+	git-gc to more aggressive optimize the repository at the expense
+	of taking much more time.  The effects of this optimization are
+	persistent, so this option only needs to be sporadically; every
+	few hundred changesets or so.
 
 Configuration
 -------------
@@ -67,6 +74,13 @@ The optional configuration variable 'gc.packrefs' determines if
 is not run in bare repositories by default, to allow older dumb-transport
 clients fetch from the repository,  but this will change in the future.
 
+The optional configuration variable 'gc.aggressiveWindow' controls how
+much time is spent optimizing the delta compression of the objects in
+the repository when the --aggressive option is specified.  The larger
+the value, the more time is spent optimizing the delta compression.  See
+the documentation for the --window' option in gitlink:git-repack[1] for
+more details.  This defaults to 10.
+
 See Also
 --------
 gitlink:git-prune[1]
diff --git a/builtin-gc.c b/builtin-gc.c
index 3b1f8c2f3..8ea165aef 100644
--- a/builtin-gc.c
+++ b/builtin-gc.c
@@ -15,13 +15,15 @@
 
 #define FAILED_RUN "failed to run %s"
 
-static const char builtin_gc_usage[] = "git-gc [--prune]";
+static const char builtin_gc_usage[] = "git-gc [--prune] [--aggressive]";
 
 static int pack_refs = -1;
+static int aggressive_window = -1;
 
+#define MAX_ADD 10
 static const char *argv_pack_refs[] = {"pack-refs", "--prune", NULL};
 static const char *argv_reflog[] = {"reflog", "expire", "--all", NULL};
-static const char *argv_repack[] = {"repack", "-a", "-d", "-l", NULL};
+static const char *argv_repack[MAX_ADD] = {"repack", "-a", "-d", "-l", NULL};
 static const char *argv_prune[] = {"prune", NULL};
 static const char *argv_rerere[] = {"rerere", "gc", NULL};
 
@@ -34,13 +36,31 @@ static int gc_config(const char *var, const char *value)
 			pack_refs = git_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "gc.aggressivewindow")) {
+		aggressive_window = git_config_int(var, value);
+		return 0;
+	}
 	return git_default_config(var, value);
 }
 
+static void append_option(const char **cmd, const char *opt, int max_length)
+{
+	int i;
+
+	for (i = 0; cmd[i]; i++)
+		;
+
+	if (i + 2 >= max_length)
+		die("Too many options specified");
+	cmd[i++] = opt;
+	cmd[i] = NULL;
+}
+
 int cmd_gc(int argc, const char **argv, const char *prefix)
 {
 	int i;
 	int prune = 0;
+	char buf[80];
 
 	git_config(gc_config);
 
@@ -53,6 +73,14 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 			prune = 1;
 			continue;
 		}
+		if (!strcmp(arg, "--aggressive")) {
+			append_option(argv_repack, "-f", MAX_ADD);
+			if (aggressive_window > 0) {
+				sprintf(buf, "--window=%d", aggressive_window);
+				append_option(argv_repack, buf, MAX_ADD);
+			}
+			continue;
+		}
 		/* perhaps other parameters later... */
 		break;
 	}