git skew: a tool to find how big a clock skew exists in the history

> As you probably guessed from the specificity of the number, I wrote a
> short program to actually traverse and find the worst skew. It takes
> about 5 seconds to run (unsurprisingly, since it is doing the same full
> traversal that we end up doing in the above numbers). So we could
> "autoskew" by setting up the configuration on clone, and then
> periodically updating it as part of "git gc".

This patch doesn't implement auto-detection of skew, but is the program
I used to calculate, and would provide the basis for such
auto-detection. It would be interesting to see average skew numbers for
popular repositories. You can run it as "git skew --all".

Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 54 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
index 14e2b6bde9..90aff17860 100644
--- a/.gitignore
+++ b/.gitignore
@@ -132,6 +132,7 @@
 /git-show-branch
 /git-show-index
 /git-show-ref
+/git-skew
 /git-stage
 /git-stash
 /git-status
diff --git a/Makefile b/Makefile
index 9aca8a16d9..e673bdf603 100644
--- a/Makefile
+++ b/Makefile
@@ -725,6 +725,7 @@ BUILTIN_OBJS += builtin/send-pack.o
 BUILTIN_OBJS += builtin/shortlog.o
 BUILTIN_OBJS += builtin/show-branch.o
 BUILTIN_OBJS += builtin/show-ref.o
+BUILTIN_OBJS += builtin/skew.o
 BUILTIN_OBJS += builtin/stripspace.o
 BUILTIN_OBJS += builtin/symbolic-ref.o
 BUILTIN_OBJS += builtin/tag.o
diff --git a/builtin.h b/builtin.h
index ed6ee26933..5f5dc0abb8 100644
--- a/builtin.h
+++ b/builtin.h
@@ -141,5 +141,6 @@ extern int cmd_verify_pack(int argc, const char **argv, const char *prefix);
 extern int cmd_show_ref(int argc, const char **argv, const char *prefix);
 extern int cmd_pack_refs(int argc, const char **argv, const char *prefix);
 extern int cmd_replace(int argc, const char **argv, const char *prefix);
+extern int cmd_skew(int argc, const char **argv, const char *prefix);
 
 #endif
diff --git a/builtin/skew.c b/builtin/skew.c
new file mode 100644
index 0000000000..1046f5f546
--- /dev/null
+++ b/builtin/skew.c
@@ -0,0 +1,50 @@
+#include "cache.h"
+#include "commit.h"
+#include "diff.h"
+#include "revision.h"
+
+unsigned long worst_skew = 0;
+
+static void check_skew_recurse(struct commit *c, unsigned long when)
+{
+	struct commit_list *p;
+
+	if (c->object.flags & SEEN)
+		return;
+	c->object.flags |= SEEN;
+
+	if (parse_commit(c) < 0)
+		return;
+
+	if (c->date > when) {
+		unsigned long skew = c->date - when;
+		if (skew > worst_skew)
+			worst_skew = skew;
+	}
+
+	for (p = c->parents; p; p = p->next)
+		check_skew_recurse(p->item, c->date < when ? c->date : when);
+}
+
+static void check_skew(struct commit *c)
+{
+	check_skew_recurse(c, time(NULL));
+}
+
+int cmd_skew(int argc, const char **argv, const char *prefix) {
+	struct rev_info revs;
+	int i;
+
+	git_config(git_default_config, NULL);
+	init_revisions(&revs, prefix);
+	argc = setup_revisions(argc, argv, &revs, NULL);
+
+	for (i = 0; i < revs.pending.nr; i++) {
+		struct object *o = revs.pending.objects[i].item;
+		if (o->type == OBJ_COMMIT)
+			check_skew((struct commit *)o);
+	}
+
+	printf("%lu\n", worst_skew);
+	return 0;
+}
diff --git a/git.c b/git.c
index 265fa09d8d..8a77fe314c 100644
--- a/git.c
+++ b/git.c
@@ -399,6 +399,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "verify-pack", cmd_verify_pack },
 		{ "show-ref", cmd_show_ref, RUN_SETUP },
 		{ "pack-refs", cmd_pack_refs, RUN_SETUP },
+		{ "skew", cmd_skew, RUN_SETUP },
 	};
 	int i;
 	static const char ext[] = STRIP_EXTENSION;