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>

1 files changed, 50 insertions, 0 deletions

diff --git a/builtin/skew.c b/builtin/skew.c
new file mode 100644
index 000000000..1046f5f54
--- /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;
+}