While unpacking trees (e.g. during git checkout), when we hit a cache
entry that's past and outside our path, we cut off iteration.
This provides about a 45% speedup on git checkout between master and
master^20000 on Twitter's monorepo. Speedup in general will depend on
repostitory structure, number of changes, and packfile packing
decisions.
Signed-off-by: David Turner <dturner@xxxxxxxxxxxxxxxx>
---
unpack-trees.c | 19 ++++++++++++++++++-
1 file changed, 18 insertions(+), 1 deletion(-)
diff --git a/unpack-trees.c b/unpack-trees.c
index 5f541c2..b18a611 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -695,8 +695,25 @@ static int find_cache_pos(struct traverse_info *info,
++o->cache_bottom;
continue;
}
- if (!ce_in_traverse_path(ce, info))
+ if (!ce_in_traverse_path(ce, info)) {
+ /*
+ * Check if we can skip future cache checks
+ * (because we're already past all possible
+ * entries in the traverse path).
+ */
+ if (info->prev && info->traverse_path) {
+ int prefix_cmp = strncmp(ce->name, info->traverse_path, info->pathlen);
+ if (prefix_cmp > 0)
+ break;
+ else if (prefix_cmp == 0 &&
+ ce_namelen(ce) >= info->pathlen &&
+ strcmp(ce->name + info->pathlen,
+ info->name.path) > 0) {
+ break;
+ }
+ }
continue;
+ }
ce_name = ce->name + pfxlen;
ce_slash = strchr(ce_name, '/');
if (ce_slash)
--
2.4.2.749.g730654d-twtrsrc
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html