From 30b939c33ad5b8a9dfbe3fe5aafc36d89c40409f Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sun, 17 Mar 2013 04:38:57 -0400 Subject: [PATCH] fast-export: do not load blob objects twice When fast-export wants to export a blob object, it first calls parse_object to get a "struct object" and check whether we have already shown the object. If we haven't shown it, we then use read_sha1_file to pull it from disk and write it out. That means we load each blob from disk twice: once for parse_object to find its type and check its sha1, and a second time when we actually output it. We can drop this to a single load by using lookup_object to check the SHOWN flag, and then checking the signature on and outputting a single buffer. This provides modest speedups on git.git (best-of-five, "git fast-export HEAD >/dev/null"): [before] [after] real 0m14.347s real 0m13.780s user 0m14.084s user 0m13.620s sys 0m0.208s sys 0m0.100s and somewhat more on more blob-heavy repos (this is a repository full of media files): [before] [after] real 0m52.236s real 0m44.451s user 0m50.568s user 0m43.000s sys 0m1.536s sys 0m1.284s Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin/fast-export.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 9e89925312..ed2916595f 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -119,6 +119,7 @@ static void export_blob(const unsigned char *sha1) enum object_type type; char *buf; struct object *object; + int eaten; if (no_data) return; @@ -126,16 +127,18 @@ static void export_blob(const unsigned char *sha1) if (is_null_sha1(sha1)) return; - object = parse_object(sha1); - if (!object) - die ("Could not read blob %s", sha1_to_hex(sha1)); - - if (object->flags & SHOWN) + object = lookup_object(sha1); + if (object && object->flags & SHOWN) return; buf = read_sha1_file(sha1, &type, &size); if (!buf) die ("Could not read blob %s", sha1_to_hex(sha1)); + if (check_sha1_signature(sha1, buf, size, typename(type)) < 0) + die("sha1 mismatch in blob %s", sha1_to_hex(sha1)); + object = parse_object_buffer(sha1, type, size, buf, &eaten); + if (!object) + die("Could not read blob %s", sha1_to_hex(sha1)); mark_next_object(object); @@ -147,7 +150,8 @@ static void export_blob(const unsigned char *sha1) show_progress(); object->flags |= SHOWN; - free(buf); + if (!eaten) + free(buf); } static int depth_first(const void *a_, const void *b_) -- 2.11.4.GIT