summaryrefslogtreecommitdiff
path: root/grep.c
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2012-02-02 03:21:11 -0500
committerJunio C Hamano <gitster@pobox.com>2012-02-02 10:36:08 -0800
commit08265798e1ff6abc1b0aaff31c1471f83bd51425 (patch)
treea18db0e50f3687e3ccaf14766ac07e1bfc96e99e /grep.c
parent41b59bfcb16abb738e5c95c95fb462e717d47d4d (diff)
downloadgit-08265798e1ff6abc1b0aaff31c1471f83bd51425.tar.gz
grep: load file data after checking binary-ness
Usually we load each file to grep into memory, check whether it's binary, and then either grep it (the default) or not (if "-I" was given). In the "-I" case, we can skip loading the file entirely if it is marked as binary via gitattributes. On my giant 3-gigabyte media repository, doing "git grep -I foo" went from: real 0m0.712s user 0m0.044s sys 0m4.780s to: real 0m0.026s user 0m0.016s sys 0m0.020s Obviously this is an extreme example. The repo is almost entirely binary files, and you can see that we spent all of our time asking the kernel to read() the data. However, with a cold disk cache, even avoiding a few binary files can have an impact. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'grep.c')
-rw-r--r--grep.c6
1 files changed, 3 insertions, 3 deletions
diff --git a/grep.c b/grep.c
index a50d161721..3821400966 100644
--- a/grep.c
+++ b/grep.c
@@ -1019,9 +1019,6 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
}
opt->last_shown = 0;
- if (grep_source_load(gs) < 0)
- return 0;
-
switch (opt->binary) {
case GREP_BINARY_DEFAULT:
if (grep_source_is_binary(gs))
@@ -1042,6 +1039,9 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
try_lookahead = should_lookahead(opt);
+ if (grep_source_load(gs) < 0)
+ return 0;
+
bol = gs->buf;
left = gs->size;
while (left) {