From 7d65848afd42f075f6db0d03da2c9f5a9bac6267 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 May 2006 16:16:15 -0700 Subject: [PATCH] Don't use "sscanf()" for tree mode scanning Doing an oprofile run on the result of my git rev-list memory leak fixes and tree parsing cleanups, I was surprised by the third-highest entry being samples % image name app name symbol name 179751 2.7163 libc-2.4.so libc-2.4.so _IO_vfscanf@@GLIBC_2.4 where that 2.7% is actually more than 5% of one CPU, because this was run on a dual CPU setup with the other CPU just being idle. That seems to all be from the use of 'sscanf(tree, "%o", &mode)' for the tree buffer parsing. So do the trivial octal parsing by hand, which also gives us where the first space in the string is (and thus where the pathname starts) so we can get rid of the "strchr(tree, ' ')" call too. This brings the "git rev-list --all --objects" time down from 63 seconds to 55 seconds on the historical kernel archive for me, so it's quite noticeable - tree parsing is a lot of what we end up doing when following all the objects. [ I also see a 5% speedup on a full "git fsck-objects" on the current kernel archive, so that sscanf() really does seem to have hurt our performance by a surprising amount ] Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano --- tree-walk.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/tree-walk.c b/tree-walk.c index 9f7abb7c..39220582 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -47,18 +47,33 @@ void update_tree_entry(struct tree_desc *desc) desc->size = size - len; } +static const char *get_mode(const char *str, unsigned int *modep) +{ + unsigned char c; + unsigned int mode = 0; + + while ((c = *str++) != ' ') { + if (c < '0' || c > '7') + return NULL; + mode = (mode << 3) + (c - '0'); + } + *modep = mode; + return str; +} + const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep) { void *tree = desc->buf; unsigned long size = desc->size; int len = strlen(tree)+1; const unsigned char *sha1 = tree + len; - const char *path = strchr(tree, ' '); + const char *path; unsigned int mode; - if (!path || size < len + 20 || sscanf(tree, "%o", &mode) != 1) + path = get_mode(tree, &mode); + if (!path || size < len + 20) die("corrupt tree file"); - *pathp = path+1; + *pathp = path; *modep = canon_mode(mode); return sha1; } -- 2.11.0