summaryrefslogtreecommitdiff
path: root/grep.c
diff options
context:
space:
mode:
authorFredrik Kuivinen <frekui@gmail.com>2011-08-20 22:42:18 (GMT)
committerJunio C Hamano <gitster@pobox.com>2011-08-21 05:33:58 (GMT)
commit9eceddeec6ccdbcb0c6ce02a45357ffd5a428f39 (patch)
treec30936b59bc81245ed33b7ce8c3b34efe675da9f /grep.c
parentb95c5ada990ee2afb83af9be5b82d2804618a59d (diff)
downloadgit-9eceddeec6ccdbcb0c6ce02a45357ffd5a428f39.zip
git-9eceddeec6ccdbcb0c6ce02a45357ffd5a428f39.tar.gz
git-9eceddeec6ccdbcb0c6ce02a45357ffd5a428f39.tar.bz2
Use kwset in grep
Benchmarks for the hot cache case: before: $ perf stat --repeat=5 git grep qwerty > /dev/null Performance counter stats for 'git grep qwerty' (5 runs): 3,478,085 cache-misses # 2.322 M/sec ( +- 2.690% ) 11,356,177 cache-references # 7.582 M/sec ( +- 2.598% ) 3,872,184 branch-misses # 0.363 % ( +- 0.258% ) 1,067,367,848 branches # 712.673 M/sec ( +- 2.622% ) 3,828,370,782 instructions # 0.947 IPC ( +- 0.033% ) 4,043,832,831 cycles # 2700.037 M/sec ( +- 0.167% ) 8,518 page-faults # 0.006 M/sec ( +- 3.648% ) 847 CPU-migrations # 0.001 M/sec ( +- 3.262% ) 6,546 context-switches # 0.004 M/sec ( +- 2.292% ) 1497.695495 task-clock-msecs # 3.303 CPUs ( +- 2.550% ) 0.453394396 seconds time elapsed ( +- 0.912% ) after: $ perf stat --repeat=5 git grep qwerty > /dev/null Performance counter stats for 'git grep qwerty' (5 runs): 2,989,918 cache-misses # 3.166 M/sec ( +- 5.013% ) 10,986,041 cache-references # 11.633 M/sec ( +- 4.899% ) (scaled from 95.06%) 3,511,993 branch-misses # 1.422 % ( +- 0.785% ) 246,893,561 branches # 261.433 M/sec ( +- 3.967% ) 1,392,727,757 instructions # 0.564 IPC ( +- 0.040% ) 2,468,142,397 cycles # 2613.494 M/sec ( +- 0.110% ) 7,747 page-faults # 0.008 M/sec ( +- 3.995% ) 897 CPU-migrations # 0.001 M/sec ( +- 2.383% ) 6,535 context-switches # 0.007 M/sec ( +- 1.993% ) 944.384228 task-clock-msecs # 3.177 CPUs ( +- 0.268% ) 0.297257643 seconds time elapsed ( +- 0.450% ) So we gain about 35% by using the kwset code. As a side effect of using kwset two grep tests are fixed by this patch. The first is fixed because kwset can deal with case-insensitive search containing NULs, something strcasestr cannot do. The second one is fixed because we consider patterns containing NULs as fixed strings (regcomp cannot accept patterns with NULs). Signed-off-by: Fredrik Kuivinen <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'grep.c')
-rw-r--r--grep.c66
1 files changed, 45 insertions, 21 deletions
diff --git a/grep.c b/grep.c
index 26e8d8e..6618cd8 100644
--- a/grep.c
+++ b/grep.c
@@ -137,16 +137,50 @@ static void free_pcre_regexp(struct grep_pat *p)
}
#endif /* !USE_LIBPCRE */
+static int is_fixed(const char *s, size_t len)
+{
+ size_t i;
+
+ /* regcomp cannot accept patterns with NULs so we
+ * consider any pattern containing a NUL fixed.
+ */
+ if (memchr(s, 0, len))
+ return 1;
+
+ for (i = 0; i < len; i++) {
+ if (is_regex_special(s[i]))
+ return 0;
+ }
+
+ return 1;
+}
+
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
int err;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
- p->fixed = opt->fixed;
- if (p->fixed)
+ if (opt->fixed || is_fixed(p->pattern, p->patternlen))
+ p->fixed = 1;
+ else
+ p->fixed = 0;
+
+ if (p->fixed) {
+ if (opt->regflags & REG_ICASE || p->ignore_case) {
+ static char trans[256];
+ int i;
+ for (i = 0; i < 256; i++)
+ trans[i] = tolower(i);
+ p->kws = kwsalloc(trans);
+ } else {
+ p->kws = kwsalloc(NULL);
+ }
+ kwsincr(p->kws, p->pattern, p->patternlen);
+ kwsprep(p->kws);
return;
+ }
if (opt->pcre) {
compile_pcre_regexp(p, opt);
@@ -395,7 +429,9 @@ void free_grep_patterns(struct grep_opt *opt)
case GREP_PATTERN: /* atom */
case GREP_PATTERN_HEAD:
case GREP_PATTERN_BODY:
- if (p->pcre_regexp)
+ if (p->kws)
+ kwsfree(p->kws);
+ else if (p->pcre_regexp)
free_pcre_regexp(p);
else
regfree(&p->regexp);
@@ -455,26 +491,14 @@ static void show_name(struct grep_opt *opt, const char *name)
static int fixmatch(struct grep_pat *p, char *line, char *eol,
regmatch_t *match)
{
- char *hit;
-
- if (p->ignore_case) {
- char *s = line;
- do {
- hit = strcasestr(s, p->pattern);
- if (hit)
- break;
- s += strlen(s) + 1;
- } while (s < eol);
- } else
- hit = memmem(line, eol - line, p->pattern, p->patternlen);
-
- if (!hit) {
+ struct kwsmatch kwsm;
+ size_t offset = kwsexec(p->kws, line, eol - line, &kwsm);
+ if (offset == -1) {
match->rm_so = match->rm_eo = -1;
return REG_NOMATCH;
- }
- else {
- match->rm_so = hit - line;
- match->rm_eo = match->rm_so + p->patternlen;
+ } else {
+ match->rm_so = offset;
+ match->rm_eo = match->rm_so + kwsm.size[0];
return 0;
}
}