From b95c5ada990ee2afb83af9be5b82d2804618a59d Mon Sep 17 00:00:00 2001 From: Fredrik Kuivinen Date: Sun, 21 Aug 2011 00:41:57 +0200 Subject: [PATCH] Use kwset in pickaxe Benchmarks in the hot cache case: before: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 47,092,744 cache-misses # 2.825 M/sec ( +- 1.607% ) 123,368,389 cache-references # 7.400 M/sec ( +- 0.812% ) 330,040,998 branch-misses # 3.134 % ( +- 0.257% ) 10,530,896,750 branches # 631.663 M/sec ( +- 0.121% ) 62,037,201,030 instructions # 1.399 IPC ( +- 0.142% ) 44,331,294,321 cycles # 2659.073 M/sec ( +- 0.326% ) 96,794 page-faults # 0.006 M/sec ( +- 11.952% ) 25 CPU-migrations # 0.000 M/sec ( +- 25.266% ) 1,424 context-switches # 0.000 M/sec ( +- 0.540% ) 16671.708650 task-clock-msecs # 0.997 CPUs ( +- 0.343% ) 16.728692052 seconds time elapsed ( +- 0.344% ) after: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 51,385,522 cache-misses # 4.619 M/sec ( +- 0.565% ) 129,177,880 cache-references # 11.611 M/sec ( +- 0.219% ) 319,222,775 branch-misses # 6.946 % ( +- 0.134% ) 4,595,913,233 branches # 413.086 M/sec ( +- 0.112% ) 31,395,042,533 instructions # 1.062 IPC ( +- 0.129% ) 29,558,348,598 cycles # 2656.740 M/sec ( +- 0.204% ) 93,224 page-faults # 0.008 M/sec ( +- 4.487% ) 19 CPU-migrations # 0.000 M/sec ( +- 10.425% ) 950 context-switches # 0.000 M/sec ( +- 0.360% ) 11125.796039 task-clock-msecs # 0.997 CPUs ( +- 0.239% ) 11.164216599 seconds time elapsed ( +- 0.240% ) So the kwset code is about 33% faster. Signed-off-by: Fredrik Kuivinen Signed-off-by: Junio C Hamano --- Makefile | 2 ++ diffcore-pickaxe.c | 34 +++++++++++++++++++++++----------- 2 files changed, 25 insertions(+), 11 deletions(-) diff --git a/Makefile b/Makefile index 4cd061fe8..45ef51f18 100644 --- a/Makefile +++ b/Makefile @@ -533,6 +533,7 @@ LIB_H += graph.h LIB_H += grep.h LIB_H += hash.h LIB_H += help.h +LIB_H += kwset.h LIB_H += levenshtein.h LIB_H += list-objects.h LIB_H += ll-merge.h @@ -624,6 +625,7 @@ LIB_OBJS += hash.o LIB_OBJS += help.o LIB_OBJS += hex.o LIB_OBJS += ident.o +LIB_OBJS += kwset.o LIB_OBJS += levenshtein.o LIB_OBJS += list-objects.o LIB_OBJS += ll-merge.o diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c index ea03b9107..c3760cfef 100644 --- a/diffcore-pickaxe.c +++ b/diffcore-pickaxe.c @@ -6,6 +6,7 @@ #include "diff.h" #include "diffcore.h" #include "xdiff-interface.h" +#include "kwset.h" struct diffgrep_cb { regex_t *regexp; @@ -146,7 +147,7 @@ static void diffcore_pickaxe_grep(struct diff_options *o) static unsigned int contains(struct diff_filespec *one, const char *needle, unsigned long len, - regex_t *regexp) + regex_t *regexp, kwset_t kws) { unsigned int cnt; unsigned long sz; @@ -175,9 +176,12 @@ static unsigned int contains(struct diff_filespec *one, } else { /* Classic exact string match */ while (sz) { - const char *found = memmem(data, sz, needle, len); - if (!found) + size_t offset = kwsexec(kws, data, sz, NULL); + const char *found; + if (offset == -1) break; + else + found = data + offset; sz -= found - data + len; data = found + len; cnt++; @@ -195,6 +199,7 @@ static void diffcore_pickaxe_count(struct diff_options *o) unsigned long len = strlen(needle); int i, has_changes; regex_t regex, *regexp = NULL; + kwset_t kws = NULL; struct diff_queue_struct outq; DIFF_QUEUE_CLEAR(&outq); @@ -209,6 +214,10 @@ static void diffcore_pickaxe_count(struct diff_options *o) die("invalid pickaxe regex: %s", errbuf); } regexp = ®ex; + } else { + kws = kwsalloc(NULL); + kwsincr(kws, needle, len); + kwsprep(kws); } if (opts & DIFF_PICKAXE_ALL) { @@ -219,16 +228,16 @@ static void diffcore_pickaxe_count(struct diff_options *o) if (!DIFF_FILE_VALID(p->two)) continue; /* ignore unmerged */ /* created */ - if (contains(p->two, needle, len, regexp)) + if (contains(p->two, needle, len, regexp, kws)) has_changes++; } else if (!DIFF_FILE_VALID(p->two)) { - if (contains(p->one, needle, len, regexp)) + if (contains(p->one, needle, len, regexp, kws)) has_changes++; } else if (!diff_unmodified_pair(p) && - contains(p->one, needle, len, regexp) != - contains(p->two, needle, len, regexp)) + contains(p->one, needle, len, regexp, kws) != + contains(p->two, needle, len, regexp, kws)) has_changes++; } if (has_changes) @@ -251,16 +260,17 @@ static void diffcore_pickaxe_count(struct diff_options *o) if (!DIFF_FILE_VALID(p->two)) ; /* ignore unmerged */ /* created */ - else if (contains(p->two, needle, len, regexp)) + else if (contains(p->two, needle, len, regexp, + kws)) has_changes = 1; } else if (!DIFF_FILE_VALID(p->two)) { - if (contains(p->one, needle, len, regexp)) + if (contains(p->one, needle, len, regexp, kws)) has_changes = 1; } else if (!diff_unmodified_pair(p) && - contains(p->one, needle, len, regexp) != - contains(p->two, needle, len, regexp)) + contains(p->one, needle, len, regexp, kws) != + contains(p->two, needle, len, regexp, kws)) has_changes = 1; if (has_changes) @@ -271,6 +281,8 @@ static void diffcore_pickaxe_count(struct diff_options *o) if (opts & DIFF_PICKAXE_REGEX) regfree(®ex); + else + kwsfree(kws); free(q->queue); *q = outq; -- 2.26.2