git/diffcore-pickaxe.c

273 lines
6.4 KiB
C
Raw Normal View History

/*
* Copyright (C) 2005 Junio C Hamano
* Copyright (C) 2010 Google Inc.
*/
#include "cache.h"
#include "diff.h"
#include "diffcore.h"
#include "xdiff-interface.h"
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 <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 06:41:57 +08:00
#include "kwset.h"
typedef int (*pickaxe_fn)(mmfile_t *one, mmfile_t *two,
struct diff_options *o,
regex_t *regexp, kwset_t kws);
static int pickaxe_match(struct diff_filepair *p, struct diff_options *o,
regex_t *regexp, kwset_t kws, pickaxe_fn fn);
static void pickaxe(struct diff_queue_struct *q, struct diff_options *o,
regex_t *regexp, kwset_t kws, pickaxe_fn fn)
{
int i;
struct diff_queue_struct outq;
DIFF_QUEUE_CLEAR(&outq);
if (o->pickaxe_opts & DIFF_PICKAXE_ALL) {
/* Showing the whole changeset if needle exists */
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (pickaxe_match(p, o, regexp, kws, fn))
return; /* do not munge the queue */
}
/*
* Otherwise we will clear the whole queue by copying
* the empty outq at the end of this function, but
* first clear the current entries in the queue.
*/
for (i = 0; i < q->nr; i++)
diff_free_filepair(q->queue[i]);
} else {
/* Showing only the filepairs that has the needle */
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (pickaxe_match(p, o, regexp, kws, fn))
diff_q(&outq, p);
else
diff_free_filepair(p);
}
}
free(q->queue);
*q = outq;
}
struct diffgrep_cb {
regex_t *regexp;
int hit;
};
static void diffgrep_consume(void *priv, char *line, unsigned long len)
{
struct diffgrep_cb *data = priv;
regmatch_t regmatch;
int hold;
if (line[0] != '+' && line[0] != '-')
return;
if (data->hit)
/*
* NEEDSWORK: we should have a way to terminate the
* caller early.
*/
return;
/* Yuck -- line ought to be "const char *"! */
hold = line[len];
line[len] = '\0';
data->hit = !regexec(data->regexp, line + 1, 1, &regmatch, 0);
line[len] = hold;
}
static int diff_grep(mmfile_t *one, mmfile_t *two,
struct diff_options *o,
regex_t *regexp, kwset_t kws)
{
regmatch_t regmatch;
struct diffgrep_cb ecbdata;
xpparam_t xpp;
xdemitconf_t xecfg;
if (!one)
return !regexec(regexp, two->ptr, 1, &regmatch, 0);
if (!two)
return !regexec(regexp, one->ptr, 1, &regmatch, 0);
/*
* We have both sides; need to run textual diff and see if
* the pattern appears on added/deleted lines.
*/
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
ecbdata.regexp = regexp;
ecbdata.hit = 0;
xecfg.ctxlen = o->context;
xecfg.interhunkctxlen = o->interhunkcontext;
xdi_diff_outf(one, two, diffgrep_consume, &ecbdata,
&xpp, &xecfg);
return ecbdata.hit;
}
static void diffcore_pickaxe_grep(struct diff_options *o)
{
int err;
regex_t regex;
int cflags = REG_EXTENDED | REG_NEWLINE;
if (DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE))
cflags |= REG_ICASE;
err = regcomp(&regex, o->pickaxe, cflags);
if (err) {
char errbuf[1024];
regerror(err, &regex, errbuf, 1024);
regfree(&regex);
die("invalid regex: %s", errbuf);
}
pickaxe(&diff_queued_diff, o, &regex, NULL, diff_grep);
regfree(&regex);
return;
}
static unsigned int contains(mmfile_t *mf, regex_t *regexp, kwset_t kws)
{
unsigned int cnt;
unsigned long sz;
const char *data;
sz = mf->size;
data = mf->ptr;
cnt = 0;
if (regexp) {
regmatch_t regmatch;
int flags = 0;
assert(data[sz] == '\0');
while (*data && !regexec(regexp, data, 1, &regmatch, flags)) {
flags |= REG_NOTBOL;
data += regmatch.rm_eo;
if (*data && regmatch.rm_so == regmatch.rm_eo)
data++;
cnt++;
}
} else { /* Classic exact string match */
while (sz) {
struct kwsmatch kwsm;
size_t offset = kwsexec(kws, data, sz, &kwsm);
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 <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 06:41:57 +08:00
const char *found;
if (offset == -1)
break;
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 <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 06:41:57 +08:00
else
found = data + offset;
sz -= found - data + kwsm.size[0];
data = found + kwsm.size[0];
cnt++;
}
}
return cnt;
}
static int has_changes(mmfile_t *one, mmfile_t *two,
struct diff_options *o,
regex_t *regexp, kwset_t kws)
{
unsigned int one_contains = one ? contains(one, regexp, kws) : 0;
unsigned int two_contains = two ? contains(two, regexp, kws) : 0;
return one_contains != two_contains;
}
static int pickaxe_match(struct diff_filepair *p, struct diff_options *o,
regex_t *regexp, kwset_t kws, pickaxe_fn fn)
{
struct userdiff_driver *textconv_one = NULL;
struct userdiff_driver *textconv_two = NULL;
mmfile_t mf1, mf2;
int ret;
if (!o->pickaxe[0])
return 0;
/* ignore unmerged */
if (!DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two))
return 0;
if (DIFF_OPT_TST(o, ALLOW_TEXTCONV)) {
textconv_one = get_textconv(p->one);
textconv_two = get_textconv(p->two);
}
/*
* If we have an unmodified pair, we know that the count will be the
* same and don't even have to load the blobs. Unless textconv is in
* play, _and_ we are using two different textconv filters (e.g.,
* because a pair is an exact rename with different textconv attributes
* for each side, which might generate different content).
*/
if (textconv_one == textconv_two && diff_unmodified_pair(p))
return 0;
mf1.size = fill_textconv(textconv_one, p->one, &mf1.ptr);
mf2.size = fill_textconv(textconv_two, p->two, &mf2.ptr);
ret = fn(DIFF_FILE_VALID(p->one) ? &mf1 : NULL,
DIFF_FILE_VALID(p->two) ? &mf2 : NULL,
o, regexp, kws);
if (textconv_one)
free(mf1.ptr);
if (textconv_two)
free(mf2.ptr);
diff_free_filespec_data(p->one);
diff_free_filespec_data(p->two);
return ret;
}
static void diffcore_pickaxe_count(struct diff_options *o)
{
const char *needle = o->pickaxe;
int opts = o->pickaxe_opts;
unsigned long len = strlen(needle);
regex_t regex, *regexp = NULL;
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 <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 06:41:57 +08:00
kwset_t kws = NULL;
if (opts & DIFF_PICKAXE_REGEX) {
int err;
err = regcomp(&regex, needle, REG_EXTENDED | REG_NEWLINE);
if (err) {
/* The POSIX.2 people are surely sick */
char errbuf[1024];
regerror(err, &regex, errbuf, 1024);
regfree(&regex);
die("invalid regex: %s", errbuf);
}
regexp = &regex;
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 <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 06:41:57 +08:00
} else {
kws = kwsalloc(DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE)
? tolower_trans_tbl : NULL);
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 <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 06:41:57 +08:00
kwsincr(kws, needle, len);
kwsprep(kws);
}
pickaxe(&diff_queued_diff, o, regexp, kws, has_changes);
if (opts & DIFF_PICKAXE_REGEX)
regfree(&regex);
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 <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 06:41:57 +08:00
else
kwsfree(kws);
return;
}
void diffcore_pickaxe(struct diff_options *o)
{
/* Might want to warn when both S and G are on; I don't care... */
if (o->pickaxe_opts & DIFF_PICKAXE_KIND_G)
diffcore_pickaxe_grep(o);
else
diffcore_pickaxe_count(o);
}