1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-18 08:56:08 +02:00
git/diffcore-pickaxe.c

285 lines
6.6 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 00:41:57 +02:00
#include "kwset.h"
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 void fill_one(struct diff_filespec *one,
mmfile_t *mf, struct userdiff_driver **textconv)
{
if (DIFF_FILE_VALID(one)) {
*textconv = get_textconv(one);
mf->size = fill_textconv(*textconv, one, &mf->ptr);
} else {
memset(mf, 0, sizeof(*mf));
}
}
static int diff_grep(struct diff_filepair *p, regex_t *regexp, struct diff_options *o)
{
regmatch_t regmatch;
struct userdiff_driver *textconv_one = NULL;
struct userdiff_driver *textconv_two = NULL;
mmfile_t mf1, mf2;
int hit;
if (diff_unmodified_pair(p))
return 0;
fill_one(p->one, &mf1, &textconv_one);
fill_one(p->two, &mf2, &textconv_two);
if (!mf1.ptr) {
if (!mf2.ptr)
return 0; /* ignore unmerged */
/* created "two" -- does it have what we are looking for? */
hit = !regexec(regexp, p->two->data, 1, &regmatch, 0);
} else if (!mf2.ptr) {
/* removed "one" -- did it have what we are looking for? */
hit = !regexec(regexp, p->one->data, 1, &regmatch, 0);
} else {
/*
* We have both sides; need to run textual diff and see if
* the pattern appears on added/deleted lines.
*/
struct diffgrep_cb ecbdata;
xpparam_t xpp;
xdemitconf_t xecfg;
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(&mf1, &mf2, diffgrep_consume, &ecbdata,
&xpp, &xecfg);
hit = ecbdata.hit;
}
if (textconv_one)
free(mf1.ptr);
if (textconv_two)
free(mf2.ptr);
return hit;
}
static void diffcore_pickaxe_grep(struct diff_options *o)
{
struct diff_queue_struct *q = &diff_queued_diff;
int i, err;
regex_t regex;
struct diff_queue_struct outq;
outq.queue = NULL;
outq.nr = outq.alloc = 0;
err = regcomp(&regex, o->pickaxe, REG_EXTENDED | REG_NEWLINE);
if (err) {
char errbuf[1024];
regerror(err, &regex, errbuf, 1024);
regfree(&regex);
die("invalid log-grep regex: %s", errbuf);
}
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 (diff_grep(p, &regex, o))
goto out; /* 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 (diff_grep(p, &regex, o))
diff_q(&outq, p);
else
diff_free_filepair(p);
}
}
free(q->queue);
*q = outq;
out:
regfree(&regex);
return;
}
static unsigned int contains(struct diff_filespec *one,
const char *needle, unsigned long len,
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 00:41:57 +02:00
regex_t *regexp, kwset_t kws)
{
unsigned int cnt;
unsigned long sz;
const char *data;
if (!len)
return 0;
if (diff_populate_filespec(one, 0))
return 0;
sz = one->size;
data = one->data;
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) {
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 00:41:57 +02:00
size_t offset = kwsexec(kws, data, sz, NULL);
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 00:41:57 +02:00
else
found = data + offset;
sz -= found - data + len;
data = found + len;
cnt++;
}
}
diff_free_filespec_data(one);
return cnt;
}
static int has_changes(struct diff_filepair *p, const char *needle,
unsigned long len, regex_t *regexp, kwset_t kws)
{
if (!DIFF_FILE_VALID(p->one)) {
if (!DIFF_FILE_VALID(p->two))
return 0; /* ignore unmerged */
/* created */
return contains(p->two, needle, len, regexp, kws) != 0;
}
if (!DIFF_FILE_VALID(p->two))
return contains(p->one, needle, len, regexp, kws) != 0;
if (!diff_unmodified_pair(p)) {
return contains(p->one, needle, len, regexp, kws) !=
contains(p->two, needle, len, regexp, kws);
}
return 0;
}
static void diffcore_pickaxe_count(struct diff_options *o)
{
const char *needle = o->pickaxe;
int opts = o->pickaxe_opts;
struct diff_queue_struct *q = &diff_queued_diff;
unsigned long len = strlen(needle);
int i;
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 00:41:57 +02:00
kwset_t kws = NULL;
struct diff_queue_struct outq;
DIFF_QUEUE_CLEAR(&outq);
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 pickaxe 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 00:41:57 +02:00
} else {
kws = kwsalloc(NULL);
kwsincr(kws, needle, len);
kwsprep(kws);
}
if (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 (has_changes(p, needle, len, regexp, kws))
goto out; /* 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 (has_changes(p, needle, len, regexp, kws))
diff_q(&outq, p);
else
diff_free_filepair(p);
}
free(q->queue);
*q = outq;
out:
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 00:41:57 +02:00
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);
}