git/test-wildmatch.c

101 lines
2.7 KiB
C
Raw Normal View History

#ifdef USE_WILDMATCH
#undef USE_WILDMATCH /* We need real fnmatch implementation here */
#endif
#include "cache.h"
#include "wildmatch.h"
test-wildmatch: add "perf" command to compare wildmatch and fnmatch It takes a text file, a pattern, a number <n> and pathname flag. Each line in the text file is matched against the pattern <n> times. If "pathname" is given, FNM_PATHNAME is used. test-wildmatch is built with -O2 and tested against glibc 2.14.1 (also -O2) and compat/fnmatch. The input file is linux-2.6.git file list. <n> is 2000. The complete command list is at the end. wildmatch is beaten in the following cases. Apparently it needs some improvement in FNM_PATHNAME case: glibc, '*/*/*' with FNM_PATHNAME: wildmatch 8s 1559us fnmatch 1s 11877us or 12.65% faster compat, '*/*/*' with FNM_PATHNAME: wildmatch 7s 922458us fnmatch 2s 905111us or 36.67% faster compat, '*/*/*' without FNM_PATHNAME: wildmatch 7s 264201us fnmatch 2s 1897us or 27.56% faster compat, '[a-z]*/[a-z]*/[a-z]*' with FNM_PATHNAME: wildmatch 8s 742827us fnmatch 0s 922943us or 10.56% faster compat, '[a-z]*/[a-z]*/[a-z]*' without FNM_PATHNAME: wildmatch 8s 284520us fnmatch 0s 6936us or 0.08% faster The rest of glibc numbers ------------------------- 'Documentation/*' wildmatch 1s 529479us fnmatch 1s 98263us or 71.81% slower 'drivers/*' wildmatch 1s 988288us fnmatch 1s 192049us or 59.95% slower 'Documentation/*' pathname wildmatch 1s 557507us fnmatch 1s 93696us or 70.22% slower 'drivers/*' pathname wildmatch 2s 161626us fnmatch 1s 230372us or 56.92% slower '[Dd]ocu[Mn]entation/*' wildmatch 1s 776581us fnmatch 1s 471693us or 82.84% slower '[Dd]o?u[Mn]en?ati?n/*' wildmatch 1s 770770us fnmatch 1s 555727us or 87.86% slower '[Dd]o?u[Mn]en?ati?n/*' pathname wildmatch 1s 783507us fnmatch 1s 537029us or 86.18% slower '[A-Za-z][A-Za-z]??*' wildmatch 4s 110386us fnmatch 4s 926306us or 119.85% slower '[A-Za-z][A-Za-z]??' wildmatch 3s 918114us fnmatch 3s 686175us or 94.08% slower '[A-Za-z][A-Za-z]??*' pathname wildmatch 4s 453746us fnmatch 4s 955856us or 111.27% slower '[A-Za-z][A-Za-z]??' pathname wildmatch 3s 896646us fnmatch 3s 733828us or 95.82% slower '*/*/*' wildmatch 7s 287985us fnmatch 1s 74083us or 14.74% slower '[a-z]*/[a-z]*/[a-z]*' pathname wildmatch 8s 796659us fnmatch 1s 568409us or 17.83% slower '[a-z]*/[a-z]*/[a-z]*' wildmatch 8s 316559us fnmatch 3s 430652us or 41.25% slower The rest of compat numbers -------------------------- 'Documentation/*' wildmatch 1s 520389us fnmatch 0s 62579us or 4.12% slower 'drivers/*' wildmatch 1s 955354us fnmatch 0s 190109us or 9.72% slower 'Documentation/*' pathname wildmatch 1s 561675us fnmatch 0s 55336us or 3.54% slower 'drivers/*' pathname wildmatch 2s 106100us fnmatch 0s 219680us or 10.43% slower '[Dd]ocu[Mn]entation/*' wildmatch 1s 750810us fnmatch 0s 542721us or 31.00% slower '[Dd]o?u[Mn]en?ati?n/*' wildmatch 1s 724791us fnmatch 0s 538948us or 31.25% slower '[Dd]o?u[Mn]en?ati?n/*' pathname wildmatch 1s 731403us fnmatch 0s 537474us or 31.04% slower '[A-Za-z][A-Za-z]??*' wildmatch 4s 28555us fnmatch 1s 67297us or 26.49% slower '[A-Za-z][A-Za-z]??' wildmatch 3s 838279us fnmatch 0s 880005us or 22.93% slower '[A-Za-z][A-Za-z]??*' pathname wildmatch 4s 379476us fnmatch 1s 55643us or 24.10% slower '[A-Za-z][A-Za-z]??' pathname wildmatch 3s 830910us fnmatch 0s 849699us or 22.18% slower The following commands are used: LANG=C ./test-wildmatch perf /tmp/filelist.txt 'Documentation/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt 'drivers/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt 'Documentation/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt 'drivers/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[Dd]ocu[Mn]entation/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[Dd]o?u[Mn]en?ati?n/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[Dd]o?u[Mn]en?ati?n/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '*/*/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '*/*/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[a-z]*/[a-z]*/[a-z]*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[a-z]*/[a-z]*/[a-z]*' 2000 Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-01-01 10:44:08 +08:00
static int perf(int ac, char **av)
{
struct timeval tv1, tv2;
struct stat st;
int fd, i, n, flags1 = 0, flags2 = 0;
char *buffer, *p;
uint32_t usec1, usec2;
const char *lang;
const char *file = av[0];
const char *pattern = av[1];
lang = getenv("LANG");
if (lang && strcmp(lang, "C"))
die("Please test it on C locale.");
if ((fd = open(file, O_RDONLY)) == -1 || fstat(fd, &st))
die_errno("file open");
buffer = xmalloc(st.st_size + 2);
if (read(fd, buffer, st.st_size) != st.st_size)
die_errno("read");
buffer[st.st_size] = '\0';
buffer[st.st_size + 1] = '\0';
for (i = 0; i < st.st_size; i++)
if (buffer[i] == '\n')
buffer[i] = '\0';
n = atoi(av[2]);
if (av[3] && !strcmp(av[3], "pathname")) {
flags1 = WM_PATHNAME;
flags2 = FNM_PATHNAME;
}
gettimeofday(&tv1, NULL);
for (i = 0; i < n; i++) {
for (p = buffer; *p; p += strlen(p) + 1)
wildmatch(pattern, p, flags1, NULL);
}
gettimeofday(&tv2, NULL);
usec1 = (uint32_t)tv2.tv_sec * 1000000 + tv2.tv_usec;
usec1 -= (uint32_t)tv1.tv_sec * 1000000 + tv1.tv_usec;
printf("wildmatch %ds %dus\n",
(int)(usec1 / 1000000),
(int)(usec1 % 1000000));
gettimeofday(&tv1, NULL);
for (i = 0; i < n; i++) {
for (p = buffer; *p; p += strlen(p) + 1)
fnmatch(pattern, p, flags2);
}
gettimeofday(&tv2, NULL);
usec2 = (uint32_t)tv2.tv_sec * 1000000 + tv2.tv_usec;
usec2 -= (uint32_t)tv1.tv_sec * 1000000 + tv1.tv_usec;
if (usec2 > usec1)
printf("fnmatch %ds %dus or %.2f%% slower\n",
(int)((usec2 - usec1) / 1000000),
(int)((usec2 - usec1) % 1000000),
(float)(usec2 - usec1) / usec1 * 100);
else
printf("fnmatch %ds %dus or %.2f%% faster\n",
(int)((usec1 - usec2) / 1000000),
(int)((usec1 - usec2) % 1000000),
(float)(usec1 - usec2) / usec1 * 100);
return 0;
}
int main(int argc, char **argv)
{
int i;
test-wildmatch: add "perf" command to compare wildmatch and fnmatch It takes a text file, a pattern, a number <n> and pathname flag. Each line in the text file is matched against the pattern <n> times. If "pathname" is given, FNM_PATHNAME is used. test-wildmatch is built with -O2 and tested against glibc 2.14.1 (also -O2) and compat/fnmatch. The input file is linux-2.6.git file list. <n> is 2000. The complete command list is at the end. wildmatch is beaten in the following cases. Apparently it needs some improvement in FNM_PATHNAME case: glibc, '*/*/*' with FNM_PATHNAME: wildmatch 8s 1559us fnmatch 1s 11877us or 12.65% faster compat, '*/*/*' with FNM_PATHNAME: wildmatch 7s 922458us fnmatch 2s 905111us or 36.67% faster compat, '*/*/*' without FNM_PATHNAME: wildmatch 7s 264201us fnmatch 2s 1897us or 27.56% faster compat, '[a-z]*/[a-z]*/[a-z]*' with FNM_PATHNAME: wildmatch 8s 742827us fnmatch 0s 922943us or 10.56% faster compat, '[a-z]*/[a-z]*/[a-z]*' without FNM_PATHNAME: wildmatch 8s 284520us fnmatch 0s 6936us or 0.08% faster The rest of glibc numbers ------------------------- 'Documentation/*' wildmatch 1s 529479us fnmatch 1s 98263us or 71.81% slower 'drivers/*' wildmatch 1s 988288us fnmatch 1s 192049us or 59.95% slower 'Documentation/*' pathname wildmatch 1s 557507us fnmatch 1s 93696us or 70.22% slower 'drivers/*' pathname wildmatch 2s 161626us fnmatch 1s 230372us or 56.92% slower '[Dd]ocu[Mn]entation/*' wildmatch 1s 776581us fnmatch 1s 471693us or 82.84% slower '[Dd]o?u[Mn]en?ati?n/*' wildmatch 1s 770770us fnmatch 1s 555727us or 87.86% slower '[Dd]o?u[Mn]en?ati?n/*' pathname wildmatch 1s 783507us fnmatch 1s 537029us or 86.18% slower '[A-Za-z][A-Za-z]??*' wildmatch 4s 110386us fnmatch 4s 926306us or 119.85% slower '[A-Za-z][A-Za-z]??' wildmatch 3s 918114us fnmatch 3s 686175us or 94.08% slower '[A-Za-z][A-Za-z]??*' pathname wildmatch 4s 453746us fnmatch 4s 955856us or 111.27% slower '[A-Za-z][A-Za-z]??' pathname wildmatch 3s 896646us fnmatch 3s 733828us or 95.82% slower '*/*/*' wildmatch 7s 287985us fnmatch 1s 74083us or 14.74% slower '[a-z]*/[a-z]*/[a-z]*' pathname wildmatch 8s 796659us fnmatch 1s 568409us or 17.83% slower '[a-z]*/[a-z]*/[a-z]*' wildmatch 8s 316559us fnmatch 3s 430652us or 41.25% slower The rest of compat numbers -------------------------- 'Documentation/*' wildmatch 1s 520389us fnmatch 0s 62579us or 4.12% slower 'drivers/*' wildmatch 1s 955354us fnmatch 0s 190109us or 9.72% slower 'Documentation/*' pathname wildmatch 1s 561675us fnmatch 0s 55336us or 3.54% slower 'drivers/*' pathname wildmatch 2s 106100us fnmatch 0s 219680us or 10.43% slower '[Dd]ocu[Mn]entation/*' wildmatch 1s 750810us fnmatch 0s 542721us or 31.00% slower '[Dd]o?u[Mn]en?ati?n/*' wildmatch 1s 724791us fnmatch 0s 538948us or 31.25% slower '[Dd]o?u[Mn]en?ati?n/*' pathname wildmatch 1s 731403us fnmatch 0s 537474us or 31.04% slower '[A-Za-z][A-Za-z]??*' wildmatch 4s 28555us fnmatch 1s 67297us or 26.49% slower '[A-Za-z][A-Za-z]??' wildmatch 3s 838279us fnmatch 0s 880005us or 22.93% slower '[A-Za-z][A-Za-z]??*' pathname wildmatch 4s 379476us fnmatch 1s 55643us or 24.10% slower '[A-Za-z][A-Za-z]??' pathname wildmatch 3s 830910us fnmatch 0s 849699us or 22.18% slower The following commands are used: LANG=C ./test-wildmatch perf /tmp/filelist.txt 'Documentation/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt 'drivers/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt 'Documentation/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt 'drivers/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[Dd]ocu[Mn]entation/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[Dd]o?u[Mn]en?ati?n/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[Dd]o?u[Mn]en?ati?n/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[A-Za-z][A-Za-z]??' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '*/*/*' 2000 LANG=C ./test-wildmatch perf /tmp/filelist.txt '*/*/*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[a-z]*/[a-z]*/[a-z]*' 2000 pathname LANG=C ./test-wildmatch perf /tmp/filelist.txt '[a-z]*/[a-z]*/[a-z]*' 2000 Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-01-01 10:44:08 +08:00
if (!strcmp(argv[1], "perf"))
return perf(argc - 2, argv + 2);
for (i = 2; i < argc; i++) {
if (argv[i][0] == '/')
die("Forward slash is not allowed at the beginning of the\n"
"pattern because Windows does not like it. Use `XXX/' instead.");
else if (!strncmp(argv[i], "XXX/", 4))
argv[i] += 3;
}
if (!strcmp(argv[1], "wildmatch"))
return !!wildmatch(argv[3], argv[2], WM_PATHNAME, NULL);
else if (!strcmp(argv[1], "iwildmatch"))
return !!wildmatch(argv[3], argv[2], WM_PATHNAME | WM_CASEFOLD, NULL);
else if (!strcmp(argv[1], "pathmatch"))
return !!wildmatch(argv[3], argv[2], 0, NULL);
else if (!strcmp(argv[1], "fnmatch"))
return !!fnmatch(argv[3], argv[2], FNM_PATHNAME);
else
return 1;
}