grep: add support for the PCRE v1 JIT API

Change the grep PCRE v1 code to use JIT when available. When PCRE
support was initially added in commit 63e7e9d8b6 ("git-grep: Learn
PCRE", 2011-05-09) PCRE had no JIT support, it was integrated into
8.20 released on 2011-10-21.

Enabling JIT support usually improves performance by more than
40%. The pattern compilation times are relatively slower, but those
relative numbers are tiny, and are easily made back in all but the
most trivial cases of grep. Detailed benchmarks & overview of
compilation times is at: http://sljit.sourceforge.net/pcre.html

With this change the difference in a t/perf/p7820-grep-engines.sh run
is, with just the /perl/ tests shown:

    $ GIT_PERF_REPEAT_COUNT=30 GIT_PERF_LARGE_REPO=~/g/linux GIT_PERF_MAKE_OPTS='-j8 USE_LIBPCRE=YesPlease CC=~/perl5/installed/bin/gcc NO_R_TO_GCC_LINKER=YesPlease CFLAGS=-O3 LIBPCREDIR=/home/avar/g/pcre/inst LDFLAGS=-Wl,-rpath,/home/avar/g/pcre/inst/lib' ./run HEAD~ HEAD p7820-grep-engines.sh
    Test                                           HEAD~             HEAD
    ---------------------------------------------------------------------------------------
    7820.3: perl grep 'how.to'                      0.35(1.11+0.43)   0.23(0.42+0.46) -34.3%
    7820.7: perl grep '^how to'                     0.64(2.71+0.36)   0.27(0.66+0.44) -57.8%
    7820.11: perl grep '[how] to'                   0.63(2.51+0.42)   0.33(0.98+0.39) -47.6%
    7820.15: perl grep '(e.t[^ ]*|v.ry) rare'       1.17(5.61+0.35)   0.34(1.08+0.46) -70.9%
    7820.19: perl grep 'm(ú|u)lt.b(æ|y)te'          0.43(1.52+0.44)   0.30(0.88+0.42) -30.2%

The conditional support for JIT is implemented as suggested in the
pcrejit(3) man page. E.g. defining PCRE_STUDY_JIT_COMPILE to 0 if it's
not present.

The implementation is relatively verbose because even if
PCRE_CONFIG_JIT is defined only a call to pcre_config() can determine
if the JIT is available, and if so the faster pcre_jit_exec() function
should be called instead of pcre_exec(), and a different (but not
complimentary!) function needs to be called to free pcre1_extra_info.

There's no graceful fallback if pcre_jit_stack_alloc() fails under
PCRE_CONFIG_JIT, instead the program will simply abort. I don't think
this is worth handling gracefully, it'll only fail in cases where
malloc() doesn't work, in which case we're screwed anyway.

That there's no assignment of `p->pcre1_jit_on = 0` when
PCRE_CONFIG_JIT isn't defined isn't a bug. The create_grep_pat()
function allocates the grep_pat allocates it with calloc(), so it's
guaranteed to be 0 when PCRE_CONFIG_JIT isn't defined.

I you're bisecting and find this change, check that your PCRE isn't
older than 8.32. This change intentionally broke really old versions
of PCRE, but that's fixed in follow-up commits.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/grep.c b/grep.c
index d03d424e5cf8d32d91e3082555d8add674e01486..ffe95995eee4351cabe8bfd956617e7dfa97d0eb 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -365,9 +365,22 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
        if (!p->pcre1_regexp)
                compile_regexp_failed(p, error);
 
-       p->pcre1_extra_info = pcre_study(p->pcre1_regexp, 0, &error);
+       p->pcre1_extra_info = pcre_study(p->pcre1_regexp, PCRE_STUDY_JIT_COMPILE, &error);
        if (!p->pcre1_extra_info && error)
                die("%s", error);
+
+#ifdef PCRE_CONFIG_JIT
+       pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on);
+       if (p->pcre1_jit_on == 1) {
+               p->pcre1_jit_stack = pcre_jit_stack_alloc(1, 1024 * 1024);
+               if (!p->pcre1_jit_stack)
+                       die("Couldn't allocate PCRE JIT stack");
+               pcre_assign_jit_stack(p->pcre1_extra_info, NULL, p->pcre1_jit_stack);
+       } else if (p->pcre1_jit_on != 0) {
+               die("BUG: The pcre1_jit_on variable should be 0 or 1, not %d",
+                   p->pcre1_jit_on);
+       }
+#endif
 }
 
 static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
@@ -378,8 +391,19 @@ static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
        if (eflags & REG_NOTBOL)
                flags |= PCRE_NOTBOL;
 
-       ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line, eol - line,
-                       0, flags, ovector, ARRAY_SIZE(ovector));
+#ifdef PCRE_CONFIG_JIT
+       if (p->pcre1_jit_on) {
+               ret = pcre_jit_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
+                                   eol - line, 0, flags, ovector,
+                                   ARRAY_SIZE(ovector), p->pcre1_jit_stack);
+       } else
+#endif
+       {
+               ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
+                               eol - line, 0, flags, ovector,
+                               ARRAY_SIZE(ovector));
+       }
+
        if (ret < 0 && ret != PCRE_ERROR_NOMATCH)
                die("pcre_exec failed with error code %d", ret);
        if (ret > 0) {
@@ -394,7 +418,15 @@ static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
 static void free_pcre1_regexp(struct grep_pat *p)
 {
        pcre_free(p->pcre1_regexp);
-       pcre_free(p->pcre1_extra_info);
+#ifdef PCRE_CONFIG_JIT
+       if (p->pcre1_jit_on) {
+               pcre_free_study(p->pcre1_extra_info);
+               pcre_jit_stack_free(p->pcre1_jit_stack);
+       } else
+#endif
+       {
+               pcre_free(p->pcre1_extra_info);
+       }
        pcre_free((void *)p->pcre1_tables);
 }
 #else /* !USE_LIBPCRE1 */

diff --git a/grep.h b/grep.h
index 38ac82b6384f8c6a505a8ed764610aa8404f8597..14f47189f9f0c94f2863836446dd16ca00ca390e 100644 (file)
--- a/grep.h
+++ b/grep.h
@@ -3,9 +3,13 @@
 #include "color.h"
 #ifdef USE_LIBPCRE1
 #include <pcre.h>
+#ifndef PCRE_STUDY_JIT_COMPILE
+#define PCRE_STUDY_JIT_COMPILE 0
+#endif
 #else
 typedef int pcre;
 typedef int pcre_extra;
+typedef int pcre_jit_stack;
 #endif
 #include "kwset.h"
 #include "thread-utils.h"
@@ -48,7 +52,9 @@ struct grep_pat {
        regex_t regexp;
        pcre *pcre1_regexp;
        pcre_extra *pcre1_extra_info;
+       pcre_jit_stack *pcre1_jit_stack;
        const unsigned char *pcre1_tables;
+       int pcre1_jit_on;
        kwset_t kws;
        unsigned fixed:1;
        unsigned ignore_case:1;