Web lists-archives.com

[PATCH v2 4/7] 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                      0.27(1.18+0.42)   0.19(0.30+0.68) -29.6%
    7820.7: perl grep ^how to                     0.48(2.74+0.41)   0.21(0.64+0.55) -56.2%
    7820.11: perl grep [how] to                   0.47(2.56+0.47)   0.26(0.86+0.56) -44.7%
    7820.15: perl grep (e.t[^ ]*|v.ry) rare       0.88(5.79+0.38)   0.26(1.06+0.54) -70.5%
    7820.19: perl grep m(ú|u)lt.b(æ|y)te          0.32(1.56+0.46)   0.23(0.86+0.48) -28.1%

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.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@xxxxxxxxx>
---
 grep.c | 37 ++++++++++++++++++++++++++++++++++++-
 grep.h |  6 ++++++
 2 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/grep.c b/grep.c
index 1157529115..accf1c45e6 100644
--- a/grep.c
+++ b/grep.c
@@ -351,6 +351,9 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
 	const char *error;
 	int erroffset;
 	int options = PCRE_MULTILINE;
+#ifdef PCRE_CONFIG_JIT
+	int canjit;
+#endif
 
 	if (opt->ignore_case) {
 		if (has_non_ascii(p->pattern))
@@ -365,9 +368,20 @@ 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, &canjit);
+	if (canjit == 1) {
+		p->pcre1_jit_stack = pcre_jit_stack_alloc(1, 1024 * 1024);
+		if (!p->pcre1_jit_stack)
+			die("BUG: Couldn't allocate PCRE JIT stack");
+		pcre_assign_jit_stack(p->pcre1_extra_info, NULL, p->pcre1_jit_stack);
+		p->pcre1_jit_on = 1;
+	}
+#endif
 }
 
 static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
@@ -378,8 +392,20 @@ static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
 	if (eflags & REG_NOTBOL)
 		flags |= PCRE_NOTBOL;
 
+#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
+		ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
+				eol - line, 0, flags, ovector,
+				ARRAY_SIZE(ovector));
+#else
 	ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line, eol - line,
 			0, flags, ovector, ARRAY_SIZE(ovector));
+#endif
+
 	if (ret < 0 && ret != PCRE_ERROR_NOMATCH)
 		die("pcre_exec failed with error code %d", ret);
 	if (ret > 0) {
@@ -394,7 +420,16 @@ 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);
+#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 {
+		pcre_free(p->pcre1_extra_info);
+	}
+#else
 	pcre_free(p->pcre1_extra_info);
+#endif
 	pcre_free((void *)p->pcre1_tables);
 }
 #else /* !USE_LIBPCRE1 */
diff --git a/grep.h b/grep.h
index 38ac82b638..14f47189f9 100644
--- 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;
-- 
2.11.0