diff options
author | kevans <kevans@FreeBSD.org> | 2017-08-16 17:38:37 +0000 |
---|---|---|
committer | kevans <kevans@FreeBSD.org> | 2017-08-16 17:38:37 +0000 |
commit | db6ebb64cc3f817db5d2be7fd2ab38ea5cc6c5b2 (patch) | |
tree | b7a214f2e0ef1b6897a2519dadf501f0653c23c7 | |
parent | 3c5634d1b9ae20b0a99db710b23f5bc2c9fda9d4 (diff) | |
download | FreeBSD-src-db6ebb64cc3f817db5d2be7fd2ab38ea5cc6c5b2.zip FreeBSD-src-db6ebb64cc3f817db5d2be7fd2ab38ea5cc6c5b2.tar.gz |
MFC r317254: bsdgrep: add BSD_GREP_FASTMATCH knob for built-in fastmatch
Bugs have been found in the fastmatch implementation as used in bsdgrep.
Some have been fixed (r316495) while fixes for others are in review
(D10098).
In comparison with the fastmatch implementation, Kyle Evans found that:
- regex(3)'s performance with literal expressions offers a speed
improvement over fastmatch
- regex(3)'s performance, both with simple BREs and EREs, seems to be
comparable
The regex implementation was imported in r226035, and the commit message
reports:
This is a temporary solution until the whole regex library is
not replaced so that BSD grep development can continue and the
backported code gets some review and testing. This change only
improves scalability slightly, there is no big performance boost
yet but several minor bugs have been found and fixed.
Introduce a WITH_/WITHOUT_BSD_GREP_FASTMATCH knob to support testing
of both approaches.
Regenerate src.conf(5) as per the original commit
PR: 175314, 194823
Approved by: emaste (mentor, blanket MFC)
-rw-r--r-- | share/man/man5/src.conf.5 | 7 | ||||
-rw-r--r-- | share/mk/src.opts.mk | 1 | ||||
-rw-r--r-- | tools/build/options/WITHOUT_BSD_GREP_FASTMATCH | 5 | ||||
-rw-r--r-- | usr.bin/grep/Makefile | 6 | ||||
-rw-r--r-- | usr.bin/grep/grep.c | 25 | ||||
-rw-r--r-- | usr.bin/grep/grep.h | 4 | ||||
-rw-r--r-- | usr.bin/grep/util.c | 8 |
7 files changed, 46 insertions, 10 deletions
diff --git a/share/man/man5/src.conf.5 b/share/man/man5/src.conf.5 index c71a7d7..5d5571c 100644 --- a/share/man/man5/src.conf.5 +++ b/share/man/man5/src.conf.5 @@ -1,6 +1,6 @@ .\" DO NOT EDIT-- this file is generated by tools/build/options/makeman. .\" $FreeBSD$ -.Dd August 5, 2017 +.Dd August 16, 2017 .Dt SRC.CONF 5 .Os .Sh NAME @@ -214,6 +214,11 @@ Set to not build the BSD licensed version of cpio based on .Xr libarchive 3 . .It Va WITH_BSD_GREP Install BSD-licensed grep as '[ef]grep' instead of GNU grep. +.It Va WITHOUT_BSD_GREP_FASTMATCH +Set this option to exclude the fastmatch implementation from +.Xr bsdgrep 1 , +instead using only +.Xr regex 3 . .It Va WITHOUT_BSNMP Set to not build or install .Xr bsnmpd 1 diff --git a/share/mk/src.opts.mk b/share/mk/src.opts.mk index fa1f7c8..2ff797c 100644 --- a/share/mk/src.opts.mk +++ b/share/mk/src.opts.mk @@ -62,6 +62,7 @@ __DEFAULT_YES_OPTIONS = \ BOOTPARAMD \ BOOTPD \ BSD_CPIO \ + BSD_GREP_FASTMATCH \ BSDINSTALL \ BSNMP \ BZIP2 \ diff --git a/tools/build/options/WITHOUT_BSD_GREP_FASTMATCH b/tools/build/options/WITHOUT_BSD_GREP_FASTMATCH new file mode 100644 index 0000000..ffb3aaf --- /dev/null +++ b/tools/build/options/WITHOUT_BSD_GREP_FASTMATCH @@ -0,0 +1,5 @@ +.\" $FreeBSD$ +Set this option to exclude the fastmatch implementation from +.Xr bsdgrep 1 , +instead using only +.Xr regex 3 . diff --git a/usr.bin/grep/Makefile b/usr.bin/grep/Makefile index 7c67659..c6b25f0 100644 --- a/usr.bin/grep/Makefile +++ b/usr.bin/grep/Makefile @@ -15,10 +15,14 @@ bsdgrep.1: grep.1 .endif SRCS= file.c grep.c queue.c util.c -# Extra files ported backported form some regex improvements +.if ${MK_BSD_GREP_FASTMATCH} == "yes" +# Extra files ported backported for some regex improvements .PATH: ${.CURDIR}/regex SRCS+= fastmatch.c hashtable.c tre-compile.c tre-fastmatch.c CFLAGS+=-I${.CURDIR}/regex +.else +CFLAGS+= -DWITHOUT_FASTMATCH +.endif CFLAGS.gcc+= --param max-inline-insns-single=500 diff --git a/usr.bin/grep/grep.c b/usr.bin/grep/grep.c index 47e6465..9709ce6 100644 --- a/usr.bin/grep/grep.c +++ b/usr.bin/grep/grep.c @@ -50,7 +50,9 @@ __FBSDID("$FreeBSD$"); #include <string.h> #include <unistd.h> +#ifndef WITHOUT_FASTMATCH #include "fastmatch.h" +#endif #include "grep.h" #ifndef WITHOUT_NLS @@ -87,7 +89,9 @@ unsigned int patterns; static unsigned int pattern_sz; struct pat *pattern; regex_t *r_pattern; +#ifndef WITHOUT_FASTMATCH fastmatch_t *fg_pattern; +#endif /* Filename exclusion/inclusion patterns */ unsigned int fpatterns, dpatterns; @@ -716,20 +720,25 @@ main(int argc, char *argv[]) usage(); } +#ifndef WITHOUT_FASTMATCH fg_pattern = grep_calloc(patterns, sizeof(*fg_pattern)); +#endif r_pattern = grep_calloc(patterns, sizeof(*r_pattern)); /* Check if cheating is allowed (always is for fgrep). */ for (i = 0; i < patterns; ++i) { +#ifndef WITHOUT_FASTMATCH + /* Attempt compilation with fastmatch regex and fallback to + regex(3) if it fails. */ if (fastncomp(&fg_pattern[i], pattern[i].pat, - pattern[i].len, cflags) != 0) { - /* Fall back to full regex library */ - c = regcomp(&r_pattern[i], pattern[i].pat, cflags); - if (c != 0) { - regerror(c, &r_pattern[i], re_error, - RE_ERROR_BUF); - errx(2, "%s", re_error); - } + pattern[i].len, cflags) == 0) + continue; +#endif + c = regcomp(&r_pattern[i], pattern[i].pat, cflags); + if (c != 0) { + regerror(c, &r_pattern[i], re_error, + RE_ERROR_BUF); + errx(2, "%s", re_error); } } diff --git a/usr.bin/grep/grep.h b/usr.bin/grep/grep.h index c82e6bb..ea17af40 100644 --- a/usr.bin/grep/grep.h +++ b/usr.bin/grep/grep.h @@ -36,7 +36,9 @@ #include <stdio.h> #include <zlib.h> +#ifndef WITHOUT_FASTMATCH #include "fastmatch.h" +#endif #ifdef WITHOUT_NLS #define getstr(n) errstr[n] @@ -127,7 +129,9 @@ extern unsigned int dpatterns, fpatterns, patterns; extern struct pat *pattern; extern struct epat *dpattern, *fpattern; extern regex_t *er_pattern, *r_pattern; +#ifndef WITHOUT_FASTMATCH extern fastmatch_t *fg_pattern; +#endif /* For regex errors */ #define RE_ERROR_BUF 512 diff --git a/usr.bin/grep/util.c b/usr.bin/grep/util.c index 285f883..8815d4f 100644 --- a/usr.bin/grep/util.c +++ b/usr.bin/grep/util.c @@ -49,7 +49,9 @@ __FBSDID("$FreeBSD$"); #include <wchar.h> #include <wctype.h> +#ifndef WITHOUT_FASTMATCH #include "fastmatch.h" +#endif #include "grep.h" static int linesqueued; @@ -317,10 +319,12 @@ procline(struct str *l, int nottext) for (i = 0; i < patterns; i++) { pmatch.rm_so = st; pmatch.rm_eo = l->len; +#ifndef WITHOUT_FASTMATCH if (fg_pattern[i].pattern) r = fastexec(&fg_pattern[i], l->dat, 1, &pmatch, leflags); else +#endif r = regexec(&r_pattern[i], l->dat, 1, &pmatch, leflags); r = (r == 0) ? 0 : REG_NOMATCH; @@ -332,7 +336,11 @@ procline(struct str *l, int nottext) (size_t)pmatch.rm_eo != l->len) r = REG_NOMATCH; /* Check for whole word match */ +#ifndef WITHOUT_FASTMATCH if (r == 0 && (wflag || fg_pattern[i].word)) { +#else + if (r == 0 && wflag) { +#endif wchar_t wbegin, wend; wbegin = wend = L' '; |