git/grep.h
Fredrik Kuivinen 9eceddeec6 Use kwset in grep
Benchmarks for the hot cache case:

before:
$ perf stat --repeat=5 git grep qwerty > /dev/null

Performance counter stats for 'git grep qwerty' (5 runs):

        3,478,085 cache-misses             #      2.322 M/sec   ( +-   2.690% )
       11,356,177 cache-references         #      7.582 M/sec   ( +-   2.598% )
        3,872,184 branch-misses            #      0.363 %       ( +-   0.258% )
    1,067,367,848 branches                 #    712.673 M/sec   ( +-   2.622% )
    3,828,370,782 instructions             #      0.947 IPC     ( +-   0.033% )
    4,043,832,831 cycles                   #   2700.037 M/sec   ( +-   0.167% )
            8,518 page-faults              #      0.006 M/sec   ( +-   3.648% )
              847 CPU-migrations           #      0.001 M/sec   ( +-   3.262% )
            6,546 context-switches         #      0.004 M/sec   ( +-   2.292% )
      1497.695495 task-clock-msecs         #      3.303 CPUs    ( +-   2.550% )

       0.453394396  seconds time elapsed   ( +-   0.912% )

after:
$ perf stat --repeat=5 git grep qwerty > /dev/null

Performance counter stats for 'git grep qwerty' (5 runs):

        2,989,918 cache-misses             #      3.166 M/sec   ( +-   5.013% )
       10,986,041 cache-references         #     11.633 M/sec   ( +-   4.899% )  (scaled from 95.06%)
        3,511,993 branch-misses            #      1.422 %       ( +-   0.785% )
      246,893,561 branches                 #    261.433 M/sec   ( +-   3.967% )
    1,392,727,757 instructions             #      0.564 IPC     ( +-   0.040% )
    2,468,142,397 cycles                   #   2613.494 M/sec   ( +-   0.110% )
            7,747 page-faults              #      0.008 M/sec   ( +-   3.995% )
              897 CPU-migrations           #      0.001 M/sec   ( +-   2.383% )
            6,535 context-switches         #      0.007 M/sec   ( +-   1.993% )
       944.384228 task-clock-msecs         #      3.177 CPUs    ( +-   0.268% )

       0.297257643  seconds time elapsed   ( +-   0.450% )

So we gain about 35% by using the kwset code.

As a side effect of using kwset two grep tests are fixed by this
patch. The first is fixed because kwset can deal with case-insensitive
search containing NULs, something strcasestr cannot do. The second one
is fixed because we consider patterns containing NULs as fixed strings
(regcomp cannot accept patterns with NULs).

Signed-off-by: Fredrik Kuivinen <frekui@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-20 22:33:58 -07:00

135 lines
2.9 KiB
C

#ifndef GREP_H
#define GREP_H
#include "color.h"
#ifdef USE_LIBPCRE
#include <pcre.h>
#else
typedef int pcre;
typedef int pcre_extra;
#endif
#include "kwset.h"
enum grep_pat_token {
GREP_PATTERN,
GREP_PATTERN_HEAD,
GREP_PATTERN_BODY,
GREP_AND,
GREP_OPEN_PAREN,
GREP_CLOSE_PAREN,
GREP_NOT,
GREP_OR
};
enum grep_context {
GREP_CONTEXT_HEAD,
GREP_CONTEXT_BODY
};
enum grep_header_field {
GREP_HEADER_AUTHOR = 0,
GREP_HEADER_COMMITTER
};
#define GREP_HEADER_FIELD_MAX (GREP_HEADER_COMMITTER + 1)
struct grep_pat {
struct grep_pat *next;
const char *origin;
int no;
enum grep_pat_token token;
const char *pattern;
size_t patternlen;
enum grep_header_field field;
regex_t regexp;
pcre *pcre_regexp;
pcre_extra *pcre_extra_info;
kwset_t kws;
unsigned fixed:1;
unsigned ignore_case:1;
unsigned word_regexp:1;
};
enum grep_expr_node {
GREP_NODE_ATOM,
GREP_NODE_NOT,
GREP_NODE_AND,
GREP_NODE_TRUE,
GREP_NODE_OR
};
struct grep_expr {
enum grep_expr_node node;
unsigned hit;
union {
struct grep_pat *atom;
struct grep_expr *unary;
struct {
struct grep_expr *left;
struct grep_expr *right;
} binary;
} u;
};
struct grep_opt {
struct grep_pat *pattern_list;
struct grep_pat **pattern_tail;
struct grep_pat *header_list;
struct grep_pat **header_tail;
struct grep_expr *pattern_expression;
const char *prefix;
int prefix_length;
regex_t regexp;
int linenum;
int invert;
int ignore_case;
int status_only;
int name_only;
int unmatch_name_only;
int count;
int word_regexp;
int fixed;
int all_match;
#define GREP_BINARY_DEFAULT 0
#define GREP_BINARY_NOMATCH 1
#define GREP_BINARY_TEXT 2
int binary;
int extended;
int pcre;
int relative;
int pathname;
int null_following_name;
int color;
int max_depth;
int funcname;
int funcbody;
char color_context[COLOR_MAXLEN];
char color_filename[COLOR_MAXLEN];
char color_function[COLOR_MAXLEN];
char color_lineno[COLOR_MAXLEN];
char color_match[COLOR_MAXLEN];
char color_selected[COLOR_MAXLEN];
char color_sep[COLOR_MAXLEN];
int regflags;
unsigned pre_context;
unsigned post_context;
unsigned last_shown;
int show_hunk_mark;
int file_break;
int heading;
void *priv;
void (*output)(struct grep_opt *opt, const void *data, size_t size);
void *output_priv;
};
extern void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t);
extern void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t);
extern void append_header_grep_pattern(struct grep_opt *, enum grep_header_field, const char *);
extern void compile_grep_patterns(struct grep_opt *opt);
extern void free_grep_patterns(struct grep_opt *opt);
extern int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size);
extern struct grep_opt *grep_opt_dup(const struct grep_opt *opt);
extern int grep_threads_ok(const struct grep_opt *opt);
#endif