1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-13 12:16:10 +02:00
git/grep.h
Ævar Arnfjörð Bjarmason 48de2a768c grep: remove the kwset optimization
A later change will replace this optimization with optimistic use of
PCRE v2. I'm completely removing it as an intermediate step, as
opposed to replacing it with PCRE v2, to demonstrate that no grep
semantics depend on this (or any other) optimization for the fixed
backend anymore.

For now this is mostly (but not entirely) a performance regression, as
shown by this hacky one-liner:

    for opt in '' ' -i'
        do
        GIT_PERF_7821_GREP_OPTS=$opt GIT_PERF_REPEAT_COUNT=10 GIT_PERF_LARGE_REPO=~/g/linux GIT_PERF_MAKE_OPTS='-j8 CFLAGS=-O3 USE_LIBPCRE=YesPlease' ./run origin/master HEAD -- p7821-grep-engines-fixed.sh
    done &&
    for opt in '' ' -i'
        do GIT_PERF_4221_LOG_OPTS=$opt GIT_PERF_REPEAT_COUNT=10 GIT_PERF_LARGE_REPO=~/g/linux GIT_PERF_MAKE_OPTS='-j8 CFLAGS=-O3 USE_LIBPCRE=YesPlease' ./run origin/master HEAD -- p4221-log-grep-engines-fixed.sh
    done

Which produces:

plain grep:

    Test                             origin/master     HEAD
    -------------------------------------------------------------------------
    7821.1: fixed grep int           0.55(1.60+0.63)   0.82(3.11+0.51) +49.1%
    7821.2: basic grep int           0.62(1.68+0.49)   0.85(3.02+0.52) +37.1%
    7821.3: extended grep int        0.61(1.63+0.53)   0.91(3.09+0.44) +49.2%
    7821.4: perl grep int            0.55(1.60+0.57)   0.41(0.93+0.57) -25.5%
    7821.6: fixed grep uncommon      0.20(0.50+0.44)   0.35(1.27+0.42) +75.0%
    7821.7: basic grep uncommon      0.20(0.49+0.45)   0.35(1.29+0.41) +75.0%
    7821.8: extended grep uncommon   0.20(0.45+0.48)   0.35(1.25+0.44) +75.0%
    7821.9: perl grep uncommon       0.20(0.53+0.41)   0.16(0.24+0.49) -20.0%
    7821.11: fixed grep æ            0.35(1.27+0.40)   0.25(0.82+0.39) -28.6%
    7821.12: basic grep æ            0.35(1.28+0.38)   0.25(0.75+0.44) -28.6%
    7821.13: extended grep æ         0.36(1.21+0.46)   0.25(0.86+0.35) -30.6%
    7821.14: perl grep æ             0.35(1.33+0.34)   0.16(0.26+0.47) -54.3%

grep with -i:

    Test                                origin/master     HEAD
    -----------------------------------------------------------------------------
    7821.1: fixed grep -i int           0.61(1.84+0.64)   1.11(4.12+0.64) +82.0%
    7821.2: basic grep -i int           0.72(1.86+0.57)   1.15(4.48+0.49) +59.7%
    7821.3: extended grep -i int        0.94(1.83+0.60)   1.53(4.12+0.58) +62.8%
    7821.4: perl grep -i int            0.66(1.82+0.59)   0.55(1.08+0.58) -16.7%
    7821.6: fixed grep -i uncommon      0.21(0.51+0.44)   0.44(1.74+0.34) +109.5%
    7821.7: basic grep -i uncommon      0.21(0.55+0.41)   0.44(1.72+0.40) +109.5%
    7821.8: extended grep -i uncommon   0.21(0.57+0.39)   0.42(1.64+0.45) +100.0%
    7821.9: perl grep -i uncommon       0.21(0.48+0.48)   0.17(0.30+0.45) -19.0%
    7821.11: fixed grep -i æ            0.25(0.73+0.45)   0.25(0.75+0.45) +0.0%
    7821.12: basic grep -i æ            0.25(0.71+0.49)   0.26(0.77+0.44) +4.0%
    7821.13: extended grep -i æ         0.25(0.75+0.44)   0.25(0.74+0.46) +0.0%
    7821.14: perl grep -i æ             0.17(0.26+0.48)   0.16(0.20+0.52) -5.9%

plain log:

    Test                                     origin/master     HEAD
    ---------------------------------------------------------------------------------
    4221.1: fixed log --grep='int'           7.31(7.06+0.21)   8.11(7.85+0.20) +10.9%
    4221.2: basic log --grep='int'           7.30(6.94+0.27)   8.16(7.89+0.19) +11.8%
    4221.3: extended log --grep='int'        7.34(7.05+0.21)   8.08(7.76+0.25) +10.1%
    4221.4: perl log --grep='int'            7.27(6.94+0.24)   7.05(6.76+0.25) -3.0%
    4221.6: fixed log --grep='uncommon'      6.97(6.62+0.32)   7.86(7.51+0.30) +12.8%
    4221.7: basic log --grep='uncommon'      7.05(6.69+0.29)   7.89(7.60+0.28) +11.9%
    4221.8: extended log --grep='uncommon'   6.89(6.56+0.32)   7.99(7.66+0.24) +16.0%
    4221.9: perl log --grep='uncommon'       7.02(6.66+0.33)   6.97(6.54+0.36) -0.7%
    4221.11: fixed log --grep='æ'            7.37(7.03+0.33)   7.67(7.30+0.31) +4.1%
    4221.12: basic log --grep='æ'            7.41(7.00+0.31)   7.60(7.28+0.26) +2.6%
    4221.13: extended log --grep='æ'         7.35(6.96+0.38)   7.73(7.31+0.34) +5.2%
    4221.14: perl log --grep='æ'             7.43(7.10+0.32)   6.95(6.61+0.27) -6.5%

log with -i:

    Test                                        origin/master     HEAD
    ------------------------------------------------------------------------------------
    4221.1: fixed log -i --grep='int'           7.40(7.05+0.23)   8.66(8.38+0.20) +17.0%
    4221.2: basic log -i --grep='int'           7.39(7.09+0.23)   8.67(8.39+0.20) +17.3%
    4221.3: extended log -i --grep='int'        7.29(6.99+0.26)   8.69(8.31+0.26) +19.2%
    4221.4: perl log -i --grep='int'            7.42(7.16+0.21)   7.14(6.80+0.24) -3.8%
    4221.6: fixed log -i --grep='uncommon'      6.94(6.58+0.35)   8.43(8.04+0.30) +21.5%
    4221.7: basic log -i --grep='uncommon'      6.95(6.62+0.31)   8.34(7.93+0.32) +20.0%
    4221.8: extended log -i --grep='uncommon'   7.06(6.75+0.25)   8.32(7.98+0.31) +17.8%
    4221.9: perl log -i --grep='uncommon'       6.96(6.69+0.26)   7.04(6.64+0.32) +1.1%
    4221.11: fixed log -i --grep='æ'            7.92(7.55+0.33)   7.86(7.44+0.34) -0.8%
    4221.12: basic log -i --grep='æ'            7.88(7.49+0.32)   7.84(7.46+0.34) -0.5%
    4221.13: extended log -i --grep='æ'         7.91(7.51+0.32)   7.87(7.48+0.32) -0.5%
    4221.14: perl log -i --grep='æ'             7.01(6.59+0.35)   6.99(6.64+0.28) -0.3%

Some of those, as noted in [1] are because PCRE is faster at finding
fixed strings. This looks bad for some engines, but in the next change
we'll optimistically use PCRE v2 for all of these, so it'll look
better.

1. https://public-inbox.org/git/87v9x793qi.fsf@evledraar.gmail.com/

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-07-01 14:33:14 -07:00

252 lines
5.6 KiB
C

#ifndef GREP_H
#define GREP_H
#include "color.h"
#ifdef USE_LIBPCRE1
#include <pcre.h>
#ifdef PCRE_CONFIG_JIT
#if PCRE_MAJOR >= 8 && PCRE_MINOR >= 32
#ifndef NO_LIBPCRE1_JIT
#define GIT_PCRE1_USE_JIT
#define GIT_PCRE_STUDY_JIT_COMPILE PCRE_STUDY_JIT_COMPILE
#endif
#endif
#endif
#ifndef GIT_PCRE_STUDY_JIT_COMPILE
#define GIT_PCRE_STUDY_JIT_COMPILE 0
#endif
#if PCRE_MAJOR <= 8 && PCRE_MINOR < 20
typedef int pcre_jit_stack;
#endif
#else
typedef int pcre;
typedef int pcre_extra;
typedef int pcre_jit_stack;
#endif
#ifdef USE_LIBPCRE2
#define PCRE2_CODE_UNIT_WIDTH 8
#include <pcre2.h>
#else
typedef int pcre2_code;
typedef int pcre2_match_data;
typedef int pcre2_compile_context;
typedef int pcre2_match_context;
typedef int pcre2_jit_stack;
#endif
#include "thread-utils.h"
#include "userdiff.h"
struct repository;
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_FIELD_MIN = 0,
GREP_HEADER_AUTHOR = GREP_HEADER_FIELD_MIN,
GREP_HEADER_COMMITTER,
GREP_HEADER_REFLOG,
/* Must be at the end of the enum */
GREP_HEADER_FIELD_MAX
};
enum grep_color {
GREP_COLOR_CONTEXT,
GREP_COLOR_FILENAME,
GREP_COLOR_FUNCTION,
GREP_COLOR_LINENO,
GREP_COLOR_COLUMNNO,
GREP_COLOR_MATCH_CONTEXT,
GREP_COLOR_MATCH_SELECTED,
GREP_COLOR_SELECTED,
GREP_COLOR_SEP,
NR_GREP_COLORS
};
struct grep_pat {
struct grep_pat *next;
const char *origin;
int no;
enum grep_pat_token token;
char *pattern;
size_t patternlen;
enum grep_header_field field;
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;
pcre2_code *pcre2_pattern;
pcre2_match_data *pcre2_match_data;
pcre2_compile_context *pcre2_compile_context;
pcre2_match_context *pcre2_match_context;
pcre2_jit_stack *pcre2_jit_stack;
uint32_t pcre2_jit_on;
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
};
enum grep_pattern_type {
GREP_PATTERN_TYPE_UNSPECIFIED = 0,
GREP_PATTERN_TYPE_BRE,
GREP_PATTERN_TYPE_ERE,
GREP_PATTERN_TYPE_FIXED,
GREP_PATTERN_TYPE_PCRE
};
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;
struct repository *repo;
const char *prefix;
int prefix_length;
regex_t regexp;
int linenum;
int columnnum;
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;
int debug;
#define GREP_BINARY_DEFAULT 0
#define GREP_BINARY_NOMATCH 1
#define GREP_BINARY_TEXT 2
int binary;
int allow_textconv;
int extended;
int use_reflog_filter;
int pcre1;
int pcre2;
int relative;
int pathname;
int null_following_name;
int only_matching;
int color;
int max_depth;
int funcname;
int funcbody;
int extended_regexp_option;
int pattern_type_option;
int ignore_locale;
char colors[NR_GREP_COLORS][COLOR_MAXLEN];
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;
};
void init_grep_defaults(struct repository *);
int grep_config(const char *var, const char *value, void *);
void grep_init(struct grep_opt *, struct repository *repo, const char *prefix);
void grep_commit_pattern_type(enum grep_pattern_type, struct grep_opt *opt);
void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t);
void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t);
void append_header_grep_pattern(struct grep_opt *, enum grep_header_field, const char *);
void compile_grep_patterns(struct grep_opt *opt);
void free_grep_patterns(struct grep_opt *opt);
int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size);
struct grep_source {
char *name;
enum grep_source_type {
GREP_SOURCE_OID,
GREP_SOURCE_FILE,
GREP_SOURCE_BUF,
} type;
void *identifier;
char *buf;
unsigned long size;
char *path; /* for attribute lookups */
struct userdiff_driver *driver;
};
void grep_source_init(struct grep_source *gs, enum grep_source_type type,
const char *name, const char *path,
const void *identifier);
void grep_source_clear_data(struct grep_source *gs);
void grep_source_clear(struct grep_source *gs);
void grep_source_load_driver(struct grep_source *gs,
struct index_state *istate);
int grep_source(struct grep_opt *opt, struct grep_source *gs);
struct grep_opt *grep_opt_dup(const struct grep_opt *opt);
int grep_threads_ok(const struct grep_opt *opt);
/*
* Mutex used around access to the attributes machinery if
* opt->use_threads. Must be initialized/destroyed by callers!
*/
extern int grep_use_locks;
extern pthread_mutex_t grep_attr_mutex;
extern pthread_mutex_t grep_read_mutex;
static inline void grep_read_lock(void)
{
if (grep_use_locks)
pthread_mutex_lock(&grep_read_mutex);
}
static inline void grep_read_unlock(void)
{
if (grep_use_locks)
pthread_mutex_unlock(&grep_read_mutex);
}
#endif