mirror of
https://github.com/git/git.git
synced 2024-12-03 23:14:23 +08:00
c46c406ae1
Performance measurements are listed right now as a flat list, which is fine when we measure big blocks. But when we start adding more and more measurements, some of them could be just part of a bigger measurement and a flat list gives a wrong impression that they are executed at the same level instead of nested. Add trace_performance_enter() and trace_performance_leave() to allow indent these nested measurements. For now it does not help much because the only nested thing is (lazy) name hash initialization (e.g. called in diff-index from "git status"). This will help more because I'm going to add some more tracing that's actually nested. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
124 lines
2.8 KiB
C
124 lines
2.8 KiB
C
/*
|
|
* Copyright (C) 2008 Linus Torvalds
|
|
*/
|
|
#include "cache.h"
|
|
#include "pathspec.h"
|
|
#include "dir.h"
|
|
#include "fsmonitor.h"
|
|
|
|
#ifdef NO_PTHREADS
|
|
static void preload_index(struct index_state *index,
|
|
const struct pathspec *pathspec)
|
|
{
|
|
; /* nothing */
|
|
}
|
|
#else
|
|
|
|
#include <pthread.h>
|
|
|
|
/*
|
|
* Mostly randomly chosen maximum thread counts: we
|
|
* cap the parallelism to 20 threads, and we want
|
|
* to have at least 500 lstat's per thread for it to
|
|
* be worth starting a thread.
|
|
*/
|
|
#define MAX_PARALLEL (20)
|
|
#define THREAD_COST (500)
|
|
|
|
struct thread_data {
|
|
pthread_t pthread;
|
|
struct index_state *index;
|
|
struct pathspec pathspec;
|
|
int offset, nr;
|
|
};
|
|
|
|
static void *preload_thread(void *_data)
|
|
{
|
|
int nr;
|
|
struct thread_data *p = _data;
|
|
struct index_state *index = p->index;
|
|
struct cache_entry **cep = index->cache + p->offset;
|
|
struct cache_def cache = CACHE_DEF_INIT;
|
|
|
|
nr = p->nr;
|
|
if (nr + p->offset > index->cache_nr)
|
|
nr = index->cache_nr - p->offset;
|
|
|
|
do {
|
|
struct cache_entry *ce = *cep++;
|
|
struct stat st;
|
|
|
|
if (ce_stage(ce))
|
|
continue;
|
|
if (S_ISGITLINK(ce->ce_mode))
|
|
continue;
|
|
if (ce_uptodate(ce))
|
|
continue;
|
|
if (ce_skip_worktree(ce))
|
|
continue;
|
|
if (ce->ce_flags & CE_FSMONITOR_VALID)
|
|
continue;
|
|
if (!ce_path_match(ce, &p->pathspec, NULL))
|
|
continue;
|
|
if (threaded_has_symlink_leading_path(&cache, ce->name, ce_namelen(ce)))
|
|
continue;
|
|
if (lstat(ce->name, &st))
|
|
continue;
|
|
if (ie_match_stat(index, ce, &st, CE_MATCH_RACY_IS_DIRTY|CE_MATCH_IGNORE_FSMONITOR))
|
|
continue;
|
|
ce_mark_uptodate(ce);
|
|
mark_fsmonitor_valid(ce);
|
|
} while (--nr > 0);
|
|
cache_def_clear(&cache);
|
|
return NULL;
|
|
}
|
|
|
|
static void preload_index(struct index_state *index,
|
|
const struct pathspec *pathspec)
|
|
{
|
|
int threads, i, work, offset;
|
|
struct thread_data data[MAX_PARALLEL];
|
|
|
|
if (!core_preload_index)
|
|
return;
|
|
|
|
threads = index->cache_nr / THREAD_COST;
|
|
if ((index->cache_nr > 1) && (threads < 2) && getenv("GIT_FORCE_PRELOAD_TEST"))
|
|
threads = 2;
|
|
if (threads < 2)
|
|
return;
|
|
trace_performance_enter();
|
|
if (threads > MAX_PARALLEL)
|
|
threads = MAX_PARALLEL;
|
|
offset = 0;
|
|
work = DIV_ROUND_UP(index->cache_nr, threads);
|
|
memset(&data, 0, sizeof(data));
|
|
for (i = 0; i < threads; i++) {
|
|
struct thread_data *p = data+i;
|
|
p->index = index;
|
|
if (pathspec)
|
|
copy_pathspec(&p->pathspec, pathspec);
|
|
p->offset = offset;
|
|
p->nr = work;
|
|
offset += work;
|
|
if (pthread_create(&p->pthread, NULL, preload_thread, p))
|
|
die("unable to create threaded lstat");
|
|
}
|
|
for (i = 0; i < threads; i++) {
|
|
struct thread_data *p = data+i;
|
|
if (pthread_join(p->pthread, NULL))
|
|
die("unable to join threaded lstat");
|
|
}
|
|
trace_performance_leave("preload index");
|
|
}
|
|
#endif
|
|
|
|
int read_index_preload(struct index_state *index,
|
|
const struct pathspec *pathspec)
|
|
{
|
|
int retval = read_index(index);
|
|
|
|
preload_index(index, pathspec);
|
|
return retval;
|
|
}
|