git/preload-index.c
Ben Peart 883e248b8a fsmonitor: teach git to optionally utilize a file system monitor to speed up detecting new or changed files.
When the index is read from disk, the fsmonitor index extension is used
to flag the last known potentially dirty index entries. The registered
core.fsmonitor command is called with the time the index was last
updated and returns the list of files changed since that time. This list
is used to flag any additional dirty cache entries and untracked cache
directories.

We can then use this valid state to speed up preload_index(),
ie_match_stat(), and refresh_cache_ent() as they do not need to lstat()
files to detect potential changes for those entries marked
CE_FSMONITOR_VALID.

In addition, if the untracked cache is turned on valid_cached_dir() can
skip checking directories for new or changed files as fsmonitor will
invalidate the cache only for those directories that have been
identified as having potential changes.

To keep the CE_FSMONITOR_VALID state accurate during git operations;
when git updates a cache entry to match the current state on disk,
it will now set the CE_FSMONITOR_VALID bit.

Inversely, anytime git changes a cache entry, the CE_FSMONITOR_VALID bit
is cleared and the corresponding untracked cache directory is marked
invalid.

Signed-off-by: Ben Peart <benpeart@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-01 17:23:01 +09:00

121 lines
2.7 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;
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");
}
}
#endif
int read_index_preload(struct index_state *index,
const struct pathspec *pathspec)
{
int retval = read_index(index);
preload_index(index, pathspec);
return retval;
}