summaryrefslogtreecommitdiffstats
path: root/preload-index.c
blob: 100f7a374dca1b8ffaae1ae9a2c00011d05a208a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
/*
 * Copyright (C) 2008 Linus Torvalds
 */
#include "cache.h"
#include "pathspec.h"
#include "dir.h"
#include "fsmonitor.h"
#include "config.h"
#include "progress.h"
#include "thread-utils.h"
#include "repository.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 progress_data {
	unsigned long n;
	struct progress *progress;
	pthread_mutex_t mutex;
};

struct thread_data {
	pthread_t pthread;
	struct index_state *index;
	struct pathspec pathspec;
	struct progress_data *progress;
	int offset, nr;
	int t2_nr_lstat;
};

static void *preload_thread(void *_data)
{
	int nr, last_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;
	last_nr = nr;

	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 (p->progress && !(nr & 31)) {
			struct progress_data *pd = p->progress;

			pthread_mutex_lock(&pd->mutex);
			pd->n += last_nr - nr;
			display_progress(pd->progress, pd->n);
			pthread_mutex_unlock(&pd->mutex);
			last_nr = nr;
		}
		if (!ce_path_match(index, ce, &p->pathspec, NULL))
			continue;
		if (threaded_has_symlink_leading_path(&cache, ce->name, ce_namelen(ce)))
			continue;
		p->t2_nr_lstat++;
		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(index, ce);
	} while (--nr > 0);
	if (p->progress) {
		struct progress_data *pd = p->progress;

		pthread_mutex_lock(&pd->mutex);
		display_progress(pd->progress, pd->n + last_nr);
		pthread_mutex_unlock(&pd->mutex);
	}
	cache_def_clear(&cache);
	return NULL;
}

void preload_index(struct index_state *index,
		   const struct pathspec *pathspec,
		   unsigned int refresh_flags)
{
	int threads, i, work, offset;
	struct thread_data data[MAX_PARALLEL];
	struct progress_data pd;
	int t2_sum_lstat = 0;

	if (!HAVE_THREADS || !core_preload_index)
		return;

	threads = index->cache_nr / THREAD_COST;
	if ((index->cache_nr > 1) && (threads < 2) && git_env_bool("GIT_TEST_PRELOAD_INDEX", 0))
		threads = 2;
	if (threads < 2)
		return;

	trace2_region_enter("index", "preload", NULL);

	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));

	memset(&pd, 0, sizeof(pd));
	if (refresh_flags & REFRESH_PROGRESS && isatty(2)) {
		pd.progress = start_delayed_progress(_("Refreshing index"), index->cache_nr);
		pthread_mutex_init(&pd.mutex, NULL);
	}

	for (i = 0; i < threads; i++) {
		struct thread_data *p = data+i;
		int err;

		p->index = index;
		if (pathspec)
			copy_pathspec(&p->pathspec, pathspec);
		p->offset = offset;
		p->nr = work;
		if (pd.progress)
			p->progress = &pd;
		offset += work;
		err = pthread_create(&p->pthread, NULL, preload_thread, p);

		if (err)
			die(_("unable to create threaded lstat: %s"), strerror(err));
	}
	for (i = 0; i < threads; i++) {
		struct thread_data *p = data+i;
		if (pthread_join(p->pthread, NULL))
			die("unable to join threaded lstat");
		t2_sum_lstat += p->t2_nr_lstat;
	}
	stop_progress(&pd.progress);

	if (pathspec) {
		/* earlier we made deep copies for each thread to work with */
		for (i = 0; i < threads; i++)
			clear_pathspec(&data[i].pathspec);
	}

	trace_performance_leave("preload index");

	trace2_data_intmax("index", NULL, "preload/sum_lstat", t2_sum_lstat);
	trace2_region_leave("index", "preload", NULL);
}

int repo_read_index_preload(struct repository *repo,
			    const struct pathspec *pathspec,
			    unsigned int refresh_flags)
{
	int retval = repo_read_index(repo);

	preload_index(repo->index, pathspec, refresh_flags);
	return retval;
}