Staging
v0.5.1
Revision ca1b4116483b397e78483376296bcd23916ab553 authored by Johannes Schindelin on 15 February 2019, 15:17:45 UTC, committed by Junio C Hamano on 15 February 2019, 18:25:28 UTC
Running up to v2.21.0, we fixed two bugs that were made prominent by the
Windows-specific change to retain copies of only the 30 latest getenv()
calls' returned strings, invalidating any copies of previous getenv()
calls' return values.

While this really shines a light onto bugs of the form where we hold
onto getenv()'s return values without copying them, it is also a real
problem for users.

And even if Jeff King's patches merged via 773e408881 (Merge branch
'jk/save-getenv-result', 2019-01-29) provide further work on that front,
we are far from done. Just one example: on Windows, we unset environment
variables when spawning new processes, which potentially invalidates
strings that were previously obtained via getenv(), and therefore we
have to duplicate environment values that are somehow involved in
spawning new processes (e.g. GIT_MAN_VIEWER in show_man_page()).

We do not have a chance to investigate, let address, all of those issues
in time for v2.21.0, so let's at least help Windows users by increasing
the number of getenv() calls' return values that are kept valid. The
number 64 was determined by looking at the average number of getenv()
calls per process in the entire test suite run on Windows (which is
around 40) and then adding a bit for good measure. And it is a power of
two (which would have hit yesterday's theme perfectly).

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
1 parent 2d08f3d
Raw File
preload-index.c
/*
 * 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;
};

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;
		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);
	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;

	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;
	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");
	}
	stop_progress(&pd.progress);

	trace_performance_leave("preload index");
}

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;
}
back to top