https://github.com/git/git
Revision 4bd481e0ad9c6e78e320288886ffdad8f76dcfc1 authored by Jeff King on 17 January 2023, 03:04:44 UTC, committed by Johannes Schindelin on 06 February 2023, 08:27:09 UTC
The IOCTLFUNCTION option has been deprecated, and generates a compiler
warning in recent versions of curl. We can switch to using SEEKFUNCTION
instead. It was added in 2008 via curl 7.18.0; our INSTALL file already
indicates we require at least curl 7.19.4.

But there's one catch: curl says we should use CURL_SEEKFUNC_{OK,FAIL},
and those didn't arrive until 7.19.5. One workaround would be to use a
bare 0/1 here (or define our own macros).  But let's just bump the
minimum required version to 7.19.5. That version is only a minor version
bump from our existing requirement, and is only a 2 month time bump for
versions that are almost 13 years old. So it's not likely that anybody
cares about the distinction.

Switching means we have to rewrite the ioctl functions into seek
functions. In some ways they are simpler (seeking is the only
operation), but in some ways more complex (the ioctl allowed only a full
rewind, but now we can seek to arbitrary offsets).

Curl will only ever use SEEK_SET (per their documentation), so I didn't
bother implementing anything else, since it would naturally be
completely untested. This seems unlikely to change, but I added an
assertion just in case.

Likewise, I doubt curl will ever try to seek outside of the buffer sizes
we've told it, but I erred on the defensive side here, rather than do an
out-of-bounds read.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
1 parent 4fab049
Raw File
Tip revision: 4bd481e0ad9c6e78e320288886ffdad8f76dcfc1 authored by Jeff King on 17 January 2023, 03:04:44 UTC
http: prefer CURLOPT_SEEKFUNCTION to CURLOPT_IOCTLFUNCTION
Tip revision: 4bd481e
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;
	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);

	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;
}
back to top