#include "utf8.h"
#include "fsmonitor.h"
#include "thread-utils.h"
+#include "progress.h"
/* Mask for the name length in ce_flags in the on-disk index */
}
}
-static int ce_compare_data(const struct cache_entry *ce, struct stat *st)
+static int ce_compare_data(struct index_state *istate,
+ const struct cache_entry *ce,
+ struct stat *st)
{
int match = -1;
int fd = git_open_cloexec(ce->name, O_RDONLY);
if (fd >= 0) {
struct object_id oid;
- if (!index_fd(&oid, fd, st, OBJ_BLOB, ce->name, 0))
+ if (!index_fd(istate, &oid, fd, st, OBJ_BLOB, ce->name, 0))
match = !oideq(&oid, &ce->oid);
/* index_fd() closed the file descriptor already */
}
return !oideq(&oid, &ce->oid);
}
-static int ce_modified_check_fs(const struct cache_entry *ce, struct stat *st)
+static int ce_modified_check_fs(struct index_state *istate,
+ const struct cache_entry *ce,
+ struct stat *st)
{
switch (st->st_mode & S_IFMT) {
case S_IFREG:
- if (ce_compare_data(ce, st))
+ if (ce_compare_data(istate, ce, st))
return DATA_CHANGED;
break;
case S_IFLNK:
if (assume_racy_is_modified)
changed |= DATA_CHANGED;
else
- changed |= ce_modified_check_fs(ce, st);
+ changed |= ce_modified_check_fs(istate, ce, st);
}
return changed;
(S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0))
return changed;
- changed_fs = ce_modified_check_fs(ce, st);
+ changed_fs = ce_modified_check_fs(istate, ce, st);
if (changed_fs)
return changed | changed_fs;
return 0;
}
}
if (!intent_only) {
- if (index_path(&ce->oid, path, st, newflags)) {
+ if (index_path(istate, &ce->oid, path, st, newflags)) {
discard_cache_entry(ce);
return error("unable to index file %s", path);
}
ce->ce_namelen = len;
ce->ce_mode = create_ce_mode(mode);
- ret = refresh_cache_entry(&the_index, ce, refresh_options);
+ ret = refresh_cache_entry(istate, ce, refresh_options);
if (ret != ce)
discard_cache_entry(ce);
return ret;
const char *typechange_fmt;
const char *added_fmt;
const char *unmerged_fmt;
+ struct progress *progress = NULL;
+
+ if (flags & REFRESH_PROGRESS && isatty(2))
+ progress = start_delayed_progress(_("Refresh index"),
+ istate->cache_nr);
trace_performance_enter();
modified_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n");
if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
continue;
- if (pathspec && !ce_path_match(&the_index, ce, pathspec, seen))
+ if (pathspec && !ce_path_match(istate, ce, pathspec, seen))
filtered = 1;
if (ce_stage(ce)) {
new_entry = refresh_cache_ent(istate, ce, options, &cache_errno, &changed);
if (new_entry == ce)
continue;
+ if (progress)
+ display_progress(progress, i);
if (!new_entry) {
const char *fmt;
replace_index_entry(istate, i, new_entry);
}
+ if (progress) {
+ display_progress(progress, istate->cache_nr);
+ stop_progress(&progress);
+ }
trace_performance_leave("refresh index");
return has_errors;
}
return read_index_from(istate, get_index_file(), get_git_dir());
}
-static struct cache_entry *create_from_disk(struct index_state *istate,
+static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
+ unsigned int version,
struct ondisk_cache_entry *ondisk,
unsigned long *ent_size,
const struct cache_entry *previous_ce)
* number of bytes to be stripped from the end of the previous name,
* and the bytes to append to the result, to come up with its name.
*/
- int expand_name_field = istate->version == 4;
+ int expand_name_field = version == 4;
/* On-disk flags are just 16 bits */
flags = get_be16(&ondisk->flags);
const unsigned char *cp = (const unsigned char *)name;
size_t strip_len, previous_len;
- previous_len = previous_ce ? previous_ce->ce_namelen : 0;
+ /* If we're at the begining of a block, ignore the previous name */
strip_len = decode_varint(&cp);
- if (previous_len < strip_len) {
- if (previous_ce)
+ if (previous_ce) {
+ previous_len = previous_ce->ce_namelen;
+ if (previous_len < strip_len)
die(_("malformed name field in the index, near path '%s'"),
- previous_ce->name);
- else
- die(_("malformed name field in the index in the first path"));
+ previous_ce->name);
+ copy_len = previous_len - strip_len;
+ } else {
+ copy_len = 0;
}
- copy_len = previous_len - strip_len;
name = (const char *)cp;
}
len += copy_len;
}
- ce = mem_pool__ce_alloc(istate->ce_mem_pool, len);
+ ce = mem_pool__ce_alloc(ce_mem_pool, len);
ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec);
ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec);
return NULL;
}
+/*
+ * A helper function that will load the specified range of cache entries
+ * from the memory mapped file and add them to the given index.
+ */
+static unsigned long load_cache_entry_block(struct index_state *istate,
+ struct mem_pool *ce_mem_pool, int offset, int nr, const char *mmap,
+ unsigned long start_offset, const struct cache_entry *previous_ce)
+{
+ int i;
+ unsigned long src_offset = start_offset;
+
+ for (i = offset; i < offset + nr; i++) {
+ struct ondisk_cache_entry *disk_ce;
+ struct cache_entry *ce;
+ unsigned long consumed;
+
+ disk_ce = (struct ondisk_cache_entry *)(mmap + src_offset);
+ ce = create_from_disk(ce_mem_pool, istate->version, disk_ce, &consumed, previous_ce);
+ set_index_entry(istate, i, ce);
+
+ src_offset += consumed;
+ previous_ce = ce;
+ }
+ return src_offset - start_offset;
+}
+
+static unsigned long load_all_cache_entries(struct index_state *istate,
+ const char *mmap, size_t mmap_size, unsigned long src_offset)
+{
+ unsigned long consumed;
+
+ if (istate->version == 4) {
+ mem_pool_init(&istate->ce_mem_pool,
+ estimate_cache_size_from_compressed(istate->cache_nr));
+ } else {
+ mem_pool_init(&istate->ce_mem_pool,
+ estimate_cache_size(mmap_size, istate->cache_nr));
+ }
+
+ consumed = load_cache_entry_block(istate, istate->ce_mem_pool,
+ 0, istate->cache_nr, mmap, src_offset, NULL);
+ return consumed;
+}
+
+#ifndef NO_PTHREADS
+
/*
* Mostly randomly chosen maximum thread counts: we
* cap the parallelism to online_cpus() threads, and we want
#define THREAD_COST (10000)
+struct load_cache_entries_thread_data
+{
+ pthread_t pthread;
+ struct index_state *istate;
+ struct mem_pool *ce_mem_pool;
+ int offset;
+ const char *mmap;
+ struct index_entry_offset_table *ieot;
+ int ieot_start; /* starting index into the ieot array */
+ int ieot_blocks; /* count of ieot entries to process */
+ unsigned long consumed; /* return # of bytes in index file processed */
+};
+
+/*
+ * A thread proc to run the load_cache_entries() computation
+ * across multiple background threads.
+ */
+static void *load_cache_entries_thread(void *_data)
+{
+ struct load_cache_entries_thread_data *p = _data;
+ int i;
+
+ /* iterate across all ieot blocks assigned to this thread */
+ for (i = p->ieot_start; i < p->ieot_start + p->ieot_blocks; i++) {
+ p->consumed += load_cache_entry_block(p->istate, p->ce_mem_pool,
+ p->offset, p->ieot->entries[i].nr, p->mmap, p->ieot->entries[i].offset, NULL);
+ p->offset += p->ieot->entries[i].nr;
+ }
+ return NULL;
+}
+
+static unsigned long load_cache_entries_threaded(struct index_state *istate, const char *mmap, size_t mmap_size,
+ unsigned long src_offset, int nr_threads, struct index_entry_offset_table *ieot)
+{
+ int i, offset, ieot_blocks, ieot_start, err;
+ struct load_cache_entries_thread_data *data;
+ unsigned long consumed = 0;
+
+ /* a little sanity checking */
+ if (istate->name_hash_initialized)
+ BUG("the name hash isn't thread safe");
+
+ mem_pool_init(&istate->ce_mem_pool, 0);
+
+ /* ensure we have no more threads than we have blocks to process */
+ if (nr_threads > ieot->nr)
+ nr_threads = ieot->nr;
+ data = xcalloc(nr_threads, sizeof(*data));
+
+ offset = ieot_start = 0;
+ ieot_blocks = DIV_ROUND_UP(ieot->nr, nr_threads);
+ for (i = 0; i < nr_threads; i++) {
+ struct load_cache_entries_thread_data *p = &data[i];
+ int nr, j;
+
+ if (ieot_start + ieot_blocks > ieot->nr)
+ ieot_blocks = ieot->nr - ieot_start;
+
+ p->istate = istate;
+ p->offset = offset;
+ p->mmap = mmap;
+ p->ieot = ieot;
+ p->ieot_start = ieot_start;
+ p->ieot_blocks = ieot_blocks;
+
+ /* create a mem_pool for each thread */
+ nr = 0;
+ for (j = p->ieot_start; j < p->ieot_start + p->ieot_blocks; j++)
+ nr += p->ieot->entries[j].nr;
+ if (istate->version == 4) {
+ mem_pool_init(&p->ce_mem_pool,
+ estimate_cache_size_from_compressed(nr));
+ } else {
+ mem_pool_init(&p->ce_mem_pool,
+ estimate_cache_size(mmap_size, nr));
+ }
+
+ err = pthread_create(&p->pthread, NULL, load_cache_entries_thread, p);
+ if (err)
+ die(_("unable to create load_cache_entries thread: %s"), strerror(err));
+
+ /* increment by the number of cache entries in the ieot block being processed */
+ for (j = 0; j < ieot_blocks; j++)
+ offset += ieot->entries[ieot_start + j].nr;
+ ieot_start += ieot_blocks;
+ }
+
+ for (i = 0; i < nr_threads; i++) {
+ struct load_cache_entries_thread_data *p = &data[i];
+
+ err = pthread_join(p->pthread, NULL);
+ if (err)
+ die(_("unable to join load_cache_entries thread: %s"), strerror(err));
+ mem_pool_combine(istate->ce_mem_pool, p->ce_mem_pool);
+ consumed += p->consumed;
+ }
+
+ free(data);
+
+ return consumed;
+}
+#endif
+
/* remember to discard_cache() before reading a different cache! */
int do_read_index(struct index_state *istate, const char *path, int must_exist)
{
- int fd, i;
+ int fd;
struct stat st;
unsigned long src_offset;
const struct cache_header *hdr;
const char *mmap;
size_t mmap_size;
- const struct cache_entry *previous_ce = NULL;
struct load_index_extensions p;
size_t extension_offset = 0;
#ifndef NO_PTHREADS
- int nr_threads;
+ int nr_threads, cpus;
+ struct index_entry_offset_table *ieot = NULL;
#endif
if (istate->initialized)
p.mmap = mmap;
p.mmap_size = mmap_size;
+ src_offset = sizeof(*hdr);
+
#ifndef NO_PTHREADS
nr_threads = git_config_get_index_threads();
- if (!nr_threads)
- nr_threads = online_cpus();
+
+ /* TODO: does creating more threads than cores help? */
+ if (!nr_threads) {
+ nr_threads = istate->cache_nr / THREAD_COST;
+ cpus = online_cpus();
+ if (nr_threads > cpus)
+ nr_threads = cpus;
+ }
if (nr_threads > 1) {
extension_offset = read_eoie_extension(mmap, mmap_size);
nr_threads--;
}
}
-#endif
- if (istate->version == 4) {
- mem_pool_init(&istate->ce_mem_pool,
- estimate_cache_size_from_compressed(istate->cache_nr));
+ /*
+ * Locate and read the index entry offset table so that we can use it
+ * to multi-thread the reading of the cache entries.
+ */
+ if (extension_offset && nr_threads > 1)
+ ieot = read_ieot_extension(mmap, mmap_size, extension_offset);
+
+ if (ieot) {
+ src_offset += load_cache_entries_threaded(istate, mmap, mmap_size, src_offset, nr_threads, ieot);
+ free(ieot);
} else {
- mem_pool_init(&istate->ce_mem_pool,
- estimate_cache_size(mmap_size, istate->cache_nr));
+ src_offset += load_all_cache_entries(istate, mmap, mmap_size, src_offset);
}
+#else
+ src_offset += load_all_cache_entries(istate, mmap, mmap_size, src_offset);
+#endif
- src_offset = sizeof(*hdr);
- for (i = 0; i < istate->cache_nr; i++) {
- struct ondisk_cache_entry *disk_ce;
- struct cache_entry *ce;
- unsigned long consumed;
-
- disk_ce = (struct ondisk_cache_entry *)(mmap + src_offset);
- ce = create_from_disk(istate, disk_ce, &consumed, previous_ce);
- set_index_entry(istate, i, ce);
-
- src_offset += consumed;
- previous_ce = ce;
- }
istate->timestamp.sec = st.st_mtime;
istate->timestamp.nsec = ST_MTIME_NSEC(st);
return 0;
}
-int index_has_changes(const struct index_state *istate,
+int index_has_changes(struct index_state *istate,
struct tree *tree,
struct strbuf *sb)
{
if (tree || !get_oid_tree("HEAD", &cmp)) {
struct diff_options opt;
- diff_setup(&opt);
+ repo_diff_setup(the_repository, &opt);
opt.flags.exit_with_status = 1;
if (!sb)
opt.flags.quick = 1;
return (write_in_full(fd, write_buffer, left) < 0) ? -1 : 0;
}
-static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
+static void ce_smudge_racily_clean_entry(struct index_state *istate,
+ struct cache_entry *ce)
{
/*
* The only thing we care about in this function is to smudge the
return;
if (ce_match_stat_basic(ce, &st))
return;
- if (ce_modified_check_fs(ce, &st)) {
+ if (ce_modified_check_fs(istate, ce, &st)) {
/* This is "racily clean"; smudge it. Note that this
* is a tricky code. At first glance, it may appear
* that it can break with this sequence:
struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
int drop_cache_tree = istate->drop_cache_tree;
off_t offset;
- int ieot_blocks = 1;
+ int ieot_entries = 1;
struct index_entry_offset_table *ieot = NULL;
int nr, nr_threads;
ieot_blocks = cpus - 1;
} else {
ieot_blocks = nr_threads;
+ if (ieot_blocks > istate->cache_nr)
+ ieot_blocks = istate->cache_nr;
}
/*
if (ieot_blocks > 1) {
ieot = xcalloc(1, sizeof(struct index_entry_offset_table)
+ (ieot_blocks * sizeof(struct index_entry_offset)));
- ieot_blocks = DIV_ROUND_UP(entries, ieot_blocks);
+ ieot_entries = DIV_ROUND_UP(entries, ieot_blocks);
}
}
#endif
if (ce->ce_flags & CE_REMOVE)
continue;
if (!ce_uptodate(ce) && is_racy_timestamp(istate, ce))
- ce_smudge_racily_clean_entry(ce);
+ ce_smudge_racily_clean_entry(istate, ce);
if (is_null_oid(&ce->oid)) {
static const char msg[] = "cache entry has null sha1: %s";
static int allow = -1;
drop_cache_tree = 1;
}
- if (ieot && i && (i % ieot_blocks == 0)) {
+ if (ieot && i && (i % ieot_entries == 0)) {
ieot->entries[ieot->nr].nr = nr;
ieot->entries[ieot->nr].offset = offset;
ieot->nr++;