@@ -2400,6 +2400,12 @@ imap::
The configuration variables in the 'imap' section are described
in linkgit:git-imap-send[1].
+index.threads::
+ Specifies the number of threads to spawn when loading the index.
+ This is meant to reduce index load time on multiprocessor machines.
+ Specifying 0 or 'true' will cause Git to auto-detect the number of
+ CPU's and set the number of threads accordingly. Defaults to 'true'.
+
index.version::
Specify the version with which new index files should be
initialized. This does not affect existing repositories.
@@ -2289,6 +2289,24 @@ int git_config_get_fsmonitor(void)
return 0;
}
+/*
+ * You can disable multi-threaded code by setting index.threads
+ * to 'false' (or 1)
+ */
+int git_config_get_index_threads(void)
+{
+ int is_bool, val;
+
+ if (!git_config_get_bool_or_int("index.threads", &is_bool, &val)) {
+ if (is_bool)
+ return val ? 0 : 1;
+ else
+ return val;
+ }
+
+ return 0; /* auto-detect */
+}
+
NORETURN
void git_die_config_linenr(const char *key, const char *filename, int linenr)
{
@@ -250,6 +250,7 @@ extern int git_config_get_untracked_cache(void);
extern int git_config_get_split_index(void);
extern int git_config_get_max_percent_split_change(void);
extern int git_config_get_fsmonitor(void);
+extern int git_config_get_index_threads(void);
/* This dies if the configured or default date is in the future */
extern int git_config_get_expiry(const char *key, const char **output);
@@ -23,6 +23,10 @@
#include "split-index.h"
#include "utf8.h"
#include "fsmonitor.h"
+#ifndef NO_PTHREADS
+#include <pthread.h>
+#include <thread-utils.h>
+#endif
/* Mask for the name length in ce_flags in the on-disk index */
@@ -1898,6 +1902,46 @@ static unsigned long read_eoie_extension(void *mmap_, size_t mmap_size);
#endif
static void write_eoie_extension(struct strbuf *sb, git_hash_ctx *eoie_context, unsigned long offset);
+struct load_index_extensions
+{
+#ifndef NO_PTHREADS
+ pthread_t pthread;
+#endif
+ struct index_state *istate;
+ void *mmap;
+ size_t mmap_size;
+ unsigned long src_offset;
+};
+
+static void *load_index_extensions(void *_data)
+{
+ struct load_index_extensions *p = _data;
+ unsigned long src_offset = p->src_offset;
+
+ while (src_offset <= p->mmap_size - the_hash_algo->rawsz - 8) {
+ /* After an array of active_nr index entries,
+ * there can be arbitrary number of extended
+ * sections, each of which is prefixed with
+ * extension name (4-byte) and section length
+ * in 4-byte network byte order.
+ */
+ uint32_t extsize;
+ memcpy(&extsize, (char *)p->mmap + src_offset + 4, 4);
+ extsize = ntohl(extsize);
+ if (read_index_extension(p->istate,
+ (const char *)p->mmap + src_offset,
+ (char *)p->mmap + src_offset + 8,
+ extsize) < 0) {
+ munmap(p->mmap, p->mmap_size);
+ die("index file corrupt");
+ }
+ src_offset += 8;
+ src_offset += extsize;
+ }
+
+ return NULL;
+}
+
/* remember to discard_cache() before reading a different cache! */
int do_read_index(struct index_state *istate, const char *path, int must_exist)
{
@@ -1908,6 +1952,11 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
void *mmap;
size_t mmap_size;
struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
+ struct load_index_extensions p = { 0 };
+ unsigned long extension_offset = 0;
+#ifndef NO_PTHREADS
+ int nr_threads;
+#endif
if (istate->initialized)
return istate->cache_nr;
@@ -1944,6 +1993,26 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
istate->cache = xcalloc(istate->cache_alloc, sizeof(*istate->cache));
istate->initialized = 1;
+ p.istate = istate;
+ p.mmap = mmap;
+ p.mmap_size = mmap_size;
+
+#ifndef NO_PTHREADS
+ nr_threads = git_config_get_index_threads();
+ if (!nr_threads)
+ nr_threads = online_cpus();
+
+ if (nr_threads >= 2) {
+ extension_offset = read_eoie_extension(mmap, mmap_size);
+ if (extension_offset) {
+ /* create a thread to load the index extensions */
+ p.src_offset = extension_offset;
+ if (pthread_create(&p.pthread, NULL, load_index_extensions, &p))
+ die(_("unable to create load_index_extensions_thread"));
+ }
+ }
+#endif
+
if (istate->version == 4) {
previous_name = &previous_name_buf;
mem_pool_init(&istate->ce_mem_pool,
@@ -1970,23 +2039,14 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
istate->timestamp.sec = st.st_mtime;
istate->timestamp.nsec = ST_MTIME_NSEC(st);
- while (src_offset <= mmap_size - the_hash_algo->rawsz - 8) {
- /* After an array of active_nr index entries,
- * there can be arbitrary number of extended
- * sections, each of which is prefixed with
- * extension name (4-byte) and section length
- * in 4-byte network byte order.
- */
- uint32_t extsize;
- memcpy(&extsize, (char *)mmap + src_offset + 4, 4);
- extsize = ntohl(extsize);
- if (read_index_extension(istate,
- (const char *) mmap + src_offset,
- (char *) mmap + src_offset + 8,
- extsize) < 0)
- goto unmap;
- src_offset += 8;
- src_offset += extsize;
+ /* if we created a thread, join it otherwise load the extensions on the primary thread */
+#ifndef NO_PTHREADS
+ if (extension_offset && pthread_join(p.pthread, NULL))
+ die(_("unable to join load_index_extensions_thread"));
+#endif
+ if (!extension_offset) {
+ p.src_offset = src_offset;
+ load_index_extensions(&p);
}
munmap(mmap, mmap_size);
return istate->cache_nr;
This patch helps address the CPU cost of loading the index by loading the cache extensions on a worker thread in parallel with loading the cache entries. In some cases, loading the extensions takes longer than loading the cache entries so this patch utilizes the new EOIE to start the thread to load the extensions before loading all the cache entries in parallel. This is possible because the current extensions don't access the cache entries in the index_state structure so are OK that they don't all exist yet. The CACHE_EXT_TREE, CACHE_EXT_RESOLVE_UNDO, and CACHE_EXT_UNTRACKED extensions don't even get a pointer to the index so don't have access to the cache entries. CACHE_EXT_LINK only uses the index_state to initialize the split index. CACHE_EXT_FSMONITOR only uses the index_state to save the fsmonitor last update and dirty flags. I used p0002-read-cache.sh to generate some performance data: Test w/100,000 files Baseline Parallel Extensions --------------------------------------------------------------------------- read_cache/discard_cache 1000 times 14.08(0.01+0.10) 9.72(0.03+0.06) -31.0% Test w/1,000,000 files Baseline Parallel Extensions ------------------------------------------------------------------------------ read_cache/discard_cache 1000 times 202.95(0.01+0.07) 154.14(0.03+0.06) -24.1% Signed-off-by: Ben Peart <Ben.Peart@microsoft.com> --- Documentation/config.txt | 6 +++ config.c | 18 ++++++++ config.h | 1 + read-cache.c | 94 ++++++++++++++++++++++++++++++++-------- 4 files changed, 102 insertions(+), 17 deletions(-)