* [PATCH v3 1/9] trace.c: add GIT_TRACE_PACK_STATS for pack usage statistics
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 2/9] read-cache.c: fix constness of verify_hdr() Nguyễn Thái Ngọc Duy
` (7 subsequent siblings)
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
trace_stats() is intended for GIT_TRACE_*_STATS variable group and
GIT_TRACE_PACK_STATS is more like an example how new vars can be added.
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
Documentation/git.txt | 3 +++
cache.h | 2 ++
git.c | 1 +
sha1_file.c | 24 ++++++++++++++++++++++++
trace.c | 13 +++++++++++++
trace.h | 1 +
6 files changed, 44 insertions(+)
diff --git a/Documentation/git.txt b/Documentation/git.txt
index a0f1ede..a124612 100644
--- a/Documentation/git.txt
+++ b/Documentation/git.txt
@@ -946,6 +946,9 @@ Unsetting the variable, or setting it to empty, "0" or
time of each Git command.
See 'GIT_TRACE' for available trace output options.
+'GIT_TRACE_PACK_STATS'::
+ Print various statistics.
+
'GIT_TRACE_SETUP'::
Enables trace messages printing the .git, working tree and current
working directory after Git has completed its setup phase.
diff --git a/cache.h b/cache.h
index fcb511d..1c84227 100644
--- a/cache.h
+++ b/cache.h
@@ -1502,4 +1502,6 @@ void stat_validity_update(struct stat_validity *sv, int fd);
int versioncmp(const char *s1, const char *s2);
+void report_pack_stats(struct trace_key *key);
+
#endif /* CACHE_H */
diff --git a/git.c b/git.c
index 9c49519..6a6a8a8 100644
--- a/git.c
+++ b/git.c
@@ -614,6 +614,7 @@ int main(int argc, char **av)
git_setup_gettext();
trace_command_performance(argv);
+ trace_stats();
/*
* "git-xxxx" is the same as "git xxxx", but we obviously:
diff --git a/sha1_file.c b/sha1_file.c
index 3f70b1d..21a487b 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -467,6 +467,7 @@ static unsigned int peak_pack_open_windows;
static unsigned int pack_open_windows;
static unsigned int pack_open_fds;
static unsigned int pack_max_fds;
+static unsigned int pack_access_nr;
static size_t peak_pack_mapped;
static size_t pack_mapped;
struct packed_git *packed_git;
@@ -492,6 +493,28 @@ void pack_report(void)
sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped));
}
+void report_pack_stats(struct trace_key *key)
+{
+ trace_printf_key(key, "\n"
+ "pack_report: getpagesize() = %10" SZ_FMT "\n"
+ "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n"
+ "pack_report: core.packedGitLimit = %10" SZ_FMT "\n"
+ "pack_report: pack_used_ctr = %10u\n"
+ "pack_report: pack_mmap_calls = %10u\n"
+ "pack_report: pack_open_windows = %10u / %10u\n"
+ "pack_report: pack_mapped = "
+ "%10" SZ_FMT " / %10" SZ_FMT "\n"
+ "pack_report: pack accesss = %10u\n",
+ sz_fmt(getpagesize()),
+ sz_fmt(packed_git_window_size),
+ sz_fmt(packed_git_limit),
+ pack_used_ctr,
+ pack_mmap_calls,
+ pack_open_windows, peak_pack_open_windows,
+ sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped),
+ pack_access_nr);
+}
+
/*
* Open and mmap the index file at path, perform a couple of
* consistency checks, then record its information to p. Return 0 on
@@ -2086,6 +2109,7 @@ static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS);
trace_printf_key(&pack_access, "%s %"PRIuMAX"\n",
p->pack_name, (uintmax_t)obj_offset);
+ pack_access_nr++;
}
int do_check_packed_object_crc;
diff --git a/trace.c b/trace.c
index e583dc6..c52da0f 100644
--- a/trace.c
+++ b/trace.c
@@ -426,3 +426,16 @@ void trace_command_performance(const char **argv)
sq_quote_argv(&command_line, argv, 0);
command_start_time = getnanotime();
}
+
+static struct trace_key trace_pack_stats = TRACE_KEY_INIT(PACK_STATS);
+
+static void print_stats_atexit(void)
+{
+ report_pack_stats(&trace_pack_stats);
+}
+
+void trace_stats(void)
+{
+ if (trace_want(&trace_pack_stats))
+ atexit(print_stats_atexit);
+}
diff --git a/trace.h b/trace.h
index ae6a332..9c06e82 100644
--- a/trace.h
+++ b/trace.h
@@ -18,6 +18,7 @@ extern int trace_want(struct trace_key *key);
extern void trace_disable(struct trace_key *key);
extern uint64_t getnanotime(void);
extern void trace_command_performance(const char **argv);
+extern void trace_stats(void);
#ifndef HAVE_VARIADIC_MACROS
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 2/9] read-cache.c: fix constness of verify_hdr()
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 1/9] trace.c: add GIT_TRACE_PACK_STATS for pack usage statistics Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 3/9] read-cache: allow to keep mmap'd memory after reading Nguyễn Thái Ngọc Duy
` (6 subsequent siblings)
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
read-cache.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/read-cache.c b/read-cache.c
index 5d3c8bd..949270b 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1324,7 +1324,7 @@ struct ondisk_cache_entry_extended {
ondisk_cache_entry_extended_size(ce_namelen(ce)) : \
ondisk_cache_entry_size(ce_namelen(ce)))
-static int verify_hdr(struct cache_header *hdr, unsigned long size)
+static int verify_hdr(const struct cache_header *hdr, unsigned long size)
{
git_SHA_CTX c;
unsigned char sha1[20];
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 3/9] read-cache: allow to keep mmap'd memory after reading
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 1/9] trace.c: add GIT_TRACE_PACK_STATS for pack usage statistics Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 2/9] read-cache.c: fix constness of verify_hdr() Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff Nguyễn Thái Ngọc Duy
` (5 subsequent siblings)
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
cache.h | 3 +++
read-cache.c | 13 ++++++++++++-
2 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/cache.h b/cache.h
index 1c84227..978e53d 100644
--- a/cache.h
+++ b/cache.h
@@ -306,10 +306,13 @@ struct index_state {
struct split_index *split_index;
struct cache_time timestamp;
unsigned name_hash_initialized : 1,
+ keep_mmap : 1,
initialized : 1;
struct hashmap name_hash;
struct hashmap dir_hash;
unsigned char sha1[20];
+ void *mmap;
+ size_t mmap_size;
};
extern struct index_state the_index;
diff --git a/read-cache.c b/read-cache.c
index 949270b..b679781 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1498,6 +1498,10 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
if (mmap == MAP_FAILED)
die_errno("unable to map index file");
+ if (istate->keep_mmap) {
+ istate->mmap = mmap;
+ istate->mmap_size = mmap_size;
+ }
close(fd);
hdr = mmap;
@@ -1550,10 +1554,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
src_offset += 8;
src_offset += extsize;
}
- munmap(mmap, mmap_size);
+ if (!istate->keep_mmap)
+ munmap(mmap, mmap_size);
return istate->cache_nr;
unmap:
+ istate->mmap = NULL;
munmap(mmap, mmap_size);
die("index file corrupt");
}
@@ -1579,6 +1585,7 @@ int read_index_from(struct index_state *istate, const char *path)
discard_index(split_index->base);
else
split_index->base = xcalloc(1, sizeof(*split_index->base));
+ split_index->base->keep_mmap = istate->keep_mmap;
ret = do_read_index(split_index->base,
git_path("sharedindex.%s",
sha1_to_hex(split_index->base_sha1)), 1);
@@ -1621,6 +1628,10 @@ int discard_index(struct index_state *istate)
free(istate->cache);
istate->cache = NULL;
istate->cache_alloc = 0;
+ if (istate->keep_mmap && istate->mmap) {
+ munmap(istate->mmap, istate->mmap_size);
+ istate->mmap = NULL;
+ }
discard_split_index(istate);
return 0;
}
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
` (2 preceding siblings ...)
2014-07-28 12:03 ` [PATCH v3 3/9] read-cache: allow to keep mmap'd memory after reading Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-30 8:08 ` Eric Sunshine
2014-07-31 2:41 ` David Turner
2014-07-28 12:03 ` [PATCH v3 5/9] trace.c: add GIT_TRACE_INDEX_STATS for index statistics Nguyễn Thái Ngọc Duy
` (4 subsequent siblings)
8 siblings, 2 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
Instead of reading the index from disk and worrying about disk
corruption, the index is cached in memory (memory bit-flips happen
too, but hopefully less often). The result is faster read.
The biggest gain is not having to verify the trailing SHA-1, which
takes lots of time especially on large index files. But this also
opens doors for further optimiztions:
- we could create an in-memory format that's essentially the memory
dump of the index to eliminate most of parsing/allocation
overhead. The mmap'd memory can be used straight away.
- we could cache non-index info such as name hash
The shared memory's name folows the template "git-<object>-<SHA1>"
where <SHA1> is the trailing SHA-1 of the index file. <object> is
"index" for cached index files (and may be "name-hash" for name-hash
cache). If such shared memory exists, it contains the same index
content as on disk. The content is already validated by the daemon and
git won't validate it again (except comparing the trailing SHA-1s).
Git can poke the daemon to tell it to refresh the index cache, or to
keep it alive some more minutes via UNIX signals. It can't give any
real index data directly to the daemon. Real data goes to disk first,
then the daemon reads and verifies it from there.
$GIT_DIR/index-helper.pid contains a reference to daemon process (and
it's pid on *nix). The file's mtime is updated every time it's accessed
(or should be updated often enough). Old index-helper.pid is considered
stale and ignored.
index-helper requires POSIX realtime extension. POSIX shm interface
however is abstracted away so that Windows support can be added later.
On webkit.git with index format v2, duplicating 8 times to 1.4m
entries and 200MB in size:
(vanilla) 0.986986364 s: read_index_from .git/index
(index-helper) 0.267850279 s: read_index_from .git/index
Interestingly with index v4, we get less out of index-helper. It makes
sense as v4 requires more processing after loading the index:
(vanilla) 0.722496666 s: read_index_from .git/index
(index-helper) 0.302741500 s: read_index_from .git/index
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
.gitignore | 1 +
Documentation/git-index-helper.txt (new) | 44 +++++++++
Makefile | 9 ++
cache.h | 2 +
config.mak.uname | 1 +
git-compat-util.h | 1 +
index-helper.c (new) | 157 +++++++++++++++++++++++++++++++
read-cache.c | 85 +++++++++++++++--
shm.c (new) | 67 +++++++++++++
shm.h (new) | 23 +++++
10 files changed, 381 insertions(+), 9 deletions(-)
create mode 100644 Documentation/git-index-helper.txt
create mode 100644 index-helper.c
create mode 100644 shm.c
create mode 100644 shm.h
diff --git a/.gitignore b/.gitignore
index 81e12c0..66148ef 100644
--- a/.gitignore
+++ b/.gitignore
@@ -71,6 +71,7 @@
/git-http-fetch
/git-http-push
/git-imap-send
+/git-index-helper
/git-index-pack
/git-init
/git-init-db
diff --git a/Documentation/git-index-helper.txt b/Documentation/git-index-helper.txt
new file mode 100644
index 0000000..da41c4d
--- /dev/null
+++ b/Documentation/git-index-helper.txt
@@ -0,0 +1,44 @@
+git-index-helper(1)
+===================
+
+NAME
+----
+git-index-helper - A simple cache daemon for speeding up index file access
+
+SYNOPSIS
+--------
+[verse]
+'git index-helper' [options]
+
+DESCRIPTION
+-----------
+Keep the index file in memory for faster access. This daemon is per
+repository.
+
+OPTIONS
+-------
+
+--exit-after=<n>::
+ Exit if the cached index is not accessed for `<n>`
+ minutes. Specify 0 to wait forever. Default is 10.
+
+NOTES
+-----
+On UNIX-like systems, $GIT_DIR/index-helper.pid contains the process
+id of the daemon. At least on Linux, shared memory objects are
+availble via /dev/shm with the name pattern "git-<something>-<SHA1>".
+Normally the daemon will clean up shared memory objects when it exits.
+But if it crashes, some objects could remain there and they can be
+safely deleted with "rm" command. The following signals are used to
+control the daemon:
+
+SIGHUP::
+ Reread the index.
+
+SIGUSR1::
+ This signal is counted as "an access", which keeps the daemon
+ alive longer, unless `--exit-after=0` is used.
+
+GIT
+---
+Part of the linkgit:git[1] suite
diff --git a/Makefile b/Makefile
index 2320de5..24734e6 100644
--- a/Makefile
+++ b/Makefile
@@ -342,6 +342,8 @@ all::
# return NULL when it receives a bogus time_t.
#
# Define HAVE_CLOCK_GETTIME if your platform has clock_gettime in librt.
+#
+# Define HAVE_SHM if you platform support shm_* functions in librt.
GIT-VERSION-FILE: FORCE
@$(SHELL_PATH) ./GIT-VERSION-GEN
@@ -876,6 +878,7 @@ LIB_OBJS += sha1-lookup.o
LIB_OBJS += sha1_file.o
LIB_OBJS += sha1_name.o
LIB_OBJS += shallow.o
+LIB_OBJS += shm.o
LIB_OBJS += sideband.o
LIB_OBJS += sigchain.o
LIB_OBJS += split-index.o
@@ -1469,6 +1472,12 @@ ifdef HAVE_DEV_TTY
BASIC_CFLAGS += -DHAVE_DEV_TTY
endif
+ifdef HAVE_SHM
+ BASIC_CFLAGS += -DHAVE_SHM
+ EXTLIBS += -lrt
+ PROGRAM_OBJS += index-helper.o
+endif
+
ifdef DIR_HAS_BSD_GROUP_SEMANTICS
COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
endif
diff --git a/cache.h b/cache.h
index 978e53d..29a0c53 100644
--- a/cache.h
+++ b/cache.h
@@ -499,6 +499,7 @@ extern int is_index_unborn(struct index_state *);
extern int read_index_unmerged(struct index_state *);
#define COMMIT_LOCK (1 << 0)
#define CLOSE_LOCK (1 << 1)
+#define REFRESH_DAEMON (1 << 2)
extern int write_locked_index(struct index_state *, struct lock_file *lock, unsigned flags);
extern int discard_index(struct index_state *);
extern int unmerged_index(const struct index_state *);
@@ -621,6 +622,7 @@ extern size_t packed_git_limit;
extern size_t delta_base_cache_limit;
extern unsigned long big_file_threshold;
extern unsigned long pack_size_limit_cfg;
+extern int dont_poke_index_helper;
/*
* Do replace refs need to be checked this run? This variable is
diff --git a/config.mak.uname b/config.mak.uname
index 00cf4c6..7e66d80 100644
--- a/config.mak.uname
+++ b/config.mak.uname
@@ -35,6 +35,7 @@ ifeq ($(uname_S),Linux)
LIBC_CONTAINS_LIBINTL = YesPlease
HAVE_DEV_TTY = YesPlease
HAVE_CLOCK_GETTIME = YesPlease
+ HAVE_SHM = YesPlease
endif
ifeq ($(uname_S),GNU/kFreeBSD)
HAVE_ALLOCA_H = YesPlease
diff --git a/git-compat-util.h b/git-compat-util.h
index 26e92f1..13eef92 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -417,6 +417,7 @@ static inline int ends_with(const char *str, const char *suffix)
#define PROT_READ 1
#define PROT_WRITE 2
#define MAP_PRIVATE 1
+#define MAP_SHARED 2
#endif
#define mmap git_mmap
diff --git a/index-helper.c b/index-helper.c
new file mode 100644
index 0000000..8fa0af9
--- /dev/null
+++ b/index-helper.c
@@ -0,0 +1,157 @@
+#include "cache.h"
+#include "parse-options.h"
+#include "sigchain.h"
+#include "exec_cmd.h"
+#include "split-index.h"
+#include "shm.h"
+
+struct index_shm {
+ unsigned char sha1[20];
+ void *shm;
+ size_t size;
+};
+
+static struct index_shm shm_index;
+static struct index_shm shm_base_index;
+
+static void free_index_shm(struct index_shm *is)
+{
+ if (!is->shm)
+ return;
+ munmap(is->shm, is->size);
+ git_shm_unlink("git-index-%s", sha1_to_hex(is->sha1));
+ is->shm = NULL;
+}
+
+static void cleanup_shm(void)
+{
+ free_index_shm(&shm_index);
+ free_index_shm(&shm_base_index);
+}
+
+static void cleanup(void)
+{
+ unlink(git_path("index-helper.pid"));
+ cleanup_shm();
+}
+
+static void cleanup_on_signal(int sig)
+{
+ cleanup();
+ sigchain_pop(sig);
+ raise(sig);
+}
+
+static void share_index(struct index_state *istate, struct index_shm *is)
+{
+ void *new_mmap;
+ if (istate->mmap_size <= 20 ||
+ hashcmp(istate->sha1,
+ (unsigned char *)istate->mmap + istate->mmap_size - 20) ||
+ !hashcmp(istate->sha1, is->sha1) ||
+ git_shm_map(O_CREAT | O_EXCL | O_RDWR, 0700, istate->mmap_size,
+ &new_mmap, PROT_READ | PROT_WRITE, MAP_SHARED,
+ "git-index-%s", sha1_to_hex(istate->sha1)) < 0)
+ return;
+
+ free_index_shm(is);
+ is->size = istate->mmap_size;
+ is->shm = new_mmap;
+ hashcpy(is->sha1, istate->sha1);
+ memcpy(new_mmap, istate->mmap, istate->mmap_size - 20);
+
+ /*
+ * The trailing hash must be written last after everything is
+ * written. It's the indication that the shared memory is now
+ * ready.
+ */
+ hashcpy((unsigned char *)new_mmap + istate->mmap_size - 20, is->sha1);
+}
+
+static void refresh(int sig)
+{
+ the_index.keep_mmap = 1;
+ if (read_cache() < 0)
+ die(_("could not read index"));
+ if (the_index.split_index && the_index.split_index->base)
+ share_index(the_index.split_index->base, &shm_base_index);
+ share_index(&the_index, &shm_index);
+ discard_index(&the_index);
+}
+
+#ifdef HAVE_SHM
+
+static void do_nothing(int sig)
+{
+ /*
+ * what we need is the signal received and interrupts
+ * sleep(). We don't need to do anything else when receving
+ * the signal
+ */
+}
+
+static void loop(const char *pid_file, int idle_in_seconds)
+{
+ sigchain_pop(SIGHUP); /* pushed by sigchain_push_common */
+ sigchain_push(SIGHUP, refresh);
+ sigchain_push(SIGUSR1, do_nothing);
+ refresh(0);
+ while (sleep(idle_in_seconds))
+ ; /* do nothing, all is handled by signal handlers already */
+}
+
+#else
+
+static void loop(const char *pid_file, int idle_in_seconds)
+{
+ die(_("index-helper is not supported on this platform"));
+}
+
+#endif
+
+static const char * const usage_text[] = {
+ N_("git index-helper [options]"),
+ NULL
+};
+
+int main(int argc, char **argv)
+{
+ static struct lock_file lock;
+ struct strbuf sb = STRBUF_INIT;
+ const char *prefix;
+ int fd, idle_in_minutes = 10;
+ struct option options[] = {
+ OPT_INTEGER(0, "exit-after", &idle_in_minutes,
+ N_("exit if not used after some minutes")),
+ OPT_END()
+ };
+
+ git_extract_argv0_path(argv[0]);
+ git_setup_gettext();
+ dont_poke_index_helper = 1; /* cyclic poking is no fun */
+
+ if (argc == 2 && !strcmp(argv[1], "-h"))
+ usage_with_options(usage_text, options);
+
+ prefix = setup_git_directory();
+ if (parse_options(argc, (const char **)argv, prefix,
+ options, usage_text, 0))
+ die(_("too many arguments"));
+
+ fd = hold_lock_file_for_update(&lock,
+ git_path("index-helper.pid"),
+ LOCK_DIE_ON_ERROR);
+ strbuf_addf(&sb,
+ "%" PRIuMAX, (uintmax_t) getpid());
+ write_in_full(fd, sb.buf, sb.len);
+ commit_lock_file(&lock);
+
+ atexit(cleanup);
+ sigchain_push_common(cleanup_on_signal);
+
+ if (!idle_in_minutes)
+ idle_in_minutes = 0xffffffff / 60;
+ loop(sb.buf, idle_in_minutes * 60);
+ strbuf_release(&sb);
+ return 0;
+}
diff --git a/read-cache.c b/read-cache.c
index b679781..ff28142 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -16,6 +16,7 @@
#include "varint.h"
#include "split-index.h"
#include "sigchain.h"
+#include "shm.h"
static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
unsigned int options);
@@ -45,6 +46,7 @@ static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
struct index_state the_index;
static const char *alternate_index_output;
+int dont_poke_index_helper;
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
@@ -1465,6 +1467,65 @@ static struct cache_entry *create_from_disk(struct ondisk_cache_entry *ondisk,
return ce;
}
+static void poke_daemon(const struct stat *st, int refresh_cache)
+{
+ int fd;
+ struct strbuf sb;
+
+ if (dont_poke_index_helper)
+ return;
+ fd = open(git_path("index-helper.pid"), O_RDONLY);
+ if (fd < 0)
+ return;
+ strbuf_init(&sb, st->st_size + 1);
+ strbuf_setlen(&sb, st->st_size);
+ if (read_in_full(fd, sb.buf, st->st_size) == st->st_size) {
+#ifdef HAVE_SHM
+ char *end = NULL;
+ pid_t pid = strtoul(sb.buf, &end, 10);
+ if (end && sb.buf + st->st_size == end)
+ kill(pid, refresh_cache ? SIGHUP : SIGUSR1);
+#endif
+ }
+ close(fd);
+ strbuf_release(&sb);
+}
+
+/*
+ * Try to open and verify a cached shm index if available. Return 0 if
+ * succeeds (istate->mmap and istate->mmap_size are updated). Return
+ * negative otherwise.
+ */
+static int try_shm(struct index_state *istate)
+{
+ void *new_mmap = NULL;
+ size_t old_size = istate->mmap_size;
+ ssize_t new_length;
+ const unsigned char *sha1;
+ struct stat st;
+
+ if (old_size <= 20 ||
+ stat(git_path("index-helper.pid"), &st))
+ return -1;
+ sha1 = (unsigned char *)istate->mmap + old_size - 20;
+ new_length = git_shm_map(O_RDONLY, 0700, -1, &new_mmap,
+ PROT_READ, MAP_SHARED,
+ "git-index-%s", sha1_to_hex(sha1));
+ if (new_length <= 20 ||
+ hashcmp((unsigned char *)istate->mmap + old_size - 20,
+ (unsigned char *)new_mmap + new_length - 20)) {
+ if (new_mmap)
+ munmap(new_mmap, new_length);
+ poke_daemon(&st, 1);
+ return -1;
+ }
+ munmap(istate->mmap, istate->mmap_size);
+ istate->mmap = new_mmap;
+ istate->mmap_size = new_length;
+ poke_daemon(&st, 0);
+ return 0;
+}
+
/* remember to discard_cache() before reading a different cache! */
int do_read_index(struct index_state *istate, const char *path, int must_exist)
{
@@ -1498,15 +1559,17 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
if (mmap == MAP_FAILED)
die_errno("unable to map index file");
- if (istate->keep_mmap) {
- istate->mmap = mmap;
- istate->mmap_size = mmap_size;
- }
close(fd);
- hdr = mmap;
- if (verify_hdr(hdr, mmap_size) < 0)
+ istate->mmap = mmap;
+ istate->mmap_size = mmap_size;
+ if (try_shm(istate) &&
+ verify_hdr(istate->mmap, istate->mmap_size) < 0)
goto unmap;
+ hdr = mmap = istate->mmap;
+ mmap_size = istate->mmap_size;
+ if (!istate->keep_mmap)
+ istate->mmap = NULL;
hashcpy(istate->sha1, (const unsigned char *)hdr + mmap_size - 20);
istate->version = ntohl(hdr->hdr_version);
@@ -2054,9 +2117,13 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l
return ret;
assert((flags & (COMMIT_LOCK | CLOSE_LOCK)) !=
(COMMIT_LOCK | CLOSE_LOCK));
- if (flags & COMMIT_LOCK)
- return commit_locked_index(lock);
- else if (flags & CLOSE_LOCK)
+ if (flags & COMMIT_LOCK) {
+ struct stat st;
+ ret = commit_locked_index(lock);
+ if (!ret && !stat(git_path("index-helper.pid"), &st))
+ poke_daemon(&st, 1);
+ return ret;
+ } else if (flags & CLOSE_LOCK)
return close_lock_file(lock);
else
return ret;
diff --git a/shm.c b/shm.c
new file mode 100644
index 0000000..4ec1a00
--- /dev/null
+++ b/shm.c
@@ -0,0 +1,67 @@
+#include "git-compat-util.h"
+#include "shm.h"
+
+#ifdef HAVE_SHM
+
+#define SHM_PATH_LEN 72 /* we don't create very long paths.. */
+
+ssize_t git_shm_map(int oflag, int perm, ssize_t length, void **mmap,
+ int prot, int flags, const char *fmt, ...)
+{
+ va_list ap;
+ char path[SHM_PATH_LEN];
+ int fd;
+
+ path[0] = '/';
+ va_start(ap, fmt);
+ vsprintf(path + 1, fmt, ap);
+ va_end(ap);
+ fd = shm_open(path, oflag, perm);
+ if (fd < 0)
+ return -1;
+ if (length > 0 && ftruncate(fd, length)) {
+ shm_unlink(path);
+ close(fd);
+ return -1;
+ }
+ if (length < 0 && !(oflag & O_CREAT)) {
+ struct stat st;
+ if (fstat(fd, &st))
+ die_errno("unable to stat %s", path);
+ length = st.st_size;
+ }
+ *mmap = xmmap(NULL, length, prot, flags, fd, 0);
+ close(fd);
+ if (*mmap == MAP_FAILED) {
+ *mmap = NULL;
+ shm_unlink(path);
+ return -1;
+ }
+ return length;
+}
+
+void git_shm_unlink(const char *fmt, ...)
+{
+ va_list ap;
+ char path[SHM_PATH_LEN];
+
+ path[0] = '/';
+ va_start(ap, fmt);
+ vsprintf(path + 1, fmt, ap);
+ va_end(ap);
+ shm_unlink(path);
+}
+
+#else
+
+ssize_t git_shm_map(int oflag, int perm, ssize_t length, void **mmap,
+ int prot, int flags, const char *fmt, ...)
+{
+ return -1;
+}
+
+void git_shm_unlink(const char *fmt, ...)
+{
+}
+
+#endif
diff --git a/shm.h b/shm.h
new file mode 100644
index 0000000..798d3fd
--- /dev/null
+++ b/shm.h
@@ -0,0 +1,23 @@
+#ifndef SHM_H
+#define SHM_H
+
+/*
+ * Create or open a shared memory and mmap it. Return mmap size if
+ * successful, -1 otherwise. If successful mmap contains the mmap'd
+ * pointer. If oflag does not contain O_CREAT and length is negative,
+ * the mmap size is retrieved from existing shared memory object.
+ *
+ * The mmap could be freed by munmap, even on Windows. Note that on
+ * Windows, git_shm_unlink() is no-op, so the last unmap will destroy
+ * the shared memory.
+ */
+ssize_t git_shm_map(int oflag, int perm, ssize_t length, void **mmap,
+ int prot, int flags, const char *fmt, ...);
+
+/*
+ * Unlink a shared memory object. Only needed on POSIX platforms. On
+ * Windows this is no-op.
+ */
+void git_shm_unlink(const char *fmt, ...);
+
+#endif
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* Re: [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff
2014-07-28 12:03 ` [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff Nguyễn Thái Ngọc Duy
@ 2014-07-30 8:08 ` Eric Sunshine
2014-07-30 10:39 ` Duy Nguyen
2014-07-31 2:41 ` David Turner
1 sibling, 1 reply; 13+ messages in thread
From: Eric Sunshine @ 2014-07-30 8:08 UTC (permalink / raw)
To: Nguyễn Thái Ngọc Duy; +Cc: git@vger.kernel.org
On Monday, July 28, 2014, Nguyễn Thái Ngọc Duy <pclouds@gmail.com> wrote:
> Instead of reading the index from disk and worrying about disk
> corruption, the index is cached in memory (memory bit-flips happen
> too, but hopefully less often). The result is faster read.
>
> The biggest gain is not having to verify the trailing SHA-1, which
> takes lots of time especially on large index files. But this also
> opens doors for further optimiztions:
s/optimiztions/optimizations/
> - we could create an in-memory format that's essentially the memory
> dump of the index to eliminate most of parsing/allocation
> overhead. The mmap'd memory can be used straight away.
>
> - we could cache non-index info such as name hash
>
> The shared memory's name folows the template "git-<object>-<SHA1>"
s/folows/follows/
> where <SHA1> is the trailing SHA-1 of the index file. <object> is
> "index" for cached index files (and may be "name-hash" for name-hash
> cache). If such shared memory exists, it contains the same index
> content as on disk. The content is already validated by the daemon and
> git won't validate it again (except comparing the trailing SHA-1s).
>
> Git can poke the daemon to tell it to refresh the index cache, or to
> keep it alive some more minutes via UNIX signals. It can't give any
> real index data directly to the daemon. Real data goes to disk first,
> then the daemon reads and verifies it from there.
>
> $GIT_DIR/index-helper.pid contains a reference to daemon process (and
> it's pid on *nix). The file's mtime is updated every time it's accessed
s/it's pid/its pid/
> (or should be updated often enough). Old index-helper.pid is considered
> stale and ignored.
>
> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
> ---
> diff --git a/index-helper.c b/index-helper.c
> new file mode 100644
> index 0000000..8fa0af9
> --- /dev/null
> +++ b/index-helper.c
> @@ -0,0 +1,157 @@
> +static void share_index(struct index_state *istate, struct index_shm *is)
> +{
> + void *new_mmap;
> + if (istate->mmap_size <= 20 ||
> + hashcmp(istate->sha1,
> + (unsigned char *)istate->mmap + istate->mmap_size - 20) ||
> + !hashcmp(istate->sha1, is->sha1) ||
> + git_shm_map(O_CREAT | O_EXCL | O_RDWR, 0700, istate->mmap_size,
> + &new_mmap, PROT_READ | PROT_WRITE, MAP_SHARED,
> + "git-index-%s", sha1_to_hex(istate->sha1)) < 0)
Do any of these failure conditions deserve a diagnostic message to let
the user know that there was a problem?
> + return;
> +
> + free_index_shm(is);
> + is->size = istate->mmap_size;
> + is->shm = new_mmap;
> + hashcpy(is->sha1, istate->sha1);
> + memcpy(new_mmap, istate->mmap, istate->mmap_size - 20);
> +
> + /*
> + * The trailing hash must be written last after everything is
> + * written. It's the indication that the shared memory is now
> + * ready.
> + */
> + hashcpy((unsigned char *)new_mmap + istate->mmap_size - 20, is->sha1);
> +}
> diff --git a/read-cache.c b/read-cache.c
> index b679781..ff28142 100644
> --- a/read-cache.c
> +++ b/read-cache.c
> @@ -1465,6 +1467,65 @@ static struct cache_entry *create_from_disk(struct ondisk_cache_entry *ondisk,
> return ce;
> }
>
> +/*
> + * Try to open and verify a cached shm index if available. Return 0 if
> + * succeeds (istate->mmap and istate->mmap_size are updated). Return
> + * negative otherwise.
> + */
> +static int try_shm(struct index_state *istate)
> +{
> + void *new_mmap = NULL;
> + size_t old_size = istate->mmap_size;
Is old_size needed? Can you not simply reference istate->mmap_size
directly each place old_size is mentioned?
> + ssize_t new_length;
Nit: 'size' vs. 'length' inconsistency in variable name choices.
> + const unsigned char *sha1;
> + struct stat st;
> +
> + if (old_size <= 20 ||
> + stat(git_path("index-helper.pid"), &st))
> + return -1;
> + sha1 = (unsigned char *)istate->mmap + old_size - 20;
> + new_length = git_shm_map(O_RDONLY, 0700, -1, &new_mmap,
> + PROT_READ, MAP_SHARED,
> + "git-index-%s", sha1_to_hex(sha1));
> + if (new_length <= 20 ||
> + hashcmp((unsigned char *)istate->mmap + old_size - 20,
> + (unsigned char *)new_mmap + new_length - 20)) {
> + if (new_mmap)
> + munmap(new_mmap, new_length);
> + poke_daemon(&st, 1);
> + return -1;
> + }
> + munmap(istate->mmap, istate->mmap_size);
> + istate->mmap = new_mmap;
> + istate->mmap_size = new_length;
> + poke_daemon(&st, 0);
> + return 0;
> +}
> +
> /* remember to discard_cache() before reading a different cache! */
> int do_read_index(struct index_state *istate, const char *path, int must_exist)
> {
> diff --git a/shm.c b/shm.c
> new file mode 100644
> index 0000000..4ec1a00
> --- /dev/null
> +++ b/shm.c
> @@ -0,0 +1,67 @@
> +#include "git-compat-util.h"
> +#include "shm.h"
> +
> +#ifdef HAVE_SHM
> +
> +#define SHM_PATH_LEN 72 /* we don't create very long paths.. */
> +
> +ssize_t git_shm_map(int oflag, int perm, ssize_t length, void **mmap,
> + int prot, int flags, const char *fmt, ...)
> +{
> + va_list ap;
> + char path[SHM_PATH_LEN];
Is there a reason to avoid strbuf here?
> + int fd;
> +
> + path[0] = '/';
> + va_start(ap, fmt);
> + vsprintf(path + 1, fmt, ap);
> + va_end(ap);
> + fd = shm_open(path, oflag, perm);
> + if (fd < 0)
> + return -1;
> + if (length > 0 && ftruncate(fd, length)) {
> + shm_unlink(path);
> + close(fd);
> + return -1;
> + }
> + if (length < 0 && !(oflag & O_CREAT)) {
> + struct stat st;
> + if (fstat(fd, &st))
> + die_errno("unable to stat %s", path);
> + length = st.st_size;
> + }
> + *mmap = xmmap(NULL, length, prot, flags, fd, 0);
> + close(fd);
> + if (*mmap == MAP_FAILED) {
> + *mmap = NULL;
> + shm_unlink(path);
> + return -1;
> + }
> + return length;
> +}
^ permalink raw reply [flat|nested] 13+ messages in thread* Re: [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff
2014-07-30 8:08 ` Eric Sunshine
@ 2014-07-30 10:39 ` Duy Nguyen
0 siblings, 0 replies; 13+ messages in thread
From: Duy Nguyen @ 2014-07-30 10:39 UTC (permalink / raw)
To: Eric Sunshine; +Cc: git@vger.kernel.org
On Wed, Jul 30, 2014 at 3:08 PM, Eric Sunshine <sunshine@sunshineco.com> wrote:
>> +static void share_index(struct index_state *istate, struct index_shm *is)
>> +{
>> + void *new_mmap;
>> + if (istate->mmap_size <= 20 ||
>> + hashcmp(istate->sha1,
>> + (unsigned char *)istate->mmap + istate->mmap_size - 20) ||
>> + !hashcmp(istate->sha1, is->sha1) ||
>> + git_shm_map(O_CREAT | O_EXCL | O_RDWR, 0700, istate->mmap_size,
>> + &new_mmap, PROT_READ | PROT_WRITE, MAP_SHARED,
>> + "git-index-%s", sha1_to_hex(istate->sha1)) < 0)
>
> Do any of these failure conditions deserve a diagnostic message to let
> the user know that there was a problem?
Hmm.. diagnostic messages are a problem already. This most likely runs
as a daemon, nowhere to print to. But if running on foreground, some
messages would help.
>> +static int try_shm(struct index_state *istate)
>> +{
>> + void *new_mmap = NULL;
>> + size_t old_size = istate->mmap_size;
>
> Is old_size needed? Can you not simply reference istate->mmap_size
> directly each place old_size is mentioned?
>
>> + ssize_t new_length;
>
> Nit: 'size' vs. 'length' inconsistency in variable name choices.
Leftovers after many iterations. Will fix.
>> +#define SHM_PATH_LEN 72 /* we don't create very long paths.. */
>> +
>> +ssize_t git_shm_map(int oflag, int perm, ssize_t length, void **mmap,
>> + int prot, int flags, const char *fmt, ...)
>> +{
>> + va_list ap;
>> + char path[SHM_PATH_LEN];
>
> Is there a reason to avoid strbuf here?
Laziness (which is ironic as I'm working on patches to clean up fixed
size buffers)
--
Duy
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff
2014-07-28 12:03 ` [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff Nguyễn Thái Ngọc Duy
2014-07-30 8:08 ` Eric Sunshine
@ 2014-07-31 2:41 ` David Turner
1 sibling, 0 replies; 13+ messages in thread
From: David Turner @ 2014-07-31 2:41 UTC (permalink / raw)
To: Nguyễn Thái Ngọc Duy; +Cc: git
On Mon, 2014-07-28 at 19:03 +0700, Nguyễn Thái Ngọc Duy wrote:
> +# Define HAVE_SHM if you platform support shm_* functions in librt.
s/you/your/
> +static void free_index_shm(struct index_shm *is)
Does not actually free its argument; should be release_index_shm.
^ permalink raw reply [flat|nested] 13+ messages in thread
* [PATCH v3 5/9] trace.c: add GIT_TRACE_INDEX_STATS for index statistics
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
` (3 preceding siblings ...)
2014-07-28 12:03 ` [PATCH v3 4/9] index-helper: new daemon for caching index and related stuff Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 6/9] index-helper: add --strict Nguyễn Thái Ngọc Duy
` (3 subsequent siblings)
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
Documentation/git.txt | 1 +
cache.h | 1 +
read-cache.c | 16 ++++++++++++++++
trace.c | 5 ++++-
4 files changed, 22 insertions(+), 1 deletion(-)
diff --git a/Documentation/git.txt b/Documentation/git.txt
index a124612..7077386 100644
--- a/Documentation/git.txt
+++ b/Documentation/git.txt
@@ -947,6 +947,7 @@ Unsetting the variable, or setting it to empty, "0" or
See 'GIT_TRACE' for available trace output options.
'GIT_TRACE_PACK_STATS'::
+'GIT_TRACE_INDEX_STATS'::
Print various statistics.
'GIT_TRACE_SETUP'::
diff --git a/cache.h b/cache.h
index 29a0c53..4266771 100644
--- a/cache.h
+++ b/cache.h
@@ -1508,5 +1508,6 @@ void stat_validity_update(struct stat_validity *sv, int fd);
int versioncmp(const char *s1, const char *s2);
void report_pack_stats(struct trace_key *key);
+void report_index_stats(struct trace_key *key);
#endif /* CACHE_H */
diff --git a/read-cache.c b/read-cache.c
index ff28142..4bd2abe 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -48,6 +48,10 @@ struct index_state the_index;
static const char *alternate_index_output;
int dont_poke_index_helper;
+static unsigned int nr_read_index;
+static unsigned int nr_read_shm_index;
+static unsigned int nr_write_index;
+
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
istate->cache[nr] = ce;
@@ -1523,6 +1527,7 @@ static int try_shm(struct index_state *istate)
istate->mmap = new_mmap;
istate->mmap_size = new_length;
poke_daemon(&st, 0);
+ nr_read_shm_index++;
return 0;
}
@@ -1619,6 +1624,7 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
}
if (!istate->keep_mmap)
munmap(mmap, mmap_size);
+ nr_read_index++;
return istate->cache_nr;
unmap:
@@ -2087,6 +2093,7 @@ static int do_write_index(struct index_state *istate, int newfd,
return -1;
istate->timestamp.sec = (unsigned int)st.st_mtime;
istate->timestamp.nsec = ST_MTIME_NSEC(st);
+ nr_write_index++;
return 0;
}
@@ -2346,3 +2353,12 @@ void stat_validity_update(struct stat_validity *sv, int fd)
fill_stat_data(sv->sd, &st);
}
}
+
+void report_index_stats(struct trace_key *key)
+{
+ trace_printf_key(key, "\n"
+ "index stats: file reads = %10u\n"
+ "index stats: cache reads = %10u\n"
+ "index stats: file writes = %10u\n",
+ nr_read_index, nr_read_shm_index, nr_write_index);
+}
diff --git a/trace.c b/trace.c
index c52da0f..eb3a11a 100644
--- a/trace.c
+++ b/trace.c
@@ -428,14 +428,17 @@ void trace_command_performance(const char **argv)
}
static struct trace_key trace_pack_stats = TRACE_KEY_INIT(PACK_STATS);
+static struct trace_key trace_index_stats = TRACE_KEY_INIT(INDEX_STATS);
static void print_stats_atexit(void)
{
report_pack_stats(&trace_pack_stats);
+ report_index_stats(&trace_index_stats);
}
void trace_stats(void)
{
- if (trace_want(&trace_pack_stats))
+ if (trace_want(&trace_pack_stats) ||
+ trace_want(&trace_index_stats))
atexit(print_stats_atexit);
}
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 6/9] index-helper: add --strict
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
` (4 preceding siblings ...)
2014-07-28 12:03 ` [PATCH v3 5/9] trace.c: add GIT_TRACE_INDEX_STATS for index statistics Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 7/9] daemonize(): set a flag before exiting the main process Nguyễn Thái Ngọc Duy
` (2 subsequent siblings)
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
There's are "holes" in the index-helper approach because the shared
memory is not verified again by git. If $USER is compromised, shared
memory could be modified. But then they can already modify
$GIT_DIR/index. A more realistic risk is some bugs in index-helper
produce corrupt shared memory. --strict is added to avoid that
Strictly speaking there's still a very small gap where corrupt shared
memory could still be read by git: after we write the trailing SHA-1 in
the shared memory (thus signaling "this shm is ready") and before
verify_shm() detects an error.
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
Documentation/git-index-helper.txt | 9 ++++++++
cache.h | 1 +
index-helper.c | 47 ++++++++++++++++++++++++++++++++++++++
read-cache.c | 9 +++++---
4 files changed, 63 insertions(+), 3 deletions(-)
diff --git a/Documentation/git-index-helper.txt b/Documentation/git-index-helper.txt
index da41c4d..406856d 100644
--- a/Documentation/git-index-helper.txt
+++ b/Documentation/git-index-helper.txt
@@ -22,6 +22,15 @@ OPTIONS
Exit if the cached index is not accessed for `<n>`
minutes. Specify 0 to wait forever. Default is 10.
+--strict::
+--no-strict::
+ Strict mode makes index-helper verify the shared memory after
+ it's created. If the result does not match what's read from
+ $GIT_DIR/index, the shared memory is destroyed. This makes
+ index-helper take more than double the amount of time required
+ for reading an index, but because it will happen in the
+ background, it's not noticable. `--strict` is enabled by default.
+
NOTES
-----
On UNIX-like systems, $GIT_DIR/index-helper.pid contains the process
diff --git a/cache.h b/cache.h
index 4266771..0f515e5 100644
--- a/cache.h
+++ b/cache.h
@@ -307,6 +307,7 @@ struct index_state {
struct cache_time timestamp;
unsigned name_hash_initialized : 1,
keep_mmap : 1,
+ always_verify_trailing_sha1 : 1,
initialized : 1;
struct hashmap name_hash;
struct hashmap dir_hash;
diff --git a/index-helper.c b/index-helper.c
index 8fa0af9..c82d307 100644
--- a/index-helper.c
+++ b/index-helper.c
@@ -13,6 +13,7 @@ struct index_shm {
static struct index_shm shm_index;
static struct index_shm shm_base_index;
+static int to_verify = 1;
static void free_index_shm(struct index_shm *is)
{
@@ -68,6 +69,48 @@ static void share_index(struct index_state *istate, struct index_shm *is)
hashcpy((unsigned char *)new_mmap + istate->mmap_size - 20, is->sha1);
}
+static int verify_shm(void)
+{
+ int i;
+ struct index_state istate;
+ memset(&istate, 0, sizeof(istate));
+ istate.always_verify_trailing_sha1 = 1;
+ i = read_index(&istate);
+ if (i != the_index.cache_nr)
+ goto done;
+ for (; i < the_index.cache_nr; i++) {
+ struct cache_entry *base, *ce;
+ /* namelen is checked separately */
+ const unsigned int ondisk_flags =
+ CE_STAGEMASK | CE_VALID | CE_EXTENDED_FLAGS;
+ unsigned int ce_flags, base_flags, ret;
+ base = the_index.cache[i];
+ ce = istate.cache[i];
+ if (ce->ce_namelen != base->ce_namelen ||
+ strcmp(ce->name, base->name)) {
+ warning("mismatch at entry %d", i);
+ break;
+ }
+ ce_flags = ce->ce_flags;
+ base_flags = base->ce_flags;
+ /* only on-disk flags matter */
+ ce->ce_flags &= ondisk_flags;
+ base->ce_flags &= ondisk_flags;
+ ret = memcmp(&ce->ce_stat_data, &base->ce_stat_data,
+ offsetof(struct cache_entry, name) -
+ offsetof(struct cache_entry, ce_stat_data));
+ ce->ce_flags = ce_flags;
+ base->ce_flags = base_flags;
+ if (ret) {
+ warning("mismatch at entry %d", i);
+ break;
+ }
+ }
+done:
+ discard_index(&istate);
+ return i == the_index.cache_nr;
+}
+
static void refresh(int sig)
{
the_index.keep_mmap = 1;
@@ -76,6 +119,8 @@ static void refresh(int sig)
if (the_index.split_index && the_index.split_index->base)
share_index(the_index.split_index->base, &shm_base_index);
share_index(&the_index, &shm_index);
+ if (to_verify && !verify_shm())
+ cleanup_shm();
discard_index(&the_index);
}
@@ -123,6 +168,8 @@ int main(int argc, char **argv)
struct option options[] = {
OPT_INTEGER(0, "exit-after", &idle_in_minutes,
N_("exit if not used after some minutes")),
+ OPT_BOOL(0, "strict", &to_verify,
+ "verify shared memory after creating"),
OPT_END()
};
diff --git a/read-cache.c b/read-cache.c
index 4bd2abe..d6eb17f 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1568,9 +1568,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
istate->mmap = mmap;
istate->mmap_size = mmap_size;
- if (try_shm(istate) &&
- verify_hdr(istate->mmap, istate->mmap_size) < 0)
- goto unmap;
+ if (try_shm(istate)) {
+ if (verify_hdr(istate->mmap, istate->mmap_size) < 0)
+ goto unmap;
+ } else if (istate->always_verify_trailing_sha1 &&
+ verify_hdr(istate->mmap, istate->mmap_size) < 0)
+ goto unmap;
hdr = mmap = istate->mmap;
mmap_size = istate->mmap_size;
if (!istate->keep_mmap)
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 7/9] daemonize(): set a flag before exiting the main process
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
` (5 preceding siblings ...)
2014-07-28 12:03 ` [PATCH v3 6/9] index-helper: add --strict Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 8/9] index-helper: add --detach Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 9/9] index-helper: add Windows support Nguyễn Thái Ngọc Duy
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
This allows signal handlers and atexit functions to realize this
situation and not clean up.
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
builtin/gc.c | 2 +-
cache.h | 2 +-
daemon.c | 2 +-
setup.c | 4 +++-
4 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/builtin/gc.c b/builtin/gc.c
index 8d219d8..f120b4f 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -341,7 +341,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
* failure to daemonize is ok, we'll continue
* in foreground
*/
- daemonize();
+ daemonize(NULL);
}
} else
add_repack_all_option();
diff --git a/cache.h b/cache.h
index 0f515e5..f568c8a 100644
--- a/cache.h
+++ b/cache.h
@@ -467,7 +467,7 @@ extern int set_git_dir_init(const char *git_dir, const char *real_git_dir, int);
extern int init_db(const char *template_dir, unsigned int flags);
extern void sanitize_stdfds(void);
-extern int daemonize(void);
+extern int daemonize(int *);
#define alloc_nr(x) (((x)+16)*3/2)
diff --git a/daemon.c b/daemon.c
index e6b51ed..cfdf0f6 100644
--- a/daemon.c
+++ b/daemon.c
@@ -1306,7 +1306,7 @@ int main(int argc, char **argv)
return execute();
if (detach) {
- if (daemonize())
+ if (daemonize(NULL))
die("--detach not supported on this platform");
} else
sanitize_stdfds();
diff --git a/setup.c b/setup.c
index 0a22f8b..b509395 100644
--- a/setup.c
+++ b/setup.c
@@ -842,7 +842,7 @@ void sanitize_stdfds(void)
close(fd);
}
-int daemonize(void)
+int daemonize(int *daemonized)
{
#ifdef NO_POSIX_GOODIES
errno = ENOSYS;
@@ -854,6 +854,8 @@ int daemonize(void)
case -1:
die_errno("fork failed");
default:
+ if (daemonized)
+ *daemonized = 1;
exit(0);
}
if (setsid() == -1)
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 8/9] index-helper: add --detach
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
` (6 preceding siblings ...)
2014-07-28 12:03 ` [PATCH v3 7/9] daemonize(): set a flag before exiting the main process Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
2014-07-28 12:03 ` [PATCH v3 9/9] index-helper: add Windows support Nguyễn Thái Ngọc Duy
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
Documentation/git-index-helper.txt | 3 +++
index-helper.c | 10 ++++++++--
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/Documentation/git-index-helper.txt b/Documentation/git-index-helper.txt
index 406856d..d8fbdab 100644
--- a/Documentation/git-index-helper.txt
+++ b/Documentation/git-index-helper.txt
@@ -31,6 +31,9 @@ OPTIONS
for reading an index, but because it will happen in the
background, it's not noticable. `--strict` is enabled by default.
+--detach::
+ Detach from the shell.
+
NOTES
-----
On UNIX-like systems, $GIT_DIR/index-helper.pid contains the process
diff --git a/index-helper.c b/index-helper.c
index c82d307..4262678 100644
--- a/index-helper.c
+++ b/index-helper.c
@@ -13,7 +13,7 @@ struct index_shm {
static struct index_shm shm_index;
static struct index_shm shm_base_index;
-static int to_verify = 1;
+static int daemonized, to_verify = 1;
static void free_index_shm(struct index_shm *is)
{
@@ -32,6 +32,8 @@ static void cleanup_shm(void)
static void cleanup(void)
{
+ if (daemonized)
+ return;
unlink(git_path("index-helper.pid"));
cleanup_shm();
}
@@ -164,12 +166,13 @@ int main(int argc, char **argv)
static struct lock_file lock;
struct strbuf sb = STRBUF_INIT;
const char *prefix;
- int fd, idle_in_minutes = 10;
+ int fd, idle_in_minutes = 10, detach = 0;
struct option options[] = {
OPT_INTEGER(0, "exit-after", &idle_in_minutes,
N_("exit if not used after some minutes")),
OPT_BOOL(0, "strict", &to_verify,
"verify shared memory after creating"),
+ OPT_BOOL(0, "detach", &detach, "detach the process"),
OPT_END()
};
@@ -196,6 +199,9 @@ int main(int argc, char **argv)
atexit(cleanup);
sigchain_push_common(cleanup_on_signal);
+ if (detach && daemonize(&daemonized))
+ die_errno("unable to detach");
+
if (!idle_in_minutes)
idle_in_minutes = 0xffffffff / 60;
loop(sb.buf, idle_in_minutes * 60);
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v3 9/9] index-helper: add Windows support
2014-07-28 12:03 [PATCH v3 0/9] Speed up cache loading time Nguyễn Thái Ngọc Duy
` (7 preceding siblings ...)
2014-07-28 12:03 ` [PATCH v3 8/9] index-helper: add --detach Nguyễn Thái Ngọc Duy
@ 2014-07-28 12:03 ` Nguyễn Thái Ngọc Duy
8 siblings, 0 replies; 13+ messages in thread
From: Nguyễn Thái Ngọc Duy @ 2014-07-28 12:03 UTC (permalink / raw)
To: git; +Cc: Nguyễn Thái Ngọc Duy
Windows supports shared memory, but the semantics is a bit different
than POSIX shm. The most noticeable thing is there's no way to get the
shared memory's size by the reader, and wrapping fstat to do that
would be hell. So the shm size is added near the end, hidden away from
shm users (storing it in headers would cause more problems with munmap,
storing it as a separate shm is even worse).
PostMessage is used instead of UNIX signals for notification.
Lightweight (at least code-wise) on the client side.
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
config.mak.uname | 2 ++
index-helper.c | 48 ++++++++++++++++++++++++++++
read-cache.c | 6 ++++
shm.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 152 insertions(+)
diff --git a/config.mak.uname b/config.mak.uname
index 7e66d80..74e764f 100644
--- a/config.mak.uname
+++ b/config.mak.uname
@@ -377,6 +377,7 @@ ifndef DEBUG
else
BASIC_CFLAGS += -Zi -MDd
endif
+ PROGRAM_OBJS += index-helper.o
X = .exe
endif
ifeq ($(uname_S),Interix)
@@ -532,6 +533,7 @@ ifneq (,$(wildcard ../THIS_IS_MSYSGIT))
else
NO_CURL = YesPlease
endif
+ PROGRAM_OBJS += index-helper.o
endif
ifeq ($(uname_S),QNX)
COMPAT_CFLAGS += -DSA_RESTART=0
diff --git a/index-helper.c b/index-helper.c
index 4262678..7c2a0e7 100644
--- a/index-helper.c
+++ b/index-helper.c
@@ -147,6 +147,51 @@ static void loop(const char *pid_file, int idle_in_seconds)
; /* do nothing, all is handled by signal handlers already */
}
+#elif defined(GIT_WINDOWS_NATIVE)
+
+static void loop(const char *pid_file, int idle_in_seconds)
+{
+ HWND hwnd;
+ UINT_PTR timer = 0;
+ MSG msg;
+ HINSTANCE hinst = GetModuleHandle(NULL);
+ WNDCLASS wc;
+
+ /*
+ * Emulate UNIX signals by sending WM_USER+x to a
+ * window. Register window class and create a new window to
+ * catch these messages.
+ */
+ memset(&wc, 0, sizeof(wc));
+ wc.lpfnWndProc = DefWindowProc;
+ wc.hInstance = hinst;
+ wc.lpszClassName = "git-index-helper";
+ if (!RegisterClass(&wc))
+ die_errno(_("could not register new window class"));
+
+ hwnd = CreateWindow("git-index-helper", pid_file,
+ 0, 0, 0, 1, 1, NULL, NULL, hinst, NULL);
+ if (!hwnd)
+ die_errno(_("could not register new window"));
+
+ refresh(0);
+ while (1) {
+ timer = SetTimer(hwnd, timer, idle_in_seconds * 1000, NULL);
+ if (!timer)
+ die(_("no timer!"));
+ if (!GetMessage(&msg, hwnd, 0, 0) || msg.message == WM_TIMER)
+ break;
+ switch (msg.message) {
+ case WM_USER:
+ refresh(0);
+ break;
+ default:
+ /* just reset the timer */
+ break;
+ }
+ }
+}
+
#else
static void loop(const char *pid_file, int idle_in_seconds)
@@ -192,6 +237,9 @@ int main(int argc, char **argv)
git_path("index-helper.pid"),
LOCK_DIE_ON_ERROR);
strbuf_addf(&sb,
+#ifdef GIT_WINDOWS_NATIVE
+ "HWND"
+#endif
"%" PRIuMAX, (uintmax_t) getpid());
write_in_full(fd, sb.buf, sb.len);
commit_lock_file(&lock);
diff --git a/read-cache.c b/read-cache.c
index d6eb17f..0ca3345 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1489,6 +1489,12 @@ static void poke_daemon(const struct stat *st, int refresh_cache)
pid_t pid = strtoul(sb.buf, &end, 10);
if (end && sb.buf + st->st_size == end)
kill(pid, refresh_cache ? SIGHUP : SIGUSR1);
+#elif defined(GIT_WINDOWS_NATIVE)
+ if (starts_with(sb.buf, "HWND")) {
+ HWND hwnd = FindWindow("git-index-helper", sb.buf);
+ PostMessage(hwnd, refresh_cache ? WM_USER : WM_USER + 1,
+ 0, 0);
+ }
#endif
}
close(fd);
diff --git a/shm.c b/shm.c
index 4ec1a00..04d8a35 100644
--- a/shm.c
+++ b/shm.c
@@ -52,6 +52,102 @@ void git_shm_unlink(const char *fmt, ...)
shm_unlink(path);
}
+#elif defined(GIT_WINDOWS_NATIVE)
+
+#define SHM_PATH_LEN 82 /* a little bit longer than POSIX because of "Local\\" */
+
+static ssize_t create_shm_map(int oflag, int perm, ssize_t length,
+ void **mmap, int prot, int flags,
+ const char *path, unsigned long page_size)
+{
+ size_t real_length;
+ void *last_page;
+ HANDLE h;
+
+ assert(perm == 0700);
+ assert(oflag == (O_CREAT | O_EXCL | O_RDWR));
+ assert(prot == (PROT_READ | PROT_WRITE));
+ assert(flags == MAP_SHARED);
+ assert(length >= 0);
+
+ real_length = length;
+ if (real_length % page_size)
+ real_length += page_size - (real_length % page_size);
+ real_length += page_size;
+ h = CreateFileMapping(INVALID_HANDLE_VALUE, NULL, PAGE_READWRITE, 0,
+ real_length, path);
+ if (!h)
+ return -1;
+ *mmap = MapViewOfFile(h, FILE_MAP_ALL_ACCESS, 0, 0, real_length);
+ CloseHandle(h);
+ if (!*mmap)
+ return -1;
+ last_page = (unsigned char *)*mmap + real_length - page_size;
+ *(unsigned long *)last_page = length;
+ return length;
+}
+
+static ssize_t open_shm_map(int oflag, int perm, ssize_t length, void **mmap,
+ int prot, int flags, const char *path,
+ unsigned long page_size)
+{
+ void *last_page;
+ HANDLE h;
+
+ assert(perm == 0700);
+ assert(oflag == O_RDONLY);
+ assert(prot == PROT_READ);
+ assert(flags == MAP_SHARED);
+ assert(length <= 0);
+
+ h = OpenFileMapping(FILE_MAP_READ, FALSE, path);
+ if (!h)
+ return -1;
+ *mmap = MapViewOfFile(h, FILE_MAP_READ, 0, 0, 0);
+ CloseHandle(h);
+ if (!*mmap)
+ return -1;
+ if (length < 0) {
+ MEMORY_BASIC_INFORMATION mbi;
+ if (!VirtualQuery(*mmap, &mbi, sizeof(mbi))) {
+ UnmapViewOfFile(*mmap);
+ return -1;
+ }
+ if (mbi.RegionSize % page_size)
+ die("expected size %lu to be %lu aligned",
+ mbi.RegionSize, page_size);
+ last_page = (unsigned char *)*mmap + mbi.RegionSize - page_size;
+ length = *(unsigned long *)last_page;
+ }
+ return length;
+}
+
+ssize_t git_shm_map(int oflag, int perm, ssize_t length, void **mmap,
+ int prot, int flags, const char *fmt, ...)
+{
+ SYSTEM_INFO si;
+ va_list ap;
+ char path[SHM_PATH_LEN];
+
+ GetSystemInfo(&si);
+
+ strcpy(path, "Local\\");
+ va_start(ap, fmt);
+ vsprintf(path + strlen(path), fmt, ap);
+ va_end(ap);
+
+ if (oflag & O_CREAT)
+ return create_shm_map(oflag, perm, length, mmap, prot,
+ flags, path, si.dwPageSize);
+ else
+ return open_shm_map(oflag, perm, length, mmap, prot,
+ flags, path, si.dwPageSize);
+}
+
+void git_shm_unlink(const char *fmt, ...)
+{
+}
+
#else
ssize_t git_shm_map(int oflag, int perm, ssize_t length, void **mmap,
--
2.1.0.rc0.66.gb9187ad
^ permalink raw reply related [flat|nested] 13+ messages in thread