git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 4/8] Add read-cache--daemon for caching index and related stuff

From
Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date
May 13, 2014, 11:15 UTC
Message-ID
<1399979737-8577-7-git-send-email-pclouds@gmail.com>
In-Reply-To
<1399979737-8577-1-git-send-email-pclouds@gmail.com>

The name of the shared memory folows the template "/git-index-<SHA1>" where <SHA1> is the trailing SHA-1 of the index file. If such a shared memory exists, it contains the same index content as on disk. The content is already validated by the daemon. Note that it does not necessarily use the same format as the on-disk version. The content could be in a format that can be parsed much faster, or even reused without parsing).

While preparing the shm object, the daemon would keep the shm object "/git-index-<SHA1>.lock". After "git-index-<SHA1>" is ready, the ".lock" object is removed. A shared object must not be updated afterwards. So if ".lock" does not exist, it's safe to assume that the associated shm object is ready.

Other info could also by cached if it's tied to the index. For example, name hash could be stored in "/git-namehash-<SHA1>"..

After Git writes a new index down, it may want to ask the daemon to preload the new index so next time Git runs the index is already validated and in memory. It does so by send a command to a UNIX socket in $GIT_DIR/daemon/index.

Windows can use its named shared memory instead of POSIX shared memory and probably named pipe in place of UNIX socket.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 .gitignore                                     |   1 +
 Documentation/git-read-cache--daemon.txt (new) |  27 ++++
 Makefile                                       |   6 +
 config.mak.uname                               |   1 +
 read-cache--daemon.c (new)                     | 207 +++++++++++++++++++++++++
 wrapper.c                                      |  14 ++
 6 files changed, 256 insertions(+)
 create mode 100644 Documentation/git-read-cache--daemon.txt
 create mode 100644 read-cache--daemon.c
diff --git a/.gitignore b/.gitignore
index 70992a4..07e0cb6 100644
--- a/.gitignore
+++ b/.gitignore
@@ -110,6 +110,7 @@
 /git-pull
 /git-push
 /git-quiltimport
+/git-read-cache--daemon
 /git-read-tree
 /git-rebase
 /git-rebase--am
diff --git a/Documentation/git-read-cache--daemon.txt b/Documentation/git-read-cache--daemon.txt
new file mode 100644
index 0000000..1b05be4
--- /dev/null
+++ b/Documentation/git-read-cache--daemon.txt
@@ -0,0 +1,27 @@
+git-read-cache--daemon(1)
+=============
+
+NAME
+----
+git-daemon - A simple cache server for speeding up index file access
+
+SYNOPSIS
+--------
+[verse]
+'git daemon' [--detach]
+
+DESCRIPTION
+-----------
+Keep the index file in memory for faster access. This daemon is per
+repository. Note that core.useReadCacheDaemon must be set for Git to
+contact the daemon. This daemon is only available on POSIX system with
+shared memory support (e.g. Linux)
+
+OPTIONS
+-------
+--detach::
+	Detach from the shell.
+
+GIT
+---
+Part of the linkgit:git[1] suite
diff --git a/Makefile b/Makefile
index d0a2b4b..a44ab0b 100644
--- a/Makefile
+++ b/Makefile
@@ -1504,6 +1504,12 @@ ifdef HAVE_DEV_TTY
 	BASIC_CFLAGS += -DHAVE_DEV_TTY
 endif
 
+ifdef HAVE_SHM
+	BASIC_CFLAGS += -DHAVE_SHM
+	EXTLIBS += -lrt
+	PROGRAM_OBJS += read-cache--daemon.o
+endif
+
 ifdef DIR_HAS_BSD_GROUP_SEMANTICS
 	COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
 endif
diff --git a/config.mak.uname b/config.mak.uname
index 23a8803..b6a37e5 100644
--- a/config.mak.uname
+++ b/config.mak.uname
@@ -33,6 +33,7 @@ ifeq ($(uname_S),Linux)
 	HAVE_PATHS_H = YesPlease
 	LIBC_CONTAINS_LIBINTL = YesPlease
 	HAVE_DEV_TTY = YesPlease
+	HAVE_SHM = YesPlease
 endif
 ifeq ($(uname_S),GNU/kFreeBSD)
 	NO_STRLCPY = YesPlease
diff --git a/read-cache--daemon.c b/read-cache--daemon.c
new file mode 100644
index 0000000..4531978
--- /dev/null
+++ b/read-cache--daemon.c
@@ -0,0 +1,207 @@
+#include "cache.h"
+#include "sigchain.h"
+#include "unix-socket.h"
+#include "split-index.h"
+#include "pkt-line.h"
+
+static char *socket_path;
+static struct strbuf shm_index = STRBUF_INIT;
+static struct strbuf shm_sharedindex = STRBUF_INIT;
+static struct strbuf shm_lock = STRBUF_INIT;
+static int lock_fd = -1;
+static int daemonized;
+
+static void cleanup_socket(void)
+{
+	if (daemonized)
+		return;
+	if (socket_path)
+		unlink(socket_path);
+	if (shm_index.len)
+		shm_unlink(shm_index.buf);
+	if (shm_sharedindex.len)
+		shm_unlink(shm_sharedindex.buf);
+	if (lock_fd != -1)
+		close(lock_fd);
+	if (shm_lock.len)
+		shm_unlink(shm_lock.buf);
+}
+
+static void cleanup_socket_on_signal(int sig)
+{
+	cleanup_socket();
+	sigchain_pop(sig);
+	raise(sig);
+}
+
+static int do_share_index(struct index_state *istate, struct strbuf *shm_path)
+{
+	struct strbuf sb = STRBUF_INIT;
+	void *map;
+	int fd;
+
+	strbuf_addf(&sb, "/git-index-%s", sha1_to_hex(istate->sha1));
+	fd = shm_open(sb.buf, O_RDWR | O_CREAT | O_EXCL, 0700);
+	if (fd < 0)
+		return -1;
+	if (shm_path->len) {
+		shm_unlink(shm_path->buf);
+		strbuf_reset(shm_path);
+	}
+	if (ftruncate(fd, istate->mmap_size)) {
+		close(fd);
+		shm_unlink(shm_path->buf);
+		return -1;
+	}
+	strbuf_addbuf(shm_path, &sb);
+	map = xmmap(NULL, istate->mmap_size, PROT_READ | PROT_WRITE,
+		    MAP_SHARED, fd, 0);
+	if (map == MAP_FAILED) {
+		close(fd);
+		shm_unlink(shm_path->buf);
+		return -1;
+	}
+	memcpy(map, istate->mmap, istate->mmap_size);
+	munmap(map, istate->mmap_size);
+	fchmod(fd, 0400);
+	close(fd);
+	return 0;
+}
+
+static void share_index(struct index_state *istate, struct strbuf *shm_path)
+{
+	if (shm_lock.len)
+		return;
+
+	strbuf_addf(&shm_lock, "/git-index-%s.lock", sha1_to_hex(istate->sha1));
+	lock_fd = shm_open(shm_lock.buf, O_CREAT | O_EXCL, 0700);
+	if (lock_fd < 0) {
+		strbuf_reset(&shm_lock);
+		return;
+	}
+	do_share_index(istate, shm_path);
+	close(lock_fd);
+	lock_fd = -1;
+	shm_unlink(shm_lock.buf);
+	strbuf_reset(&shm_lock);
+}
+
+static void refresh()
+{
+	the_index.keep_mmap = 1;
+	if (read_cache() < 0)
+		die("could not read index");
+	share_index(&the_index, &shm_index);
+	if (the_index.split_index &&
+	    the_index.split_index->base)
+		share_index(the_index.split_index->base, &shm_sharedindex);
+	discard_index(&the_index);
+}
+
+static void serve_one_client(int fd)
+{
+	char *buf = packet_read_line(fd, NULL);
+	if (!strcmp(buf, "refresh"))
+		refresh();
+	else
+		fprintf(stderr, "unrecognized command %s\n", buf);
+}
+
+static unsigned long next;
+static int serve_cache_loop(int fd)
+{
+	struct pollfd pfd;
+	unsigned long now = time(NULL);
+
+	if (now > next)
+		return 0;
+
+	pfd.fd = fd;
+	pfd.events = POLLIN;
+	if (poll(&pfd, 1, 1000 * (next - now)) < 0) {
+		if (errno != EINTR)
+			die_errno("poll failed");
+		return 1;
+	}
+
+	if (pfd.revents & POLLIN) {
+		int client = accept(fd, NULL, NULL);
+		if (client < 0) {
+			warning("accept failed: %s", strerror(errno));
+			return 1;
+		}
+		serve_one_client(client);
+		close(client);
+		next = now + 600;
+	}
+	return 1;
+}
+
+static void serve_cache(const char *socket_path, int detach)
+{
+	int fd;
+
+	fd = unix_stream_listen(socket_path);
+	if (fd < 0)
+		die_errno("unable to bind to '%s'", socket_path);
+
+	refresh();
+	if (detach && daemonize(&daemonized))
+		die_errno("unable to detach");
+
+	next = time(NULL) + 600;
+	while (serve_cache_loop(fd))
+		; /* nothing */
+
+	close(fd);
+	unlink(socket_path);
+}
+
+static void check_socket_directory(const char *path)
+{
+	struct stat st;
+	char *path_copy = xstrdup(path);
+	char *dir = dirname(path_copy);
+
+	if (!stat(dir, &st)) {
+		free(path_copy);
+		return;
+	}
+
+	/*
+	 * We must be sure to create the directory with the correct mode,
+	 * not just chmod it after the fact; otherwise, there is a race
+	 * condition in which somebody can chdir to it, sleep, then try to open
+	 * our protected socket.
+	 */
+	if (safe_create_leading_directories_const(dir) < 0)
+		die_errno("unable to create directories for '%s'", dir);
+	if (mkdir(dir, 0700) < 0)
+		die_errno("unable to mkdir '%s'", dir);
+	free(path_copy);
+}
+
+int main(int argc, const char **argv)
+{
+	int detach = 0;
+	switch (argc) {
+	case 1:
+		break;
+	case 2:
+		if (!strcmp(argv[1], "--detach"))
+			detach = 1;
+		else
+			die("unknown option %s", argv[1]);
+		break;
+	default:
+		die("unexpected argument number %d\n", argc);
+	}
+
+	setup_git_directory();
+	socket_path = git_pathdup("daemon/index");
+	check_socket_directory(socket_path);
+	atexit(cleanup_socket);
+	sigchain_push_common(cleanup_socket_on_signal);
+	serve_cache(socket_path, detach);
+	return 0;
+}
diff --git a/wrapper.c b/wrapper.c
index 0cc5636..4cd7415 100644
--- a/wrapper.c
+++ b/wrapper.c
@@ -455,3 +455,17 @@ struct passwd *xgetpwuid_self(void)
 		    errno ? strerror(errno) : _("no such user"));
 	return pw;
 }
+
+#ifndef HAVE_SHM
+int shm_open(const char *path, int flags, mode_t mode)
+{
+	errno = ENOSYS;
+	return -1;
+}
+
+int shm_unlink(const char *path)
+{
+	errno = ENOSYS;
+	return -1;
+}
+#endif
-- 
1.9.1.346.ga2b5940
Previous: Nguyễn Thái Ngọc DuyNext: Erik Faye-Lund
Message 61 of 75 in “Split index mode for very large indexes”
  1. 00/32 Split index mode for very large indexesNguyễn Thái Ngọc Duy, Apr 28, 2014
  2. 01/32 ewah: fix constness of ewah_read_mmapNguyễn Thái Ngọc Duy, Apr 28, 2014
  3. 02/32 ewah: delete unused ewah_read_mmap_native declarationNguyễn Thái Ngọc Duy, Apr 28, 2014
  4. 03/32 sequencer: do not update/refresh index if the lock cannot be heldNguyễn Thái Ngọc Duy, Apr 28, 2014
  5. 04/32 read-cache: new API write_locked_index instead of write_index/write_cacheNguyễn Thái Ngọc Duy, Apr 28, 2014
  6. 05/32 read-cache: relocate and unexport commit_locked_index()Nguyễn Thái Ngọc Duy, Apr 28, 2014
  7. 06/32 read-cache: store in-memory flags in the first 12 bits of ce_flagsNguyễn Thái Ngọc Duy, Apr 28, 2014
  8. 07/32 read-cache: be strict about "changed" in remove_marked_cache_entries()Nguyễn Thái Ngọc Duy, Apr 28, 2014
  9. 08/32 read-cache: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Apr 28, 2014
  10. 09/32 update-index: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Apr 28, 2014
  11. 10/32 resolve-undo: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Apr 28, 2014
  12. 11/32 unpack-trees: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Apr 28, 2014
  13. 12/32 cache-tree: mark istate->cache_changed on cache tree invalidationNguyễn Thái Ngọc Duy, Apr 28, 2014
  14. 13/32 cache-tree: mark istate->cache_changed on cache tree updateNguyễn Thái Ngọc Duy, Apr 28, 2014
  15. 14/32 cache-tree: mark istate->cache_changed on prime_cache_tree()Nguyễn Thái Ngọc Duy, Apr 28, 2014
  16. 15/32 entry.c: update cache_changed if refresh_cache is set in checkout_entry()Nguyễn Thái Ngọc Duy, Apr 28, 2014
  17. 16/32 read-cache: save index SHA-1 after readingNguyễn Thái Ngọc Duy, Apr 28, 2014
  18. 17/32 read-cache: split-index modeNguyễn Thái Ngọc Duy, Apr 28, 2014
  19. Junio C HamanoApr 28, 2014
  20. Duy NguyenApr 29, 2014
  21. Junio C HamanoApr 29, 2014
  22. Duy NguyenApr 29, 2014
  23. Junio C HamanoApr 30, 2014
  24. 18/32 read-cache: mark new entries for split indexNguyễn Thái Ngọc Duy, Apr 28, 2014
  25. Eric SunshineApr 30, 2014
  26. 19/32 read-cache: save deleted entries in split indexNguyễn Thái Ngọc Duy, Apr 28, 2014
  27. 20/32 read-cache: mark updated entries for split indexNguyễn Thái Ngọc Duy, Apr 28, 2014
  28. 21/32 split-index: the writing partNguyễn Thái Ngọc Duy, Apr 28, 2014
  29. 22/32 split-index: the reading partNguyễn Thái Ngọc Duy, Apr 28, 2014
  30. 23/32 split-index: do not invalidate cache-tree at read timeNguyễn Thái Ngọc Duy, Apr 28, 2014
  31. 24/32 split-index: strip pathname of on-disk replaced entriesNguyễn Thái Ngọc Duy, Apr 28, 2014
  32. Junio C HamanoApr 29, 2014
  33. 25/32 update-index: new options to enable/disable split index modeNguyễn Thái Ngọc Duy, Apr 28, 2014
  34. 26/32 update-index --split-index: do not split if $GIT_DIR is read onlyNguyễn Thái Ngọc Duy, Apr 28, 2014
  35. 27/32 rev-parse: add --shared-index-path to get shared index pathNguyễn Thái Ngọc Duy, Apr 28, 2014
  36. 28/32 read-tree: force split-index mode off on --index-outputNguyễn Thái Ngọc Duy, Apr 28, 2014
  37. 29/32 read-tree: note about dropping split-index mode or index versionNguyễn Thái Ngọc Duy, Apr 28, 2014
  38. 30/32 read-cache: force split index mode with GIT_TEST_SPLIT_INDEXNguyễn Thái Ngọc Duy, Apr 28, 2014
  39. 31/32 t2104: make sure split index mode is off for the version testNguyễn Thái Ngọc Duy, Apr 28, 2014
  40. 32/32 t1700: new tests for split-index modeNguyễn Thái Ngọc Duy, Apr 28, 2014
  41. Shawn PearceApr 28, 2014
  42. Duy NguyenApr 29, 2014
  43. Duy NguyenMay 9, 2014
  44. Junio C HamanoMay 9, 2014
  45. 0/8 Speed up cache loading timeNguyễn Thái Ngọc Duy, May 13, 2014
  46. 1/8 read-cache: allow to keep mmap'd memory after readingNguyễn Thái Ngọc Duy, May 13, 2014
  47. 2/3 Add read-cache--daemonNguyễn Thái Ngọc Duy, May 13, 2014
  48. Erik Faye-LundMay 13, 2014
  49. Duy NguyenMay 13, 2014
  50. Duy NguyenMay 13, 2014
  51. Erik Faye-LundMay 13, 2014
  52. Duy NguyenMay 13, 2014
  53. Erik Faye-LundMay 13, 2014
  54. Duy NguyenMay 13, 2014
  55. Erik Faye-LundMay 13, 2014
  56. 2/8 unix-socket: stub impl. for platforms with no unix socket supportNguyễn Thái Ngọc Duy, May 13, 2014
  57. Erik Faye-LundMay 13, 2014
  58. Erik Faye-LundMay 13, 2014
  59. 3/8 daemonize: set a flag before exiting the main processNguyễn Thái Ngọc Duy, May 13, 2014
  60. 3/3 read-cache: try index data from shared memoryNguyễn Thái Ngọc Duy, May 13, 2014
  61. 4/8 Add read-cache--daemon for caching index and related stuffNguyễn Thái Ngọc Duy, May 13, 2014
  62. Erik Faye-LundMay 13, 2014
  63. 5/8 read-cache: try index data from shared memoryNguyễn Thái Ngọc Duy, May 13, 2014
  64. Erik Faye-LundMay 13, 2014
  65. 6/8 read-cache--daemon: do not read index from shared memoryNguyễn Thái Ngọc Duy, May 13, 2014
  66. 7/8 read-cache: skip verifying trailing SHA-1 on cached indexNguyễn Thái Ngọc Duy, May 13, 2014
  67. 8/8 read-cache: inform the daemon that the index has been updatedNguyễn Thái Ngọc Duy, May 13, 2014
  68. Erik Faye-LundMay 13, 2014
  69. David TurnerMay 22, 2014
  70. Stefan BellerMay 13, 2014
  71. Duy NguyenMay 13, 2014
  72. 9/8 even faster loading time with index version 254Nguyễn Thái Ngọc Duy, May 13, 2014
  73. Junio C HamanoApr 28, 2014
  74. Richard HansenApr 30, 2014
  75. Duy NguyenMay 1, 2014

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.