Merge branch 'bp/fsmonitor'

We learned to talk to watchman to speed up "git status" and other
operations that need to see which paths have been modified.

* bp/fsmonitor:
  fsmonitor: preserve utf8 filenames in fsmonitor-watchman log
  fsmonitor: read entirety of watchman output
  fsmonitor: MINGW support for watchman integration
  fsmonitor: add a performance test
  fsmonitor: add a sample integration script for Watchman
  fsmonitor: add test cases for fsmonitor extension
  split-index: disable the fsmonitor extension when running the split index test
  fsmonitor: add a test tool to dump the index extension
  update-index: add fsmonitor support to update-index
  ls-files: Add support in ls-files to display the fsmonitor valid bit
  fsmonitor: add documentation for the fsmonitor extension.
  fsmonitor: teach git to optionally utilize a file system monitor to speed up detecting new or changed files.
  update-index: add a new --force-write-index option
  preload-index: add override to enable testing preload-index
  bswap: add 64 bit endianness helper get_be64

Author: gitster

Documentation/config.txt

@@ -416,6 +416,13 @@ core.protectNTFS::
 	8.3 "short" names.
 	Defaults to `true` on Windows, and `false` elsewhere.
 
+core.fsmonitor::
+	If set, the value of this variable is used as a command which
+	will identify all files that may have changed since the
+	requested date/time. This information is used to speed up git by
+	avoiding unnecessary processing of files that have not changed.
+	See the "fsmonitor-watchman" section of linkgit:githooks[5].
+
 core.trustctime::
 	If false, the ctime differences between the index and the
 	working tree are ignored; useful when the inode change time

Documentation/git-ls-files.txt

@@ -9,7 +9,7 @@ git-ls-files - Show information about files in the index and the working tree
 SYNOPSIS
 --------
 [verse]
-'git ls-files' [-z] [-t] [-v]
+'git ls-files' [-z] [-t] [-v] [-f]
 		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified])*
 		(-[c|d|o|i|s|u|k|m])*
 		[--eol]
@@ -133,6 +133,11 @@ a space) at the start of each line:
 	that are marked as 'assume unchanged' (see
 	linkgit:git-update-index[1]).
 
+-f::
+	Similar to `-t`, but use lowercase letters for files
+	that are marked as 'fsmonitor valid' (see
+	linkgit:git-update-index[1]).
+
 --full-name::
 	When run from a subdirectory, the command usually
 	outputs paths relative to the current directory.  This

Documentation/git-update-index.txt

@@ -16,9 +16,11 @@ SYNOPSIS
 	     [--chmod=(+|-)x]
 	     [--[no-]assume-unchanged]
 	     [--[no-]skip-worktree]
+	     [--[no-]fsmonitor-valid]
 	     [--ignore-submodules]
 	     [--[no-]split-index]
 	     [--[no-|test-|force-]untracked-cache]
+	     [--[no-]fsmonitor]
 	     [--really-refresh] [--unresolve] [--again | -g]
 	     [--info-only] [--index-info]
 	     [-z] [--stdin] [--index-version <n>]
@@ -111,6 +113,12 @@ you will need to handle the situation manually.
 	set and unset the "skip-worktree" bit for the paths. See
 	section "Skip-worktree bit" below for more information.
 
+--[no-]fsmonitor-valid::
+	When one of these flags is specified, the object name recorded
+	for the paths are not updated. Instead, these options
+	set and unset the "fsmonitor valid" bit for the paths. See
+	section "File System Monitor" below for more information.
+
 -g::
 --again::
 	Runs 'git update-index' itself on the paths whose index
@@ -201,6 +209,15 @@ will remove the intended effect of the option.
 	`--untracked-cache` used to imply `--test-untracked-cache` but
 	this option would enable the extension unconditionally.
 
+--fsmonitor::
+--no-fsmonitor::
+	Enable or disable files system monitor feature. These options
+	take effect whatever the value of the `core.fsmonitor`
+	configuration variable (see linkgit:git-config[1]). But a warning
+	is emitted when the change goes against the configured value, as
+	the configured value will take effect next time the index is
+	read and this will remove the intended effect of the option.
+
 \--::
 	Do not interpret any more arguments as options.
 
@@ -447,6 +464,34 @@ command reads the index; while when `--[no-|force-]untracked-cache`
 are used, the untracked cache is immediately added to or removed from
 the index.
 
+File System Monitor
+-------------------
+
+This feature is intended to speed up git operations for repos that have
+large working directories.
+
+It enables git to work together with a file system monitor (see the
+"fsmonitor-watchman" section of linkgit:githooks[5]) that can
+inform it as to what files have been modified. This enables git to avoid
+having to lstat() every file to find modified files.
+
+When used in conjunction with the untracked cache, it can further improve
+performance by avoiding the cost of scanning the entire working directory
+looking for new files.
+
+If you want to enable (or disable) this feature, it is easier to use
+the `core.fsmonitor` configuration variable (see
+linkgit:git-config[1]) than using the `--fsmonitor` option to
+`git update-index` in each repository, especially if you want to do so
+across all repositories you use, because you can set the configuration
+variable to `true` (or `false`) in your `$HOME/.gitconfig` just once
+and have it affect all repositories you touch.
+
+When the `core.fsmonitor` configuration variable is changed, the
+file system monitor is added to or removed from the index the next time
+a command reads the index. When `--[no-]fsmonitor` are used, the file
+system monitor is immediately added to or removed from the index.
+
 Configuration
 -------------
 

Documentation/githooks.txt

@@ -454,6 +454,34 @@ the name of the file that holds the e-mail to be sent.  Exiting with a
 non-zero status causes 'git send-email' to abort before sending any
 e-mails.
 
+fsmonitor-watchman
+~~~~~~~~~~~~~~~~~~
+
+This hook is invoked when the configuration option core.fsmonitor is
+set to .git/hooks/fsmonitor-watchman.  It takes two arguments, a version
+(currently 1) and the time in elapsed nanoseconds since midnight,
+January 1, 1970.
+
+The hook should output to stdout the list of all files in the working
+directory that may have changed since the requested time.  The logic
+should be inclusive so that it does not miss any potential changes.
+The paths should be relative to the root of the working directory
+and be separated by a single NUL.
+
+It is OK to include files which have not actually changed.  All changes
+including newly-created and deleted files should be included. When
+files are renamed, both the old and the new name should be included.
+
+Git will limit what files it checks for changes as well as which
+directories are checked for untracked files based on the path names
+given.
+
+An optimized way to tell git "all files have changed" is to return
+the filename '/'.
+
+The exit status determines whether git will use the data from the
+hook to limit its search.  On error, it will fall back to verifying
+all files and folders.
 
 GIT
 ---

Documentation/technical/index-format.txt

@@ -295,3 +295,22 @@ The remaining data of each directory block is grouped by type:
     in the previous ewah bitmap.
 
   - One NUL.
+
+== File System Monitor cache
+
+  The file system monitor cache tracks files for which the core.fsmonitor
+  hook has told us about changes.  The signature for this extension is
+  { 'F', 'S', 'M', 'N' }.
+
+  The extension starts with
+
+  - 32-bit version number: the current supported version is 1.
+
+  - 64-bit time: the extension data reflects all changes through the given
+	time which is stored as the nanoseconds elapsed since midnight,
+	January 1, 1970.
+
+  - 32-bit bitmap size: the size of the CE_FSMONITOR_VALID bitmap.
+
+  - An ewah bitmap, the n-th bit indicates whether the n-th index entry
+    is not CE_FSMONITOR_VALID.

Makefile

@@ -646,7 +646,9 @@ TEST_PROGRAMS_NEED_X += test-ctype
 TEST_PROGRAMS_NEED_X += test-config
 TEST_PROGRAMS_NEED_X += test-date
 TEST_PROGRAMS_NEED_X += test-delta
+TEST_PROGRAMS_NEED_X += test-drop-caches
 TEST_PROGRAMS_NEED_X += test-dump-cache-tree
+TEST_PROGRAMS_NEED_X += test-dump-fsmonitor
 TEST_PROGRAMS_NEED_X += test-dump-split-index
 TEST_PROGRAMS_NEED_X += test-dump-untracked-cache
 TEST_PROGRAMS_NEED_X += test-fake-ssh
@@ -794,6 +796,7 @@ LIB_OBJS += ewah/ewah_rlw.o
 LIB_OBJS += exec_cmd.o
 LIB_OBJS += fetch-pack.o
 LIB_OBJS += fsck.o
+LIB_OBJS += fsmonitor.o
 LIB_OBJS += gettext.o
 LIB_OBJS += gpg-interface.o
 LIB_OBJS += graph.o

builtin/ls-files.c

@@ -31,6 +31,7 @@ static int show_resolve_undo;
 static int show_modified;
 static int show_killed;
 static int show_valid_bit;
+static int show_fsmonitor_bit;
 static int line_terminator = '\n';
 static int debug_mode;
 static int show_eol;
@@ -86,7 +87,8 @@ static const char *get_tag(const struct cache_entry *ce, const char *tag)
 {
 	static char alttag[4];
 
-	if (tag && *tag && show_valid_bit && (ce->ce_flags & CE_VALID)) {
+	if (tag && *tag && ((show_valid_bit && (ce->ce_flags & CE_VALID)) ||
+		(show_fsmonitor_bit && (ce->ce_flags & CE_FSMONITOR_VALID)))) {
 		memcpy(alttag, tag, 3);
 
 		if (isalpha(tag[0])) {
@@ -515,6 +517,8 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 			N_("identify the file status with tags")),
 		OPT_BOOL('v', NULL, &show_valid_bit,
 			N_("use lowercase letters for 'assume unchanged' files")),
+		OPT_BOOL('f', NULL, &show_fsmonitor_bit,
+			N_("use lowercase letters for 'fsmonitor clean' files")),
 		OPT_BOOL('c', "cached", &show_cached,
 			N_("show cached files in the output (default)")),
 		OPT_BOOL('d', "deleted", &show_deleted,
@@ -584,7 +588,7 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 	for (i = 0; i < exclude_list.nr; i++) {
 		add_exclude(exclude_list.items[i].string, "", 0, el, --exclude_args);
 	}
-	if (show_tag || show_valid_bit) {
+	if (show_tag || show_valid_bit || show_fsmonitor_bit) {
 		tag_cached = "H ";
 		tag_unmerged = "M ";
 		tag_removed = "R ";

builtin/update-index.c

@@ -16,6 +16,7 @@
 #include "pathspec.h"
 #include "dir.h"
 #include "split-index.h"
+#include "fsmonitor.h"
 
 /*
  * Default to not allowing changes to the list of files. The
@@ -32,6 +33,7 @@ static int force_remove;
 static int verbose;
 static int mark_valid_only;
 static int mark_skip_worktree_only;
+static int mark_fsmonitor_only;
 #define MARK_FLAG 1
 #define UNMARK_FLAG 2
 static struct strbuf mtime_dir = STRBUF_INIT;
@@ -228,6 +230,7 @@ static int mark_ce_flags(const char *path, int flag, int mark)
 	int namelen = strlen(path);
 	int pos = cache_name_pos(path, namelen);
 	if (0 <= pos) {
+		mark_fsmonitor_invalid(&the_index, active_cache[pos]);
 		if (mark)
 			active_cache[pos]->ce_flags |= flag;
 		else
@@ -460,6 +463,11 @@ static void update_one(const char *path)
 			die("Unable to mark file %s", path);
 		return;
 	}
+	if (mark_fsmonitor_only) {
+		if (mark_ce_flags(path, CE_FSMONITOR_VALID, mark_fsmonitor_only == MARK_FLAG))
+			die("Unable to mark file %s", path);
+		return;
+	}
 
 	if (force_remove) {
 		if (remove_file_from_cache(path))
@@ -917,6 +925,8 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 	struct refresh_params refresh_args = {0, &has_errors};
 	int lock_error = 0;
 	int split_index = -1;
+	int force_write = 0;
+	int fsmonitor = -1;
 	struct lock_file lock_file = LOCK_INIT;
 	struct parse_opt_ctx_t ctx;
 	strbuf_getline_fn getline_fn;
@@ -1008,6 +1018,16 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 			    N_("test if the filesystem supports untracked cache"), UC_TEST),
 		OPT_SET_INT(0, "force-untracked-cache", &untracked_cache,
 			    N_("enable untracked cache without testing the filesystem"), UC_FORCE),
+		OPT_SET_INT(0, "force-write-index", &force_write,
+			N_("write out the index even if is not flagged as changed"), 1),
+		OPT_BOOL(0, "fsmonitor", &fsmonitor,
+			N_("enable or disable file system monitor")),
+		{OPTION_SET_INT, 0, "fsmonitor-valid", &mark_fsmonitor_only, NULL,
+			N_("mark files as fsmonitor valid"),
+			PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, MARK_FLAG},
+		{OPTION_SET_INT, 0, "no-fsmonitor-valid", &mark_fsmonitor_only, NULL,
+			N_("clear fsmonitor valid bit"),
+			PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, UNMARK_FLAG},
 		OPT_END()
 	};
 
@@ -1146,7 +1166,23 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 		die("BUG: bad untracked_cache value: %d", untracked_cache);
 	}
 
-	if (active_cache_changed) {
+	if (fsmonitor > 0) {
+		if (git_config_get_fsmonitor() == 0)
+			warning(_("core.fsmonitor is unset; "
+				"set it if you really want to "
+				"enable fsmonitor"));
+		add_fsmonitor(&the_index);
+		report(_("fsmonitor enabled"));
+	} else if (!fsmonitor) {
+		if (git_config_get_fsmonitor() == 1)
+			warning(_("core.fsmonitor is set; "
+				"remove it if you really want to "
+				"disable fsmonitor"));
+		remove_fsmonitor(&the_index);
+		report(_("fsmonitor disabled"));
+	}
+
+	if (active_cache_changed || force_write) {
 		if (newfd < 0) {
 			if (refresh_args.flags & REFRESH_QUIET)
 				exit(128);

cache.h

@@ -204,6 +204,7 @@ struct cache_entry {
 #define CE_ADDED             (1 << 19)
 
 #define CE_HASHED            (1 << 20)
+#define CE_FSMONITOR_VALID   (1 << 21)
 #define CE_WT_REMOVE         (1 << 22) /* remove in work directory */
 #define CE_CONFLICTED        (1 << 23)
 
@@ -327,6 +328,7 @@ static inline unsigned int canon_mode(unsigned int mode)
 #define CACHE_TREE_CHANGED	(1 << 5)
 #define SPLIT_INDEX_ORDERED	(1 << 6)
 #define UNTRACKED_CHANGED	(1 << 7)
+#define FSMONITOR_CHANGED	(1 << 8)
 
 struct split_index;
 struct untracked_cache;
@@ -345,6 +347,7 @@ struct index_state {
 	struct hashmap dir_hash;
 	unsigned char sha1[20];
 	struct untracked_cache *untracked;
+	uint64_t fsmonitor_last_update;
 };
 
 extern struct index_state the_index;
@@ -700,8 +703,10 @@ extern void *read_blob_data_from_index(const struct index_state *, const char *,
 #define CE_MATCH_IGNORE_MISSING		0x08
 /* enable stat refresh */
 #define CE_MATCH_REFRESH		0x10
-extern int ie_match_stat(const struct index_state *, const struct cache_entry *, struct stat *, unsigned int);
-extern int ie_modified(const struct index_state *, const struct cache_entry *, struct stat *, unsigned int);
+/* don't refresh_fsmonitor state or do stat comparison even if CE_FSMONITOR_VALID is true */
+#define CE_MATCH_IGNORE_FSMONITOR 0X20
+extern int ie_match_stat(struct index_state *, const struct cache_entry *, struct stat *, unsigned int);
+extern int ie_modified(struct index_state *, const struct cache_entry *, struct stat *, unsigned int);
 
 #define HASH_WRITE_OBJECT 1
 #define HASH_FORMAT_CHECK 2
@@ -799,6 +804,7 @@ extern int core_apply_sparse_checkout;
 extern int precomposed_unicode;
 extern int protect_hfs;
 extern int protect_ntfs;
+extern const char *core_fsmonitor;
 
 /*
  * Include broken refs in all ref iterations, which will

compat/bswap.h

@@ -158,7 +158,9 @@ static inline uint64_t git_bswap64(uint64_t x)
 
 #define get_be16(p)	ntohs(*(unsigned short *)(p))
 #define get_be32(p)	ntohl(*(unsigned int *)(p))
+#define get_be64(p)	ntohll(*(uint64_t *)(p))
 #define put_be32(p, v)	do { *(unsigned int *)(p) = htonl(v); } while (0)
+#define put_be64(p, v)	do { *(uint64_t *)(p) = htonll(v); } while (0)
 
 #else
 
@@ -178,6 +180,13 @@ static inline uint32_t get_be32(const void *ptr)
 		(uint32_t)p[3] <<  0;
 }
 
+static inline uint64_t get_be64(const void *ptr)
+{
+	const unsigned char *p = ptr;
+	return	(uint64_t)get_be32(&p[0]) << 32 |
+		(uint64_t)get_be32(&p[4]) <<  0;
+}
+
 static inline void put_be32(void *ptr, uint32_t value)
 {
 	unsigned char *p = ptr;
@@ -187,4 +196,17 @@ static inline void put_be32(void *ptr, uint32_t value)
 	p[3] = value >>  0;
 }
 
+static inline void put_be64(void *ptr, uint64_t value)
+{
+	unsigned char *p = ptr;
+	p[0] = value >> 56;
+	p[1] = value >> 48;
+	p[2] = value >> 40;
+	p[3] = value >> 32;
+	p[4] = value >> 24;
+	p[5] = value >> 16;
+	p[6] = value >>  8;
+	p[7] = value >>  0;
+}
+
 #endif