fsmonitor: teach git to optionally utilize a file system monitor to speed up detecting new or changed files.

When the index is read from disk, the fsmonitor index extension is used
to flag the last known potentially dirty index entries. The registered
core.fsmonitor command is called with the time the index was last
updated and returns the list of files changed since that time. This list
is used to flag any additional dirty cache entries and untracked cache
directories.

We can then use this valid state to speed up preload_index(),
ie_match_stat(), and refresh_cache_ent() as they do not need to lstat()
files to detect potential changes for those entries marked
CE_FSMONITOR_VALID.

In addition, if the untracked cache is turned on valid_cached_dir() can
skip checking directories for new or changed files as fsmonitor will
invalidate the cache only for those directories that have been
identified as having potential changes.

To keep the CE_FSMONITOR_VALID state accurate during git operations;
when git updates a cache entry to match the current state on disk,
it will now set the CE_FSMONITOR_VALID bit.

Inversely, anytime git changes a cache entry, the CE_FSMONITOR_VALID bit
is cleared and the corresponding untracked cache directory is marked
invalid.

Signed-off-by: Ben Peart <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: benpeart

Makefile

@@ -786,6 +786,7 @@ 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/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
@@ -233,6 +234,7 @@ static int mark_ce_flags(const char *path, int flag, int mark)
 		else
 			active_cache[pos]->ce_flags &= ~flag;
 		active_cache[pos]->ce_flags |= CE_UPDATE_IN_BASE;
+		mark_fsmonitor_invalid(&the_index, active_cache[pos]);
 		cache_tree_invalidate_path(&the_index, path);
 		active_cache_changed |= CE_ENTRY_CHANGED;
 		return 0;

cache.h

@@ -203,6 +203,7 @@ 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)
 
@@ -326,6 +327,7 @@ 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;
@@ -344,6 +346,7 @@ 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;
@@ -679,8 +682,10 @@ 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
@@ -773,6 +778,7 @@ 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

config.c

@@ -2165,6 +2165,20 @@ int git_config_get_max_percent_split_change(void)
 	return -1; /* default value */
 }
 
+int git_config_get_fsmonitor(void)
+{
+	if (git_config_get_pathname("core.fsmonitor", &core_fsmonitor))
+		core_fsmonitor = getenv("GIT_FSMONITOR_TEST");
+
+	if (core_fsmonitor && !*core_fsmonitor)
+		core_fsmonitor = NULL;
+
+	if (core_fsmonitor)
+		return 1;
+
+	return 0;
+}
+
 NORETURN
 void git_die_config_linenr(const char *key, const char *filename, int linenr)
 {

config.h

@@ -211,6 +211,7 @@ extern int git_config_get_pathname(const char *key, const char **dest);
 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);
 
 /* This dies if the configured or default date is in the future */
 extern int git_config_get_expiry(const char *key, const char **output);

diff-lib.c

@@ -12,6 +12,7 @@
 #include "refs.h"
 #include "submodule.h"
 #include "dir.h"
+#include "fsmonitor.h"
 
 /*
  * diff-files
@@ -228,6 +229,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 
 		if (!changed && !dirty_submodule) {
 			ce_mark_uptodate(ce);
+			mark_fsmonitor_valid(ce);
 			if (!DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
 				continue;
 		}

dir.c

@@ -18,6 +18,7 @@
 #include "utf8.h"
 #include "varint.h"
 #include "ewah/ewok.h"
+#include "fsmonitor.h"
 
 /*
  * Tells read_directory_recursive how a file or directory should be treated.
@@ -1688,17 +1689,23 @@ static int valid_cached_dir(struct dir_struct *dir,
 	if (!untracked)
 		return 0;
 
-	if (stat(path->len ? path->buf : ".", &st)) {
-		invalidate_directory(dir->untracked, untracked);
-		memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
-		return 0;
-	}
-	if (!untracked->valid ||
-	    match_stat_data_racy(istate, &untracked->stat_data, &st)) {
-		if (untracked->valid)
+	/*
+	 * With fsmonitor, we can trust the untracked cache's valid field.
+	 */
+	refresh_fsmonitor(istate);
+	if (!(dir->untracked->use_fsmonitor && untracked->valid)) {
+		if (stat(path->len ? path->buf : ".", &st)) {
 			invalidate_directory(dir->untracked, untracked);
-		fill_stat_data(&untracked->stat_data, &st);
-		return 0;
+			memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
+			return 0;
+		}
+		if (!untracked->valid ||
+			match_stat_data_racy(istate, &untracked->stat_data, &st)) {
+			if (untracked->valid)
+				invalidate_directory(dir->untracked, untracked);
+			fill_stat_data(&untracked->stat_data, &st);
+			return 0;
+		}
 	}
 
 	if (untracked->check_only != !!check_only) {

dir.h

@@ -139,6 +139,8 @@ struct untracked_cache {
 	int gitignore_invalidated;
 	int dir_invalidated;
 	int dir_opened;
+	/* fsmonitor invalidation data */
+	unsigned int use_fsmonitor : 1;
 };
 
 struct dir_struct {

entry.c

@@ -4,6 +4,7 @@
 #include "streaming.h"
 #include "submodule.h"
 #include "progress.h"
+#include "fsmonitor.h"
 
 static void create_directories(const char *path, int path_len,
 			       const struct checkout *state)
@@ -357,6 +358,7 @@ static int write_entry(struct cache_entry *ce,
 			lstat(ce->name, &st);
 		fill_stat_cache_info(ce, &st);
 		ce->ce_flags |= CE_UPDATE_IN_BASE;
+		mark_fsmonitor_invalid(state->istate, ce);
 		state->istate->cache_changed |= CE_ENTRY_CHANGED;
 	}
 	return 0;

environment.c

@@ -76,6 +76,7 @@ int protect_hfs = PROTECT_HFS_DEFAULT;
 #define PROTECT_NTFS_DEFAULT 0
 #endif
 int protect_ntfs = PROTECT_NTFS_DEFAULT;
+const char *core_fsmonitor;
 
 /*
  * The character that begins a commented line in user-editable file