[PATCH v3 08/16] Add watchman support to reduce index refresh cost

[David Turner <dturner@twopensource.com>]

From: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>

The previous patch has the logic to clear bits in 'WAMA' bitmap. This
patch has logic to set bits as told by watchman. The missing bit,
_using_ these bits, are not here yet.

A lot of this code is written by David Turner originally, mostly from
[1]. I'm just copying and polishing it a bit.

[1] http://article.gmane.org/gmane.comp.version-control.git/248006

Signed-off-by: David Turner <dturner@twopensource.com>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Makefile           |  12 +++++
 cache.h            |   1 +
 config.c           |   5 ++
 configure.ac       |   8 ++++
 environment.c      |   3 ++
 watchman-support.c | 135 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 watchman-support.h |   7 +++
 7 files changed, 171 insertions(+)
 create mode 100644 watchman-support.c
 create mode 100644 watchman-support.h

diff --git a/Makefile b/Makefile
index 24d6c0e..8ad8e1f 100644
--- a/Makefile
+++ b/Makefile
@@ -453,6 +453,7 @@ MSGFMT = msgfmt
 CURL_CONFIG = curl-config
 PTHREAD_LIBS = -lpthread
 PTHREAD_CFLAGS =
+WATCHMAN_LIBS =
 GCOV = gcov
 
 export TCL_PATH TCLTK_PATH
@@ -1419,6 +1420,13 @@ else
 	LIB_OBJS += thread-utils.o
 endif
 
+ifdef USE_WATCHMAN
+	LIB_H += watchman-support.h
+	LIB_OBJS += watchman-support.o
+	WATCHMAN_LIBS = -lwatchman
+	BASIC_CFLAGS += -DUSE_WATCHMAN
+endif
+
 ifdef HAVE_PATHS_H
 	BASIC_CFLAGS += -DHAVE_PATHS_H
 endif
@@ -2030,6 +2038,9 @@ git-remote-testsvn$X: remote-testsvn.o GIT-LDFLAGS $(GITLIBS) $(VCSSVN_LIB)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) \
 	$(VCSSVN_LIB)
 
+git-index-helper$X: index-helper.o GIT-LDFLAGS $(GITLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) $(WATCHMAN_LIBS)
+
 $(REMOTE_CURL_ALIASES): $(REMOTE_CURL_PRIMARY)
 	$(QUIET_LNCP)$(RM) $@ && \
 	ln $< $@ 2>/dev/null || \
@@ -2169,6 +2180,7 @@ GIT-BUILD-OPTIONS: FORCE
 	@echo NO_PYTHON=\''$(subst ','\'',$(subst ','\'',$(NO_PYTHON)))'\' >>$@+
 	@echo NO_UNIX_SOCKETS=\''$(subst ','\'',$(subst ','\'',$(NO_UNIX_SOCKETS)))'\' >>$@+
 	@echo HAVE_SHM=\''$(subst ','\'',$(subst ','\'',$(HAVE_SHM)))'\' >>$@+
+	@echo USE_WATCHMAN=\''$(subst ','\'',$(subst ','\'',$(USE_WATCHMAN)))'\' >>$@+
 ifdef TEST_OUTPUT_DIRECTORY
 	@echo TEST_OUTPUT_DIRECTORY=\''$(subst ','\'',$(subst ','\'',$(TEST_OUTPUT_DIRECTORY)))'\' >>$@+
 endif
diff --git a/cache.h b/cache.h
index f4f7eef..37f211b 100644
--- a/cache.h
+++ b/cache.h
@@ -687,6 +687,7 @@ extern char *git_replace_ref_base;
 
 extern int fsync_object_files;
 extern int core_preload_index;
+extern int core_watchman_sync_timeout;
 extern int core_apply_sparse_checkout;
 extern int precomposed_unicode;
 extern int protect_hfs;
diff --git a/config.c b/config.c
index 9ba40bc..e6dc141 100644
--- a/config.c
+++ b/config.c
@@ -882,6 +882,11 @@ static int git_default_core_config(const char *var, const char *value)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.watchmansynctimeout")) {
+		core_watchman_sync_timeout = git_config_int(var, value);
+		return 0;
+	}
+
 	if (!strcmp(var, "core.createobject")) {
 		if (!strcmp(value, "rename"))
 			object_creation_mode = OBJECT_CREATION_USES_RENAMES;
diff --git a/configure.ac b/configure.ac
index 0cd9f46..334d63b 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1099,6 +1099,14 @@ AC_COMPILE_IFELSE([BSD_SYSCTL_SRC],
 	HAVE_BSD_SYSCTL=])
 GIT_CONF_SUBST([HAVE_BSD_SYSCTL])
 
+#
+# Check for watchman client library
+
+AC_CHECK_LIB([watchman], [watchman_connect],
+	[USE_WATCHMAN=YesPlease],
+	[USE_WATCHMAN=])
+GIT_CONF_SUBST([USE_WATCHMAN])
+
 ## Other checks.
 # Define USE_PIC if you need the main git objects to be built with -fPIC
 # in order to build and link perl/Git.so.  x86-64 seems to need this.
diff --git a/environment.c b/environment.c
index 6dec9d0..35e03c7 100644
--- a/environment.c
+++ b/environment.c
@@ -94,6 +94,9 @@ int core_preload_index = 1;
  */
 int ignore_untracked_cache_config;
 
+int core_watchman_sync_timeout = 300;
+
+
 /* This is set by setup_git_dir_gently() and/or git_default_config() */
 char *git_work_tree_cfg;
 static char *work_tree;
diff --git a/watchman-support.c b/watchman-support.c
new file mode 100644
index 0000000..b168e88
--- /dev/null
+++ b/watchman-support.c
@@ -0,0 +1,135 @@
+#include "cache.h"
+#include "watchman-support.h"
+#include "strbuf.h"
+#include "dir.h"
+#include <watchman.h>
+
+static struct watchman_query *make_query(const char *last_update)
+{
+	struct watchman_query *query = watchman_query();
+	watchman_query_set_fields(query, WATCHMAN_FIELD_NAME |
+					 WATCHMAN_FIELD_EXISTS |
+					 WATCHMAN_FIELD_NEWER);
+	watchman_query_set_empty_on_fresh(query, 1);
+	query->sync_timeout = core_watchman_sync_timeout;
+	if (*last_update)
+		watchman_query_set_since_oclock(query, last_update);
+	return query;
+}
+
+static struct watchman_query_result* query_watchman(
+	struct index_state *istate, struct watchman_connection *connection,
+	const char *fs_path, const char *last_update)
+{
+	struct watchman_error wm_error;
+	struct watchman_query *query;
+	struct watchman_expression *expr;
+	struct watchman_query_result *result;
+
+	query = make_query(last_update);
+	expr = watchman_true_expression();
+	result = watchman_do_query(connection, fs_path, query, expr, &wm_error);
+	watchman_free_query(query);
+	watchman_free_expression(expr);
+
+	if (!result)
+		warning("Watchman query error: %s (at %s)",
+			wm_error.message,
+			*last_update ? last_update : "the beginning");
+
+	return result;
+}
+
+static void update_index(struct index_state *istate,
+			 struct watchman_query_result *result)
+{
+	int i;
+
+	if (result->is_fresh_instance) {
+		/* let refresh clear them later */
+		for (i = 0; i < istate->cache_nr; i++)
+			istate->cache[i]->ce_flags |= CE_WATCHMAN_DIRTY;
+		goto done;
+	}
+
+	for (i = 0; i < result->nr; i++) {
+		struct watchman_stat *wm = result->stats + i;
+		int pos;
+
+		if (S_ISDIR(wm->mode) ||
+		    !strncmp(wm->name, ".git/", 5) ||
+		    strstr(wm->name, "/.git/"))
+			continue;
+
+		pos = index_name_pos(istate, wm->name, strlen(wm->name));
+		if (pos < 0) {
+			if (istate->untracked) {
+				char *name = xstrdup(wm->name);
+				char *dname = dirname(name);
+
+				/*
+				 * dirname() returns '.' for the root,
+				 * but we call it ''.
+				 */
+				if (dname[0] == '.' && dname[1] == 0)
+					string_list_append(&istate->untracked->invalid_untracked, "");
+				else
+					string_list_append(&istate->untracked->invalid_untracked,
+							   dname);
+				free(name);
+			}
+			continue;
+		}
+		/* FIXME: ignore staged entries and gitlinks too? */
+
+		istate->cache[pos]->ce_flags |= CE_WATCHMAN_DIRTY;
+	}
+
+done:
+	free(istate->last_update);
+	istate->last_update    = xstrdup(result->clock);
+	istate->cache_changed |= WATCHMAN_CHANGED;
+	if (istate->untracked)
+		string_list_remove_duplicates(&istate->untracked->invalid_untracked, 0);
+}
+
+int check_watchman(struct index_state *istate)
+{
+	struct watchman_error wm_error;
+	struct watchman_connection *connection;
+	struct watchman_query_result *result;
+	const char *fs_path;
+	struct timeval timeout;
+	/*
+	 * Convert core_watchman_sync_timeout, in milliseconds, to
+	 * struct timeval, in seconds and microseconds.
+	 */
+
+	fs_path = get_git_work_tree();
+	if (!fs_path)
+		return -1;
+
+	timeout.tv_sec = core_watchman_sync_timeout / 1000;
+	timeout.tv_usec = (core_watchman_sync_timeout % 1000) * 1000;
+	connection = watchman_connect(timeout, &wm_error);
+
+	if (!connection) {
+		warning("Watchman watch error: %s", wm_error.message);
+		return -1;
+	}
+
+	if (watchman_watch(connection, fs_path, &wm_error)) {
+		warning("Watchman watch error: %s", wm_error.message);
+		watchman_connection_close(connection);
+		return -1;
+	}
+
+
+	result = query_watchman(istate, connection, fs_path, istate->last_update);
+	watchman_connection_close(connection);
+	if (!result)
+		return -1;
+	update_index(istate, result);
+	watchman_free_query_result(result);
+	return 0;
+}
diff --git a/watchman-support.h b/watchman-support.h
new file mode 100644
index 0000000..ee1ef2c
--- /dev/null
+++ b/watchman-support.h
@@ -0,0 +1,7 @@
+#ifndef WATCHMAN_SUPPORT_H
+#define WATCHMAN_SUPPORT_H
+
+struct index_state;
+int check_watchman(struct index_state *index);
+
+#endif /* WATCHMAN_SUPPORT_H */
-- 
2.4.2.767.g62658d5-twtrsrc