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

[PATCH v13 09/20] read-cache: add watchman 'WAMA' extension

From
David Turner <novalis@novalis.org>
Date
Jun 26, 2016, 04:14 UTC
Message-ID
<1466914464-10358-9-git-send-email-novalis@novalis.org>
In-Reply-To
<1466914464-10358-1-git-send-email-novalis@novalis.org>
From: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>

The extension contains a bitmap, one bit for each entry in the index. If the n-th bit is zero, the n-th entry is considered unchanged, we can ce_mark_uptodate() it without refreshing. If the bit is non-zero and we found out the corresponding file is clean after refresh, we can clear the bit.

In addition, there's a list of directories in the untracked-cache to invalidate (because they have new or modified entries).

The 'skipping refresh' bit is not in this patch yet as we would need watchman. More details in later patches.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: David Turner <dturner@twopensource.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Documentation/technical/index-format.txt |  22 ++++++
 cache.h                                  |   4 +
 dir.h                                    |   3 +
 read-cache.c                             | 127 ++++++++++++++++++++++++++++++-
 4 files changed, 154 insertions(+), 2 deletions(-)
diff --git a/Documentation/technical/index-format.txt b/Documentation/technical/index-format.txt
index ade0b0c..86ed3a6 100644
--- a/Documentation/technical/index-format.txt
+++ b/Documentation/technical/index-format.txt
@@ -295,3 +295,25 @@ The remaining data of each directory block is grouped by type:
     in the previous ewah bitmap.
 
   - One NUL.
+
+== Watchman cache
+
+  The watchman cache tracks files for which watchman has told us about
+  changes.  The signature for this extension is { 'W', 'A', 'M', 'A' }.
+
+  The extension starts with
+
+  - A NUL-terminated string: the watchman vector clock at the last
+    time we heard from watchman.
+
+  - 32-bit bitmap size: the size of the CE_WATCHMAN_DIRTY bitmap
+
+  - 32-bit untracked cache entry count: the number of dirty untracked
+    cache entries
+
+  - An ewah bitmap, the n-th bit indicates whether the n-th index entry
+    is CE_WATCHMAN_DIRTY.
+
+  - a list of N NUL-terminated strings.  Each is a directory that should
+    be marked dirty in the untracked cache because watchman has told us
+    about an update to a file in it.
diff --git a/cache.h b/cache.h
index 4c1529a..f10992d 100644
--- a/cache.h
+++ b/cache.h
@@ -182,6 +182,8 @@ struct cache_entry {
 #define CE_VALID     (0x8000)
 #define CE_STAGESHIFT 12
 
+#define CE_WATCHMAN_DIRTY  (0x0001)
+
 /*
  * Range 0xFFFF0FFF in ce_flags is divided into
  * two parts: in-memory flags and on-disk ones.
@@ -320,6 +322,7 @@ 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 WATCHMAN_CHANGED	(1 << 8)
 
 struct split_index;
 struct untracked_cache;
@@ -353,6 +356,7 @@ struct index_state {
 	struct untracked_cache *untracked;
 	void *mmap;
 	size_t mmap_size;
+	char *last_update;
 };
 
 extern struct index_state the_index;
diff --git a/dir.h b/dir.h
index cd46f30..896b64a 100644
--- a/dir.h
+++ b/dir.h
@@ -139,6 +139,9 @@ struct untracked_cache {
 	int gitignore_invalidated;
 	int dir_invalidated;
 	int dir_opened;
+	/* watchman invalidation data */
+	unsigned int use_watchman : 1;
+	struct string_list invalid_untracked;
 };
 
 struct dir_struct {
diff --git a/read-cache.c b/read-cache.c
index befc499..e0fc634 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -21,6 +21,7 @@
 #include "unix-socket.h"
 #include "pkt-line.h"
 #include "sigchain.h"
+#include "ewah/ewok.h"
 
 static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
 					       unsigned int options);
@@ -43,11 +44,13 @@ static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
 #define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */
 #define CACHE_EXT_LINK 0x6c696e6b	  /* "link" */
 #define CACHE_EXT_UNTRACKED 0x554E5452	  /* "UNTR" */
+#define CACHE_EXT_WATCHMAN 0x57414D41	  /* "WAMA" */
 
 /* changes that can be kept in $GIT_DIR/index (basically all extensions) */
 #define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
 		 CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
-		 SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED)
+		 SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED | \
+		 WATCHMAN_CHANGED)
 
 struct index_state the_index;
 static const char *alternate_index_output;
@@ -1222,8 +1225,23 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 			continue;
 
 		new = refresh_cache_ent(istate, ce, options, &cache_errno, &changed);
-		if (new == ce)
+		if (new == ce) {
+			if (ce->ce_flags & CE_WATCHMAN_DIRTY) {
+				/* The rule is index-helper sets
+				 * CE_WATCHMAN_DIRTY when a file is changed,
+				 * then git clears it when it has verified
+				 * that the in-index entry now matches the
+				 * worktree version. index-helper does not
+				 * clear the bit and git does not set it. We
+				 * have verified here that stat info (and even
+				 * content) matches, so it's safe to clear
+				 * CE_WATCHMAN_DIRTY now.
+				 */
+				ce->ce_flags          &= ~CE_WATCHMAN_DIRTY;
+				istate->cache_changed |= WATCHMAN_CHANGED;
+			}
 			continue;
+		}
 		if (!new) {
 			const char *fmt;
 
@@ -1367,6 +1385,94 @@ static int verify_hdr(const struct cache_header *hdr, unsigned long size)
 	return 0;
 }
 
+static void mark_no_watchman(size_t pos, void *data)
+{
+	struct index_state *istate = data;
+	assert(pos < istate->cache_nr);
+	istate->cache[pos]->ce_flags |= CE_WATCHMAN_DIRTY;
+}
+
+static int read_watchman_ext(struct index_state *istate, const void *data,
+			     unsigned long sz)
+{
+	struct ewah_bitmap *bitmap;
+	int ret, len;
+	uint32_t bitmap_size;
+	uint32_t untracked_nr;
+
+	if (memchr(data, 0, sz) == NULL)
+		return error("invalid extension");
+
+	len = strlen(data) + 1;
+	memcpy(&bitmap_size, (const char *)data + len, 4);
+	memcpy(&untracked_nr, (const char *)data + len + 4, 4);
+	untracked_nr = ntohl(untracked_nr);
+	bitmap_size = ntohl(bitmap_size);
+
+	bitmap = ewah_new();
+	ret = ewah_read_mmap(bitmap, (const char *)data + len + 8, bitmap_size);
+	if (ret != bitmap_size) {
+		ewah_free(bitmap);
+		return error("failed to parse ewah bitmap reading watchman index extension");
+	}
+	istate->last_update = xstrdup(data);
+	ewah_each_bit(bitmap, mark_no_watchman, istate);
+	ewah_free(bitmap);
+
+	/*
+	 * TODO: update the untracked cache from the untracked data in this
+	 * extension.
+	 */
+	return 0;
+}
+
+static int untracked_entry_append(struct string_list_item *item, void *sbvoid)
+{
+	struct strbuf *sb = sbvoid;
+
+	strbuf_addstr(sb, item->string);
+	strbuf_addch(sb, 0);
+	return 0;
+}
+
+void write_watchman_ext(struct strbuf *sb, struct index_state *istate)
+{
+	struct ewah_bitmap *bitmap;
+	int i;
+	int ewah_start;
+	int ewah_size = 0;
+	int fixup = 0;
+
+	strbuf_add(sb, istate->last_update, strlen(istate->last_update) + 1);
+	fixup = sb->len;
+	strbuf_add(sb, &ewah_size, 4); /* we'll fix this up later */
+	if (istate->untracked) {
+		uint32_t nr = istate->untracked->invalid_untracked.nr;
+		nr = htonl(nr);
+		strbuf_add(sb, &nr, 4);
+	} else {
+		/* zero */
+		strbuf_add(sb, &ewah_size, 4);
+	}
+
+	ewah_start = sb->len;
+	bitmap = ewah_new();
+	for (i = 0; i < istate->cache_nr; i++)
+		if (istate->cache[i]->ce_flags & CE_WATCHMAN_DIRTY)
+			ewah_set(bitmap, i);
+	ewah_serialize_strbuf(bitmap, sb);
+	ewah_free(bitmap);
+
+	/* fix up size field */
+	ewah_size = sb->len - ewah_start;
+	ewah_size = htonl(ewah_size);
+	memcpy(sb->buf + fixup, &ewah_size, 4);
+
+	if (istate->untracked)
+		for_each_string_list(&istate->untracked->invalid_untracked,
+				     untracked_entry_append, sb);
+}
+
 static int read_index_extension(struct index_state *istate,
 				const char *ext, void *data, unsigned long sz)
 {
@@ -1384,6 +1490,11 @@ static int read_index_extension(struct index_state *istate,
 	case CACHE_EXT_UNTRACKED:
 		istate->untracked = read_untracked_extension(data, sz);
 		break;
+
+	case CACHE_EXT_WATCHMAN:
+		read_watchman_ext(istate, data, sz);
+		break;
+
 	default:
 		if (*ext < 'A' || 'Z' < *ext)
 			return error("index uses %.4s extension, which we do not understand",
@@ -1815,6 +1926,8 @@ int discard_index(struct index_state *istate)
 	istate->untracked = NULL;
 	istate->from_shm = 0;
 	istate->to_shm   = 0;
+	free(istate->last_update);
+	istate->last_update = NULL;
 	return 0;
 }
 
@@ -2212,6 +2325,16 @@ static int do_write_index(struct index_state *istate, int newfd,
 		if (err)
 			return -1;
 	}
+	if (!strip_extensions && istate->last_update) {
+		struct strbuf sb = STRBUF_INIT;
+
+		write_watchman_ext(&sb, istate);
+		err = write_index_ext_header(&c, newfd, CACHE_EXT_WATCHMAN, sb.len) < 0
+			|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
+		strbuf_release(&sb);
+		if (err)
+			return -1;
+	}
 
 	if (ce_flush(&c, newfd, istate->sha1) || fstat(newfd, &st))
 		return -1;

-- 
1.9.1
Previous: David TurnerNext: David Turner
Message 18 of 35 in “read-cache.c: fix constness of verify_hdr()”
  1. 01/20 read-cache.c: fix constness of verify_hdr()David Turner, Jun 26, 2016
  2. 04/20 index-helper: new daemon for caching index and related stuffDavid Turner, Jun 26, 2016
  3. Johannes SchindelinJun 30, 2016
  4. Duy NguyenJun 30, 2016
  5. Johannes SchindelinJul 2, 2016
  6. Duy NguyenJul 2, 2016
  7. 03/20 pkt-line: add gentle version of packet_writeDavid Turner, Jun 26, 2016
  8. 02/20 read-cache: allow to keep mmap'd memory after readingDavid Turner, Jun 26, 2016
  9. 06/20 daemonize(): set a flag before exiting the main processDavid Turner, Jun 26, 2016
  10. 05/20 index-helper: add --strictDavid Turner, Jun 26, 2016
  11. 18/20 index-helper: optionally automatically runDavid Turner, Jun 26, 2016
  12. 17/20 index-helper: autorun modeDavid Turner, Jun 26, 2016
  13. 15/20 index-helper: kill modeDavid Turner, Jun 26, 2016
  14. 14/20 watchman: add a config option to enable the extensionDavid Turner, Jun 26, 2016
  15. 13/20 unpack-trees: preserve index extensionsDavid Turner, Jun 26, 2016
  16. 16/20 index-helper: don't run if already runningDavid Turner, Jun 26, 2016
  17. 12/20 update-index: enable/disable watchman supportDavid Turner, Jun 26, 2016
  18. 09/20 read-cache: add watchman 'WAMA' extensionDavid Turner, Jun 26, 2016
  19. 10/20 watchman: support watchman to reduce index refresh costDavid Turner, Jun 26, 2016
  20. 11/20 index-helper: use watchman to avoid refreshing index with lstat()David Turner, Jun 26, 2016
  21. Ben PeartJun 30, 2016
  22. Duy NguyenJun 30, 2016
  23. Ben PeartJun 30, 2016
  24. Duy NguyenJul 3, 2016
  25. Ben PeartJul 6, 2016
  26. Duy NguyenJul 8, 2016
  27. Duy NguyenJul 8, 2016
  28. 07/20 index-helper: add --detachDavid Turner, Jun 26, 2016
  29. 08/20 index-helper: log warningsDavid Turner, Jun 26, 2016
  30. 19/20 trace: measure where the time is spent in the index-heavy operationsDavid Turner, Jun 26, 2016
  31. 21/20 unix-socket.c: add stub implementation when unix sockets are not supportedNguyễn Thái Ngọc Duy, Jun 26, 2016
  32. Johannes SchindelinJun 27, 2016
  33. Duy NguyenJun 27, 2016
  34. Johannes SchindelinJun 28, 2016
  35. David TurnerJun 27, 2016

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.