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

[PATCH 10/19] read-cache: add watchman 'WAMA' extension

From
David Turner <dturner@twopensource.com>
Date
Mar 9, 2016, 18:36 UTC
Message-ID
<1457548582-28302-11-git-send-email-dturner@twopensource.com>
In-Reply-To
<1457548582-28302-1-git-send-email-dturner@twopensource.com>
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.

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>
---
 cache.h      |  4 ++++
 read-cache.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 73 insertions(+), 2 deletions(-)
diff --git a/cache.h b/cache.h
index cc1f6f5..8f7b4b1 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;
@@ -344,6 +347,7 @@ 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/read-cache.c b/read-cache.c
index 16fbdf6..85ef15b 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -19,6 +19,7 @@
 #include "split-index.h"
 #include "utf8.h"
 #include "shm.h"
+#include "ewah/ewok.h"
 
 static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
 					       unsigned int options);
@@ -41,11 +42,13 @@ 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;
@@ -1224,8 +1227,13 @@ 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) {
+				ce->ce_flags          &= ~CE_WATCHMAN_DIRTY;
+				istate->cache_changed |= WATCHMAN_CHANGED;
+			}
 			continue;
+		}
 		if (!new) {
 			const char *fmt;
 
@@ -1369,6 +1377,48 @@ 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;
+
+	if (memchr(data, 0, sz) == NULL)
+		return error("invalid extension");
+	len = strlen(data) + 1;
+	bitmap = ewah_new();
+	ret = ewah_read_mmap(bitmap, (const char *)data + len, sz - len);
+	if (ret != sz - len) {
+		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);
+	return 0;
+}
+
+static void write_watchman_ext(struct strbuf *sb, struct index_state* istate)
+{
+	struct ewah_bitmap *bitmap;
+	int i;
+
+	strbuf_add(sb, istate->last_update, strlen(istate->last_update) + 1);
+	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);
+}
+
 static int read_index_extension(struct index_state *istate,
 				const char *ext, void *data, unsigned long sz)
 {
@@ -1386,6 +1436,11 @@ 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",
@@ -1817,6 +1872,8 @@ 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;
 }
 
@@ -2214,6 +2271,16 @@ 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;
-- 
2.4.2.767.g62658d5-twtrsrc
Previous: Duy NguyenNext: David Turner
Message 29 of 60 in “index-helper, watchman”
  1. 00/19 index-helper, watchmanDavid Turner, Mar 9, 2016
  2. 01/19 trace.c: add GIT_TRACE_PACK_STATS for pack usage statisticsDavid Turner, Mar 9, 2016
  3. Junio C HamanoMar 9, 2016
  4. David TurnerMar 10, 2016
  5. Duy NguyenMar 10, 2016
  6. 02/19 read-cache.c: fix constness of verify_hdr()David Turner, Mar 9, 2016
  7. 03/19 read-cache: allow to keep mmap'd memory after readingDavid Turner, Mar 9, 2016
  8. Junio C HamanoMar 9, 2016
  9. David TurnerMar 10, 2016
  10. 04/19 index-helper: new daemon for caching index and related stuffDavid Turner, Mar 9, 2016
  11. Junio C HamanoMar 9, 2016
  12. Junio C HamanoMar 9, 2016
  13. David TurnerMar 10, 2016
  14. Duy NguyenMar 10, 2016
  15. David TurnerMar 10, 2016
  16. Duy NguyenMar 11, 2016
  17. David TurnerMar 10, 2016
  18. Duy NguyenMar 15, 2016
  19. Junio C HamanoMar 15, 2016
  20. Duy NguyenMar 15, 2016
  21. 05/19 trace.c: add GIT_TRACE_INDEX_STATS for index statisticsDavid Turner, Mar 9, 2016
  22. 06/19 index-helper: add --strictDavid Turner, Mar 9, 2016
  23. 07/19 daemonize(): set a flag before exiting the main processDavid Turner, Mar 9, 2016
  24. 08/19 index-helper: add --detachDavid Turner, Mar 9, 2016
  25. 09/19 index-helper: add Windows supportDavid Turner, Mar 9, 2016
  26. Duy NguyenMar 16, 2016
  27. Johannes SchindelinMar 17, 2016
  28. Duy NguyenMar 17, 2016
  29. 10/19 read-cache: add watchman 'WAMA' extensionDavid Turner, Mar 9, 2016
  30. 11/19 Add watchman support to reduce index refresh costDavid Turner, Mar 9, 2016
  31. 12/19 read-cache: allow index-helper to prepare shm before git reads itDavid Turner, Mar 9, 2016
  32. 13/19 index-helper: use watchman to avoid refreshing index with lstat()David Turner, Mar 9, 2016
  33. 14/19 update-index: enable/disable watchman supportDavid Turner, Mar 9, 2016
  34. 15/19 unpack-trees: preserve index extensionsDavid Turner, Mar 9, 2016
  35. 16/19 index-helper: rewrite pidfile after daemonizingDavid Turner, Mar 9, 2016
  36. 17/19 index-helper: process managementDavid Turner, Mar 9, 2016
  37. 18/19 index-helper: autorunDavid Turner, Mar 9, 2016
  38. Duy NguyenMar 15, 2016
  39. Johannes SchindelinMar 15, 2016
  40. Duy NguyenMar 16, 2016
  41. David TurnerMar 16, 2016
  42. Johannes SchindelinMar 16, 2016
  43. Duy NguyenMar 17, 2016
  44. Johannes SchindelinMar 17, 2016
  45. David TurnerMar 17, 2016
  46. Duy NguyenMar 18, 2016
  47. Johannes SchindelinMar 18, 2016
  48. Duy NguyenMar 18, 2016
  49. David TurnerMar 18, 2016
  50. Duy NguyenMar 18, 2016
  51. Johannes SchindelinMar 18, 2016
  52. Duy NguyenMar 18, 2016
  53. Johannes SchindelinMar 18, 2016
  54. 19/19 hack: watchman/untracked cache mashupDavid Turner, Mar 9, 2016
  55. Duy NguyenMar 15, 2016
  56. David TurnerMar 17, 2016
  57. Duy NguyenMar 17, 2016
  58. David TurnerMar 17, 2016
  59. Torsten BögershausenMar 29, 2016
  60. David TurnerMar 29, 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.