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

[PATCH/RFC v2 11/16] Read cache-tree in index-v5

From
Thomas Gummerer <t.gummerer@gmail.com>
Date
Aug 5, 2012, 21:49 UTC
Message-ID
<1344203353-2819-12-git-send-email-t.gummerer@gmail.com>
In-Reply-To
<1344203353-2819-1-git-send-email-t.gummerer@gmail.com>

Since the cache-tree data is saved as part of the directory data, we already read it at the beginning of the index. The cache-tree is only converted from this directory data.

The cache-tree data is arranged in a tree, with the children sorted by pathlen at each node, while the ondisk format is sorted lexically. So we have to rebuild this format from the on-disk directory list.

Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com>
---
 cache-tree.c |   93 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 cache-tree.h |   10 +++++++
 read-cache.c |    1 +
 3 files changed, 104 insertions(+)
diff --git a/cache-tree.c b/cache-tree.c
index 28ed657..440cd04 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -519,6 +519,99 @@ struct cache_tree *cache_tree_read(const char *buffer, unsigned long size)
 	return read_one(&buffer, &size);
 }
 
+static struct cache_tree *convert_one(struct directory_queue *queue, int dirnr)
+{
+	int i, subtree_nr;
+	struct cache_tree *it;
+	struct directory_queue *down;
+
+	it = cache_tree();
+	it->entry_count = queue[dirnr].de->de_nentries;
+	subtree_nr = queue[dirnr].de->de_nsubtrees;
+	if (0 <= it->entry_count)
+		hashcpy(it->sha1, queue[dirnr].de->sha1);
+
+	/*
+	* Just a heuristic -- we do not add directories that often but
+	* we do not want to have to extend it immediately when we do,
+	* hence +2.
+	*/
+	it->subtree_alloc = subtree_nr + 2;
+	it->down = xcalloc(it->subtree_alloc, sizeof(struct cache_tree_sub *));
+	down = queue[dirnr].down;
+	for (i = 0; i < subtree_nr; i++) {
+		struct cache_tree *sub;
+		struct cache_tree_sub *subtree;
+		char *buf, *name;
+
+		name = "";
+		buf = strtok(down[i].de->pathname, "/");
+		while (buf) {
+			name = buf;
+			buf = strtok(NULL, "/");
+		}
+		sub = convert_one(down, i);
+		if(!sub)
+			goto free_return;
+		subtree = cache_tree_sub(it, name);
+		subtree->cache_tree = sub;
+	}
+	if (subtree_nr != it->subtree_nr)
+		die("cache-tree: internal error");
+	return it;
+ free_return:
+	cache_tree_free(&it);
+	return NULL;
+}
+
+static int compare_cache_tree_elements(const void *a, const void *b)
+{
+	const struct directory_entry *de1, *de2;
+
+	de1 = ((const struct directory_queue *)a)->de;
+	de2 = ((const struct directory_queue *)b)->de;
+	return subtree_name_cmp(de1->pathname, de1->de_pathlen,
+				de2->pathname, de2->de_pathlen);
+}
+
+static struct directory_entry *sort_directories(struct directory_entry *de,
+						struct directory_queue *queue)
+{
+	int i, nsubtrees;
+
+	nsubtrees = de->de_nsubtrees;
+	for (i = 0; i < nsubtrees; i++) {
+		struct directory_entry *new_de;
+		de = de->next;
+		new_de = xmalloc(directory_entry_size(de->de_pathlen));
+		memcpy(new_de, de, directory_entry_size(de->de_pathlen));
+		queue[i].de = new_de;
+		if (de->de_nsubtrees) {
+			queue[i].down = xcalloc(de->de_nsubtrees,
+					sizeof(struct directory_queue));
+			de = sort_directories(de,
+					queue[i].down);
+		}
+	}
+	qsort(queue, nsubtrees, sizeof(struct directory_queue),
+			compare_cache_tree_elements);
+	return de;
+}
+
+struct cache_tree *cache_tree_convert_v5(struct directory_entry *de)
+{
+	struct directory_queue *queue;
+
+	if (!de->de_nentries)
+		return NULL;
+	queue = xcalloc(1, sizeof(struct directory_queue));
+	queue[0].de = de;
+	queue[0].down = xcalloc(de->de_nsubtrees, sizeof(struct directory_queue));
+
+	sort_directories(de, queue[0].down);
+	return convert_one(queue, 0);
+}
+
 static struct cache_tree *cache_tree_find(struct cache_tree *it, const char *path)
 {
 	if (!it)
diff --git a/cache-tree.h b/cache-tree.h
index d8cb2e9..7f29d26 100644
--- a/cache-tree.h
+++ b/cache-tree.h
@@ -20,6 +20,11 @@ struct cache_tree {
 	struct cache_tree_sub **down;
 };
 
+struct directory_queue {
+	struct directory_queue *down;
+	struct directory_entry *de;
+};
+
 struct cache_tree *cache_tree(void);
 void cache_tree_free(struct cache_tree **);
 void cache_tree_invalidate_path(struct cache_tree *, const char *);
@@ -27,6 +32,11 @@ struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *);
 
 void cache_tree_write(struct strbuf *, struct cache_tree *root);
 struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
+/*
+ * This function modifys the directory argument that is given to it.
+ * Don't use it if the directory entries are still needed after.
+ */
+struct cache_tree *cache_tree_convert_v5(struct directory_entry *de);
 
 int cache_tree_fully_valid(struct cache_tree *);
 int cache_tree_update(struct cache_tree *, struct cache_entry **, int, int);
diff --git a/read-cache.c b/read-cache.c
index 03370f9..21ae804 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -2087,6 +2087,7 @@ static void read_index_v5(struct index_state *istate, void *mmap, int mmap_size,
 	while (de)
 		de = read_entries_v5(istate, de, &entry_offset,
 				&mmap, mmap_size, &nr, &foffsetblock, fd);
+	istate->cache_tree = cache_tree_convert_v5(root_directory);
 }
 
 /* remember to discard_cache() before reading a different cache! */
-- 
1.7.10.GIT
Previous: Thomas GummererNext: Thomas Gummerer
Message 34 of 59 in “Introduce index file format version 5”
  1. 0/16 Introduce index file format version 5Thomas Gummerer, Aug 5, 2012
  2. 01/16 Modify cache_header to prepare for other index formatsThomas Gummerer, Aug 5, 2012
  3. Junio C HamanoAug 6, 2012
  4. Thomas GummererAug 7, 2012
  5. Junio C HamanoAug 7, 2012
  6. 02/16 Modify read functions to prepare for other index formatsThomas Gummerer, Aug 5, 2012
  7. 03/16 Modify match_stat_basic to prepare for other index formatsThomas Gummerer, Aug 5, 2012
  8. 04/16 Modify write functions to prepare for other index formatsThomas Gummerer, Aug 5, 2012
  9. Junio C HamanoAug 6, 2012
  10. Thomas GummererAug 7, 2012
  11. 05/16 t2104: Don't fail for index versions other than [23]Thomas Gummerer, Aug 5, 2012
  12. Junio C HamanoAug 6, 2012
  13. 06/16 t3700: sleep for 1 second, to avoid interfering with the racy codeThomas Gummerer, Aug 5, 2012
  14. Junio C HamanoAug 6, 2012
  15. Thomas GummererAug 7, 2012
  16. Junio C HamanoAug 8, 2012
  17. Junio C HamanoAug 8, 2012
  18. Thomas GummererAug 9, 2012
  19. Junio C HamanoAug 9, 2012
  20. Thomas GummererAug 9, 2012
  21. 07/16 Add documentation of the index-v5 file formatThomas Gummerer, Aug 5, 2012
  22. 08/16 Make in-memory format aware of stat_crcThomas Gummerer, Aug 5, 2012
  23. Junio C HamanoAug 6, 2012
  24. Thomas GummererAug 7, 2012
  25. 09/16 Read index-v5Thomas Gummerer, Aug 5, 2012
  26. Junio C HamanoAug 6, 2012
  27. Thomas GummererAug 8, 2012
  28. Junio C HamanoAug 8, 2012
  29. Thomas GummererAug 8, 2012
  30. Junio C HamanoAug 8, 2012
  31. 10/16 Read resolve-undo dataThomas Gummerer, Aug 5, 2012
  32. Junio C HamanoAug 6, 2012
  33. Thomas GummererAug 7, 2012
  34. 11/16 Read cache-tree in index-v5Thomas Gummerer, Aug 5, 2012
  35. 12/16 Write index-v5Thomas Gummerer, Aug 5, 2012
  36. 13/16 Write index-v5 cache-tree dataThomas Gummerer, Aug 5, 2012
  37. 14/16 Write resolve-undo data for index-v5Thomas Gummerer, Aug 5, 2012
  38. 15/16 update-index.c: add a force-rewrite optionThomas Gummerer, Aug 5, 2012
  39. Junio C HamanoAug 6, 2012
  40. Thomas GummererAug 8, 2012
  41. 16/16 p0002-index.sh: add perf test for the index formatsThomas Gummerer, Aug 5, 2012
  42. Nguyễn Thái Ngọc DuyAug 6, 2012
  43. 1/2 Move index v2 specific code out of read-cacheNguyễn Thái Ngọc Duy, Aug 6, 2012
  44. 2/2 Add index-v5Nguyễn Thái Ngọc Duy, Aug 6, 2012
  45. Robin RosenbergAug 7, 2012
  46. Thomas GummererAug 8, 2012
  47. Junio C HamanoAug 6, 2012
  48. Thomas GummererAug 6, 2012
  49. Junio C HamanoAug 6, 2012
  50. Nguyen Thai Ngoc DuyAug 7, 2012
  51. Junio C HamanoAug 8, 2012
  52. Nguyen Thai Ngoc DuyAug 8, 2012
  53. Junio C HamanoAug 8, 2012
  54. Nguyen Thai Ngoc DuyAug 9, 2012
  55. Thomas RastAug 7, 2012
  56. Junio C HamanoAug 7, 2012
  57. Thomas RastAug 8, 2012
  58. Junio C HamanoAug 8, 2012
  59. Nguyen Thai Ngoc DuyAug 8, 2012

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.