From: Thomas Gummerer <t.gummerer@gmail.com>
To: git@vger.kernel.org
Cc: trast@student.ethz.ch, mhagger@alum.mit.edu, gitster@pobox.com,
pclouds@gmail.com, robin.rosenberg@dewire.com,
Thomas Gummerer <t.gummerer@gmail.com>
Subject: [PATCH 11/16] Read cache-tree in index-v5
Date: Thu, 2 Aug 2012 13:02:01 +0200 [thread overview]
Message-ID: <1343905326-23790-12-git-send-email-t.gummerer@gmail.com> (raw)
In-Reply-To: <1343905326-23790-1-git-send-email-t.gummerer@gmail.com>
Since the cache-tree data is saved as part of the directory data,
we have already read it, when we want to read the cache-tree. The
cache-tree then only has to be converted from the directory data.
The cache-tree isn't lexically sorted, but after the pathlen at
each level, therefore the directories have to be reordered with
respect to the ondisk layout.
Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com>
---
cache-tree.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
cache-tree.h | 6 ++++
read-cache.c | 1 +
3 files changed, 100 insertions(+)
diff --git a/cache-tree.c b/cache-tree.c
index 28ed657..6a314aa 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);
}
+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..f4131a6 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 +32,7 @@ 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);
+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 cef9a4e..fd095ec 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -2054,6 +2054,7 @@ void read_index_v5(struct index_state *istate, void *mmap, int mmap_size, int fd
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! */
--
1.7.10.886.gdf6792c.dirty
next prev parent reply other threads:[~2012-08-02 11:03 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-02 11:01 [RFC 0/16] Introduce index file format version 5 Thomas Gummerer
2012-08-02 11:01 ` [PATCH 01/16] Modify cache_header to prepare for other index formats Thomas Gummerer
2012-08-02 12:15 ` Nguyen Thai Ngoc Duy
2012-08-02 11:01 ` [PATCH 02/16] Modify read functions " Thomas Gummerer
2012-08-02 11:01 ` [PATCH 03/16] Modify match_stat_basic " Thomas Gummerer
2012-08-02 12:20 ` Nguyen Thai Ngoc Duy
2012-08-02 14:16 ` Thomas Gummerer
2012-08-02 11:01 ` [PATCH 04/16] Modify write functions " Thomas Gummerer
2012-08-02 12:22 ` Nguyen Thai Ngoc Duy
2012-08-02 14:11 ` Thomas Gummerer
2012-08-02 11:01 ` [PATCH 05/16] t2104: Don't fail when index version is 5 Thomas Gummerer
2012-08-03 8:22 ` Thomas Rast
2012-08-03 12:42 ` Thomas Gummerer
2012-08-03 16:12 ` Junio C Hamano
2012-08-02 11:01 ` [PATCH 06/16] t3700: sleep for 1 second, to avoid interfering with the racy code Thomas Gummerer
2012-08-02 11:01 ` [PATCH 07/16] Add documentation of the index-v5 file format Thomas Gummerer
2012-08-02 11:01 ` [PATCH 08/16] Make in-memory format aware of stat_crc Thomas Gummerer
2012-08-02 11:01 ` [PATCH 09/16] Read index-v5 Thomas Gummerer
2012-08-02 12:45 ` Nguyen Thai Ngoc Duy
2012-08-02 14:04 ` Thomas Gummerer
2012-08-02 11:02 ` [PATCH 10/16] Read resolve-undo data Thomas Gummerer
2012-08-02 11:02 ` Thomas Gummerer [this message]
2012-08-03 8:31 ` [PATCH 11/16] Read cache-tree in index-v5 Thomas Rast
2012-08-03 12:41 ` Thomas Gummerer
2012-08-02 11:02 ` [PATCH 12/16] Write index-v5 Thomas Gummerer
2012-08-02 11:02 ` [PATCH 13/16] Write index-v5 cache-tree data Thomas Gummerer
2012-08-02 11:02 ` [PATCH 14/16] Write resolve-undo data for index-v5 Thomas Gummerer
2012-08-02 11:02 ` [PATCH 15/16] update-index.c: add a force-rewrite option Thomas Gummerer
2012-08-02 11:02 ` [PATCH 16/16] p0002-index.sh: add perf test for the index formats Thomas Gummerer
2012-08-02 12:50 ` Nguyen Thai Ngoc Duy
2012-08-02 13:56 ` Thomas Gummerer
2012-08-02 12:10 ` [RFC 0/16] Introduce index file format version 5 Nguyen Thai Ngoc Duy
2012-08-02 13:47 ` Thomas Gummerer
2012-08-02 13:53 ` Nguyen Thai Ngoc Duy
2012-08-03 3:16 ` Nguyen Thai Ngoc Duy
2012-08-03 12:46 ` Thomas Gummerer
2012-08-03 9:13 ` Thomas Rast
2012-08-03 12:34 ` Thomas Gummerer
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1343905326-23790-12-git-send-email-t.gummerer@gmail.com \
--to=t.gummerer@gmail.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=mhagger@alum.mit.edu \
--cc=pclouds@gmail.com \
--cc=robin.rosenberg@dewire.com \
--cc=trast@student.ethz.ch \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).