2006-04-23 23:52:20 +00:00
|
|
|
#ifndef CACHE_TREE_H
|
|
|
|
#define CACHE_TREE_H
|
|
|
|
|
2009-04-20 10:58:18 +00:00
|
|
|
#include "tree.h"
|
Optimize "diff-index --cached" using cache-tree
When running "diff-index --cached" after making a change to only a small
portion of the index, there is no point unpacking unchanged subtrees into
the index recursively, only to find that all entries match anyway. Tweak
unpack_trees() logic that is used to read in the tree object to catch the
case where the tree entry we are looking at matches the index as a whole
by looking at the cache-tree.
As an exercise, after modifying a few paths in the kernel tree, here are
a few numbers on my Athlon 64X2 3800+:
(without patch, hot cache)
$ /usr/bin/time git diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.07user 0.02system 0:00.09elapsed 102%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+9407minor)pagefaults 0swaps
(with patch, hot cache)
$ /usr/bin/time ../git.git/git-diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.02user 0.00system 0:00.02elapsed 103%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+2446minor)pagefaults 0swaps
Cold cache numbers are very impressive, but it does not matter very much
in practice:
(without patch, cold cache)
$ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches'
$ /usr/bin/time git diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.06user 0.17system 0:10.26elapsed 2%CPU (0avgtext+0avgdata 0maxresident)k
247032inputs+0outputs (1172major+8237minor)pagefaults 0swaps
(with patch, cold cache)
$ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches'
$ /usr/bin/time ../git.git/git-diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.02user 0.01system 0:01.01elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k
18440inputs+0outputs (79major+2369minor)pagefaults 0swaps
This of course helps "git status" as well.
(without patch, hot cache)
$ /usr/bin/time ../git.git/git-status >/dev/null
0.17user 0.18system 0:00.35elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+5336outputs (0major+10970minor)pagefaults 0swaps
(with patch, hot cache)
$ /usr/bin/time ../git.git/git-status >/dev/null
0.10user 0.16system 0:00.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+5336outputs (0major+3921minor)pagefaults 0swaps
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-05-20 22:57:22 +00:00
|
|
|
#include "tree-walk.h"
|
2009-04-20 10:58:18 +00:00
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
struct cache_tree;
|
|
|
|
struct cache_tree_sub {
|
|
|
|
struct cache_tree *cache_tree;
|
|
|
|
int namelen;
|
|
|
|
int used;
|
|
|
|
char name[FLEX_ARRAY];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct cache_tree {
|
|
|
|
int entry_count; /* negative means "invalid" */
|
|
|
|
unsigned char sha1[20];
|
|
|
|
int subtree_nr;
|
|
|
|
int subtree_alloc;
|
|
|
|
struct cache_tree_sub **down;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct cache_tree *cache_tree(void);
|
2006-04-25 04:18:58 +00:00
|
|
|
void cache_tree_free(struct cache_tree **);
|
2006-04-23 23:52:20 +00:00
|
|
|
void cache_tree_invalidate_path(struct cache_tree *, const char *);
|
2006-04-27 08:33:07 +00:00
|
|
|
struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *);
|
2006-04-23 23:52:20 +00:00
|
|
|
|
2007-09-25 08:22:44 +00:00
|
|
|
void cache_tree_write(struct strbuf *, struct cache_tree *root);
|
2006-04-25 04:18:58 +00:00
|
|
|
struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
|
2006-04-23 23:52:20 +00:00
|
|
|
|
2006-04-25 04:18:58 +00:00
|
|
|
int cache_tree_fully_valid(struct cache_tree *);
|
2012-01-16 02:36:46 +00:00
|
|
|
int cache_tree_update(struct cache_tree *, struct cache_entry **, int, int);
|
2011-12-06 17:43:37 +00:00
|
|
|
|
|
|
|
int update_main_cache_tree(int);
|
2006-04-23 23:52:20 +00:00
|
|
|
|
2009-05-20 18:04:35 +00:00
|
|
|
/* bitmasks to write_cache_as_tree flags */
|
|
|
|
#define WRITE_TREE_MISSING_OK 1
|
|
|
|
#define WRITE_TREE_IGNORE_CACHE_TREE 2
|
2012-01-16 02:36:46 +00:00
|
|
|
#define WRITE_TREE_DRY_RUN 4
|
|
|
|
#define WRITE_TREE_SILENT 8
|
2009-05-20 18:04:35 +00:00
|
|
|
|
|
|
|
/* error return codes */
|
2008-01-11 06:49:35 +00:00
|
|
|
#define WRITE_TREE_UNREADABLE_INDEX (-1)
|
|
|
|
#define WRITE_TREE_UNMERGED_INDEX (-2)
|
|
|
|
#define WRITE_TREE_PREFIX_ERROR (-3)
|
|
|
|
|
2009-05-20 18:04:35 +00:00
|
|
|
int write_cache_as_tree(unsigned char *sha1, int flags, const char *prefix);
|
2009-04-20 10:58:18 +00:00
|
|
|
void prime_cache_tree(struct cache_tree **, struct tree *);
|
|
|
|
|
Optimize "diff-index --cached" using cache-tree
When running "diff-index --cached" after making a change to only a small
portion of the index, there is no point unpacking unchanged subtrees into
the index recursively, only to find that all entries match anyway. Tweak
unpack_trees() logic that is used to read in the tree object to catch the
case where the tree entry we are looking at matches the index as a whole
by looking at the cache-tree.
As an exercise, after modifying a few paths in the kernel tree, here are
a few numbers on my Athlon 64X2 3800+:
(without patch, hot cache)
$ /usr/bin/time git diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.07user 0.02system 0:00.09elapsed 102%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+9407minor)pagefaults 0swaps
(with patch, hot cache)
$ /usr/bin/time ../git.git/git-diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.02user 0.00system 0:00.02elapsed 103%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+2446minor)pagefaults 0swaps
Cold cache numbers are very impressive, but it does not matter very much
in practice:
(without patch, cold cache)
$ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches'
$ /usr/bin/time git diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.06user 0.17system 0:10.26elapsed 2%CPU (0avgtext+0avgdata 0maxresident)k
247032inputs+0outputs (1172major+8237minor)pagefaults 0swaps
(with patch, cold cache)
$ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches'
$ /usr/bin/time ../git.git/git-diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.02user 0.01system 0:01.01elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k
18440inputs+0outputs (79major+2369minor)pagefaults 0swaps
This of course helps "git status" as well.
(without patch, hot cache)
$ /usr/bin/time ../git.git/git-status >/dev/null
0.17user 0.18system 0:00.35elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+5336outputs (0major+10970minor)pagefaults 0swaps
(with patch, hot cache)
$ /usr/bin/time ../git.git/git-status >/dev/null
0.10user 0.16system 0:00.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+5336outputs (0major+3921minor)pagefaults 0swaps
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-05-20 22:57:22 +00:00
|
|
|
extern int cache_tree_matches_traversal(struct cache_tree *, struct name_entry *ent, struct traverse_info *info);
|
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
#endif
|