From b65982b60876c8f5f4d3b2898d5174f4812552b1 Mon Sep 17 00:00:00 2001
From: Junio C Hamano <gitster@pobox.com>
Date: Wed, 20 May 2009 15:57:22 -0700
Subject: 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>
---
 cache-tree.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'cache-tree.c')

diff --git a/cache-tree.c b/cache-tree.c
index 5481e4334..16a65dfac 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -631,3 +631,35 @@ void prime_cache_tree(struct cache_tree **it, struct tree *tree)
 	*it = cache_tree();
 	prime_cache_tree_rec(*it, tree);
 }
+
+/*
+ * find the cache_tree that corresponds to the current level without
+ * exploding the full path into textual form.  The root of the
+ * cache tree is given as "root", and our current level is "info".
+ * (1) When at root level, info->prev is NULL, so it is "root" itself.
+ * (2) Otherwise, find the cache_tree that corresponds to one level
+ *     above us, and find ourselves in there.
+ */
+static struct cache_tree *find_cache_tree_from_traversal(struct cache_tree *root,
+							 struct traverse_info *info)
+{
+	struct cache_tree *our_parent;
+
+	if (!info->prev)
+		return root;
+	our_parent = find_cache_tree_from_traversal(root, info->prev);
+	return cache_tree_find(our_parent, info->name.path);
+}
+
+int cache_tree_matches_traversal(struct cache_tree *root,
+				 struct name_entry *ent,
+				 struct traverse_info *info)
+{
+	struct cache_tree *it;
+
+	it = find_cache_tree_from_traversal(root, info);
+	it = cache_tree_find(it, ent->path);
+	if (it && it->entry_count > 0 && !hashcmp(ent->sha1, it->sha1))
+		return it->entry_count;
+	return 0;
+}
-- 
cgit v1.2.1