From 06b6d81b7929ce6f5542ba869e7bb9d8e437e6f8 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 19 Apr 2017 17:06:17 +0000 Subject: [PATCH] read-cache: speed up has_dir_name (part 1) Teach has_dir_name() to see if the path of the new item is greater than the last path in the index array before attempting to search for it. has_dir_name() is looking for file/directory collisions in the index and has to consider each sub-directory prefix in turn. This can cause multiple binary searches for each path. During operations like checkout, merge_working_tree() populates the new index in sorted order, so we expect to be able to append in many cases. This commit is part 1 of 2. This commit handles the top of has_dir_name() and the trivial optimization. Signed-off-by: Jeff Hostetler Signed-off-by: Junio C Hamano --- read-cache.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/read-cache.c b/read-cache.c index 836338b3ba..5aa097afb7 100644 --- a/read-cache.c +++ b/read-cache.c @@ -910,6 +910,9 @@ int strcmp_offset(const char *s1, const char *s2, size_t *first_change) /* * Do we have another file with a pathname that is a proper * subset of the name we're trying to add? + * + * That is, is there another file in the index with a path + * that matches a sub-directory in the given entry? */ static int has_dir_name(struct index_state *istate, const struct cache_entry *ce, int pos, int ok_to_replace) @@ -918,6 +921,48 @@ static int has_dir_name(struct index_state *istate, int stage = ce_stage(ce); const char *name = ce->name; const char *slash = name + ce_namelen(ce); + size_t len_eq_last; + int cmp_last = 0; + + /* + * We are frequently called during an iteration on a sorted + * list of pathnames and while building a new index. Therefore, + * there is a high probability that this entry will eventually + * be appended to the index, rather than inserted in the middle. + * If we can confirm that, we can avoid binary searches on the + * components of the pathname. + * + * Compare the entry's full path with the last path in the index. + */ + if (istate->cache_nr > 0) { + cmp_last = strcmp_offset(name, + istate->cache[istate->cache_nr - 1]->name, + &len_eq_last); + if (cmp_last > 0) { + if (len_eq_last == 0) { + /* + * The entry sorts AFTER the last one in the + * index and their paths have no common prefix, + * so there cannot be a F/D conflict. + */ + return retval; + } else { + /* + * The entry sorts AFTER the last one in the + * index, but has a common prefix. Fall through + * to the loop below to disect the entry's path + * and see where the difference is. + */ + } + } else if (cmp_last == 0) { + /* + * The entry exactly matches the last one in the + * index, but because of multiple stage and CE_REMOVE + * items, we fall through and let the regular search + * code handle it. + */ + } + } for (;;) { int len; -- 2.11.4.GIT