summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLibravatar Brandon Casey <drafnel@gmail.com>2013-07-08 01:58:39 -0700
committerLibravatar Junio C Hamano <gitster@pobox.com>2013-07-08 09:04:31 -0700
commitf1bd15ab1553de76f297b8566b5779c43e3bfe2a (patch)
tree9517a543ead79ae3d2609f4af5e61a47e808cbb7
parentGit 1.8.3 (diff)
downloadtgif-f1bd15ab1553de76f297b8566b5779c43e3bfe2a.tar.xz
remote.c: avoid O(m*n) behavior in match_push_refs
When pushing using a matching refspec or a pattern refspec, each ref in the local repository must be paired with a ref advertised by the remote server. This is accomplished by using the refspec to transform the name of the local ref into the name it should have in the remote repository, and then performing a linear search through the list of remote refs to see if the remote ref was advertised by the remote system. Each of these lookups has O(n) complexity and makes match_push_refs() be an O(m*n) operation, where m is the number of local refs and n is the number of remote refs. If there are many refs 100,000+, then this ref matching can take a significant amount of time. Let's prepare an index of the remote refs to allow searching in O(log n) time and reduce the complexity of match_push_refs() to O(m log n). We prepare the index lazily so that it is only created when necessary. So, there should be no impact when _not_ using a matching or pattern refspec, i.e. when pushing using only explicit refspecs. Dry-run push of a repository with 121,913 local and remote refs: before after real 1m40.582s 0m0.804s user 1m39.914s 0m0.515s sys 0m0.125s 0m0.106s The creation of the index has overhead. So, if there are very few local refs, then it could take longer to create the index than it would have taken to just perform n linear lookups into the remote ref space. Using the index should provide some improvement when the number of local refs is roughly greater than the log of the number of remote refs (i.e. m >= log n). The pathological case is when there is a single local ref and very many remote refs. Dry-run push of a repository with 121,913 remote refs and a single local ref: before after real 0m0.525s 0m0.566s user 0m0.243s 0m0.279s sys 0m0.075s 0m0.099s Using an index takes 41 ms longer, or roughly 7.8% longer. Jeff King measured a no-op push of a single ref into a remote repo with 370,000 refs: before after real 0m1.087s 0m1.156s user 0m1.344s 0m1.412s sys 0m0.288s 0m0.284s Using an index takes 69 ms longer, or roughly 6.3% longer. None of the measurements above required transferring any objects to the remote repository. If the push required transferring objects and updating the refs in the remote repository, the impact of preparing the search index would be even smaller. A similar operation is performed in the reverse direction when pruning using a matching or pattern refspec. Let's avoid O(m*n) behavior in the same way by lazily preparing an index on the local refs. Signed-off-by: Brandon Casey <drafnel@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--remote.c27
1 files changed, 25 insertions, 2 deletions
diff --git a/remote.c b/remote.c
index 68eb99bdf0..61de31a034 100644
--- a/remote.c
+++ b/remote.c
@@ -1317,6 +1317,14 @@ static void add_missing_tags(struct ref *src, struct ref **dst, struct ref ***ds
free(sent_tips.tip);
}
+static void prepare_ref_index(struct string_list *ref_index, struct ref *ref)
+{
+ for ( ; ref; ref = ref->next)
+ string_list_append_nodup(ref_index, ref->name)->util = ref;
+
+ sort_string_list(ref_index);
+}
+
/*
* Given the set of refs the local repository has, the set of refs the
* remote repository has, and the refspec used for push, determine
@@ -1335,6 +1343,7 @@ int match_push_refs(struct ref *src, struct ref **dst,
int errs;
static const char *default_refspec[] = { ":", NULL };
struct ref *ref, **dst_tail = tail_ref(dst);
+ struct string_list dst_ref_index = STRING_LIST_INIT_NODUP;
if (!nr_refspec) {
nr_refspec = 1;
@@ -1345,6 +1354,7 @@ int match_push_refs(struct ref *src, struct ref **dst,
/* pick the remainder */
for (ref = src; ref; ref = ref->next) {
+ struct string_list_item *dst_item;
struct ref *dst_peer;
const struct refspec *pat = NULL;
char *dst_name;
@@ -1353,7 +1363,11 @@ int match_push_refs(struct ref *src, struct ref **dst,
if (!dst_name)
continue;
- dst_peer = find_ref_by_name(*dst, dst_name);
+ if (!dst_ref_index.nr)
+ prepare_ref_index(&dst_ref_index, *dst);
+
+ dst_item = string_list_lookup(&dst_ref_index, dst_name);
+ dst_peer = dst_item ? dst_item->util : NULL;
if (dst_peer) {
if (dst_peer->peer_ref)
/* We're already sending something to this ref. */
@@ -1370,6 +1384,8 @@ int match_push_refs(struct ref *src, struct ref **dst,
/* Create a new one and link it */
dst_peer = make_linked_ref(dst_name, &dst_tail);
hashcpy(dst_peer->new_sha1, ref->new_sha1);
+ string_list_insert(&dst_ref_index,
+ dst_peer->name)->util = dst_peer;
}
dst_peer->peer_ref = copy_ref(ref);
dst_peer->force = pat->force;
@@ -1377,10 +1393,13 @@ int match_push_refs(struct ref *src, struct ref **dst,
free(dst_name);
}
+ string_list_clear(&dst_ref_index, 0);
+
if (flags & MATCH_REFS_FOLLOW_TAGS)
add_missing_tags(src, dst, &dst_tail);
if (send_prune) {
+ struct string_list src_ref_index = STRING_LIST_INIT_NODUP;
/* check for missing refs on the remote */
for (ref = *dst; ref; ref = ref->next) {
char *src_name;
@@ -1391,11 +1410,15 @@ int match_push_refs(struct ref *src, struct ref **dst,
src_name = get_ref_match(rs, nr_refspec, ref, send_mirror, FROM_DST, NULL);
if (src_name) {
- if (!find_ref_by_name(src, src_name))
+ if (!src_ref_index.nr)
+ prepare_ref_index(&src_ref_index, src);
+ if (!string_list_has_string(&src_ref_index,
+ src_name))
ref->peer_ref = alloc_delete_ref();
free(src_name);
}
}
+ string_list_clear(&src_ref_index, 0);
}
if (errs)
return -1;