From: Julian Phillips <julian@quantumfyre.co.uk>
To: git@vger.kernel.org
Cc: Junio C Hamano <gitster@pobox.com>
Subject: [RFC/PATCH v2] fetch: Speed up fetch by rewriting find_non_local_tags
Date: Wed, 16 Sep 2009 23:53:49 +0100 [thread overview]
Message-ID: <20090916225350.45746.85139.julian@quantumfyre.co.uk> (raw)
In-Reply-To: <alpine.LNX.2.00.0909162141140.13697@reaper.quantumfyre.co.uk>
When trying to get a list of remote tags to see if we need to fetch
any we were doing a linear search for the matching tag ref for the
tag^{} commit entries. This proves to be incredibly slow for large
numbers of tags. Rewrite the function so that we can do lookup in
string_lists instead.
For a repository with 50000 tags (and just a single commit on a single
branch), a fetch that does nothing goes from ~ 1m50s to ~4.2s.
Signed-off-by: Julian Phillips <julian@quantumfyre.co.uk>
---
Not only does this not require a custom hash table, it is also slightly
faster than the last version (~4.2s vs ~4.5s).
If nothing else, having rewritten it completely, at least I now
understand what the old find_non_local_tags function was actually doing
... ;)
builtin-fetch.c | 85 ++++++++++++++++++++++++++++++++++++++-----------------
1 files changed, 59 insertions(+), 26 deletions(-)
diff --git a/builtin-fetch.c b/builtin-fetch.c
index cb48c57..c9a2563 100644
--- a/builtin-fetch.c
+++ b/builtin-fetch.c
@@ -504,57 +504,90 @@ static int will_fetch(struct ref **head, const unsigned char *sha1)
return 0;
}
+struct tag_data {
+ struct ref **head;
+ struct ref ***tail;
+ struct string_list *refs;
+};
+
+static int add_to_tail(struct string_list_item *item, void *cb_data)
+{
+ struct tag_data *data = (struct tag_data *)cb_data;
+ unsigned char *commit = (unsigned char *)item->util;
+ struct ref *rm = NULL;
+ struct string_list_item *sli;
+
+ /* Tag objects will have the commit sha1 associated with the peeled
+ * ref, if there is not a peeled ref then the ref is probably a
+ * lightweight tag and so refers to a commit directly */
+ sli = string_list_lookup(item->string, data->refs);
+ if (sli)
+ commit = sli->util;
+
+ /* skip over tags that we don't have the commits for. */
+ if (!has_sha1_file(commit) && !will_fetch(data->head, commit))
+ return 0;
+
+ rm = alloc_ref(item->string);
+ rm->peer_ref = alloc_ref(item->string);
+ hashcpy(rm->old_sha1, item->util);
+
+ **data->tail = rm;
+ *data->tail = &rm->next;
+
+ return 0;
+}
+
static void find_non_local_tags(struct transport *transport,
struct ref **head,
struct ref ***tail)
{
struct string_list existing_refs = { NULL, 0, 0, 0 };
- struct string_list new_refs = { NULL, 0, 0, 1 };
+ struct string_list peeled_refs = { NULL, 0, 0, 1 };
+ struct string_list remote_refs = { NULL, 0, 0, 1 };
+ struct tag_data data = {head, tail, &peeled_refs};
+ struct string_list *refs;
char *ref_name;
int ref_name_len;
- const unsigned char *ref_sha1;
- const struct ref *tag_ref;
- struct ref *rm = NULL;
const struct ref *ref;
+ struct string_list_item *item;
for_each_ref(add_existing, &existing_refs);
for (ref = transport_get_remote_refs(transport); ref; ref = ref->next) {
if (prefixcmp(ref->name, "refs/tags"))
continue;
+ /* skip duplicates */
+ if (string_list_lookup(ref->name, &remote_refs))
+ continue;
+
+ refs = &remote_refs;
ref_name = xstrdup(ref->name);
ref_name_len = strlen(ref_name);
- ref_sha1 = ref->old_sha1;
+ /* we want to store peeled refs by the base ref name in the
+ * peeled_refs string list */
if (!strcmp(ref_name + ref_name_len - 3, "^{}")) {
ref_name[ref_name_len - 3] = 0;
- tag_ref = transport_get_remote_refs(transport);
- while (tag_ref) {
- if (!strcmp(tag_ref->name, ref_name)) {
- ref_sha1 = tag_ref->old_sha1;
- break;
- }
- tag_ref = tag_ref->next;
- }
+ refs = &peeled_refs;
}
- if (!string_list_has_string(&existing_refs, ref_name) &&
- !string_list_has_string(&new_refs, ref_name) &&
- (has_sha1_file(ref->old_sha1) ||
- will_fetch(head, ref->old_sha1))) {
- string_list_insert(ref_name, &new_refs);
-
- rm = alloc_ref(ref_name);
- rm->peer_ref = alloc_ref(ref_name);
- hashcpy(rm->old_sha1, ref_sha1);
-
- **tail = rm;
- *tail = &rm->next;
+ /* ignore refs that we already have */
+ if (!string_list_has_string(&existing_refs, ref_name)) {
+ item = string_list_insert(ref_name, refs);
+ item->util = (void *)ref->old_sha1;
}
+
free(ref_name);
}
+
+ /* For all the tags in the remote_refs string list, call add_to_tail to
+ * add them to the list of refs to be fetched */
+ for_each_string_list(add_to_tail, &remote_refs, &data);
+
string_list_clear(&existing_refs, 0);
- string_list_clear(&new_refs, 0);
+ string_list_clear(&peeled_refs, 0);
+ string_list_clear(&remote_refs, 0);
}
static void check_not_current_branch(struct ref *ref_map)
--
1.6.4.2
next prev parent reply other threads:[~2009-09-16 22:58 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-16 7:53 [RFC/PATCH 0/2] Speed up fetch with large number of tags Julian Phillips
2009-09-16 7:53 ` [RFC/PATCH 1/2] ref-dict: Add a set of functions for working with a ref dictionary Julian Phillips
2009-09-16 7:53 ` [RFC/PATCH 2/2] fetch: Speed up fetch by using " Julian Phillips
2009-09-16 9:44 ` [RFC/PATCH 0/2] Speed up fetch with large number of tags Junio C Hamano
2009-09-16 22:32 ` Julian Phillips
2009-09-16 22:42 ` Shawn O. Pearce
2009-09-16 22:52 ` Junio C Hamano
2009-09-16 23:03 ` Shawn O. Pearce
2009-09-16 23:19 ` Junio C Hamano
2009-09-16 22:53 ` Julian Phillips [this message]
2009-09-16 23:15 ` [RFC/PATCH v2] fetch: Speed up fetch by rewriting find_non_local_tags Junio C Hamano
2009-09-16 23:46 ` Julian Phillips
2009-09-17 1:30 ` Julian Phillips
2009-09-17 7:13 ` Johan Herland
2009-09-17 7:33 ` [RFC/PATCH v3] " Julian Phillips
2009-09-16 22:46 ` [RFC/PATCH 0/2] Speed up fetch with large number of tags Shawn O. Pearce
2009-09-22 20:36 ` Junio C Hamano
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
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20090916225350.45746.85139.julian@quantumfyre.co.uk \
--to=julian@quantumfyre.co.uk \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
/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.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
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 read-only IMAP folder(s) and NNTP newsgroup(s).