1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
|
From 8e55634b47858f036ca773f3e1d754e5dbd4bb59 Mon Sep 17 00:00:00 2001
Message-Id: <8e55634b47858f036ca773f3e1d754e5dbd4bb59.1647334702.git.ps@pks.im>
In-Reply-To: <4de656263aa195080495fc0a103351b9eaac8160.1647334702.git.ps@pks.im>
References: <4de656263aa195080495fc0a103351b9eaac8160.1647334702.git.ps@pks.im>
From: Patrick Steinhardt <ps@pks.im>
Date: Tue, 1 Mar 2022 10:33:41 +0100
Subject: [PATCH 36/39] fetch: avoid lookup of commits when not appending to
FETCH_HEAD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When fetching from a remote repository we will by default write what has
been fetched into the special FETCH_HEAD reference. The order in which
references are written depends on whether the reference is for merge or
not, which, despite some other conditions, is also determined based on
whether the old object ID the reference is being updated from actually
exists in the repository.
To write FETCH_HEAD we thus loop through all references thrice: once for
the references that are about to be merged, once for the references that
are not for merge, and finally for all references that are ignored. For
every iteration, we then look up the old object ID to determine whether
the referenced object exists so that we can label it as "not-for-merge"
if it doesn't exist. It goes without saying that this can be expensive
in case where we are fetching a lot of references.
While this is hard to avoid in the case where we're writing FETCH_HEAD,
users can in fact ask us to skip this work via `--no-write-fetch-head`.
In that case, we do not care for the result of those lookups at all
because we don't have to order writes to FETCH_HEAD in the first place.
Skip this busywork in case we're not writing to FETCH_HEAD. The
following benchmark performs a mirror-fetch in a repository with about
two million references via `git fetch --prune --no-write-fetch-head
+refs/*:refs/*`:
Benchmark 1: HEAD~
Time (mean ± σ): 75.388 s ± 1.942 s [User: 71.103 s, System: 8.953 s]
Range (min … max): 73.184 s … 76.845 s 3 runs
Benchmark 2: HEAD
Time (mean ± σ): 69.486 s ± 1.016 s [User: 65.941 s, System: 8.806 s]
Range (min … max): 68.864 s … 70.659 s 3 runs
Summary
'HEAD' ran
1.08 ± 0.03 times faster than 'HEAD~'
Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
builtin/fetch.c | 42 +++++++++++++++++++++++++++---------------
1 file changed, 27 insertions(+), 15 deletions(-)
diff --git a/builtin/fetch.c b/builtin/fetch.c
index ec1ec91da2..3d4581d3c6 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -1143,7 +1143,6 @@ static int store_updated_refs(const char *raw_url, const char *remote_name,
want_status <= FETCH_HEAD_IGNORE;
want_status++) {
for (rm = ref_map; rm; rm = rm->next) {
- struct commit *commit = NULL;
struct ref *ref = NULL;
if (rm->status == REF_STATUS_REJECT_SHALLOW) {
@@ -1154,21 +1153,34 @@ static int store_updated_refs(const char *raw_url, const char *remote_name,
}
/*
- * References in "refs/tags/" are often going to point
- * to annotated tags, which are not part of the
- * commit-graph. We thus only try to look up refs in
- * the graph which are not in that namespace to not
- * regress performance in repositories with many
- * annotated tags.
+ * When writing FETCH_HEAD we need to determine whether
+ * we already have the commit or not. If not, then the
+ * reference is not for merge and needs to be written
+ * to the reflog after other commits which we already
+ * have. We're not interested in this property though
+ * in case FETCH_HEAD is not to be updated, so we can
+ * skip the classification in that case.
*/
- if (!starts_with(rm->name, "refs/tags/"))
- commit = lookup_commit_in_graph(the_repository, &rm->old_oid);
- if (!commit) {
- commit = lookup_commit_reference_gently(the_repository,
- &rm->old_oid,
- 1);
- if (!commit)
- rm->fetch_head_status = FETCH_HEAD_NOT_FOR_MERGE;
+ if (fetch_head->fp) {
+ struct commit *commit = NULL;
+
+ /*
+ * References in "refs/tags/" are often going to point
+ * to annotated tags, which are not part of the
+ * commit-graph. We thus only try to look up refs in
+ * the graph which are not in that namespace to not
+ * regress performance in repositories with many
+ * annotated tags.
+ */
+ if (!starts_with(rm->name, "refs/tags/"))
+ commit = lookup_commit_in_graph(the_repository, &rm->old_oid);
+ if (!commit) {
+ commit = lookup_commit_reference_gently(the_repository,
+ &rm->old_oid,
+ 1);
+ if (!commit)
+ rm->fetch_head_status = FETCH_HEAD_NOT_FOR_MERGE;
+ }
}
if (rm->fetch_head_status != want_status)
--
2.35.1
|
