From 0aaf05b3bdc1ce48bed9f8dcba54153a2b7cdc09 Mon Sep 17 00:00:00 2001
From: Derrick Stolee <dstolee@microsoft.com>
Date: Thu, 22 Mar 2018 13:40:10 -0400
Subject: [PATCH] sha1_name: use bsearch_pack() for abbreviations
When computing abbreviation lengths for an object ID against a single
packfile, the method find_abbrev_len_for_pack() currently implements
binary search. This is one of several implementations. One issue with
this implementation is that it ignores the fanout table in the pack-
index.
Translate this binary search to use the existing bsearch_pack() method
that correctly uses a fanout table.
Due to the use of the fanout table, the abbreviation computation is
slightly faster than before. For a fully-repacked copy of the Linux
repo, the following 'git log' commands improved:
* git log --oneline --parents --raw
Before: 59.2s
After: 56.9s
Rel %: -3.8%
* git log --oneline --parents
Before: 6.48s
After: 5.91s
Rel %: -8.9%
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
sha1_name.c | 24 ++++--------------------
1 file changed, 4 insertions(+), 20 deletions(-)
diff --git a/sha1_name.c b/sha1_name.c
index 16e0003396..24894b3dbe 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -512,32 +512,16 @@ static void find_abbrev_len_for_pack(struct packed_git *p,
struct min_abbrev_data *mad)
{
int match = 0;
- uint32_t num, last, first = 0;
+ uint32_t num, first = 0;
struct object_id oid;
+ const struct object_id *mad_oid;
if (open_pack_index(p) || !p->num_objects)
return;
num = p->num_objects;
- last = num;
- while (first < last) {
- uint32_t mid = first + (last - first) / 2;
- const unsigned char *current;
- int cmp;
-
- current = nth_packed_object_sha1(p, mid);
- cmp = hashcmp(mad->oid->hash, current);
- if (!cmp) {
- match = 1;
- first = mid;
- break;
- }
- if (cmp > 0) {
- first = mid + 1;
- continue;
- }
- last = mid;
- }
+ mad_oid = mad->oid;
+ match = bsearch_pack(mad_oid, p, &first);
/*
* first is now the position in the packfile where we would insert