sha1_name: unroll len loop in find_unique_abbrev_r()
Unroll the while loop inside find_unique_abbrev_r to avoid iterating through all loose objects and packfiles multiple times when the short name is longer than the predicted length. Instead, inspect each object that collides with the estimated abbreviation to find the longest common prefix. The focus of this change is to refactor the existing method in a way that clearly does not change the current behavior. In some cases, the new method is slower than the previous method. Later changes will correct all performance loss. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Derrick Stolee committed
Oct 8, 2017 at 14:49 UTC
5b20ace6a81e5fe1366b07c51b1f577f356a20ff
1 file changed
+42
-15
sha1_name.c
+42
-15
@@ -474,10 +474,32 @@ static unsigned msb(unsigned long val)
474
return r;
475
}
476
477
-int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)
477
+struct min_abbrev_data {
478
+ unsigned int init_len;
479
+ unsigned int cur_len;
480
+ char *hex;
481
+};
482
+
483
+static int extend_abbrev_len(const struct object_id *oid, void *cb_data)
484
{
479
- int status, exists;
485
+ struct min_abbrev_data *mad = cb_data;
486
+
487
+ char *hex = oid_to_hex(oid);
488
+ unsigned int i = mad->init_len;
489
+ while (mad->hex[i] && mad->hex[i] == hex[i])
490
+ i++;
491
+
492
+ if (i < GIT_MAX_RAWSZ && i >= mad->cur_len)
493
+ mad->cur_len = i + 1;
494
+
495
+ return 0;
496
+}
497
498
+int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)
499
+{
500
+ struct disambiguate_state ds;
501
+ struct min_abbrev_data mad;
502
+ struct object_id oid_ret;
503
if (len < 0) {
504
unsigned long count = approximate_object_count();
505
/*
@@ -503,19 +525,24 @@ int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)
525
sha1_to_hex_r(hex, sha1);
526
if (len == GIT_SHA1_HEXSZ || !len)
527
return GIT_SHA1_HEXSZ;
506
- exists = has_sha1_file(sha1);
507
- while (len < GIT_SHA1_HEXSZ) {
508
- struct object_id oid_ret;
509
- status = get_short_oid(hex, len, &oid_ret, GET_OID_QUIETLY);
510
- if (exists
511
- ? !status
512
- : status == SHORT_NAME_NOT_FOUND) {
513
- hex[len] = 0;
514
- return len;
515
- }
516
- len++;
517
- }
518
- return len;
528
+
529
+ if (init_object_disambiguation(hex, len, &ds) < 0)
530
+ return -1;
531
+
532
+ mad.init_len = len;
533
+ mad.cur_len = len;
534
+ mad.hex = hex;
535
+
536
+ ds.fn = extend_abbrev_len;
537
+ ds.always_call_fn = 1;
538
+ ds.cb_data = (void *)&mad;
539
+
540
+ find_short_object_filename(&ds);
541
+ find_short_packed_object(&ds);
542
+ (void)finish_object_disambiguation(&ds, &oid_ret);
543
+
544
+ hex[mad.cur_len] = 0;
545
+ return mad.cur_len;
546
}
547
548
const char *find_unique_abbrev(const unsigned char *sha1, int len)