[PATCH v3 3/5] sha1_name: Unroll len loop in find_unique_abbrev_r

From: Derrick Stolee <dstolee@microsoft.com>
Date: Oct 2, 2017, 14:56 UTC
Message-ID: <20171002145651.204984-4-dstolee@microsoft.com>
In-Reply-To: <20170925095452.66833-1-dstolee@microsoft.com>

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.

p0008.1: find_unique_abbrev() for existing objects --------------------------------------------------

For 10 repeated tests, each checking 100,000 known objects, we find the following results when running in a Linux VM:

|       | Pack  | Packed  | Loose  | Base   | New    |         |
| Repo  | Files | Objects | Objects| Time   | Time   | Rel%    |
|-------|-------|---------|--------|--------|--------|---------|
| Git   |     1 |  230078 |      0 | 0.09 s | 0.06 s | - 33.3% |
| Git   |     5 |  230162 |      0 | 0.11 s | 0.08 s | - 27.3% |
| Git   |     4 |  154310 |  75852 | 0.09 s | 0.07 s | - 22.2% |
| Linux |     1 | 5606645 |      0 | 0.12 s | 0.32 s | +146.2% |
| Linux |    24 | 5606645 |      0 | 1.12 s | 1.12 s | -  0.9% |
| Linux |    23 | 5283204 | 323441 | 1.08 s | 1.05 s | -  2.8% |
| VSTS  |     1 | 4355923 |      0 | 0.12 s | 0.23 s | + 91.7% |
| VSTS  |    32 | 4355923 |      0 | 1.02 s | 1.08 s | +  5.9% |
| VSTS  |    31 | 4276829 |  79094 | 2.25 s | 2.08 s | -  7.6% |

For the Windows repo running in Windows Subsystem for Linux:

    Pack Files: 50
Packed Objects: 22,385,898
 Loose Objects: 492
     Base Time: 5.69 s
      New Time: 4.62 s
         Rel %: -18.9%

p0008.2: find_unique_abbrev() for missing objects -------------------------------------------------

For 10 repeated tests, each checking 100,000 missing objects, we find the following results when running in a Linux VM:

|       | Pack  | Packed  | Loose  | Base   | New    |        |
| Repo  | Files | Objects | Objects| Time   | Time   | Rel%   |
|-------|-------|---------|--------|--------|--------|--------|
| Git   |     1 |  230078 |      0 | 0.66 s | 0.08 s | -87.9% |
| Git   |     5 |  230162 |      0 | 0.90 s | 0.13 s | -85.6% |
| Git   |     4 |  154310 |  75852 | 0.79 s | 0.10 s | -87.3% |
| Linux |     1 | 5606645 |      0 | 0.48 s | 0.32 s | -33.3% |
| Linux |    24 | 5606645 |      0 | 4.41 s | 1.09 s | -75.3% |
| Linux |    23 | 5283204 | 323441 | 4.11 s | 0.99 s | -75.9% |
| VSTS  |     1 | 4355923 |      0 | 0.46 s | 0.25 s | -45.7% |
| VSTS  |    32 | 4355923 |      0 | 5.40 s | 1.15 s | -78.7% |
| VSTS  |    31 | 4276829 |  79094 | 5.88 s | 1.18 s | -79.9% |

For the Windows repo running in Windows Subsystem for Linux:

    Pack Files: 50
Packed Objects: 22,385,898
 Loose Objects: 492
     Base Time: 39.0 s
      New Time:  3.9 s
         Rel %: -90.0%

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 sha1_name.c | 57 ++++++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 42 insertions(+), 15 deletions(-)

diff --git a/sha1_name.c b/sha1_name.c
index 134ac9742..f2a1ebe49 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -474,10 +474,32 @@ static unsigned msb(unsigned long val)
 	return r;
 }
 
-int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)
+struct min_abbrev_data {
+	unsigned int init_len;
+	unsigned int cur_len;
+	char *hex;
+};
+
+static int extend_abbrev_len(const struct object_id *oid, void *cb_data)
 {
-	int status, exists;
+	struct min_abbrev_data *mad = cb_data;
+
+	char *hex = oid_to_hex(oid);
+	unsigned int i = mad->init_len;
+	while (mad->hex[i] && mad->hex[i] == hex[i])
+		i++;
+
+	if (i < GIT_MAX_RAWSZ && i >= mad->cur_len)
+		mad->cur_len = i + 1;
+
+	return 0;
+}
 
+int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)
+{
+	struct disambiguate_state ds;
+	struct min_abbrev_data mad;
+	struct object_id oid_ret;
 	if (len < 0) {
 		unsigned long count = approximate_object_count();
 		/*
@@ -503,19 +525,24 @@ int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)
 	sha1_to_hex_r(hex, sha1);
 	if (len == GIT_SHA1_HEXSZ || !len)
 		return GIT_SHA1_HEXSZ;
-	exists = has_sha1_file(sha1);
-	while (len < GIT_SHA1_HEXSZ) {
-		struct object_id oid_ret;
-		status = get_short_oid(hex, len, &oid_ret, GET_OID_QUIETLY);
-		if (exists
-		    ? !status
-		    : status == SHORT_NAME_NOT_FOUND) {
-			hex[len] = 0;
-			return len;
-		}
-		len++;
-	}
-	return len;
+
+	if (init_object_disambiguation(hex, len, &ds) < 0)
+		return -1;
+
+	mad.init_len = len;
+	mad.cur_len = len;
+	mad.hex = hex;
+
+	ds.fn = extend_abbrev_len;
+	ds.always_call_fn = 1;
+	ds.cb_data = (void*)&mad;
+
+	find_short_object_filename(&ds);
+	find_short_packed_object(&ds);
+	(void)finish_object_disambiguation(&ds, &oid_ret);
+
+	hex[mad.cur_len] = 0;
+	return mad.cur_len;
 }
 
 const char *find_unique_abbrev(const unsigned char *sha1, int len)

-- 
2.14.1.538.g56ec8fc98.dirty