Create get_hex_char_from_oid() to parse oids one hex character at a
time. This prevents unnecessary copying of hex characters in
extend_abbrev_len() when finding the length of a 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 | 0.08 s | 0.08 s | 0.0% |
| Git | 5 | 230162 | 0 | 0.17 s | 0.16 s | - 5.9% |
| Git | 4 | 154310 | 75852 | 0.14 s | 0.12 s | -14.3% |
| Linux | 1 | 5606645 | 0 | 0.50 s | 0.25 s | -50.0% |
| Linux | 24 | 5606645 | 0 | 2.41 s | 2.08 s | -13.7% |
| Linux | 23 | 5283204 | 323441 | 1.99 s | 1.69 s | -15.1% |
| VSTS | 1 | 4355923 | 0 | 0.40 s | 0.22 s | -45.0% |
| VSTS | 32 | 4355923 | 0 | 2.09 s | 1.99 s | - 4.8% |
| VSTS | 31 | 4276829 | 79094 | 3.60 s | 3.20 s | -11.1% |
For the Windows repo running in Windows Subsystem for Linux:
Pack Files: 50
Packed Objects: 22,385,898
Loose Objects: 492
Base Time: 4.61 s
New Time: 4.61 s
Rel %: 0.0%
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 | 0.06 s | 0.05 s | -16.7% |
| Git | 5 | 230162 | 0 | 0.14 s | 0.15 s | + 7.1% |
| Git | 4 | 154310 | 75852 | 0.12 s | 0.12 s | 0.0% |
| Linux | 1 | 5606645 | 0 | 0.40 s | 0.17 s | -57.5% |
| Linux | 24 | 5606645 | 0 | 1.59 s | 1.30 s | -18.2% |
| Linux | 23 | 5283204 | 323441 | 1.23 s | 1.10 s | -10.6% |
| VSTS | 1 | 4355923 | 0 | 0.25 s | 0.12 s | -52.0% |
| VSTS | 32 | 4355923 | 0 | 1.45 s | 1.34 s | - 7.6% |
| VSTS | 31 | 4276829 | 79094 | 1.59 s | 1.34 s | -15.7% |
For the Windows repo running in Windows Subsystem for Linux:
Pack Files: 50
Packed Objects: 22,385,898
Loose Objects: 492
Base Time: 3.91 s
New Time: 3.08 s
Rel %: -21.1%
Signed-off-by: Derrick Stolee <[email protected]>
Signed-off-by: Derrick Stolee <[email protected]>
---
sha1_name.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/sha1_name.c b/sha1_name.c
index f2a1ebe49..bb47b6702 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -480,13 +480,22 @@ struct min_abbrev_data {
char *hex;
};
+static inline char get_hex_char_from_oid(const struct object_id *oid, int i)
+{
+ static const char hex[] = "0123456789abcdef";
+
+ if ((i & 1) == 0)
+ return hex[oid->hash[i >> 1] >> 4];
+ else
+ return hex[oid->hash[i >> 1] & 0xf];
+}
+
static int extend_abbrev_len(const struct object_id *oid, void *cb_data)
{
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])
+ while (mad->hex[i] && mad->hex[i] == get_hex_char_from_oid(oid, i))
i++;
if (i < GIT_MAX_RAWSZ && i >= mad->cur_len)
--
2.14.1.538.g56ec8fc98.dirty
