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 | 0.06 s | 0.05 s | -16.7% |
| Git | 5 | 230162 | 0 | 0.08 s | 0.08 s | 0.0% |
| Git | 4 | 154310 | 75852 | 0.07 s | 0.06 s | -14.3% |
| Linux | 1 | 5606645 | 0 | 0.32 s | 0.14 s | -56.3% |
| Linux | 24 | 5606645 | 0 | 1.12 s | 0.94 s | -16.1% |
| Linux | 23 | 5283204 | 323441 | 1.05 s | 0.86 s | -18.1% |
| VSTS | 1 | 4355923 | 0 | 0.23 s | 0.11 s | -52.2% |
| VSTS | 32 | 4355923 | 0 | 1.08 s | 0.95 s | -12.0% |
| VSTS | 31 | 4276829 | 79094 | 2.08 s | 1.82 s | -12.5% |
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 | 0.08 s | 0.07 s | -12.5% |
| Git | 5 | 230162 | 0 | 0.13 s | 0.12 s | - 7.7% |
| Git | 4 | 154310 | 75852 | 0.10 s | 0.09 s | -10.0% |
| Linux | 1 | 5606645 | 0 | 0.32 s | 0.13 s | -59.4% |
| Linux | 24 | 5606645 | 0 | 1.09 s | 0.89 s | -18.3% |
| Linux | 23 | 5283204 | 323441 | 0.99 s | 0.83 s | -16.2% |
| VSTS | 1 | 4355923 | 0 | 0.25 s | 0.11 s | -56.0% |
| VSTS | 32 | 4355923 | 0 | 1.15 s | 0.99 s | -13.9% |
| VSTS | 31 | 4276829 | 79094 | 1.18 s | 1.02 s | -13.6% |
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 <dstolee@xxxxxxxxxxxxx>
---
sha1_name.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/sha1_name.c b/sha1_name.c
index f2a1ebe49..5081aeb71 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -480,13 +480,23 @@ struct min_abbrev_data {
char *hex;
};
+static inline char get_hex_char_from_oid(const struct object_id *oid,
+ int pos)
+{
+ static const char hex[] = "0123456789abcdef";
+
+ if ((pos & 1) == 0)
+ return hex[oid->hash[pos >> 1] >> 4];
+ else
+ return hex[oid->hash[pos >> 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
