refs/reftable: don't recompute committer ident
In order to write reflog entries we need to compute the committer's identity as it gets encoded in the log record itself. The reftable backend does this via `git_committer_info()` and `split_ident_line()` in `fill_reftable_log_record()`, which use the Git config as well as environment variables to figure out the identity. While most callers would only call `fill_reftable_log_record()` once or twice, `write_transaction_table()` will call it as many times as there are queued ref updates. This can be quite a waste of effort when writing many refs with reflog entries in a single transaction. Refactor the code to pre-compute the committer information. This results in a small speedup when writing 100000 refs in a single transaction: Benchmark 1: update-ref: create many refs (HEAD~) Time (mean ± σ): 2.895 s ± 0.020 s [User: 1.516 s, System: 1.374 s] Range (min … max): 2.868 s … 2.983 s 100 runs Benchmark 2: update-ref: create many refs (HEAD) Time (mean ± σ): 2.845 s ± 0.017 s [User: 1.461 s, System: 1.379 s] Range (min … max): 2.803 s … 2.913 s 100 runs Summary update-ref: create many refs (HEAD) ran 1.02 ± 0.01 times faster than update-ref: create many refs (HEAD~) Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Patrick Steinhardt committed
Apr 8, 2024 at 14:24 UTC
44afd85fbd4cf69a0f030df98b3626f82e51bb33
1 file changed
+34
-18
refs/reftable-backend.c
+34
-18
@@ -171,32 +171,30 @@ static int should_write_log(struct ref_store *refs, const char *refname)
171
}
172
}
173
174
-static void fill_reftable_log_record(struct reftable_log_record *log)
174
+static void fill_reftable_log_record(struct reftable_log_record *log, const struct ident_split *split)
175
{
176
- const char *info = git_committer_info(0);
177
- struct ident_split split = {0};
176
+ const char *tz_begin;
177
int sign = 1;
178
180
- if (split_ident_line(&split, info, strlen(info)))
181
- BUG("failed splitting committer info");
182
-
179
reftable_log_record_release(log);
180
log->value_type = REFTABLE_LOG_UPDATE;
181
log->value.update.name =
186
- xstrndup(split.name_begin, split.name_end - split.name_begin);
182
+ xstrndup(split->name_begin, split->name_end - split->name_begin);
183
log->value.update.email =
188
- xstrndup(split.mail_begin, split.mail_end - split.mail_begin);
189
- log->value.update.time = atol(split.date_begin);
190
- if (*split.tz_begin == '-') {
184
+ xstrndup(split->mail_begin, split->mail_end - split->mail_begin);
185
+ log->value.update.time = atol(split->date_begin);
186
+
187
+ tz_begin = split->tz_begin;
188
+ if (*tz_begin == '-') {
189
sign = -1;
192
- split.tz_begin++;
190
+ tz_begin++;
191
}
194
- if (*split.tz_begin == '+') {
192
+ if (*tz_begin == '+') {
193
sign = 1;
196
- split.tz_begin++;
194
+ tz_begin++;
195
}
196
199
- log->value.update.tz_offset = sign * atoi(split.tz_begin);
197
+ log->value.update.tz_offset = sign * atoi(tz_begin);
198
}
199
200
static int read_ref_without_reload(struct reftable_stack *stack,
@@ -1018,9 +1016,15 @@ static int write_transaction_table(struct reftable_writer *writer, void *cb_data
1016
reftable_stack_merged_table(arg->stack);
1017
uint64_t ts = reftable_stack_next_update_index(arg->stack);
1018
struct reftable_log_record *logs = NULL;
1019
+ struct ident_split committer_ident = {0};
1020
size_t logs_nr = 0, logs_alloc = 0, i;
1021
+ const char *committer_info;
1022
int ret = 0;
1023
1024
+ committer_info = git_committer_info(0);
1025
+ if (split_ident_line(&committer_ident, committer_info, strlen(committer_info)))
1026
+ BUG("failed splitting committer info");
1027
+
1028
QSORT(arg->updates, arg->updates_nr, transaction_update_cmp);
1029
1030
reftable_writer_set_limits(writer, ts, ts);
@@ -1086,7 +1090,7 @@ static int write_transaction_table(struct reftable_writer *writer, void *cb_data
1090
log = &logs[logs_nr++];
1091
memset(log, 0, sizeof(*log));
1092
1089
- fill_reftable_log_record(log);
1093
+ fill_reftable_log_record(log, &committer_ident);
1094
log->update_index = ts;
1095
log->refname = xstrdup(u->refname);
1096
memcpy(log->value.update.new_hash, u->new_oid.hash, GIT_MAX_RAWSZ);
@@ -1233,9 +1237,11 @@ static int write_create_symref_table(struct reftable_writer *writer, void *cb_da
1237
.value.symref = (char *)create->target,
1238
.update_index = ts,
1239
};
1240
+ struct ident_split committer_ident = {0};
1241
struct reftable_log_record log = {0};
1242
struct object_id new_oid;
1243
struct object_id old_oid;
1244
+ const char *committer_info;
1245
int ret;
1246
1247
reftable_writer_set_limits(writer, ts, ts);
@@ -1263,7 +1269,11 @@ static int write_create_symref_table(struct reftable_writer *writer, void *cb_da
1269
!should_write_log(&create->refs->base, create->refname))
1270
return 0;
1271
1266
- fill_reftable_log_record(&log);
1272
+ committer_info = git_committer_info(0);
1273
+ if (split_ident_line(&committer_ident, committer_info, strlen(committer_info)))
1274
+ BUG("failed splitting committer info");
1275
+
1276
+ fill_reftable_log_record(&log, &committer_ident);
1277
log.refname = xstrdup(create->refname);
1278
log.update_index = ts;
1279
log.value.update.message = xstrndup(create->logmsg,
@@ -1339,10 +1349,16 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
1349
struct reftable_log_record old_log = {0}, *logs = NULL;
1350
struct reftable_iterator it = {0};
1351
struct string_list skip = STRING_LIST_INIT_NODUP;
1352
+ struct ident_split committer_ident = {0};
1353
struct strbuf errbuf = STRBUF_INIT;
1354
size_t logs_nr = 0, logs_alloc = 0, i;
1355
+ const char *committer_info;
1356
int ret;
1357
1358
+ committer_info = git_committer_info(0);
1359
+ if (split_ident_line(&committer_ident, committer_info, strlen(committer_info)))
1360
+ BUG("failed splitting committer info");
1361
+
1362
if (reftable_stack_read_ref(arg->stack, arg->oldname, &old_ref)) {
1363
ret = error(_("refname %s not found"), arg->oldname);
1364
goto done;
@@ -1417,7 +1433,7 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
1433
1434
ALLOC_GROW(logs, logs_nr + 1, logs_alloc);
1435
memset(&logs[logs_nr], 0, sizeof(logs[logs_nr]));
1420
- fill_reftable_log_record(&logs[logs_nr]);
1436
+ fill_reftable_log_record(&logs[logs_nr], &committer_ident);
1437
logs[logs_nr].refname = (char *)arg->newname;
1438
logs[logs_nr].update_index = deletion_ts;
1439
logs[logs_nr].value.update.message =
@@ -1449,7 +1465,7 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
1465
*/
1466
ALLOC_GROW(logs, logs_nr + 1, logs_alloc);
1467
memset(&logs[logs_nr], 0, sizeof(logs[logs_nr]));
1452
- fill_reftable_log_record(&logs[logs_nr]);
1468
+ fill_reftable_log_record(&logs[logs_nr], &committer_ident);
1469
logs[logs_nr].refname = (char *)arg->newname;
1470
logs[logs_nr].update_index = creation_ts;
1471
logs[logs_nr].value.update.message =