From: Patrick Steinhardt <ps@pks.im>
To: git@vger.kernel.org
Cc: Junio C Hamano <gitster@pobox.com>, Han-Wen Nienhuys <hanwenn@gmail.com>
Subject: [PATCH v3 05/11] refs/reftable: don't recompute committer ident
Date: Mon, 8 Apr 2024 14:24:11 +0200 [thread overview]
Message-ID: <1ca7d9b6cff2eeceddf2dc1c8cb8f5d0216487cc.1712578837.git.ps@pks.im> (raw)
In-Reply-To: <cover.1712578837.git.ps@pks.im>
[-- Attachment #1: Type: text/plain, Size: 6848 bytes --]
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>
---
refs/reftable-backend.c | 52 +++++++++++++++++++++++++++--------------
1 file changed, 34 insertions(+), 18 deletions(-)
diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c
index 8a54b0d8b2..a5ef36ffa9 100644
--- a/refs/reftable-backend.c
+++ b/refs/reftable-backend.c
@@ -171,32 +171,30 @@ static int should_write_log(struct ref_store *refs, const char *refname)
}
}
-static void fill_reftable_log_record(struct reftable_log_record *log)
+static void fill_reftable_log_record(struct reftable_log_record *log, const struct ident_split *split)
{
- const char *info = git_committer_info(0);
- struct ident_split split = {0};
+ const char *tz_begin;
int sign = 1;
- if (split_ident_line(&split, info, strlen(info)))
- BUG("failed splitting committer info");
-
reftable_log_record_release(log);
log->value_type = REFTABLE_LOG_UPDATE;
log->value.update.name =
- xstrndup(split.name_begin, split.name_end - split.name_begin);
+ xstrndup(split->name_begin, split->name_end - split->name_begin);
log->value.update.email =
- xstrndup(split.mail_begin, split.mail_end - split.mail_begin);
- log->value.update.time = atol(split.date_begin);
- if (*split.tz_begin == '-') {
+ xstrndup(split->mail_begin, split->mail_end - split->mail_begin);
+ log->value.update.time = atol(split->date_begin);
+
+ tz_begin = split->tz_begin;
+ if (*tz_begin == '-') {
sign = -1;
- split.tz_begin++;
+ tz_begin++;
}
- if (*split.tz_begin == '+') {
+ if (*tz_begin == '+') {
sign = 1;
- split.tz_begin++;
+ tz_begin++;
}
- log->value.update.tz_offset = sign * atoi(split.tz_begin);
+ log->value.update.tz_offset = sign * atoi(tz_begin);
}
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
reftable_stack_merged_table(arg->stack);
uint64_t ts = reftable_stack_next_update_index(arg->stack);
struct reftable_log_record *logs = NULL;
+ struct ident_split committer_ident = {0};
size_t logs_nr = 0, logs_alloc = 0, i;
+ const char *committer_info;
int ret = 0;
+ committer_info = git_committer_info(0);
+ if (split_ident_line(&committer_ident, committer_info, strlen(committer_info)))
+ BUG("failed splitting committer info");
+
QSORT(arg->updates, arg->updates_nr, transaction_update_cmp);
reftable_writer_set_limits(writer, ts, ts);
@@ -1086,7 +1090,7 @@ static int write_transaction_table(struct reftable_writer *writer, void *cb_data
log = &logs[logs_nr++];
memset(log, 0, sizeof(*log));
- fill_reftable_log_record(log);
+ fill_reftable_log_record(log, &committer_ident);
log->update_index = ts;
log->refname = xstrdup(u->refname);
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
.value.symref = (char *)create->target,
.update_index = ts,
};
+ struct ident_split committer_ident = {0};
struct reftable_log_record log = {0};
struct object_id new_oid;
struct object_id old_oid;
+ const char *committer_info;
int ret;
reftable_writer_set_limits(writer, ts, ts);
@@ -1263,7 +1269,11 @@ static int write_create_symref_table(struct reftable_writer *writer, void *cb_da
!should_write_log(&create->refs->base, create->refname))
return 0;
- fill_reftable_log_record(&log);
+ committer_info = git_committer_info(0);
+ if (split_ident_line(&committer_ident, committer_info, strlen(committer_info)))
+ BUG("failed splitting committer info");
+
+ fill_reftable_log_record(&log, &committer_ident);
log.refname = xstrdup(create->refname);
log.update_index = ts;
log.value.update.message = xstrndup(create->logmsg,
@@ -1339,10 +1349,16 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
struct reftable_log_record old_log = {0}, *logs = NULL;
struct reftable_iterator it = {0};
struct string_list skip = STRING_LIST_INIT_NODUP;
+ struct ident_split committer_ident = {0};
struct strbuf errbuf = STRBUF_INIT;
size_t logs_nr = 0, logs_alloc = 0, i;
+ const char *committer_info;
int ret;
+ committer_info = git_committer_info(0);
+ if (split_ident_line(&committer_ident, committer_info, strlen(committer_info)))
+ BUG("failed splitting committer info");
+
if (reftable_stack_read_ref(arg->stack, arg->oldname, &old_ref)) {
ret = error(_("refname %s not found"), arg->oldname);
goto done;
@@ -1417,7 +1433,7 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
ALLOC_GROW(logs, logs_nr + 1, logs_alloc);
memset(&logs[logs_nr], 0, sizeof(logs[logs_nr]));
- fill_reftable_log_record(&logs[logs_nr]);
+ fill_reftable_log_record(&logs[logs_nr], &committer_ident);
logs[logs_nr].refname = (char *)arg->newname;
logs[logs_nr].update_index = deletion_ts;
logs[logs_nr].value.update.message =
@@ -1449,7 +1465,7 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
*/
ALLOC_GROW(logs, logs_nr + 1, logs_alloc);
memset(&logs[logs_nr], 0, sizeof(logs[logs_nr]));
- fill_reftable_log_record(&logs[logs_nr]);
+ fill_reftable_log_record(&logs[logs_nr], &committer_ident);
logs[logs_nr].refname = (char *)arg->newname;
logs[logs_nr].update_index = creation_ts;
logs[logs_nr].value.update.message =
--
2.44.GIT
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2024-04-08 12:24 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-02 17:29 [PATCH 0/9] reftable: optimize write performance Patrick Steinhardt
2024-04-02 17:29 ` [PATCH 1/9] refs/reftable: fix D/F conflict error message on ref copy Patrick Steinhardt
2024-04-03 18:28 ` Junio C Hamano
2024-04-02 17:29 ` [PATCH 2/9] refs/reftable: perform explicit D/F check when writing symrefs Patrick Steinhardt
2024-04-02 17:30 ` [PATCH 3/9] refs/reftable: skip duplicate name checks Patrick Steinhardt
2024-04-02 17:30 ` [PATCH 4/9] refs/reftable: don't recompute committer ident Patrick Steinhardt
2024-04-03 18:58 ` Junio C Hamano
2024-04-04 5:36 ` Patrick Steinhardt
2024-04-02 17:30 ` [PATCH 5/9] reftable/writer: refactorings for `writer_add_record()` Patrick Steinhardt
2024-04-02 17:30 ` [PATCH 6/9] reftable/writer: refactorings for `writer_flush_nonempty_block()` Patrick Steinhardt
2024-04-02 17:30 ` [PATCH 7/9] reftable/block: reuse zstream when writing log blocks Patrick Steinhardt
2024-04-03 19:35 ` Junio C Hamano
2024-04-04 5:36 ` Patrick Steinhardt
2024-04-02 17:30 ` [PATCH 8/9] reftable/block: reuse compressed array Patrick Steinhardt
2024-04-02 17:30 ` [PATCH 9/9] reftable/writer: reset `last_key` instead of releasing it Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 00/11] reftable: optimize write performance Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 01/11] refs/reftable: fix D/F conflict error message on ref copy Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 02/11] refs/reftable: perform explicit D/F check when writing symrefs Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 03/11] refs/reftable: skip duplicate name checks Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 04/11] reftable: remove " Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 05/11] refs/reftable: don't recompute committer ident Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 06/11] reftable/writer: refactorings for `writer_add_record()` Patrick Steinhardt
2024-04-04 6:58 ` Han-Wen Nienhuys
2024-04-04 7:32 ` Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 07/11] reftable/writer: refactorings for `writer_flush_nonempty_block()` Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 08/11] reftable/writer: unify releasing memory Patrick Steinhardt
2024-04-04 7:08 ` Han-Wen Nienhuys
2024-04-04 7:32 ` Patrick Steinhardt
2024-04-04 9:00 ` Han-Wen Nienhuys
2024-04-04 11:43 ` Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 09/11] reftable/writer: reset `last_key` instead of releasing it Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 10/11] reftable/block: reuse zstream when writing log blocks Patrick Steinhardt
2024-04-04 5:48 ` [PATCH v2 11/11] reftable/block: reuse compressed array Patrick Steinhardt
2024-04-04 7:09 ` [PATCH v2 00/11] reftable: optimize write performance Han-Wen Nienhuys
2024-04-04 7:32 ` Patrick Steinhardt
2024-04-08 12:23 ` [PATCH v3 " Patrick Steinhardt
2024-04-08 12:23 ` [PATCH v3 01/11] refs/reftable: fix D/F conflict error message on ref copy Patrick Steinhardt
2024-04-08 12:23 ` [PATCH v3 02/11] refs/reftable: perform explicit D/F check when writing symrefs Patrick Steinhardt
2024-04-08 12:24 ` [PATCH v3 03/11] refs/reftable: skip duplicate name checks Patrick Steinhardt
2024-04-08 12:24 ` [PATCH v3 04/11] reftable: remove " Patrick Steinhardt
2024-04-08 12:24 ` Patrick Steinhardt [this message]
2024-04-08 12:24 ` [PATCH v3 06/11] reftable/writer: refactorings for `writer_add_record()` Patrick Steinhardt
2024-04-08 12:24 ` [PATCH v3 07/11] reftable/writer: refactorings for `writer_flush_nonempty_block()` Patrick Steinhardt
2024-04-08 12:24 ` [PATCH v3 08/11] reftable/writer: unify releasing memory Patrick Steinhardt
2024-04-08 12:24 ` [PATCH v3 09/11] reftable/writer: reset `last_key` instead of releasing it Patrick Steinhardt
2024-04-08 12:24 ` [PATCH v3 10/11] reftable/block: reuse zstream when writing log blocks Patrick Steinhardt
2024-04-08 12:24 ` [PATCH v3 11/11] reftable/block: reuse compressed array Patrick Steinhardt
2024-04-09 0:09 ` [PATCH v3 00/11] reftable: optimize write performance Junio C Hamano
2024-04-09 3:16 ` Patrick Steinhardt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1ca7d9b6cff2eeceddf2dc1c8cb8f5d0216487cc.1712578837.git.ps@pks.im \
--to=ps@pks.im \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=hanwenn@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).