From: | Andres Freund <andres(at)anarazel(dot)de> |
---|---|
To: | pgsql-hackers(at)postgresql(dot)org |
Subject: | computing completion tag is expensive for pgbench -S -M prepared |
Date: | 2018-06-07 04:13:41 |
Message-ID: | 20180607041341.37swzwqluyfendjl@alap3.anarazel.de |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
Hi,
While looking at a profile I randomly noticed that we spend a surprising
amount of time in snprintf() and its subsidiary functions. That turns
out to be
if (strcmp(portal->commandTag, "SELECT") == 0)
snprintf(completionTag, COMPLETION_TAG_BUFSIZE,
"SELECT " UINT64_FORMAT, nprocessed);
in PortalRun(). That's actually fairly trivial to optimize - we don't
need the full blown snprintf machinery here. A quick benchmark
replacing it with:
memcpy(completionTag, "SELECT ", sizeof("SELECT "));
pg_lltoa(nprocessed, completionTag + 7);
yields nearly a ~2% increase in TPS. Larger than I expected. The code
is obviously less pretty, but it's also not actually that bad.
Attached is the patch I used for benchmarking. I wonder if I just hit
some specific version of glibc that regressed snprintf performance, or
whether others can reproduce this.
If it actually reproducible, I think we should go for it. But update the
rest of the completionTag writes in the same file too.
Greetings,
Andres Freund
Attachment | Content-Type | Size |
---|---|---|
completion-tag.patch | text/x-diff | 864 bytes |
From | Date | Subject | |
---|---|---|---|
Next Message | Michael Paquier | 2018-06-07 04:47:21 | Re: SCRAM with channel binding downgrade attack |
Previous Message | David Rowley | 2018-06-07 04:13:10 | Re: Needless additional partition check in INSERT? |