From: | Andres Freund <andres(at)anarazel(dot)de> |
---|---|
To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
Cc: | pgsql-hackers(at)postgresql(dot)org |
Subject: | Re: computing completion tag is expensive for pgbench -S -M prepared |
Date: | 2018-06-07 18:21:04 |
Message-ID: | 20180607182104.y526arpl3bt6x3bk@alap3.anarazel.de |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
On 2018-06-07 10:30:14 -0400, Tom Lane wrote:
> Andres Freund <andres(at)anarazel(dot)de> writes:
> > ... 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);
>
> While I don't have any objection to this change if the speedup is
> reproducible, I do object to spelling the same constant as
> 'sizeof("SELECT ")' and '7' on adjacent lines ...
Hah, yes. Nor would I want to keep the #if 0 around it ;). I mostly
wanted to know whether others can reproduce the effect - the actual
patch would need to be bigger and affect more places.
Greetings,
Andres Freund
From | Date | Subject | |
---|---|---|---|
Next Message | Andres Freund | 2018-06-07 18:31:35 | Re: computing completion tag is expensive for pgbench -S -M prepared |
Previous Message | Andres Freund | 2018-06-07 18:20:10 | Re: computing completion tag is expensive for pgbench -S -M prepared |