[prev in list] [next in list] [prev in thread] [next in thread] 

List:       postgresql-hackers
Subject:    Re: Performance degradation on concurrent COPY into a single relation in PG16.
From:       John Naylor <john.naylor () enterprisedb ! com>
Date:       2023-07-31 9:39:04
Message-ID: CAFBsxsF7GdxNbEeiRpTBBuiDBnyMH6d_HMehtZUZYZmdP2Tcqg () mail ! gmail ! com
[Download RAW message or body]

On Thu, Jul 27, 2023 at 7:17 AM David Rowley <dgrowleyml@gmail.com> wrote:
>
> It would be really good if someone with another a newish intel CPU
> could test this too.

I ran the lotsaints test from last email on an i7-10750H (~3 years old) and
got these results (gcc 13.1 , turbo off):

REL_15_STABLE:
latency average = 956.453 ms
latency stddev = 4.854 ms

REL_16_STABLE @ 695f5deb7902 (28-JUL-2023):
latency average = 999.354 ms
latency stddev = 3.611 ms

master @ 39055cb4cc (31-JUL-2023):
latency average = 995.310 ms
latency stddev = 5.176 ms

master + revert c1308ce2d (the replace-palloc0 fix)
latency average = 1080.909 ms
latency stddev = 8.707 ms

master + pg_strtoint_fastpath1.patch
latency average = 938.146 ms
latency stddev = 9.354 ms

master + pg_strtoint_fastpath2.patch
latency average = 902.808 ms
latency stddev = 3.957 ms

For me, PG16 seems to regress from PG15, and the second patch seems faster
than the first.

--
John Naylor
EDB: http://www.enterprisedb.com

[Attachment #3 (text/html)]

<div dir="ltr"><br>On Thu, Jul 27, 2023 at 7:17 AM David Rowley &lt;<a \
href="mailto:dgrowleyml@gmail.com">dgrowleyml@gmail.com</a>&gt; \
wrote:<br>&gt;<br>&gt; It would be really good if someone with another a newish intel \
CPU<br>&gt; could test this too.<br><br>I ran the lotsaints test from last email on \
an  i7-10750H (~3 years old) and got these results (gcc 13.1 , turbo \
off):<br><br>REL_15_STABLE:<br>latency average = 956.453 ms<br>latency stddev = 4.854 \
ms<br><br>REL_16_STABLE @ 695f5deb7902 (28-JUL-2023):<br>latency average = 999.354 \
ms<br>latency stddev = 3.611 ms<br><br>master @ 39055cb4cc (31-JUL-2023):<br>latency \
average = 995.310 ms<br>latency stddev = 5.176 ms<br><br>master + revert c1308ce2d \
(the replace-palloc0 fix)<br>latency average = 1080.909 ms<br>latency stddev = 8.707 \
ms<br><br>master + pg_strtoint_fastpath1.patch<br>latency average = 938.146 \
ms<br>latency stddev = 9.354 ms<br><br>master + \
pg_strtoint_fastpath2.patch<br>latency average = 902.808 ms<br>latency stddev = 3.957 \
ms<div><br></div><div>For me, PG16 seems to regress from PG15, and the second patch \
seems faster than the first.  </div><div><br>--<br>John Naylor<br>EDB: <a \
href="http://www.enterprisedb.com">http://www.enterprisedb.com</a></div></div>



[prev in list] [next in list] [prev in thread] [next in thread]