Re: Improving spin-lock implementation on ARM. - Mailing list pgsql-hackers

From Krunal Bauskar
Subject Re: Improving spin-lock implementation on ARM.
Date
Msg-id CAB10pyYiPQeabqbK7jqOOfJqJqsDq84hFBzCFfUwJtABjsDL2A@mail.gmail.com
Whole thread Raw
In response to Re: Improving spin-lock implementation on ARM.  (Michael Paquier <michael@paquier.xyz>)
List pgsql-hackers

scalability   baseline                       patched
-----------        ---------                     ----------
              update    tpcb              update     tpcb
--------------------------------------------------------------
128           107932 78554          108081 78569  
256            82877 64682            101543 73774
512            55174 46494              77886 61105
1024           32267 27020             33170 30597

configuration: https://github.com/mysqlonarm/benchmark-suites/blob/master/pgsql-pbench/conf/pgsql.cnf/postgresql.conf


On Thu, 26 Nov 2020 at 10:36, Michael Paquier <michael@paquier.xyz> wrote:
On Thu, Nov 26, 2020 at 10:00:50AM +0530, Krunal Bauskar wrote:
> (Thanks to Amit Khandekar for rigorously performance testing this patch
>  with different combinations).

For the simple-update and tpcb-like graphs, do you have any actual
numbers to share between 128 and 1024 connections?  The blue lines
look like they are missing some measurements in-between, so it is hard
to tell if this is an actual improvement or just some lack of data.
--
Michael


--
Regards,
Krunal Bauskar

pgsql-hackers by date:

Previous
From: Michael Paquier
Date:
Subject: Re: Improving spin-lock implementation on ARM.
Next
From: Tom Lane
Date:
Subject: Re: Improving spin-lock implementation on ARM.