From: Tom Lane <tgl@sss.pgh.pa.us>
To: Jordan Hurwich <jhurwich@pulsasensors.com>
cc: Samed YILDIRIM <samed@reddoc.net>, pgsql-performance@lists.postgresql.org,
        Gautam Bellary <gautam@pulsasensors.com>
Subject: Re: Increased iowait and blk_read_time with higher shared_buffers
In-reply-to: 
 <CAJKqsjvsuFWoBD7++aPRmdfrr7UmsZbc2Whg6zqd3VQB02FTmg@mail.gmail.com>
References: 
 <CAJKqsjvU3Er=FKwS8wc1E3QOUmJK8bPWVUfZXzm=Nzg55FULcQ@mail.gmail.com>
 <CAAo1mbmDJctnPfxY_85Zm+-koTDhWJQp3Pmu9kARMzy40ryMEA@mail.gmail.com>
 <CAJKqsjvsuFWoBD7++aPRmdfrr7UmsZbc2Whg6zqd3VQB02FTmg@mail.gmail.com>
Comments: In-reply-to Jordan Hurwich <jhurwich@pulsasensors.com>
	message dated "Wed, 14 Dec 2022 10:12:16 -0800"
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <2784234.1671042443.1@sss.pgh.pa.us>
Date: Wed, 14 Dec 2022 13:27:23 -0500
Message-ID: <2784235.1671042443@sss.pgh.pa.us>
Archived-At: 
 <https://www.postgresql.org/message-id/2784235.1671042443%40sss.pgh.pa.us>
Precedence: bulk

Jordan Hurwich <jhurwich@pulsasensors.com> writes:
> I'm familiar with the article you linked to, and part of my surprise is
> that with these 32GB RAM machines we're seeing better performance at 12.5%
> (4GB) than the commonly recommended 25% (8GB) of system memory for
> shared_buffers. Your notes about disk read stats from Postgres potentially
> actually representing blocks read from the OS cache make sense, I just
> imagined that Postgres would be better at managing the memory when it was
> dedicated to it via shared_buffers than the OS (obviously with some point
> of diminishing returns); and I'm still hoping there's some Postgres
> configuration change we can make that enables better performance through
> improved utilization of shared_buffers at the commonly recommended 25% of
> system memory.

Keep in mind that 25% was never some kind of golden number.  It is
a rough rule of thumb that was invented for far smaller machines than
what you're talking about here.

			regards, tom lane