| From: | Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> |
|---|---|
| To: | Jerry Sievers <gsievers19(at)comcast(dot)net> |
| Cc: | "pgsql-general(at)postgresql(dot)org" <pgsql-general(at)postgresql(dot)org> |
| Subject: | Re: Up to date conventional wisdom re max shared_buffer size? |
| Date: | 2017-09-20 19:23:14 |
| Message-ID: | CAOR=d=0ASFyG1XfdrARQiUWbwzT9egmcWa=X4+-j=c=OTAsGoA@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-general |
On Tue, Sep 19, 2017 at 4:00 PM, Jerry Sievers <gsievers19(at)comcast(dot)net> wrote:
> Briefly, just curious if legacy max values for shared_buffers have
> scaled up since 8G was like 25% of RAM?
>
> Pg 9.3 on monster 2T/192 CPU Xenial thrashing
>
> Upgrade pending but we recently started having $interesting performance
> issues at times looking like I/O slowness and other times apparently
> causing CPU spins.
Have you looked at things like zone reclaim mode and transparent huge
pages? Both of those can cause odd problems. Also it's usually a good
idea to turn off swap as the linux kernel, presented with lots of ram
and a small (by comparison) swap file sometimes makes bad life choices
and starts using swap for things like storing currently unused shared
buffers or something.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Ron Johnson | 2017-09-20 19:24:52 | Re: Up to date conventional wisdom re max shared_buffer size? |
| Previous Message | Scott Marlowe | 2017-09-20 19:21:11 | Re: Any known issues Pg 9.3 on Ubuntu Xenial kernel 4.4.0? |