Re: How to tune Postgres to take advantage of 256GB RAM hardware - Mailing list pgsql-performance

From Imre Samu
Subject Re: How to tune Postgres to take advantage of 256GB RAM hardware
Date
Msg-id CAJnEWwmpRt9HWzLwahCRD-yaUaBc9VPO+asMGRXefdgsw-w1nw@mail.gmail.com
Whole thread Raw
In response to Re: How to tune Postgres to take advantage of 256GB RAM hardware  (Carmen Mardiros <bluecorr@gmail.com>)
Responses Re: How to tune Postgres to take advantage of 256GB RAM hardware  (Carmen Mardiros <bluecorr@gmail.com>)
List pgsql-performance
> I am trying to configure Postgres (version 9.5) 

This is the latest PG 9.5 ?  (  =  9.5.5 ? [ Release Date : 2016-10-27 ] )  

2016-11-24 9:17 GMT+01:00 Carmen Mardiros <bluecorr@gmail.com>:
Hi Andreas,

Thanks for the reply. fsync is off because I don't care if the data gets corrupted in this environment if it means a performance gain, as it's only a minor inconvenience to restore from backups.


Here is the query itself that pushes memory usage to 100%: http://pastebin.com/VzCAerwd . What's interesting is that if I execute this stand-alone, memory usage never exceeds 1.3% and query completes in 7 minutes. But if I paste 2 other queries in the query window, followed by this one and execute them all at the same time, by the time postgres reaches the 3rd (this query), memory usage goes up to 100%. I don't understand why this is.

And the EXPLAIN output: https://explain.depesz.com/s/hwH5 (have to admit I don't know how to read this!). Any help is greatly appreciated.

On Thu, 24 Nov 2016 at 04:19 Andreas Kretschmer <andreas@a-kretschmer.de> wrote:


Am 23. November 2016 23:15:25 MEZ, schrieb Carmen Mardiros <bluecorr@gmail.com>:
>
>various combinations)? How can I investigate what's limiting postgres
>from
>doing so?

Why fsync=off?

Please run the queries with EXPLAIN ANALYSE and show us the output.

--
Diese Nachricht wurde von meinem Android-Mobiltelefon mit K-9 Mail gesendet.

pgsql-performance by date:

Previous
From: Carmen Mardiros
Date:
Subject: Re: How to tune Postgres to take advantage of 256GB RAM hardware
Next
From: Carmen Mardiros
Date:
Subject: Re: How to tune Postgres to take advantage of 256GB RAM hardware