Re: Postgresql TPS Bottleneck - Mailing list pgsql-performance

From Guillaume Cottenceau
Subject Re: Postgresql TPS Bottleneck
Date
Msg-id 87zgl64342.fsf@mnc.ch
Whole thread Raw
In response to Postgresql TPS Bottleneck  (<wakandavision@outlook.com>)
List pgsql-performance
<wakandavision 'at' outlook.com> writes:

> Optimally I would like to fully use the CPU and get about 3-4 times
> more TPS (if even possible).

Disclaimer: I'm really not a pg performance expert.
I don't understand your hope to fully use the CPU; if your
scenario is disk-limited, which may very well be the case, then
of course you cannot fully use the CPU. With synchronous commits
and fsync, the system is probably spending time just waiting for
the disks to report the writes completion. Are iostat/vmstat
showing a lot of IO-wait?
Also, if you can live with a few lost transactions in case of
server crash, synchronous_commit=off is very ok and provides a
lot of performance gain.

-- 
Guillaume Cottenceau



pgsql-performance by date:

Previous
From:
Date:
Subject: Postgresql TPS Bottleneck
Next
From: Mladen Gogala
Date:
Subject: Re: HIGH IO and Less CPU utilization