Re: measuring lwlock-related latency spikes - Mailing list pgsql-hackers

From Albe Laurenz
Subject Re: measuring lwlock-related latency spikes
Date
Msg-id D960CB61B694CF459DCFB4B0128514C207B2C39E@exadv11.host.magwien.gv.at
Whole thread Raw
In response to Re: measuring lwlock-related latency spikes  (Robert Haas <robertmhaas@gmail.com>)
List pgsql-hackers
Robert Haas wrote:
> I suppose one interesting question is to figure out if there's a way I
> can optimize the disk configuration in this machine, or the Linux I/O
> scheduler, or something, so as to reduce the amount of time it spends
> waiting for the disk.

I'd be curious to know if using the deadline scheduler will improve
things.  I have experienced pretty bad performance with cfq under
load, where sequential table scans were starved to the point where
they took hours instead of less than a minute (on an idle system).
But I believe that also depends a lot on the storage system used.

Yours,
Laurenz Albe


pgsql-hackers by date:

Previous
From: David Johnston
Date:
Subject: Re: Switching to Homebrew as recommended Mac install?
Next
From: Simon Riggs
Date:
Subject: Re: measuring lwlock-related latency spikes