Re: Poor NFS server performance in 6.0 with SMP and mpsafenet=1

From: Gavin Atkinson <gavin.atkinson_at_ury.york.ac.uk>
Date: Wed, 02 Nov 2005 18:07:21 +0000
On Wed, 2005-11-02 at 16:45 +0100, Martin Hudec wrote:
> Hello,
> 
> 
> On Wed, Nov 02, 2005 at 03:37:29PM +0000 or thereabouts, Gavin Atkinson wrote:
> > When I get home, I'll have a play with both ULE and POLLING to see what
> > difference they make, however ideally I'd like to not use polling in
> > production if possible.
> 
>   What's wrong with polling on production in your current environment if
>   I may ask?

Certainly.  For heavily loaded machines, polling seems to significantly
improve performance, but in my experience on lightly loaded machines it
seems to increase latency on response to packets.  For the particular
workloads it will be used for, (serving web content and databases), the
latency can be noticeable.

IMHO, polling is great for lower-spec boxes or highly loaded machines,
but can hinder performance when the machine is lightly loaded.  I have a
few machines which run with polling on, and for those usage patterns it
really helps.  I just don't believe this is one of those cases.

Gavin
Received on Wed Nov 02 2005 - 17:07:37 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:47 UTC