ADSM-L

Re: [ADSM-L] Devtype FILE on NFS performance problem

2010-03-04 01:56:27
Subject: Re: [ADSM-L] Devtype FILE on NFS performance problem
From: Remco Post <r.post AT PLCS DOT NL>
To: ADSM-L AT VM.MARIST DOT EDU
Date: Thu, 4 Mar 2010 07:54:45 +0100
On 4 mrt 2010, at 05:23, Roger Deschner wrote:

> Well THAT was dramatic! Thanks, Gary.
> 
> With DIRECTIO NO set, the write speed to NFS got a LOT faster. However,
> the system also started to page memory very heavily. Watching it with
> topas, migration would write to NFS nicely for about 15 seconds, and
> then it would stop for 5 seconds while AIX thrashed. This cycle repeats
> every 20 seconds or so. Before seting DIRECTIO NO, this system didn't
> page at all. It's still a large net improvement, even with the memory
> thrashing.
> 

Be aware, 'normal' filesystem I/O is handled trough the kernel paging 
mechanism, this is normal, expected behavior. This is actually the major 
difference between direct i/o and normal i/o.

What you need to check is that the amount of memory set aside for filesystem 
cache is not so big that AIX is paging TSM bufferpool or application memory. 
There are some tuning variables you can set, I forgot what they are called. 
Using nmon or topas you can check that you still have enough free memory.


> I'm now adjusting the number of migration processes to see what number
> produces the greatest total throughput, with only a tolerable amount of
> thrashing. I'm also looking into AIX memory management settings.
> 
> I'm also going to watch database I/O performance closely. I've heard it
> can be slowed by DIRECTIO NO.
> 




-- 

Met vriendelijke groeten/Kind regards,

Remco Post

<Prev in Thread] Current Thread [Next in Thread>