httpd-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Gonyou, Austin" <aus...@coremetrics.com>
Subject RE: mod_file_cache performance
Date Mon, 02 Jul 2001 22:49:54 GMT
Well..you can at least look at sar for iostats..on the client box. That will
help a little. And usually, even as a user, you can still run SAR..just not
as a daemon.

-- 
Austin Gonyou
Systems Architect, CCNA
Coremetrics, Inc.
Phone: 512-796-9023
email: austin@coremetrics.com 

> -----Original Message-----
> From: Cliff Woolley [mailto:cliffwoolley@yahoo.com]
> Sent: Monday, July 02, 2001 4:58 PM
> To: new-httpd@apache.org
> Subject: RE: mod_file_cache performance
> 
> 
> On Mon, 2 Jul 2001, Gonyou, Austin wrote:
> 
> 
> > One thing you can also do, on the nfs side, is get rid of any timing
> > issues with NFS. Like turn off timestamp updating for 
> access, change,
> > and read. Also mounting it with caching turned on/off to see if that
> > makes any difference, (probably screw up the numbers more), would
> > happne.
> ...
> > OOh oooh. One other thing to, can you do a top or sar or 
> something and watch
> > your block reads/writes on the nfs volume? (on both the NFS 
> server and
> > client) This will tell us the length at which the 
> bottleneck is extending,
> > either it's on the server side or the client side. I'm 
> asking about that
> > mainly because there could be things you could do on the 
> server side to
> > tweak performance rather than client side when mounting. 
> Also, the CPU time
> > the server takes to answer those requests is a pretty 
> significant problem
> > I've found. I used to actually have a load ballanced server farm all
> > connected across NFS which servered up the entire perl 
> libraries on every
> > request..and that just killed everything one day. All our 
> servers were way
> > screwed up from that. :) ulimit got killed and CPU time was 
> through the
> > roof. :)
> 
> 
> Unfortunately I don't have any control over (or even the 
> ability to log
> into) my department's NFS server.  Nor do I have root on my 
> testing boxes.
> These would be interesting things to look at, I agree, but I 
> can't do it.
> :-(  Someone else is free to volunteer...
> 
> --Cliff
> 
> 
> --------------------------------------------------------------
>    Cliff Woolley
>    cliffwoolley@yahoo.com
>    Charlottesville, VA
> 
> 

Mime
View raw message