Need Advice for Tuning NFS to place nice with a Netapp

[N. Harrington]

--- Freminlins <freminlins at gmail.com> wrote:
> Nicole,
> 
> On 02/08/06, N. Harrington <drumslayer2 at yahoo.com>
> wrote:
> >
> > Hi
> > I have several web servers that are attached to a
> > Netapp (network appliance) unit via NFS-3. A few
> > servers are 5.5 and a few are 6.1 for comparison
> > testing. All seem to have lousy performance.
> 
> 
> We have a similar setup and it runs smoothly.

 Cool! Can you share with me what sort of settings you
use on your boxes? sysctl/kerneltunes/mount options?

 It has taken me a over a month to even get to speak
to someone high enough up he food chain at Netapp to
not say "FreeBSD - that's a version of Linux right?"
 
> Can you define "lousy performance" ?

 The web server replies (using either Apache and
Lighthttpd) seem to max out at about 17mb/s. Response
time for the web server will rise gradually, then
suddenly become 10-20seconds for a reply. Much like a
backup on a highway. They claim that the netapp unit
is spending too much time dealing with file
information IOPS than actual transfer of files.
However even on a non in-use server, if I make a
request for a file, that "heavy file access" seems
normal.
IE:
GtAttr Lookup Rdlink   Read  Write Rename Access 
Rddir
 0      0      0      0      0      0      0      0
 248  160      0      4      0      0    236      0
 0      0      0      0      0      0      0      0
 
> Can you give more details on your network? Are you
> using Gig ethernet? And
> over what medium?

 Yes, 4X GigE from the filer via a Vif and trunking on
the switch. A nice 10Gb ready HP unit. I have asked if
using the Vif and trunking could have any effects but
been assured it should not. It does mean I cannot use
jumbo frames. But since web pages and images are
small, I don't think there would be any benefit.
 
> Can you also try just copying a 100MB file from the
> filer to one of the web
> servers and record the time?

 9907187 bytes/sec for a 16M file.
 It will transfer in nanotime. So, I believe that
eliminates network performance as an issue.

> Are you running nfsiod?

Yes, I show 4 instances running.

> When
> > going through the issues with Netapp, the reasons
> > given were that we have too many GettAdr/Lookup
> > requests compared to actual reads. So all the NFS
> IOPS
> > are being used up by these requests. As soon as
> the
> > webservers get busy,  requests pile up.
> >
> > I have tried everything I can think of. The web
> > servers are even mounted read only with no help.
> >
> > My current mount options are:
> > filer:/vol/fvol31    /home/13/13  nfs
> > ro,noatime,-r=32768,-T,-b,-R0,-i,-D2,-L 0  0
> 
> 
> Mounting noatime for web servers is a good idea
> but... your "noatime" option
> has no effect on NFS mounts (check out the mount man
> page). You need "vol
> options no_atime_update" on the NetApp.

 Hmm. Drat. We have some web servers that do nothing
but send out data, but some that are used for
uploading and file manipulation. I will have to make
sure that global of an option will not effect what
they do.

 
> Any advice for sysctl tunes or anything else would
> be
> > much appreciatted!
> >
> > Thanks
> >
> >   Nicole
> >
> 
> One last thing - are you female?! In a UNIX
> newsgroup?!

 Yup :)
 Oh, and yes, I do play the drums :)

> Frem.
> 


 Thanks for your assistance!!

  Nicole



The Large Print Giveth And The Small Print Taketh Away
 -- Anon

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com