Neale,

- No changes have been made to z/VM.

- These are 1G WebSphere guests, each with 768MB java heap size.

- All other commands work fine on all 4 servers.  Only commands going
against the NFS, e.g. df, ls,  on the effected system(s) run slowly
until that system is bounced.

- z/VM has 17GB of storage configured as 13056MB central and 4352MB
expanded.

- We've adjusted the SRM parameters as has everyone running this
environment:
q srm                                   
IABIAS : INTENSITY=90%; DURATION=2      
LDUBUF : Q1=300% Q2=200% Q3=100%        
STORBUF: Q1=200% Q2=175% Q3=150%        
DSPBUF : Q1=32767 Q2=32767 Q3=32767     
DISPATCHING MINOR TIMESLICE = 5 MS      
MAXWSS : LIMIT=9999%                    
...... : PAGES=999999                   
XSTORE : 0%
                             
- I will run the #CP IND Q report when the problem occurs next.

- We run the IBM Perfkit.

Thanks,
Hank

-----Original Message-----
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of
Neale Ferguson
Sent: Tuesday, February 14, 2006 10:37 AM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: NFS hangs

Some questions:
- What other changes have taken place on the VM system?
- How big are the virtual machines?
- Do other commands on the affected Linux guests respond quickly (what
about on the NFS server(s))?
- How much storage does your VM system have?
- What are the SRM settings for your VM system? (Q SRM from an
apporpriately privileged user)
- What does #CP IND Q report when the hang is happening?
- Do you have a performance tool on your system?

Neale

-----Original Message-----
Hello,
We have a filesystem which is shared by 4 Linux guests via NFS.  We have
been using this setup for quite some time.  Recently we've seen 2 cases
where access to the NFS file on 1 or more of the non-owning guests began
to slow down.  A "df" command on the effected system would stop before
the NFS file and hang for >10 seconds.  We've stopped all the tasks
using the file, unmounted, and remounted it, with the same result.  The
only way to resolve the problem was to shutdown and IPL the effected
Linux guest(s).  The owning guest, i.e. the one running the NFS server,
never had to be bounced.

The network setup used for these mounts is a Guest LAN.  Linux is SLES8
SP2, VM is V5.1.  We take all the defaults for rsize, wsize, etc. in
/etc/fstab for the mount.

----------------------------------------------------------------------
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or
visit
http://www.marist.edu/htbin/wlvindex?LINUX-390
*************************************************************************
The information contained in this communication is confidential, is
intended only for the use of the recipient named above, and may be
legally privileged.

If the reader of this message is not the intended recipient, you are 
hereby notified that any dissemination, distribution or copying of this
communication is strictly prohibited.

If you have received this communication in error, please resend this
communication to the sender and delete the original message or any copy
of it from your computer system.

Thank you.
*************************************************************************

----------------------------------------------------------------------
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit
http://www.marist.edu/htbin/wlvindex?LINUX-390

Reply via email to