Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 15 Sep 2010 19:38:28 -0400 (EDT)
From:      Rick Macklem <rmacklem@uoguelph.ca>
To:        Steve Polyack <korvus@comcast.net>
Cc:        Eric Crist <ecrist@secure-computing.net>, freebsd-fs@freebsd.org, Thomas Johnson <tom@claimlynx.com>
Subject:   Re: NFS nfs_getpages errors
Message-ID:  <1847513949.997169.1284593908573.JavaMail.root@erie.cs.uoguelph.ca>
In-Reply-To: <4C90E88D.9050608@comcast.net>

next in thread | previous in thread | raw e-mail | index | archive | help
> We see these errors on some 8.1 clients as well:
> nfs_getpages: error 1110586608
> nfs_getpages: error 1108948624
> vm_fault: pager read error, pid 56216 (php)
> nfs_getpages: error 1114969744
> vm_fault: pager read error, pid 54770 (php)
> nfs_getpages: error 1137006224
> vm_fault: pager read error, pid 50578 (php)
> 
> They do not show up often, so we haven't spent much time looking into
> it
> (no tcpdumps yet). Our NFS server is a 8-STABLE system backed by ZFS,
> so maybe its related to that (again :) ).
> 
> Eric, is your NFS server backed by ZFS as well?
> 
> The NFS server doesn't seem to be logging any errors, but the
> ret-failed
> count is always increasing:
> 
ret-failed doesn't really tell us anything. As I understand it, any
error return, such as ENOENT, EACCES,... is being counted. (ie. legit)

You could try switching to the exp. server. That would tell us if
the problem is specific to the regular server or not. To switch the
server over:
- create an empty stable restart file
  # install -o root -g wheel -m 600 /dev/null /var/db/nfs-stablerestart
- either set nfsv4_server_enable="YES" in /etc/rc.conf
or
  add "-e" to both mountd and nfsd

It had been stable for others (of course your mmv:-) and should be fine
for NFSv3 (ie. you don't have to use NFSv4).

rick
ps: Use "nfsstat -e -s" for stats related to the exp. server.





Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1847513949.997169.1284593908573.JavaMail.root>