* nfsd problem?
@ 2002-03-28 21:15 Luis Cano
0 siblings, 0 replies; only message in thread
From: Luis Cano @ 2002-03-28 21:15 UTC (permalink / raw)
To: nfs
Hello,
Here is my configuration:
- One Raizone, dual processors PIII, 1.5g RAM, running 2.4.16-12smp,
servicing as a NFS server, exporting a reiser filesystem.
- Five Dells 2450, dual processors PIII, 1g RAM, running 2.4.3-12smp,
nfs-utils 0.3.1, mounting the raidzone reiser filesystem via NFS:
rzdm:/home/ftp on /var/ftp/pub type nfs
(ro,noatime,rsize=8192,wsize=8192,hard,intr,nolock,addr=x.x.x.x)
rzdm:/home/www on /var/www type nfs
(rw,sync,noatime,rsize=8192,wsize=8192,hard,intr,nolock,addr=x.x.x.x)
where x.x.x.x is the ip of the raidzone.
The five dell servers are serving as ftp/web servers and front ended
with a load balancer for ftp and http traffic. During peak periods, the
dell server load average climbs to over 400 and ftp throughput
progressively drops from 7.6Mbytes per second to 1.5Mbytes per second.
If we restart NFSD on the raidzone, the dell servers load average drops
to less than 2.5 and ftp throughput increases to the normal 7.6Mbytes
per second. It takes about a day for the load average to climb up again
and ftp throughput to decrease.
Is this a NFSD problem with 2.4.16? Is there something I can look at or
other information needed to determine the problem?
Thank you and appreciate any help.
Luis Cano
_______________________________________________
NFS maillist - NFS@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nfs
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2002-03-28 21:17 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2002-03-28 21:15 nfsd problem? Luis Cano
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.