We have a SuperMicro SATA server we're using for
tier 2 data storage. NFS mounts from this box
are absurdly slow (10 seconds or more is the
minimum, and I have observed much longer). If
one attempts to perform mounts of the other
file systems from that system soon thereafter,
the mounts take about 10 seconds.
Automounts here expire in 1 minute, and that
seems to happen in a timely fashion.
Any ideas? Any diagnostic hints? Things to
tweak?
DETAILS
=======
This server uses a single, 1.6GHz Opteron 242.
It has 5 300GB WD drives in RAID5 plus 1 hot
spare, off a 3Ware 9000 8 port SATA controller.
These are formatted as an XFS filesystem. The
OS and related partitions are on a separate WD
SATA drive. I believe it's on the same controller
(when it was on the built-in controller we never
could see both it and the RAID drives at the
same time). Local access times to the XFS part
are fine; I originally remote mounted another filer
to copy data here and it performed beautifully.
The sole problem we're aware of is NFS mount times
for the three mount points on the XFS RAID
partition.
We do not use LVM on this box.
It's SL4.0 stock, except we installed the
kernel-smp-2.6.9-11.EL.XFS.x86_64 RPM and
boot from that. We also installed
xfsprogs-2.6.13-3.rf.x86_64 .
We use NIS for password, group, netgroup, and
automount data. This server is configured the
same as three other, similar servers, (as much
as possible) except that they are running RH9,
SL304, or SL305. Those are older boxes, using
either SCSI or SATA drives, some Athlon some
Pentium, all dual processor. They all use ext3
filesystems, and handle mount requests very
quickly.
chkconfig info (only what's turned on):
acpid 0:off 1:off 2:off 3:on 4:on 5:on 6:off
anacron 0:off 1:off 2:on 3:on 4:on 5:on 6:off
atd 0:off 1:off 2:off 3:on 4:on 5:on 6:off
autofs 0:off 1:off 2:off 3:on 4:on 5:on 6:off
cpuspeed 0:off 1:on 2:on 3:on 4:on 5:on 6:off
crond 0:off 1:off 2:on 3:on 4:on 5:on 6:off
gpm 0:off 1:off 2:on 3:on 4:on 5:on 6:off
haldaemon 0:off 1:off 2:off 3:on 4:on 5:on 6:off
iiim 0:off 1:off 2:on 3:on 4:on 5:on 6:off
irqbalance 0:off 1:off 2:off 3:on 4:on 5:on 6:off
kudzu 0:off 1:off 2:off 3:on 4:on 5:on 6:off
lm_sensors 0:off 1:off 2:on 3:on 4:on 5:on 6:off
messagebus 0:off 1:off 2:off 3:on 4:on 5:on 6:off
netfs 0:off 1:off 2:off 3:on 4:on 5:on 6:off
network 0:off 1:off 2:on 3:on 4:on 5:on 6:off
nfs 0:off 1:off 2:on 3:on 4:on 5:on 6:off
nfslock 0:off 1:off 2:off 3:on 4:on 5:on 6:off
ntpd 0:off 1:off 2:off 3:on 4:off 5:on 6:off
portmap 0:off 1:off 2:off 3:on 4:on 5:on 6:off
rawdevices 0:off 1:off 2:off 3:on 4:on 5:on 6:off
readahead 0:off 1:off 2:off 3:off 4:off 5:on 6:off
readahead_early 0:off 1:off 2:off 3:off 4:off 5:on 6:off
rpcgssd 0:off 1:off 2:off 3:on 4:on 5:on 6:off
rpcidmapd 0:off 1:off 2:off 3:on 4:on 5:on 6:off
rpcsvcgssd 0:off 1:off 2:off 3:on 4:on 5:on 6:off
sshd 0:off 1:off 2:on 3:on 4:on 5:on 6:off
syslog 0:off 1:off 2:on 3:on 4:on 5:on 6:off
sysstat 0:off 1:on 2:on 3:on 4:on 5:on 6:off
xfs 0:off 1:off 2:on 3:on 4:on 5:on 6:off
ypbind 0:off 1:off 2:on 3:on 4:on 5:on 6:off
Other info:
# /etc/nsswitch.conf
#
# standard for eng.intrisity.com and farm.intrinsity.com
# 30 May 2001
#
passwd: files nis
shadow: files nis
group: files nis
hosts: files dns
bootparams: files
ethers: files
netmasks: files
networks: files
protocols: files
rpc: files
services: files
netgroup: nis
publickey: files
automount: nis
aliases: nis
passwd: files nis
shadow: files nis
group: files nis
hosts: files dns
bootparams: files
ethers: files
netmasks: files
networks: files
protocols: files
rpc: files
services: files
netgroup: nis
publickey: files
automount: nis
aliases: nis
# df -h
Filesystem Size Used Avail Use% Mounted on
/dev/sdb2 20G 6.7G 13G 36% /
/dev/sdb1 1012M 44M 917M 5% /boot
none 1005M 0 1005M 0% /dev/shm
/dev/sdb5 9.9G 55M 9.3G 1% /tmp
/dev/sdb3 35G 432M 33G 2% /var
/dev/sda1 1.5T 924G 566G 63% /mnt/raid0
# cat /etc/exports
/mnt/raid0/fs1 *(async,rw) nismaster(async,rw,no_root_squash) ent1(async,rw,no_root_squash) ent2(async,rw,no_root_squash)
/mnt/raid0/fs2 *(async,rw) nismaster(async,rw,no_root_squash) ent1(async,rw,no_root_squash) ent2(async,rw,no_root_squash)
/mnt/raid0/fs3 *(async,rw) nismaster(async,rw,no_root_squash) ent1(async,rw,no_root_squash) ent2(async,rw,no_root_squash)
# *** The above is correct AFAIK but I see the following errors in /var/log/messages:
Aug 17 10:38:00 xfsbox rpc.mountd: /mnt/raid0/fs1 exported to both * and ent1.xxx.yyy.zzz in *,ent2.xxx.yyy.zzz
Aug 17 10:38:00 xfsbox rpc.mountd: /mnt/raid0/fs2 exported to both * and ent1.xxx.yyy.zzz in *,ent2.xxx.yyy.zzz
Aug 17 10:38:00 xfsbox rpc.mountd: /mnt/raid0/fs3 exported to both * and ent1.xxx.yyy.zzz in *,ent2.xxx.yyy.zzz
# *** Nothing else in the message log or boot log seems pertinent.
|