Monitoring I/O in RHEL5?
I have a server that is a database master. It's supposed to replicate with about 75 other servers at various sites around the globe. About a month ago, after 2 new luns were added, the replication started failing. I am concerned that i/o to the san is being overloaded. Is there anything I can use to monitor the i/o through the fibre cards?
(It's a Hitachi SAN, and I am using Hitachi fibre cards - multipathing is enabled.)
# multipath -ll
mpath2 (360060e800429550000002955000003b9) dm-31 HITACHI,OPEN-V
[size=34G][features=0][hwhandler=0]
\_ round-robin 0 [prio=0][active]
\_ 0:0:0:2 sdc 8:32 [active][ready]
mpath1 (360060e8004295500000029550000039a) dm-30 HITACHI,OPEN-V
[size=34G][features=0][hwhandler=0]
\_ round-robin 0 [prio=0][active]
\_ 0:0:0:1 sdb 8:16 [active][ready]
mpath0 (360060e80042955000000295500000323) dm-29 HITACHI,OPEN-V*11
[size=374G][features=0][hwhandler=0]
\_ round-robin 0 [prio=0][active]
\_ 0:0:0:0 sda 8:0 [active][ready]
Any help is appreciated.
ETA: My multipath.conf:
defaults {
udev_dir /dev
polling_interval 10
selector "round-robin 0"
#path_grouping_policy multibus
path_grouping_policy failover
getuid_callout "/sbin/scsi_id -g -u -s /block/%n"
prio_callout /bin/true
path_checker readsector0
rr_min_io 100
rr_weight priorities
failback immediate
no_path_retry fail
user_friendly_name yes
Last edited by epoh; 05-07-2008 at 02:16 PM.
|