Megaraid module recomendation

Manuel Bujan bujan at isqsolutions.com
Thu Mar 10 13:35:14 CST 2005


Hi list,

I have been reading a lot during this week trying to find which module works best with kernel 2.6.X without find any good recomendation. Some people use the megaraid2 (unified module) from LSI and others the native module that is include with kernel 2.6.10 know as megaraid_mm and megaraid_mbox.

Any experience around this ?

Currently we are running a cluster of two PE1850 with kernel 2.6.10 and the native modules that are included in the kernel. After 20 days of medium load I got the following error:

Mar  9 04:47:45 atmail-2 kernel: megaraid: aborting-171105322 cmd=28 <c=2 t=0 l=0>
Mar  9 04:47:45 atmail-2 kernel: megaraid abort: 171105322:20[255:0], fw owner
Mar  9 04:47:45 atmail-2 kernel: megaraid: reseting the host...
Mar  9 04:47:45 atmail-2 kernel: megaraid: 1 outstanding commands. Max wait 180 sec
Mar  9 04:47:45 atmail-2 kernel: megaraid mbox: Wait for 1 commands to complete:180
Mar  9 04:47:50 atmail-2 kernel: megaraid mbox: Wait for 1 commands to complete:175
Mar  9 04:47:55 atmail-2 kernel: megaraid mbox: Wait for 1 commands to complete:170
Mar  9 04:47:58 atmail-2 kernel: megaraid mbox: reset sequence completed sucessfully
Mar  9 04:47:58 atmail-2 kernel: megaraid: fast sync command timed out
Mar  9 04:47:58 atmail-2 kernel: megaraid: reservation reset failed
Mar  9 04:47:58 atmail-2 kernel: megaraid: reseting the host...
Mar  9 04:47:58 atmail-2 kernel: megaraid mbox: reset sequence completed sucessfully
Mar  9 04:47:58 atmail-2 kernel: megaraid: fast sync command timed out
Mar  9 04:47:58 atmail-2 kernel: megaraid: reservation reset failed
Mar  9 04:47:58 atmail-2 kernel: megaraid: reseting the host...
Mar  9 04:47:58 atmail-2 kernel: megaraid mbox: reset sequence completed sucessfully
Mar  9 04:47:58 atmail-2 kernel: megaraid: fast sync command timed out
Mar  9 04:47:58 atmail-2 kernel: megaraid: reservation reset failed
Mar  9 04:47:58 atmail-2 kernel: scsi: Device offlined - not ready after error recovery: host 1 channel 2 id 0 lun 0
Mar  9 04:47:58 atmail-2 kernel: SCSI error : <1 2 0 0> return code = 0x6000000
Mar  9 04:47:58 atmail-2 kernel: end_request: I/O error, dev sdb, sector 115136575
Mar  9 04:47:58 atmail-2 kernel: GFS: fsid=ISQCLUSTER:gfs001.1: fatal: I/O error
Mar  9 04:47:58 atmail-2 kernel: GFS: fsid=ISQCLUSTER:gfs001.1:   block = 14392016
Mar  9 04:47:58 atmail-2 kernel: GFS: fsid=ISQCLUSTER:gfs001.1:   function = gfs_dreread
Mar  9 04:47:58 atmail-2 kernel: GFS: fsid=ISQCLUSTER:gfs001.1:   file = /usr/src/cluster/gfs-kernel/src/gfs/dio.c, line = 605
Mar  9 04:47:58 atmail-2 kernel: GFS: fsid=ISQCLUSTER:gfs001.1:   time = 1110361678
Mar  9 04:47:58 atmail-2 kernel: scsi1 (0:0): rejecting I/O to offline device
Mar  9 04:47:58 atmail-2 last message repeated 4 times
Mar  9 04:47:59 atmail-2 kernel: GFS: fsid=ISQCLUSTER:gfs001.1: about to withdraw from the cluster
Mar  9 04:47:59 atmail-2 kernel: scsi1 (0:0): rejecting I/O to offline device

Any hints ??????
There is no disk in a failure state.

Regards
Bujan



-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.us.dell.com/pipermail/linux-poweredge/attachments/20050310/b10d7fcc/attachment.htm


More information about the Linux-PowerEdge mailing list