We have a 5220 running 2.5.1 connected via fibre to EMC Clariion CX4-480. We see a whole raft of errors in the datacollect logs such as:-
I/O error, dev sdfx, sector 0
sd 7:0:0:59: SCSI error: return code = 0x00000018
end_request: I/O error, dev sdfx, sector 9511736
sd 4:0:0:59: SCSI error: return code = 0x00000018
end_request: I/O error, dev sdbk, sector 0
sd 7:0:0:59: SCSI error: return code = 0x00000018
end_request: I/O error, dev sdfx, sector 0
sd 7:0:0:59: SCSI error: return code = 0x00000018
end_request: I/O error, dev sdfx, sector 0
sd 4:0:0:59: SCSI error: return code = 0x00000018
Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request: I/O error, dev sdhy, sector 0
sd 7:0:2:20: Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request: I/O error, dev sdhz, sector 0
sd 7:0:2:2: Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request: I/O error, dev sdhh, sector 0
sd 7:0:2:20: Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request: I/O error, dev sdhz, sector 0
sd 7:0:2:4: Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request: I/O error, dev sdhj, sector 0
sd 7:0:2:6: Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request: I/O error, dev sdhl, sector 0
sd 7:0:2:7: Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request: I/O error, dev sdhm, sector 0
sd 7:0:2:9: Device not ready: <6>: Current: sense key: Not Ready
Additional sense: Logical unit not ready, manual intervention required
end_request:
They also cause a condiderable delay when rebooting the appliance.
Anyone have any thoughts on what may be behind these. We get no errors on the SAN and backups over SAN transport are working OK though do have question makes on throughput when high client volumes going through..
Cheers
Ed
