OCUM reports weekly on Sunday a high disk utilization on root aggregate and shm.threshold.highIOLatency errors in one node
Applies to
- FAS8200
- Disk model X477_TTCRE04TA07 with NA02 firmware
- The drive is the data one in a 3 RAID-DP root aggregate
Issue
- OnCommand Unified Manager report the following messages:
Sun Apr 12 00:18:18 CEST [node_name: disk_latency_monitor: shm.threshold.highIOLatency:error]: Disk 0a.00.8 exceeds the average IO latency threshold and will be recommended for failure.
- ONTAP EMS messages report:
Wed Apr 22 18:21:48 CEST [node_name: disk_latency_monitor: shm.threshold.ioLatency:debug]: Disk 0a.00.8 has exceeded the expected IO latency in the current window with average latency of 182 msecs and average utilization of 28 percent. Highest average IO latency: 0a.00.8: 182 msecs; next highest IO latency: 0a.00.0: 10 msecs. Disk 0a.00.8 Shelf 0 Bay 8 [NETAPP X477_TTCRE04TA07 NA02] S/N [XNXNXNNNXNXX] UID [XXXXXXXX:XXXXXXXX:XXXXXXXX:XXXXXXXX:XXXXXXXX:XXXXXXXX:XXXXXXXX:XXXXXXXX:XXXXXXXX:XXXXXXXX]