Disks fail aggressively in a single disk stack
Applies to
- ONTAP 9
- Fabric MetroCluster
- ATTO FB7500N
Issue
Multiple disks fail in a short space of time
Example:
ClusterA::> storage disk show -broken
Original Owner: ClusterB-01
Checksum Compatibility: block
Drawer Usable Physical
Disk Outage Reason HA Shelf Bay /Slot Chan Pool Type RPM Size Size
--------------- ------------- --- ----- --- ------ ---- ------ ----- ------ -------- --------
1.51.22 failed 11b 51 22 -/- A FAILED SSD - - 6.99TB
Original Owner: ClusterB-01
Checksum Compatibility: block
Drawer Usable Physical
Disk Outage Reason HA Shelf Bay /Slot Chan Pool Type RPM Size Size
--------------- ------------- --- ----- --- ------ ---- ------ ----- ------ -------- --------
1.51.15 failed 11b 51 15 -/- A FAILED SSD - - 894.3GB
Original Owner: ClusterA-01
Checksum Compatibility: block
Drawer Usable Physical
Disk Outage Reason HA Shelf Bay /Slot Chan Pool Type RPM Size Size
--------------- ------------- --- ----- --- ------ ---- ------ ----- ------ -------- --------
1.51.6 failed 1d 51 6 -/- B FAILED SSD - 894.0GB 894.3GB
1.51.16 failed 1d 51 16 -/- B FAILED SSD - 6.99TB 6.99TB
1.51.17 failed 1d 51 17 -/- B FAILED SSD - 6.99TB 6.99TB
1.51.18 failed 1d 51 18 -/- B FAILED SSD - 6.99TB 6.99TBA significant amount of errors are found in the event log for one of the ATTO bridges
Example:
INFO FC TM Cmd Rcvd: Abort Task Set to LUN:27 on FC Port 1
Error counters on the ATTO bridge are increasing
Example:
; Fibre Channel Error Counts ; Port | Link Failures | Sync Loss | Signal Loss | Invalid Tx | Invalid CRC ;========================================================================== 1 1 2 0 16 4796 2 1 1 0 4 0