由于单磁盘IO介质错误、NFS延迟较长

适用场景

问题描述

• 多个卷报告了高延迟。 

• 在高延迟时间段内、EMS会显示以下消息

Sun May 07 12:00:34 +0000 [node01: disk_server_1: disk.ioMediumError:notice]: Medium error on disk 2a.15.23: op 0x2a:02352e00:0200 sector 37039683 SCSI:medium error -  - If the disk is in a RAID group, the subsystem will attempt to reconstruct unreadable data (3 3 0 3a) (3446) Disk 2a.15.23 Shelf 15 Bay 23 [NETAPP   X316_HARIH06TA07 NA00] S/N [1EH8NDAF] UID [5000CCA2:32481C2C:00000000:00000000:00000000:00000000:00000000:00000000:00000000:00000000]

Sun May 07 12:00:34 +0000 [node01: disk_server_0: disk.ioReassignSuccess:notice]: disk 2a.15.23: sector 37039683 was reassigned (785). Disk 2a.15.23 Shelf 15 Bay 23 [NETAPP   X316_HARIH06TA07 NA00] S/N [1EH8NDAF] UID [5000CCA2:32481C2C:00000000:00000000:00000000:00000000:00000000:00000000:00000000:00000000]

Sun May 07 12:02:52 +0000 [node01: disk_latency_monitor: shm.threshold.ioLatency:debug]: Disk 2a.15.23 has exceeded the expected IO latency in the current window with average latency of 52 msecs and average utilization of 53 percent. Highest average IO latency: 2a.15.23: 52 msecs; next highest IO latency: 9d.67.0: 35 msecs. Disk 2a.15.23 Shelf 15 Bay 23 [NETAPP   X316_HARIH06TA07 NA00] S/N [1EH8NDAF] UID [5000CCA2:32481C2C:00000000:00000000:00000000:00000000:00000000:00000000:00000000:00000000]

Sun May 07 12:03:22 +0000 [node01: disk_latency_monitor: shm.threshold.ioLatency:debug]: Disk 2a.15.23 has exceeded the expected IO latency in the current window with average latency of 65 msecs and average utilization of 62 percent. Highest average IO latency: 2a.15.23: 65 msecs; next highest IO latency: 9d.67.0: 37 msecs. Disk 2a.15.23 Shelf 15 Bay 23 [NETAPP   X316_HARIH06TA07 NA00] S/N [1EH8NDAF] UID [5000CCA2:32481C2C:00000000:00000000:00000000:00000000:00000000:00000000:00000000:00000000]