NS224 磁盘架中的 NVMe I/O 超时和 SCSI 错误
适用于
NS224 磁盘架
问题
- 从虚拟机主机检测到一致性点延迟问题和 SCSI 错误。
- 带有超时的 EMS 消息：
Thu Dec 03 20:51:03 CET [node_name: intr: nvmeof.timeout:notice]: Timeout on subnqn nqn.2014-08.org.nvmexpress.discovery, controller ID 5, qpair ID 0, sequence number 45417.Thu Dec 03 20:51:03 CET [node_name: intr: nvmeof.rdma.disconnect.status:notice]: NVMe-oF disconnect on subnqn nqn.2014-08.org.nvmexpress.discovery, controller ID 5, qpair ID 0.- 控制器到磁盘架端口的 ifstat 输出中的 NVMe 高计数器。
-- interface e0c (53 days, 23 hours, 58 minutes, 41 seconds) --
RECEIVE
Total frames: 11625k | Frames/second: 2 | Total bytes: 5312m
Bytes/second: 1139 | Total errors: 0 | Errors/minute: 0
Total discards: 1789k | Discards/minute: 23 | Multi/broadcast: 4969k
Non-primary u/c: 0 | CRC errors: 0 | Runt frames: 0
Fragment: 0 | Long frames: 0 | Jabber: 0
Length errors: 0 | Alignment errors: 0 | No buffer: 0
Pause: 0 | Jumbo: 25792m | Error symbol: 0
Bus overruns: 1789k | Queue drops: 0 | LRO segments: 0
LRO bytes: 0 | LRO6 segments: 6520k | LRO6 bytes: 4178m
Bad UDP cksum: 0 | Bad UDP6 cksum: 0 | Bad TCP cksum: 0
Bad TCP6 cksum: 0 | Mcast v6 solicit: 1552k
TRANSMIT
Total frames: 10504k | Frames/second: 2 | Total bytes: 1081m
Bytes/second: 232 | Total errors: 0 | Errors/minute: 0
Total discards: 0 | Queue overflow: 0 | Multi/broadcast: 3259k
Pause: 471k | Jumbo: 29818m | Cfg Up to Downs: 2
TSO segments: 0 | TSO bytes: 0 | TSO6 segments: 0
TSO6 bytes: 0 | HW UDP cksums: 0 | HW UDP6 cksums: 3104k