AFF 上的 T6 网卡 e1a/e1b ( t6nex1 )出现致命错误 A800
适用场景
- AFF A800
- X1146A 双 40/100G 以太网 T62100-CR 网络接口卡( NIC )
- 交换机升级
问题描述
- 发生崩溃之前,带有 watchdog NMI 的节点崩溃以及 e1a/e1b 上的致命奇偶校验错误:
e1a/e1b (t6nex1): ! PL_PERR_CAUSE 0x19404 = 0x00000010, E 0x1fffe3ff, F 0xffffffff
e1a/e1b (t6nex1): ! [0x00000010] MPS
PANIC: watchdog nmi on cpu 45, hang cpu is 3 in process idle: cpu45 on release 9.7P5 (C)
- 如果节点能够启动或保持正常运行,可能还会看到 EMS 消息:
[node01: intr: netif.fatal.err:alert]: The network device in slot 1 encountered fatal error e1a/e1b.
- 节点可能不会发生崩溃、但会收到HA互连关闭EMS消息:
callhome.hainterconnect.down:alert]: Call home for HA INTERCONNECT DOWN due to link1 down.