崩溃:CPU 4上的watchdog NMI、挂起CPU为4 AFF A900
适用场景
- AFF A900
问题描述
- 系统发生故障、控制台日志中可能会出现以下崩溃:
PANIC : watchdog nmi on cpu 4, hang cpu is 4
- 在BMC系统事件日志中可以看到以下内容
Record 694: Mon Nov 07 11:23:21.254863 2022 [IPMI.notice]: 01dc | 02 | EVT: 6fc824ff | System_Watchdog | Assertion Event, "Timer interrupt"
Record 695: Mon Nov 07 11:23:21.696757 2022 [IPMI Event.critical]: NMI
Record 696: Mon Nov 07 11:23:21.729303 2022 [IPMI.notice]: 01dd | 02 | EVT: 6f00ffff | CriticalInt | Assertion Event, "NMI/Diag Interrupt"
Record 697: Mon Nov 07 11:23:29.627384 2022 [BMC.critical]: Filer Reboots
Record 698: Mon Nov 07 11:23:29.645845 2022 [Trap Event.critical]: SNMP abnormal_reboot (28)