AF-A400 会由于不可更正的 ECC 错误而发生 watchdog 重置
适用场景
- AFF A400
- FAS 8300
- FAS 8700
问题描述
- 节点重新启动,无法完成开机自检
- 自
system log sel
10d | 12/25/2021 | 07:10: 44 | Memory #0x08 | Uncorrectable ECC | Asserted
10e | 12/25/2021 | 07:10: 44 | Memory #0x08 | Uncorrectable ECC | Asserted
10f | 12/25/2021 | 07:10:46 | Watchdog 2 #0xb1 | Timer interrupt (NMI/SMS/OS) | Asserted
110 | 12/25/2021 | 07:10: 46 | Critical Interrupt #0xb0 | NMI/Diag Interrupt | Asserted
- 自
system log console
PANIC: watchdog nmi on cpu 8, hang cpu is 0 in process idle: cpu8 on release 9.7P12 (C) on Sat Dec 25 01:10:45 CST 2021