由于看门狗 NMI 恐慌,AFF A800 节点故障
适用于
- ONTAP 9
- AFF A800,AFF C800,ASA A800,ASA C800
问题
- 节点因看门狗 NMI 而关闭
PANIC : watchdog nmi on cpu 34, hang cpu is 2
version: 9.13.1P6: Tue Dec 5 11:06:25 EST 2023
conf : x86_64.optimize
cpuid = 34
KDB: stack backtrace:
vpanic() at vpanic+0x3b2/frame 0xfffffe00c6c43c60
- 启动时,系统死机,并显示以下死机消息:
PANIC : System is going to shutdown because NVMEM subsystem failed initialization or configuration check.
- 从共享 SP 日志中,NVDIMM 处于错误状态,报告的事件为由于 SDRAM 未处于自刷新模式导致 NVMEM 初始化失败。
DIMM F1: NVDIMM in ERROR condition (0x00000801).
DIMM M1: NVDIMM in ERROR condition (0x00000801).
Tue Aug 20 04:56:52 2024 [nvdimm.nvmem.initfail:FAULT]:NVMEM subsystem initialization failed because NVDIMM device in slot-11 lost persistence due to SDRAM not in self-refresh mode , andNVDIMM HARDWARE error.. To prevent NVMEM data loss, halt the system.
Tue Aug 20 04:56:52 2024 [nvdimm.nvmem.initfail:FAULT]:NVMEM subsystem initialization failed because NVDIMM device in slot-23 lost persistence due to SDRAM not in self-refresh mode , andNVDIMM HARDWARE error.. To prevent NVMEM data loss, halt the system.
Tue Aug 20 04:56:52 2024 [nvdimm.nvmem.destage.failure:ALERT]:NVMEM subsystem failed to copy nonvolatile data to flash memory on NVDIMM device because SDRAM is not in self-refresh mode, and because of a hardware error..