使用 Real Time 内核的系统出现崩溃,带有 "Kernel panic - not syncing: RCU Stall" 错误信息
Issue
- 内存出现问题(panic),在控制台中带有以下信息:
Kernel panic - not syncing: RCU Stall
PID: 425416 TASK: ffff8b257ca8d3c0 CPU: 40 COMMAND: XXXXXXXXXXXXXXXXX
#0 [ffff8b1d9df09e40] crash_nmi_callback at ffffffff83245e57
#1 [ffff8b1d9df09e50] nmi_handle at ffffffff8395f8e4
#2 [ffff8b1d9df09ea8] do_nmi at ffffffff8395fafd
#3 [ffff8b1d9df09ef0] end_repeat_nmi at ffffffff8395ed39
[exception RIP: generic_exec_single+0xfa]
RIP: ffffffff83306d6a RSP: ffff8b24eb39fb20 RFLAGS: 00000202
RAX: ffff8b0e2df73c00 RBX: ffff8b24eb39fb20 RCX: ffff8b0e2df73c30
RDX: ffff8b359be1cb40 RSI: ffff8b24eb39fb20 RDI: ffff8b24eb39fb20
RBP: ffff8b24eb39fb68 R8: 0000000000000001 R9: 000000055076903e
R10: fffff70944138980 R11: 0000000000000000 R12: 0000000000000014
R13: 0000000000000001 R14: 0000000000000001 R15: ffff8b24eb39fbf8
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000
--- <NMI exception stack> ---
#4 [ffff8b24eb39fb20] generic_exec_single at ffffffff83306d6a
#5 [ffff8b24eb39fb70] smp_call_function_single at ffffffff83306e92
#6 [ffff8b24eb39fba8] smp_call_function_many at ffffffff833074ca
#7 [ffff8b24eb39fbf0] native_flush_tlb_others at ffffffff8326abe8
[...]
Environment
- Red Hat Enterprise Linux 7 for Real Time
- 特别是内核版本
kernel-rt-3.10.0-514.1.1.rt56.422.el7及更高的版本 - 请注意,Red Hat Enterprise Linux 8 for Real Time 或其他 Red Hat Enterprise Linux 版本没有这个问题
- 特别是内核版本
Subscriber exclusive content
A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.