偶现cpu/内存温度获取不到问题

// 此模板仅供参考,如果不适用可以修改

问题描述

os重启后,出现CPU 内存温度获取失败的告警,一分钟之后才消失;

  1. 出现告警前后有下面imu告警

889: 2026-06-08 16:47:59.157060 ipmi_coreNOTICE: host_checker.lua(181): [systemId:1]communation with imu is abnormal
1703: 2026-06-08 17:01:43.659392 ipmi core: NOTICE: host checker.lua(181): [systemId:1]communation with imu is abnormal
2166: 2026-06-08 17:07:26.787395 ipmi_coreNOTICE: host_checker.lua(181): [systemId:1]communation with imu is abnormal
2593: 2026-06-08 17:11:58.842056 ipmi core: NOTICE: host checker.lua(181): [systemId:1]communation with imu is abnormal
3741: 2026-06-08 17:48:42.728191 ipmi core: NOTICE: host checker.lua(181): [systemId:1]communation with imu is abnormal
4386: 2026-06-08 17:54:17.834564 ipmi coreNOTICE: host checker.lua(181): [systemId:1]communation with imu is abnorma
5725:2026-06-08 18:09:18.497090 ipmi core: NOTICE: host checker.lua(181): [systemId:1]communation with imu is abnormal
6148: 2026-06-08 18:13:48.557165 ipmi core NOTICE: host checker.lua(181): [systemId:1]communation with imu iis abnormal

  1. imu_log里有大量0x80错误:

[ERR]IpmiSendRequest failed in task ipmis

ACK Check Failed. Completion code = 0x80

IpmbWrite failed, Try Again Times:1 !!!

ACK Check Failed. Completion code = 0x80

IpmbWrite failed, Try Again Times:2 !!!

ACK Check Failed. Completion code = 0x80

IpmbWrite failed, Try Again Times:3 !!!

IPMB Send msg failed! Status:1

版本信息:基于330版本

想问一下:

  1. 出现communation with imu is abnormal错误是说明imu异常还是bmc这边有问题

  2. imu_log里的日志里0x80错误码是bmc返回给imu的还是imu返回给bmc的

当然是bmc返回的错误码