centos7.9日志排查硬件故障问题【温度过高导致硬盘故障】

centos7.9日志排查硬件故障问题【温度过高导致硬盘故障】

工控机8g+128g.经常出现无法正常重启的情况。经过相关日志排查，定位到cpu温度过高，导致cpu时钟频率异常，并经常出现硬盘连接异常。

1./var/log/dmesg日志排查

/var/log/dmesg日志可以排查出硬盘的故障信息。

1.1出现pci设备分配内存空间异常信息

[    1.041807] pci 0000:00:1c.0: BAR 14: failed to assign [mem size 0x00200000]
[    1.041816] pci 0000:00:1c.0: BAR 15: no space for [mem size 0x00200000 64bit pref]
[    1.041821] pci 0000:00:1c.0: BAR 15: failed to assign [mem size 0x00200000 64bit pref]
[    1.041827] pci 0000:00:1c.0: PCI bridge to [bus 01]

2.出现文件系统还原的信息

[    4.721879]  sda: sda1 sda2
[    4.722851] sd 1:0:0:0: [sda] Attached SCSI disk
[    5.242966] random: fast init done
[    5.434299] SGI XFS with ACLs, security attributes, no debug enabled
[    5.438591] XFS (dm-0): Mounting V5 Filesystem
[    5.528502] XFS (dm-0): Starting recovery (logdev: internal)
[    5.768210] XFS (dm-0): Ending recovery (logdev: internal)

2./var/log/messages日志排查

1.出现硬盘连接缓慢信息

localhost kernel: ata2.00: exception Emask 0x0 SAct 0x0 SErr oxo action 0x6 frozen
localhost kernel: ata2: link is slow to respond,please be patient (ready=0)
localhost kernel: ata2:COMRESET failed (error=-6)
localhost kernel: ata2:hard resetting link

2.出现CPU温度超过阈值（超过85度），频率下降信息

Sep  3 00:50:59 localhost kernel: CPU0: Core temperature above threshold, cpu clock throttled (total events = 586124)
Sep  3 00:50:59 localhost kernel: CPU1: Core temperature above threshold, cpu clock throttled (total events = 586231)
Sep  3 00:50:59 localhost kernel: CPU2: Core temperature above threshold, cpu clock throttled (total events = 584496)
Sep  3 00:50:59 localhost kernel: CPU3: Core temperature above threshold, cpu clock throttled (total events = 584627)

3.查看温度

使用命令sensors来查看当前cpu温度

4.解决方案

1.静待一段时间，等温度降下来，可能可以正常重启

2.更换新设备

3.工控机增加散热鳍片、增加8500转的风扇