有个vmware上的数据库虚拟机，message日志报错BUG: soft lockup - CPU#0 stuck for 22s!

[root@db3 ~]#  grep 'BUG: soft lockup' /var/log/messages

May  2 01:28:08 db3 kernel: BUG: soft lockup - CPU#0 stuck for 22s! [kworker/u:1:9790]
May  2 05:28:08 db3 kernel: BUG: soft lockup - CPU#0 stuck for 22s! [kworker/u:1:11290]
May  4 01:17:44 db3 kernel: BUG: soft lockup - CPU#8 stuck for 22s! [kworker/u:1:24737]
May  4 01:18:12 db3 kernel: BUG: soft lockup - CPU#0 stuck for 22s! [kworker/u:1:24737]
May  5 01:05:44 db3 kernel: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/u:0:25931]

卡死后必须在管理平台重启该机器，机器重启正常后，直接做如下操作

echo 'kernel.watchdog_thresh=30' >> /etc/sysctl.conf
sysctl -p

观察3天多已不再报错cpu了