最近装了一批DELL 12代的服务器(R620),运行几天后,发现在系统日志中出现很多CPU报警,如下:
CPU13: Package power limit notification (total events = 1)
CPU1: Package power limit notification (total events = 1)
CPU17: Package power limit notification (total events = 1)
CPU3: Package power limit notification (total events = 1)
CPU19: Package power limit notification (total events = 1)
CPU5: Package power limit notification (total events = 1)
CPU21: Package power limit notification (total events = 1)
CPU7: Package power limit notification (total events = 1)
CPU23: Package power limit notification (total events = 1)
CPU9: Package power limit notification (total events = 1)
CPU25: Package power limit notification (total events = 1)
CPU11: Package power limit notification (total events = 1)
CPU27: Package power limit notification (total events = 1)
CPU31: Package power limit notification (total events = 1)
CPU15: Package power limit notification (total events = 1)
CPU29: Package power limit notification (total events = 1)
CPU17: Core power limit normal
CPU1: Core power limit normal
CPU3: Core power limit normal
CPU19: Core power limit normal
CPU21: Core power limit normal
CPU5: Core power limit normal
CPU23: Core power limit normal
CPU7: Core power limit normal
查了一下google资料,解释说是应该是CPU的保护温度阈值在BIOS中设置的过于低了,于是在BIOS中搜索一番后,没有发现设置的CPU温度报警阈值的地方。在dell官网找到一份12代服务器的资料后,得到如下解释:
再次进入BIOS中,进入system profile settings,第一个选项默认是performance per watt(DAPC),选择该选项后,默认是开启Turbo boost的
在system profile中选择最后一个手动模式,剩下的其他选项就可以设置了,只要修改Turbo boost为disable,其余选项均不变即可,保存后重启机器。