是否硬件真的有问题了呢，还是内核问题？

-scofield-

Jul  5 08:29:05 mail kernel: EDAC i5000 MC0: FATAL ERRORS Found!!! 1st FATAL Err Reg= 0x4
Jul  5 08:29:05 mail kernel: EDAC i5000 MC0: >Tmid Thermal event with intelligent throttling disabled
Jul  5 08:29:05 mail kernel: EDAC MC0: UE row 1, channel-a= 0 channel-b= 1 labels "-": (Branch=0 DRAM-Bank=0 RDWR=Read RAS=2080 CAS=0 FATAL Err=0x4)
Jul  5 08:29:06 mail kernel: EDAC i5000 MC0: FATAL ERRORS Found!!! 1st FATAL Err Reg= 0x4
Jul  5 08:29:06 mail kernel: EDAC i5000 MC0: >Tmid Thermal event with intelligent throttling disabled
Jul  5 08:29:06 mail kernel: EDAC MC0: UE row 0, channel-a= 0 channel-b= 1 labels "-": (Branch=0 DRAM-Bank=1 RDWR=Read RAS=261 CAS=0 FATAL Err=0x4)
Jul  5 08:29:07 mail kernel: EDAC i5000 MC0: FATAL ERRORS Found!!! 1st FATAL Err Reg= 0x4
Jul  5 08:29:07 mail kernel: EDAC i5000 MC0: >Tmid Thermal event with intelligent throttling disabled


这是日志内容，今天早上来一连接上服务器就报这个东西，不停的刷屏，到了无法操作的地步，GOOGLE后得出结论有可能是内存问题，然后执行了
echo "1" >/sys/devices/system/edac/mc/log_ce
但是我现在有了疑虑，这个执行后是不提示了，可是服务器是安全的么，要是那天应用很紧张会不会就挂掉了，影响到了关键的事情呢，还是等到闲的时候拆下内存来更换呢，其实也不能确定是否真的就是内存问题，还是内核问题？

-scofield-

2.6.18-92.el5PAE

-scofield-

是不是应该换到非PAE下呢