<br><br><div class="gmail_quote">2011/3/22 <span dir="ltr"><<a href="mailto:m.roth@5-cent.us">m.roth@5-cent.us</a>></span><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="im">Vladimir Budnev wrote:<br>
> 2011/3/22 <<a href="mailto:m.roth@5-cent.us">m.roth@5-cent.us</a>><br>
>> Vladimir Budnev wrote:<br>
>> > 2011/3/21 <<a href="mailto:m.roth@5-cent.us">m.roth@5-cent.us</a>><br>
>> >> Vladimir Budnev wrote:<br>
>> >> ><br>
</div><div class="im">>> >> > We are running, Centos 4.8 on SuperMicro SYS-6026T-3RF with 2xIntel<br>
>> >> > Xeon E5630 and 8xKingston KVR1333D3D4R9S/4G<br>
>> >> ><br>
>> >> > For some time we have lots of MCE in mcelog and we cant find out<br>
>> >> > the reason.<br>
>> >><br>
>> >> The only thing that shows there (when it shows, since sometimes it<br>
>> >> doesn't seem to) is a hardware error. You *WILL* be replacing<br>
>> >> hardware, sometime soon, like yesterday.<br>
>> <snip><br>
>> >> Bad news: you have *two* DIMMs failing, one associated with the<br>
>> >> physical CPU that has core 53, and another associated with the<br>
physical CPU<br>
>> >> that has cores 32-35.<br>
</div>>> <snip, memory reseating><br>
<div class="im">>> > Now we are just waiting will there be errors again.<br>
>><br>
>> I'm sure there will. Reseating the memory may have done something, but<br>
>> there will, I'll wager.<br>
><br>
> mark, you are absolutely right :) Approximetely 1h ago errors appeared.<br>
> They appeared only once since reboot, but they r back. Hi there :(<br>
><br>
> The good idea is that CPU numbers changed, so now we have cpu 1,2,3 and<br>
> 18,19,20,21.We definetely moved "broken" modules to another slots.<br>
> Anyway bad dimm is really a good news for us instead of e.g. motherboard.<br>
</div><snip><br>
<div class="im">> Is it possible to determine which physical dimms correspond to those cpus<br>
> noticed in mce messagees? We have two rows of slots(6 slot for each row)<br>
> one for cpu1 and second for cpu2. Used slots marked as<br>
> cpu1-a1,cpu1-a2,cpu1-a3,cpu1-b1 and cpu2-a1,cpu2-a2,cpu2-a3,cpu2-b1.<br>
><br>
> I remeber that you adviced to divide cpu number on physical core count. We<br>
> have 2 quad core proc, so 8 cpu. 1/8=0 Is it cpu-a1 slot or depends on<br>
> situation? I hope we will find those bustards ourselvs but hint would be<br>
> great.<br>
><br>
> And one more thing i cant funderstand ... if there is,say, 8 "cpu numbers"<br>
> per each memory module(in our situation), why we see only 4 numbers and<br>
> not 8 e.g. 0,1,2,3,4,5,6,7 ?<br>
<br>
</div>I'm now confused about a lot: originally, you mentioned 53 - 57, was it?<br>
That doesn't add up, since you say you have 2 quad core processors, for a<br>
total of 8 cpus, and each of those processors have 6 banks, which would<br>
mean each processor should only see six (directly). Where I'm confused is<br>
how you could have cores 32-35, or 53-whatsit, when you only have 8 cores<br>
in two processors.<br></blockquote><div> </div><div> 2 cpu each 8 cores and HT support. So 16 at max i think. for such way is it ok?<br> I really lost the idea line with those cpu to memory bank mappings...<br><br></div>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="im">><br>
>> Here's a question out of left field: who was the manufacturer of the 4G<br>
>> DIMMs? Not Supermicro, but the DIMMs themselves?<br>
>><br>
> This is Kingston KVR1333D3D4R9S/4G if i got the question<br>
<br>
</div>Oh, ok. I was wondering if they were Hynix - I've seen a good number of<br>
bad 4G and 8G DIMMs from them recently, and that across three different<br>
OEMs and model DIMMs.<br>
<div><div></div><div class="h5"><br>
mark<br>
<br>
_______________________________________________<br>
CentOS mailing list<br>
<a href="mailto:CentOS@centos.org">CentOS@centos.org</a><br>
<a href="http://lists.centos.org/mailman/listinfo/centos" target="_blank">http://lists.centos.org/mailman/listinfo/centos</a><br>
</div></div></blockquote></div><br>