On 6/5/07, BERES Laszlo <[EMAIL PROTECTED]> wrote:
Hello,
thanks for your answers, but:
>> Really bad case ventillation. I suggest installing 2 extra fans, one in the
>> front and another in the back of the case. The air direction should
>> be the same, move the air to the back of the case.
My question is: why this problem occured on RHEL5 and why not on FC3?
Both systems have the same load, almost the same environment, and using
FC3 again works great again. What changed between 2.6.11 and 2.6.18? :)
Luck of the draw.. the problem could have been marginal for a while
and finally melted. Things like this happen all the time... even
though a CPU has no large moving parts (one might argue that logic
gates and such are nano-moving parts)... it does have wear and tear
that will eventually build up. If a CPU has been marginal it might
finally tip over due to:
1) CPU now uses a different part of itself a bit more than it did
before and god knows how one can figure that out without a logic map
the size of a major city.
2) CPU bad bit finally choked and would have choked on FC3 at the same time.
3) Cosmic ray chose that time to hit that cpu at that time etc etc.
I worked at a place where a group spent a couple of thousand/million
man-hours going over why CPU's failed in servers and basically their
conclusions on most of them were 'act of deus ex-machina'. Some could
be contributed to bad hardware practices.. but a lot seemed to be that
some chip degraded because some part of the CPU was bad and a
continued for-loop finally burnt it out. 20 other chips running the
same thing didnt do it though so it was just bad luck.
--
Stephen J Smoogen. -- CSIRT/Linux System Administrator
How far that little candle throws his beams! So shines a good deed
in a naughty world. = Shakespeare. "The Merchant of Venice"
_______________________________________________
rhelv5-list mailing list
[email protected]
https://www.redhat.com/mailman/listinfo/rhelv5-list
