How do you keep clusters running....

[Jim Lux]

You know, fans shouldn't fail...... There are fans available with 50,000 
hour MTBFs.. sure, they cost a bit more than $5, but, given the cost of the 
time to replace them (especially if you cook something), it might be a good 
investment.

You might cannibalize one of your failed fans to look for the number and 
kind of bearings.  I have heard that some "ball bearing" fans actually have 
sleeve bearings, a sure recipe for short life.  It's not unheard of to have 
some fans that are mislabelled.  Bear in mind that most fans have two 
bearings (one on each end of the shaft) and it is entirely possible to 
build a fan with one sleeve and one ball bearing.

At 03:04 PM 4/3/2002 -0600, Cris Rhea wrote:

>What are folks doing about keeping hardware running on large clusters?
>
>Right now, I'm running 10 Racksaver RS-1200's (for a total of 20 nodes)...
>
>Sure seems like every week or two, I notice dead fans (each RS-1200
>has 6 case fans in addition to the 2 CPU fans and 2 power supply fans).



>Jim Lux

Spacecraft Telecommunications Equipment Section
Jet Propulsion Laboratory
4800 Oak Grove Road, Mail Stop 161-213
Pasadena CA 91109

818/354-2075, fax 818/393-6875