On Fri, Feb 26, 2010 at 12:27:59PM -0600, Les Mikesell wrote: > On 2/26/2010 12:11 PM, Dominik Zyla wrote: > > On Fri, Feb 26, 2010 at 09:57:52AM -0800, John R Pierce wrote: > >> Dominik Zyla wrote: > >>> But it'll not give information about temperature in server room. > >>> > >> > >> actually, it sorta can. find the lowest reading sensor on the > >> system, probably one on the mainboard... use a manual thermometer to > >> read the intake air temp and calculate the delta. > >> > >> i think you'll find under normal operating conditions that delta is > >> pretty constant if the server is under a reasonably consistent workload. > > > > True.. We're also doing like this in some of server rooms. But sometimes > > we had strange values. So this sort of stuff can be not good enough. :) > > If you can get graphs from two different pieces of equipment on the same > page you can pretty much see the trend. A single device might have a > fan go bad or something - but that should probably be fixed anyway. On > servers that have variable CPU power you might see temperature > variations depending on the load. You have right. While you checking sensors from few machines, you can see the trend. Gotta think about changing the way of temperature monitoring here. -- Dominik Zyla -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 195 bytes Desc: not available URL: <http://lists.centos.org/pipermail/centos/attachments/20100226/bca7dd83/attachment-0005.sig>