Chris Samuel wrote: > But as soon as we went to the mainline kernel (started at 2.6.22.3, > currently at 2.6.23.1) those problems went away.
Hi, This prompted me to wonder how close to the bleeding edge people in clusterland are living with regard to Linux kernel versions? We've Debian stable deployed on our main customer's cluster and I'm inclined to run with their latest stable kernel (a flavour of 2.6.18 with some patches at the moment) rather than going with the latest kernel.org release. My understanding is that the "stable" kernel in 2.6 isn't quite the stable kernel we had in 2.4 (with commensurate pros and cons to that arrangement). If people are on the bleeding edge, how well do you hammer on a kernel before rolling it into production? In terms of cost-benefit, I think we're better off where we are at the moment, just curious where others are. Thanks, -stephen -- Stephen Mulcahy, Applepie Solutions Ltd., Innovation in Business Center, GMIT, Dublin Rd, Galway, Ireland. +353.91.751262 http://www.aplpi.com Registered in Ireland, no. 289353 (5 Woodlands Avenue, Renmore, Galway) _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
