[Beowulf] [gorelsky@stanford.edu: CCL:dual-coreOpteron275performance]
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Mark Hahn hahn at physics.mcmaster.caThu Jul 14 15:10:45 PDT 2005
- Previous message: [Beowulf] [gorelsky@stanford.edu: CCL:dual-coreOpteron275performance]
- Next message: [Beowulf] Re: Opteron 275 performance
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
> taskset is part of schedutils by Robert Love http://rlove.org/schedutils/ it's also worth knowing that sched_setaffinity does all the work (not much!). for most normal systems, setting affinity (especially to a single core) is probably going to have bad effects some times. for instance, interrupt handling. which has a similar bitmask-based interface like echo 1 > /proc/irq/0/smp_affinity I've wondered whether this makes sense to do on opteron systems where the IO bridge is attached to a single socket. regards, mark hahn.
- Previous message: [Beowulf] [gorelsky@stanford.edu: CCL:dual-coreOpteron275performance]
- Next message: [Beowulf] Re: Opteron 275 performance
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
