[Beowulf] Threaded code
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.
Robert G. Brown rgb at phy.duke.eduTue Aug 17 09:11:41 PDT 2004
- Previous message: [Beowulf] Threaded code
- Next message: [Beowulf] Torque on Cray XD1 ?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Mon, 16 Aug 2004, Art Edwards wrote: > Newbie question: > > We just purchased a dual opteron box that is running an SMP kernel. We > have built a fortran code using g77 and a pthreaded atlas. Currently, we > see only one processor. What really simple thing have we missed? What do you mean you only "see" one processor? You SHOULD see e.g.: rgb at ganesh|B:1023>s00 cat /proc/cpuinfo processor : 0 vendor_id : AuthenticAMD cpu family : 15 model : 5 model name : AMD Opteron(tm) Processor 242 stepping : 1 cpu MHz : 1603.699 cache size : 1024 KB fpu : yes fpu_exception : yes cpuid level : 1 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr s e sse2 syscall nx mmxext lm 3dnowext 3dnow bogomips : 3153.92 TLB size : 1088 4K pages clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: ts ttp processor : 1 vendor_id : AuthenticAMD cpu family : 15 model : 5 model name : AMD Opteron(tm) Processor 242 stepping : 1 cpu MHz : 1603.699 cache size : 1024 KB fpu : yes fpu_exception : yes cpuid level : 1 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr s e sse2 syscall nx mmxext lm 3dnowext 3dnow bogomips : 3203.07 TLB size : 1088 4K pages clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: ts ttp If you don't, there are really only two possibilities I can think of. a) You aren't really running an SMP kernel, or your SMP kernel is badly broken. Check: rgb at ganesh|B:1024>s00 uname -a Linux s00 2.6.5-1.358smp #1 SMP Sat May 8 09:28:14 EDT 2004 x86_64 x86_64 x86_64 GNU/Linux Not a certain check -- depends on how your kernel was labelled more than on whether or not it really is SMP. To be double sure, check your distribution and kernel RPM(s). This one is from FC2, for example. If you're building your own kernels, be certain that you have configured the kernel for SMP (or consider NOT building your own and instead use the smp kernel(s) from a reliable x86_64 distro). Note that the installation kernel (the one used to actually run a distribution install) is never an SMP kernel, in case you are somehow still running that via a PXE/diskless boot. b) You don't really have two functioning processors in the box. Opening the box and physically verifying that there are two CPUs is called for. Seriously. I had this same problem with the very first SMP system I ever ordered (dual PPros, kernel 2.0.0). Turned out that the systems had dual motherboards with only a single CPU mounted -- the vendor had screwed up the order. Alternatively you could have two cpus physically present but CPU2 could be DOA. Conceivably you could have two functioning CPUs but a BIOS problem (I don't know if this is possible on the opteron hardware but it is not IMpossible overall). Hope this helps, rgb > > Art Edwards > > -- Robert G. Brown http://www.phy.duke.edu/~rgb/ Duke University Dept. of Physics, Box 90305 Durham, N.C. 27708-0305 Phone: 1-919-660-2567 Fax: 919-660-2525 email:rgb at phy.duke.edu
- Previous message: [Beowulf] Threaded code
- Next message: [Beowulf] Torque on Cray XD1 ?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
