| 1 |
On Fri, 23 Sep 2005, Joao Patricio wrote: |
| 2 |
|
| 3 |
> Did you enable SMP when you compiled your kernel? |
| 4 |
|
| 5 |
Both SMP and SMT are enabled in this kernel: |
| 6 |
|
| 7 |
# grep SMP /usr/src/linux/.config |
| 8 |
|
| 9 |
# CONFIG_X86_BIGSMP is not set |
| 10 |
CONFIG_SMP=y |
| 11 |
CONFIG_X86_FIND_SMP_CONFIG=y |
| 12 |
CONFIG_X86_SMP=y |
| 13 |
|
| 14 |
# grep SMT /usr/src/linux/.config |
| 15 |
|
| 16 |
CONFIG_SCHED_SMT=y |
| 17 |
|
| 18 |
|
| 19 |
|
| 20 |
> |
| 21 |
> Em Sexta, 23 de Setembro de 2005 23:05, o A. Khattri escreveu: |
| 22 |
> > On Fri, 23 Sep 2005, kashani wrote: |
| 23 |
> > > A. Khattri wrote: |
| 24 |
> > > > I switched on SMP and HT when building my kernel but I see this among |
| 25 |
> > > > the boot messages: |
| 26 |
> > > > |
| 27 |
> > > > CPU: After generic identify, caps: bfebfbff 00000000 00000000 00000000 |
| 28 |
> > > > 0000441d 00000000 00000000 |
| 29 |
> > > > CPU: After vendor identify, caps: bfebfbff 00000000 00000000 00000000 |
| 30 |
> > > > 0000441d 00000000 00000000 |
| 31 |
> > > > monitor/mwait feature present. |
| 32 |
> > > > using mwait in idle threads. |
| 33 |
> > > > CPU: Trace cache: 12K uops, L1 D cache: 16K |
| 34 |
> > > > CPU: L2 cache: 1024K |
| 35 |
> > > > CPU: Hyper-Threading is disabled |
| 36 |
> > > |
| 37 |
> > > Is it possible it's disabled in the Bios? Some servers shipped that way |
| 38 |
> > > when they first came out IIRC. |
| 39 |
> > |
| 40 |
> > I didn't find any BIOS setting unfortunately... |
| 41 |
> > |
| 42 |
> > This is a Supermicro 5013C-T server with a P4 (P4SCE?) board in it. |
| 43 |
> > |
| 44 |
> > # cat /proc/cpuinfo |
| 45 |
> > processor : 0 |
| 46 |
> > vendor_id : GenuineIntel |
| 47 |
> > cpu family : 15 |
| 48 |
> > model : 4 |
| 49 |
> > model name : Intel(R) Pentium(R) 4 CPU 2.40GHz |
| 50 |
> > stepping : 1 |
| 51 |
> > cpu MHz : 2395.003 |
| 52 |
> > cache size : 1024 KB |
| 53 |
> > fdiv_bug : no |
| 54 |
> > hlt_bug : no |
| 55 |
> > f00f_bug : no |
| 56 |
> > coma_bug : no |
| 57 |
> > fpu : yes |
| 58 |
> > fpu_exception : yes |
| 59 |
> > cpuid level : 5 |
| 60 |
> > wp : yes |
| 61 |
> > flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca |
| 62 |
> > cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe pni monitor |
| 63 |
> > ds_cpl cid xtpr |
| 64 |
> > bogomips : 4718.59 |
| 65 |
> > |
| 66 |
> > |
| 67 |
> > -- |
| 68 |
> |
| 69 |
|
| 70 |
-- |
| 71 |
wheel of reincarnation |
| 72 |
|
| 73 |
[coined in a paper by T. H. Myer |
| 74 |
and I.E. Sutherland "On the Design of Display Processors", Comm. |
| 75 |
ACM, Vol. 11, no. 6, June 1968)] Term used to refer to a well-known |
| 76 |
effect whereby function in a computing system family is migrated |
| 77 |
out to special-purpose peripheral hardware for speed, then the |
| 78 |
peripheral evolves toward more computing power as it does its job, |
| 79 |
then somebody notices that it is inefficient to support two |
| 80 |
asymmetrical processors in the architecture and folds the function |
| 81 |
back into the main CPU, at which point the cycle begins again. |
| 82 |
|
| 83 |
Several iterations of this cycle have been observed in |
| 84 |
graphics-processor design, and at least one or two in |
| 85 |
communications and floating-point processors. Also known as `the |
| 86 |
Wheel of Life', `the Wheel of Samsara', and other variations of |
| 87 |
the basic Hindu/Buddhist theological idea. See also blitter, |
| 88 |
bit bang. |
| 89 |
|
| 90 |
-- |
| 91 |
gentoo-server@g.o mailing list |
Archives