Messages in this thread | | | Date | Mon, 22 Mar 2004 08:24:36 -0800 (PST) | From | markw@osdl ... | Subject | Re: 2.6.4-mm2 |
| |
On 20 Mar, Nick Piggin wrote: > > > Len Brown wrote: > >>On Fri, 2004-03-19 at 23:19, Brown, Len wrote: >> >>>CONFIG_X86_HT=y does not enable HT. >>>CONFIG_X86_HT=n does not disable HT. >>>It only controls if the cpu_sibling_map[] etc. are initialized. >>> >>>acpi=off does not disable HT >>> >> >>oops, that line incorrect. >>we fixed "acpi=off" to _really_ mean ACPI off -- table parsing >>and all, so it does disable HT, along w/ all the other stuff >>that depends on ACPI. >> >> > > So how come oprofile seems to think there is a sibling? > Can you verify both cases use physical only CPUs?
The sar output still only lists data for 4 individual CPUs. Is that a good way to verify it? - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |