lkml.org 
[lkml]   [2010]   [Jan]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH -v2 5/5] x86: use dmi check to treat disabled cpus as hotplug cpus.
On 01/12/2010 06:21 PM, Suresh Siddha wrote:
> On Tue, 2010-01-12 at 18:13 -0800, Yinghai Lu wrote:
>> On 01/12/2010 06:06 PM, Suresh Siddha wrote:
>>> On Tue, 2010-01-12 at 17:55 -0800, Yinghai Lu wrote:
>>>> you mean this blacklist could be too long?
>>>
>>> yes.
>>>
>>>>
>>>> switch to whitelist for the box can treat disabled cpus as hotplug
>>>> cpus?
>>>
>>> Do we really need all this? Systems which support physical hotplug
>>> typically have lot's of cpu's (mostly will have atleast > 8). Even if we
>>> really need to identify, then perhaps we can check if ACPI has any hints
>>> regarding the physical hotplug support at boot time (we should check
>>> with Andi Kleen or Len Brown on this).
>>>
>>> For now, I think we can keep it simple by using the detected enabled
>>> cpu's.
>>
>> sth like this ?
>
> Well, I was referring more to the apic model selection than the prefill
> case. About this possible cpu's, will the wastage be more than few kb
> for few disabled cpu's.

for 8 sockets systems if only have two cpus instatalled.

that disabled cpus will be 6 * 8 * 2 = 96.

and per_cpu area is about per cpu 2M, so will waste about 96 x 2M

YH


\
 
 \ /
  Last update: 2010-01-13 03:31    [W:0.120 / U:1.992 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site