2012-05-08 21:03:27

by wilson self

[permalink] [raw]
Subject: Work queues and cpu isolation

I have done some reading on the subject of work queues and CPU
isolation, and specifically I've read a number of posts from Max K.
dating back to 2008 on the subject of CPU isolation. However, I have
not seen much in the way of discussion on the subject in more recent
times, specifically in the 3.x kernels; where it appears there are
some significant differences in the structure of workqueue in general.

Is there anyone currently doing work on additional isolation of CPUs
from work queues? I have some requirement to further isolate cores on
a machine from these queues and am hoping someone here could point me
in the right direction.

Thanks.
wilson


2012-05-08 21:10:40

by Jack Stone

[permalink] [raw]
Subject: Re: Work queues and cpu isolation

[Adding CCs]

On 05/08/2012 10:03 PM, wilson self wrote:
> I have done some reading on the subject of work queues and CPU
> isolation, and specifically I've read a number of posts from Max K.
> dating back to 2008 on the subject of CPU isolation. However, I have
> not seen much in the way of discussion on the subject in more recent
> times, specifically in the 3.x kernels; where it appears there are
> some significant differences in the structure of workqueue in general.
>
> Is there anyone currently doing work on additional isolation of CPUs
> from work queues? I have some requirement to further isolate cores on
> a machine from these queues and am hoping someone here could point me
> in the right direction.
>
> Thanks.
> wilson

2012-05-09 14:35:58

by Gilad Ben-Yossef

[permalink] [raw]
Subject: Re: Work queues and cpu isolation

Hi Wilson,

On Wed, May 9, 2012 at 12:03 AM, wilson self <[email protected]> wrote:
> I have done some reading on the subject of work queues and CPU
> isolation, and specifically I've read a number of posts from Max K.
> dating back to 2008 on the subject of CPU isolation. ?However, I have
> not seen much in the way of discussion on the subject in more recent
> times, specifically in the 3.x kernels; where it appears there are
> some significant differences in the structure of workqueue in general.
>
> Is there anyone currently doing work on additional isolation of CPUs
> from work queues? I have some requirement to further isolate cores on
> a machine from these queues and am hoping someone here could point me
> in the right direction.
>

Yes, I am and so do many other people on the general topic of CPU isolation.

Start here: https://github.com/gby/linux/wiki

Continue here: https://lkml.org/lkml/2012/5/3/268

And if you are interested in CPU isolation in general, then these will
interest you as well:

http://lwn.net/Articles/495422/

http://lkml.indiana.edu/hypermail/linux/kernel/1202.1/00590.html (this
last patch set has gone into 3.4-rc1 already)

I'd be very glad to cooperate :-)

Gilad

> Thanks.
> wilson
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at ?http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at ?http://www.tux.org/lkml/



--
Gilad Ben-Yossef
Chief Coffee Drinker
[email protected]
Israel Cell: +972-52-8260388
US Cell: +1-973-8260388
http://benyossef.com

"If you take a class in large-scale robotics, can you end up in a
situation where the homework eats your dog?"
?-- Jean-Baptiste Queru