On Wed, Jan 16, 2013 at 05:42:32PM -0800, Tejun Heo wrote:
> Currently, on the backend side, there are two layers of abstraction.
> For each CPU and the special unbound wq-specific CPU, there's one
> global_cwq. gcwq in turn hosts two worker_pools - one for normal
> priority, the other for highpri
Hey, Lai.
On Thu, Jan 24, 2013 at 09:36:39PM +0800, Lai Jiangshan wrote:
> For the whole patchset
> Reviewed-by: Lai Jiangshan
Thanks for reviewing it.
> The only concern: get_work_pool() may slow down __queue_work().
Yeap, I'm currently working on to optimize idr so that the fast path
basical
On 17/01/13 09:42, Tejun Heo wrote:
Hello,
Currently, on the backend side, there are two layers of abstraction.
For each CPU and the special unbound wq-specific CPU, there's one
global_cwq. gcwq in turn hosts two worker_pools - one for normal
priority, the other for highpri - each of which actu
Hey.
On Tue, Jan 22, 2013 at 02:37:02PM +0900, Joonsoo Kim wrote:
> > It seems like we'll need to support worker pools with custom
> > attributes, which is planned to be implemented as extra worker_pools
> > for the unbound CPU. Removing gcwq and having worker_pool as the top
> > level abstractio
Hello, Tejun.
On Wed, Jan 16, 2013 at 05:42:32PM -0800, Tejun Heo wrote:
> Hello,
>
> Currently, on the backend side, there are two layers of abstraction.
> For each CPU and the special unbound wq-specific CPU, there's one
> global_cwq. gcwq in turn hosts two worker_pools - one for normal
> prio
On Thu, Jan 17, 2013 at 11:25:28AM +0800, Wanlong Gao wrote:
> > git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git for-3.9-remove-gcwq
>
> Forgot to push out this branch?
Yeap, I did. Pushed out last night from phone so should be there now.
Thanks!
--
tejun
--
To unsubscribe from this
On 01/17/2013 09:42 AM, Tejun Heo wrote:
> Hello,
>
> Currently, on the backend side, there are two layers of abstraction.
> For each CPU and the special unbound wq-specific CPU, there's one
> global_cwq. gcwq in turn hosts two worker_pools - one for normal
> priority, the other for highpri - eac
Forgot to cc Jens and Jeff.
Jens, Jeff, the patchset itself probably won't interest you guys too
much but it's part of effort towards worker pool w/ custom attributes.
I'm working toward a design where the custom pools are integral part
of workqueue which share all the interface and semantics, whi
Hello,
Currently, on the backend side, there are two layers of abstraction.
For each CPU and the special unbound wq-specific CPU, there's one
global_cwq. gcwq in turn hosts two worker_pools - one for normal
priority, the other for highpri - each of which actually serves the
work items.
worker_po
9 matches
Mail list logo
