On Thu, Jul 31, 2014 at 09:54:21AM +0100, Morten Rasmussen wrote:
>
> Overall, it is not clear to me why it is necessary to rewrite the
> per-entity load-tracking. The code is somewhat simpler, but I don't see
> any functional additions/improvements. If we have to go through a long
> review and te
On Wed, Jul 30, 2014 at 08:17:39PM +0100, Yuyang Du wrote:
> Hi Morten,
>
> On Wed, Jul 30, 2014 at 11:13:31AM +0100, Morten Rasmussen wrote:
> > > > 2. runnable_load_avg and blocked_load_avg are combined
> > > >
> > > > runnable_load_avg currently represents the sum of load_avg_contrib of
> > >
Hi Morten,
On Wed, Jul 30, 2014 at 11:13:31AM +0100, Morten Rasmussen wrote:
> > > 2. runnable_load_avg and blocked_load_avg are combined
> > >
> > > runnable_load_avg currently represents the sum of load_avg_contrib of
> > > all tasks on the rq, while blocked_load_avg is the sum of those tasks
>
On Wed, Jul 30, 2014 at 11:21:28AM +0100, Peter Zijlstra wrote:
> On Wed, Jul 30, 2014 at 11:13:31AM +0100, Morten Rasmussen wrote:
> > It is a very real problem when user-space uses priorities extensively
> > like Android does. Tasks related to audio run at very high priorities
> > but only for a
On Wed, Jul 30, 2014 at 11:13:31AM +0100, Morten Rasmussen wrote:
> It is a very real problem when user-space uses priorities extensively
> like Android does. Tasks related to audio run at very high priorities
> but only for a very short amount of time, but due the to priority
> scaling their load
On Sun, Jul 27, 2014 at 08:02:37PM +0100, Yuyang Du wrote:
> Hi Morten,
>
> On Fri, Jul 18, 2014 at 04:39:31PM +0100, Morten Rasmussen wrote:
> > 1. runnable_avg_period is removed
> >
> > load_avg_contrib used to be runnable_avg_sum/runnable_avg_period scaled
> > by the task load weight (priority
On Tue, Jul 29, 2014 at 09:17:13AM +0800, Yuyang Du wrote:
> On Mon, Jul 28, 2014 at 12:38:12PM +0200, Peter Zijlstra wrote:
> > On Mon, Jul 28, 2014 at 03:02:37AM +0800, Yuyang Du wrote:
> > > > Another thing that might be an issue is that the blocked of a terminated
> > > > task lives on for quit
On Mon, Jul 28, 2014 at 12:38:12PM +0200, Peter Zijlstra wrote:
> On Mon, Jul 28, 2014 at 03:02:37AM +0800, Yuyang Du wrote:
> > > Another thing that might be an issue is that the blocked of a terminated
> > > task lives on for quite a while until has decayed away.
> >
> > Good point. To do so, if
On Mon, Jul 28, 2014 at 03:02:37AM +0800, Yuyang Du wrote:
> > Another thing that might be an issue is that the blocked of a terminated
> > task lives on for quite a while until has decayed away.
>
> Good point. To do so, if I read correctly, we need to hook do_exit(), but
> probably
> we are gon
On Mon, Jul 28, 2014 at 03:34:53AM +0800, Yuyang Du wrote:
> Thanks a lot, Mike.
>
> Ben asked for this test, but actually I don't know how to get pipe-test, still
> not even after google it.
perf bench sched pipe
I realize that's a mouth full, but there it is.
pgpuZBDC7SrZ8.pgp
Description: P
On Mon, Jul 28, 2014 at 09:49:18AM +0200, Mike Galbraith wrote:
> On Mon, 2014-07-28 at 03:34 +0800, Yuyang Du wrote:
> > Thanks a lot, Mike.
> >
> > Ben asked for this test, but actually I don't know how to get pipe-test,
> > still
> > not even after google it.
>
> You could write it trivially
On Mon, 2014-07-28 at 03:34 +0800, Yuyang Du wrote:
> Thanks a lot, Mike.
>
> Ben asked for this test, but actually I don't know how to get pipe-test, still
> not even after google it.
You could write it trivially, it's just pipe ping-pong. I can send you
a copy of the one I use if you like. I
Thanks a lot, Mike.
Ben asked for this test, but actually I don't know how to get pipe-test, still
not even after google it.
On Sun, Jul 20, 2014 at 07:46:23AM +0200, Mike Galbraith wrote:
> On Fri, 2014-07-18 at 07:26 +0800, Yuyang Du wrote:
> > Thanks to Morten, Ben, and Fengguang.
> >
> > v4
Hi Morten,
On Fri, Jul 18, 2014 at 04:39:31PM +0100, Morten Rasmussen wrote:
> 1. runnable_avg_period is removed
>
> load_avg_contrib used to be runnable_avg_sum/runnable_avg_period scaled
> by the task load weight (priority). The runnable_avg_period is replaced
> by a constant in this patch set.
On Fri, 2014-07-18 at 07:26 +0800, Yuyang Du wrote:
> Thanks to Morten, Ben, and Fengguang.
>
> v4 changes:
>
> - Insert memory barrier before writing cfs_rq->load_last_update_copy.
> - Fix typos.
My little desktop box says lovely minus signs have had their usual
effect on the general case (cgr
On Fri, Jul 18, 2014 at 12:26:04AM +0100, Yuyang Du wrote:
> Thanks to Morten, Ben, and Fengguang.
>
> v4 changes:
>
> - Insert memory barrier before writing cfs_rq->load_last_update_copy.
> - Fix typos.
It is quite a challenge keeping up with your revisions :) Three
revisions in five days. It t
Thanks to Morten, Ben, and Fengguang.
v4 changes:
- Insert memory barrier before writing cfs_rq->load_last_update_copy.
- Fix typos.
We carried out some performance tests (thanks to Fengguang and his LKP). The
results are shown
as follows. The patchset (including two patches) is on top of mainl
17 matches
Mail list logo