Hi Will,
On 2017年10月02日 22:14, Will Deacon wrote:
Hi Qiao,
On Mon, Sep 25, 2017 at 07:02:03PM +0800, qiaozhou wrote:
Will this bodging patch be merged? It can solve the livelock issue on arm64
platforms(at least improve a lot).
Whilst it seemed to help in some cases, I'm not keen to merge
Hi Will,
On 2017年10月02日 22:14, Will Deacon wrote:
Hi Qiao,
On Mon, Sep 25, 2017 at 07:02:03PM +0800, qiaozhou wrote:
Will this bodging patch be merged? It can solve the livelock issue on arm64
platforms(at least improve a lot).
Whilst it seemed to help in some cases, I'm not keen to merge
Hi Qiao,
On Mon, Sep 25, 2017 at 07:02:03PM +0800, qiaozhou wrote:
> Will this bodging patch be merged? It can solve the livelock issue on arm64
> platforms(at least improve a lot).
Whilst it seemed to help in some cases, I'm not keen to merge it until
we've identified a sensible way to
Hi Qiao,
On Mon, Sep 25, 2017 at 07:02:03PM +0800, qiaozhou wrote:
> Will this bodging patch be merged? It can solve the livelock issue on arm64
> platforms(at least improve a lot).
Whilst it seemed to help in some cases, I'm not keen to merge it until
we've identified a sensible way to
Hi Will,
Will this bodging patch be merged? It can solve the livelock issue on
arm64 platforms(at least improve a lot).
I suspected that CCI-freq might impact the contention between little and
big core, but on my platform, it impacts little. In fact the frequency
of external DDR controller
Hi Will,
Will this bodging patch be merged? It can solve the livelock issue on
arm64 platforms(at least improve a lot).
I suspected that CCI-freq might impact the contention between little and
big core, but on my platform, it impacts little. In fact the frequency
of external DDR controller
On 2017年08月29日 07:12, Vikram Mulukutla wrote:
Well here's something interesting. I tried a different platform and
found that
the workaround doesn't help much at all, similar to Qiao's observation
on his b.L
chipset. Something to do with the WFE implementation or event-stream?
Hi Vikram,
On 2017年08月29日 07:12, Vikram Mulukutla wrote:
Well here's something interesting. I tried a different platform and
found that
the workaround doesn't help much at all, similar to Qiao's observation
on his b.L
chipset. Something to do with the WFE implementation or event-stream?
Hi Vikram,
Hi Will,
On 2017-08-25 12:48, Vikram Mulukutla wrote:
Hi Will,
On 2017-08-15 11:40, Will Deacon wrote:
Hi Vikram,
On Thu, Aug 03, 2017 at 04:25:12PM -0700, Vikram Mulukutla wrote:
On 2017-07-31 06:13, Will Deacon wrote:
>On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
>>On
Hi Will,
On 2017-08-25 12:48, Vikram Mulukutla wrote:
Hi Will,
On 2017-08-15 11:40, Will Deacon wrote:
Hi Vikram,
On Thu, Aug 03, 2017 at 04:25:12PM -0700, Vikram Mulukutla wrote:
On 2017-07-31 06:13, Will Deacon wrote:
>On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
>>On
On 2017-08-25 12:48, Vikram Mulukutla wrote:
If I understand the code correctly, the upper 32 bits of an ARM64
virtual
address will overflow when 1 is added to it, and so we'll keep WFE'ing
on
every subsequent cpu_relax invoked from the same PC, until we cross the
hard-coded threshold,
On 2017-08-25 12:48, Vikram Mulukutla wrote:
If I understand the code correctly, the upper 32 bits of an ARM64
virtual
address will overflow when 1 is added to it, and so we'll keep WFE'ing
on
every subsequent cpu_relax invoked from the same PC, until we cross the
hard-coded threshold,
Hi Will,
On 2017-08-15 11:40, Will Deacon wrote:
Hi Vikram,
On Thu, Aug 03, 2017 at 04:25:12PM -0700, Vikram Mulukutla wrote:
On 2017-07-31 06:13, Will Deacon wrote:
>On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
>>On 2017-07-28 02:28, Will Deacon wrote:
>>>On Thu, Jul
Hi Will,
On 2017-08-15 11:40, Will Deacon wrote:
Hi Vikram,
On Thu, Aug 03, 2017 at 04:25:12PM -0700, Vikram Mulukutla wrote:
On 2017-07-31 06:13, Will Deacon wrote:
>On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
>>On 2017-07-28 02:28, Will Deacon wrote:
>>>On Thu, Jul
Hi Vikram,
On Thu, Aug 03, 2017 at 04:25:12PM -0700, Vikram Mulukutla wrote:
> On 2017-07-31 06:13, Will Deacon wrote:
> >On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
> >>On 2017-07-28 02:28, Will Deacon wrote:
> >>>On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla
Hi Vikram,
On Thu, Aug 03, 2017 at 04:25:12PM -0700, Vikram Mulukutla wrote:
> On 2017-07-31 06:13, Will Deacon wrote:
> >On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
> >>On 2017-07-28 02:28, Will Deacon wrote:
> >>>On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla
On 2017年08月04日 07:32, Vikram Mulukutla wrote:
Hi Qiao,
On 2017-08-01 00:37, qiaozhou wrote:
On 2017年07月31日 19:20, qiaozhou wrote:
=
Also apply Vikram's patch and have a test.
cpu2: a53, 832MHz, cpu7: a73, 1.75Hz
Without
On 2017年08月04日 07:32, Vikram Mulukutla wrote:
Hi Qiao,
On 2017-08-01 00:37, qiaozhou wrote:
On 2017年07月31日 19:20, qiaozhou wrote:
=
Also apply Vikram's patch and have a test.
cpu2: a53, 832MHz, cpu7: a73, 1.75Hz
Without
Hi Qiao,
On 2017-08-01 00:37, qiaozhou wrote:
On 2017年07月31日 19:20, qiaozhou wrote:
=
Also apply Vikram's patch and have a test.
cpu2: a53, 832MHz, cpu7: a73, 1.75Hz
Without cpu_relax bodging patch
Hi Qiao,
On 2017-08-01 00:37, qiaozhou wrote:
On 2017年07月31日 19:20, qiaozhou wrote:
=
Also apply Vikram's patch and have a test.
cpu2: a53, 832MHz, cpu7: a73, 1.75Hz
Without cpu_relax bodging patch
Hi Will,
On 2017-07-31 06:13, Will Deacon wrote:
Hi Vikram,
On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
On 2017-07-28 02:28, Will Deacon wrote:
>On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
>
This does seem to help. Here's some data after 5 runs
Hi Will,
On 2017-07-31 06:13, Will Deacon wrote:
Hi Vikram,
On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
On 2017-07-28 02:28, Will Deacon wrote:
>On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
>
This does seem to help. Here's some data after 5 runs
On 2017年07月31日 19:20, qiaozhou wrote:
On 2017年07月29日 03:09, Vikram Mulukutla wrote:
On 2017-07-28 02:28, Will Deacon wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
Does bodging cpu_relax to back-off to wfe after a while help? The event
stream will wake it up
On 2017年07月31日 19:20, qiaozhou wrote:
On 2017年07月29日 03:09, Vikram Mulukutla wrote:
On 2017-07-28 02:28, Will Deacon wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
Does bodging cpu_relax to back-off to wfe after a while help? The event
stream will wake it up
Hi Vikram,
On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
> On 2017-07-28 02:28, Will Deacon wrote:
> >On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
>
>
>
> >>
> >>I think we should have this discussion now - I brought this up earlier
> >>[1]
> >>and I
Hi Vikram,
On Fri, Jul 28, 2017 at 12:09:38PM -0700, Vikram Mulukutla wrote:
> On 2017-07-28 02:28, Will Deacon wrote:
> >On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
>
>
>
> >>
> >>I think we should have this discussion now - I brought this up earlier
> >>[1]
> >>and I
On 2017年07月29日 03:09, Vikram Mulukutla wrote:
On 2017-07-28 02:28, Will Deacon wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
I think we should have this discussion now - I brought this up
earlier [1]
and I promised a test case that I completely forgot about
On 2017年07月29日 03:09, Vikram Mulukutla wrote:
On 2017-07-28 02:28, Will Deacon wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
I think we should have this discussion now - I brought this up
earlier [1]
and I promised a test case that I completely forgot about
On 2017-07-28 02:28, Peter Zijlstra wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
I think we should have this discussion now - I brought this up earlier
[1]
and I promised a test case that I completely forgot about - but here
it
is (attached). Essentially a Big CPU
On 2017-07-28 02:28, Peter Zijlstra wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
I think we should have this discussion now - I brought this up earlier
[1]
and I promised a test case that I completely forgot about - but here
it
is (attached). Essentially a Big CPU
On 2017-07-28 02:28, Will Deacon wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
I think we should have this discussion now - I brought this up earlier
[1]
and I promised a test case that I completely forgot about - but here
it
is (attached). Essentially a Big
On 2017-07-28 02:28, Will Deacon wrote:
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
I think we should have this discussion now - I brought this up earlier
[1]
and I promised a test case that I completely forgot about - but here
it
is (attached). Essentially a Big
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
> On 2017-07-26 18:29, qiaozhou wrote:
> >On 2017年07月26日 22:16, Thomas Gleixner wrote:
> >>On Wed, 26 Jul 2017, qiaozhou wrote:
> >>For that particular timer case we can clear base->running_timer w/o the
> >>lock held (see patch
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
> I think we should have this discussion now - I brought this up earlier [1]
> and I promised a test case that I completely forgot about - but here it
> is (attached). Essentially a Big CPU in an acquire-check-release loop
> will
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
> On 2017-07-26 18:29, qiaozhou wrote:
> >On 2017年07月26日 22:16, Thomas Gleixner wrote:
> >>On Wed, 26 Jul 2017, qiaozhou wrote:
> >>For that particular timer case we can clear base->running_timer w/o the
> >>lock held (see patch
On Thu, Jul 27, 2017 at 06:10:34PM -0700, Vikram Mulukutla wrote:
> I think we should have this discussion now - I brought this up earlier [1]
> and I promised a test case that I completely forgot about - but here it
> is (attached). Essentially a Big CPU in an acquire-check-release loop
> will
cc: Sudeep Holla
On 2017-07-26 18:29, qiaozhou wrote:
On 2017年07月26日 22:16, Thomas Gleixner wrote:
On Wed, 26 Jul 2017, qiaozhou wrote:
Cc'ed ARM folks.
For that particular timer case we can clear base->running_timer w/o
the
lock held (see patch below), but this kind of
lock
cc: Sudeep Holla
On 2017-07-26 18:29, qiaozhou wrote:
On 2017年07月26日 22:16, Thomas Gleixner wrote:
On Wed, 26 Jul 2017, qiaozhou wrote:
Cc'ed ARM folks.
For that particular timer case we can clear base->running_timer w/o
the
lock held (see patch below), but this kind of
lock
On Thu, 27 Jul 2017, Will Deacon wrote:
> On Thu, Jul 27, 2017 at 09:29:20AM +0800, qiaozhou wrote:
> > On 2017年07月26日 22:16, Thomas Gleixner wrote:
> > >--- a/kernel/time/timer.c
> > >+++ b/kernel/time/timer.c
> > >@@ -1301,10 +1301,12 @@ static void expire_timers(struct timer_b
> > >
On Thu, 27 Jul 2017, Will Deacon wrote:
> On Thu, Jul 27, 2017 at 09:29:20AM +0800, qiaozhou wrote:
> > On 2017年07月26日 22:16, Thomas Gleixner wrote:
> > >--- a/kernel/time/timer.c
> > >+++ b/kernel/time/timer.c
> > >@@ -1301,10 +1301,12 @@ static void expire_timers(struct timer_b
> > >
On Thu, Jul 27, 2017 at 09:29:20AM +0800, qiaozhou wrote:
> On 2017年07月26日 22:16, Thomas Gleixner wrote:
> >--- a/kernel/time/timer.c
> >+++ b/kernel/time/timer.c
> >@@ -1301,10 +1301,12 @@ static void expire_timers(struct timer_b
> > if (timer->flags & TIMER_IRQSAFE) {
> >
On Thu, Jul 27, 2017 at 09:29:20AM +0800, qiaozhou wrote:
> On 2017年07月26日 22:16, Thomas Gleixner wrote:
> >--- a/kernel/time/timer.c
> >+++ b/kernel/time/timer.c
> >@@ -1301,10 +1301,12 @@ static void expire_timers(struct timer_b
> > if (timer->flags & TIMER_IRQSAFE) {
> >
On 2017年07月26日 22:16, Thomas Gleixner wrote:
On Wed, 26 Jul 2017, qiaozhou wrote:
Cc'ed ARM folks.
I want to ask you for suggestions about how to fix one contention between
expire_timers and try_to_del_timer_sync. Thanks in advance.
The issue is a hard-lockup issue detected on our
On 2017年07月26日 22:16, Thomas Gleixner wrote:
On Wed, 26 Jul 2017, qiaozhou wrote:
Cc'ed ARM folks.
I want to ask you for suggestions about how to fix one contention between
expire_timers and try_to_del_timer_sync. Thanks in advance.
The issue is a hard-lockup issue detected on our
On Wed, 26 Jul 2017, qiaozhou wrote:
Cc'ed ARM folks.
> I want to ask you for suggestions about how to fix one contention between
> expire_timers and try_to_del_timer_sync. Thanks in advance.
> The issue is a hard-lockup issue detected on our platform(arm64, one cluster
> with 4 a53, and the
On Wed, 26 Jul 2017, qiaozhou wrote:
Cc'ed ARM folks.
> I want to ask you for suggestions about how to fix one contention between
> expire_timers and try_to_del_timer_sync. Thanks in advance.
> The issue is a hard-lockup issue detected on our platform(arm64, one cluster
> with 4 a53, and the
46 matches
Mail list logo