On Tue, Apr 09, 2019 at 03:05:27PM +0200 Peter Zijlstra wrote:
> On Tue, Apr 09, 2019 at 08:48:16AM -0400, Phil Auld wrote:
> > Hi Ingo, Peter,
> >
> > On Wed, Apr 03, 2019 at 01:38:39AM -0700 tip-bot for Phil Auld wrote:
> > > Commit-ID: 06ec5d30e8d57b820d44df6
Hi Ingo, Peter,
On Wed, Apr 03, 2019 at 01:38:39AM -0700 tip-bot for Phil Auld wrote:
> Commit-ID: 06ec5d30e8d57b820d44df6340dcb25010d6d0fa
> Gitweb:
> https://git.kernel.org/tip/06ec5d30e8d57b820d44df6340dcb25010d6d0fa
> Author: Phil Auld
> AuthorDate: Tue, 19 Mar 2019
Commit-ID: 06ec5d30e8d57b820d44df6340dcb25010d6d0fa
Gitweb: https://git.kernel.org/tip/06ec5d30e8d57b820d44df6340dcb25010d6d0fa
Author: Phil Auld
AuthorDate: Tue, 19 Mar 2019 09:00:05 -0400
Committer: Ingo Molnar
CommitDate: Wed, 3 Apr 2019 09:50:23 +0200
sched/fair: Limit
On Thu, Mar 21, 2019 at 07:01:37PM +0100 Peter Zijlstra wrote:
> On Tue, Mar 19, 2019 at 09:00:05AM -0400, Phil Auld wrote:
> > sched/fair: Limit sched_cfs_period_timer loop to avoid hard lockup
> >
> > With extremely short cfs_period_us setting on a parent task group with a
is state and the new values.
v2: Math reworked/simplified by Peter Zijlstra.
Signed-off-by: Phil Auld
Cc: Ben Segall
Cc: Ingo Molnar
Cc: Peter Zijlstra (Intel)
Cc: Anton Blanchard
---
kernel/sched/fair.c | 25 +
1 file changed, 25 insertions(+)
diff --git a/kernel/sc
On Mon, Mar 18, 2019 at 10:14:22AM -0700 bseg...@google.com wrote:
> Phil Auld writes:
>
> > On Fri, Mar 15, 2019 at 05:03:47PM +0100 Peter Zijlstra wrote:
> >> On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
> >>
> >> >> I'll rewor
On Fri, Mar 15, 2019 at 05:03:47PM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
>
> >> I'll rework the maths in the averaged version and post v2 if that makes
> >> sense.
> >
> > It may have the extra timer f
On Fri, Mar 15, 2019 at 04:59:33PM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 09:51:25AM -0400, Phil Auld wrote:
> > On Fri, Mar 15, 2019 at 11:33:57AM +0100 Peter Zijlstra wrote:
> > > On Fri, Mar 15, 2019 at 11:11:50AM +0100, Peter Zijlstra wrote:
> > >
On Fri, Mar 15, 2019 at 05:03:47PM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
>
> > In my defense here, all the fair.c imbalance pct code also uses 100 :)
>
> Yes, I know, I hate on that too ;-) Just never got around to fixing
>
On Fri, Mar 15, 2019 at 11:11:50AM +0100 Peter Zijlstra wrote:
> On Wed, Mar 13, 2019 at 11:08:26AM -0400, Phil Auld wrote:
...
> Computers _suck_ at /100. And since you're free to pick the constant,
> pick a power of two, computers love those.
>
> > +
> > +
On Fri, Mar 15, 2019 at 11:33:57AM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 11:11:50AM +0100, Peter Zijlstra wrote:
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index ea74d43924b2..b71557be6b42 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@
On Fri, Mar 15, 2019 at 11:11:50AM +0100 Peter Zijlstra wrote:
> On Wed, Mar 13, 2019 at 11:08:26AM -0400, Phil Auld wrote:
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 310d0637fe4b..90cc67bbf592 100644
> > --- a/kernel/sched/fair.c
> >
On Wed, Mar 13, 2019 at 01:26:51PM -0700 bseg...@google.com wrote:
> Phil Auld writes:
>
> > On Wed, Mar 13, 2019 at 10:44:09AM -0700 bseg...@google.com wrote:
> >> Phil Auld writes:
> >>
> >> > On Mon, Mar 11, 2019 at 04:25:36PM -0400 Phil Auld wr
On Wed, Mar 13, 2019 at 10:44:09AM -0700 bseg...@google.com wrote:
> Phil Auld writes:
>
> > On Mon, Mar 11, 2019 at 04:25:36PM -0400 Phil Auld wrote:
> >> On Mon, Mar 11, 2019 at 10:44:25AM -0700 bseg...@google.com wrote:
> >> > Letting it spin for 100ms and
as suggested by Ben Segall
.
Signed-off-by: Phil Auld
Cc: Ben Segall
Cc: Ingo Molnar
Cc: Peter Zijlstra (Intel)
---
Note: This is against v5.0 as suggested by the documentation. It won't apply to
5.0+ due to
the change to raw_spin_lock_irqsave. I can respin as needed.
kernel/
On Mon, Mar 11, 2019 at 04:25:36PM -0400 Phil Auld wrote:
> On Mon, Mar 11, 2019 at 10:44:25AM -0700 bseg...@google.com wrote:
> > Letting it spin for 100ms and then only increasing by 6% seems extremely
> > generous. If we went this route I'd probably say "after loo
On Mon, Mar 11, 2019 at 10:44:25AM -0700 bseg...@google.com wrote:
> Phil Auld writes:
>
> > On Wed, Mar 06, 2019 at 11:25:02AM -0800 bseg...@google.com wrote:
> >> Phil Auld writes:
> >>
> >> > On Tue, Mar 05, 2019 at 12:45:34PM -0800 bseg...@g
On Wed, Mar 06, 2019 at 11:25:02AM -0800 bseg...@google.com wrote:
> Phil Auld writes:
>
> > On Tue, Mar 05, 2019 at 12:45:34PM -0800 bseg...@google.com wrote:
> >> Phil Auld writes:
> >>
> >> > Interestingly, if I limit the number of child cgroups
On Tue, Mar 05, 2019 at 12:45:34PM -0800 bseg...@google.com wrote:
> Phil Auld writes:
>
> > Interestingly, if I limit the number of child cgroups to the number of
> > them I'm actually putting processes into (16 down from 2500) the problem
> > does not r
On Tue, Mar 05, 2019 at 10:49:01AM -0800 bseg...@google.com wrote:
> Phil Auld writes:
>
> >> >
> >> > raw_spin_lock(&cfs_b->lock);
> >> > for (;;) {
> >> > overrun = hrtimer_forward_now(timer, cfs_b->peri
On Mon, Mar 04, 2019 at 10:13:49AM -0800 bseg...@google.com wrote:
> Phil Auld writes:
>
> > Hi,
> >
> > I have a reproducible case of this:
> >
> > [ 217.264946] NMI watchdog: Watchdog detected hard LOCKUP on cpu 24
> > [ 217.264948] M
Hi,
I have a reproducible case of this:
[ 217.264946] NMI watchdog: Watchdog detected hard LOCKUP on cpu 24
[ 217.264948] Modules linked in: sunrpc iTCO_wdt gpio_ich iTCO_vendor_support
intel_powerclamp coretemp kvm_intel kvm ipmi_ssif irqbypass crct10dif_pclmul
crc32_pclmul ghash_clmulni_in
On Tue, Feb 19, 2019 at 05:22:50PM +0100 Peter Zijlstra wrote:
> On Tue, Feb 19, 2019 at 11:13:43AM -0500, Phil Auld wrote:
> > On Mon, Feb 18, 2019 at 05:56:23PM +0100 Peter Zijlstra wrote:
> > > In preparation of playing games with rq->lock, abstract the thing
&g
On Mon, Feb 18, 2019 at 05:56:23PM +0100 Peter Zijlstra wrote:
> In preparation of playing games with rq->lock, abstract the thing
> using an accessor.
>
> Signed-off-by: Peter Zijlstra (Intel)
Hi Peter,
Sorry... what tree are these for? They don't apply to mainline.
Some branch on tip, I gue
Commit-ID: baa9be4ffb55876923dc9716abc0a448e510ba30
Gitweb: https://git.kernel.org/tip/baa9be4ffb55876923dc9716abc0a448e510ba30
Author: Phil Auld
AuthorDate: Mon, 8 Oct 2018 10:36:40 -0400
Committer: Ingo Molnar
CommitDate: Thu, 11 Oct 2018 13:10:18 +0200
sched/fair: Fix throttle_list
Commit-ID: 8b48300108248e950cde0bdc5708039fc3836623
Gitweb: https://git.kernel.org/tip/8b48300108248e950cde0bdc5708039fc3836623
Author: Phil Auld
AuthorDate: Mon, 8 Oct 2018 10:36:40 -0400
Committer: Ingo Molnar
CommitDate: Thu, 11 Oct 2018 11:18:32 +0200
sched/fair: Fix throttle_list
eeds to be fixed - and at first sight the quota
> > of 1000 looks very
> > low - could we improve the arithmetics perhaps?
> >
> > A low quota of 1000 is used because there's many VMs or containers
> > provisioned on the system
> > that is trig
I believe that's a different issue, though. The
kernel
allows this setting and should handle it better than it currently does. The
proposed
patch fixes it so that all the tasks make progress (even if not much progress)
rather
than having some starve at the back of the list.
Cheers,
Ph
From: "Phil Auld"
sched/fair: Avoid throttle_list starvation with low cfs quota
With a very low cpu.cfs_quota_us setting, such as the minimum of 1000,
distribute_cfs_runtime may not empty the throttled_list before it runs
out of runtime to distribute. In that case, due to the c
Alexander Viro wrote:
...snip...
>
> We should start removing the crap from procfs in 2.5. Documenting shit is
> a good step, but taking it out would be better.
>
Not to open a what may be can of worms but ...
What's wrong with procfs?
It allows a general interface to the kernel that does
Alan Cox wrote:
>
> > That can be a problem for fiber channel devices. I saw some issues with
> > invalidate_buffers and page caching discussed in 2.4 space. Any reasons
> > come to mind why I shouldn't call invalidate on the the way down instead
> > (or in addition)?
>
> The I/O completed a few
Alan Cox wrote:
>
> > does not do anything to invalidate the buffers associated with the
> > unmounted device. We then rely on disk change detection on a
> > subsequent mount to prevent us from seeing the old super_block.
>
> 2.2 yes, 2.4 no
That can be a problem for fiber channel devices. I sa
Hello,
It appears that the umount path in the 2.2 series kernels
does not do anything to invalidate the buffers associated with the
unmounted device. We then rely on disk change detection on a
subsequent mount to prevent us from seeing the old super_block.
Since deja was gobbled by goog
101 - 133 of 133 matches
Mail list logo