Tejun,
commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14 (sched, cgroup: replace
signal_struct->group_rwsem with a global percpu_rwsem) causes some noticably
hickups when starting several kvm guests (which libvirt will move into cgroups
- each vcpu thread and each i/o thread)
When you now start lo
On Tue, Sep 15, 2015 at 02:05:14PM +0200, Christian Borntraeger wrote:
> Tejun,
>
>
> commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14 (sched, cgroup: replace
> signal_struct->group_rwsem with a global percpu_rwsem) causes some noticably
> hickups when starting several kvm guests (which libvirt w
Am 15.09.2015 um 15:05 schrieb Peter Zijlstra:
> On Tue, Sep 15, 2015 at 02:05:14PM +0200, Christian Borntraeger wrote:
>> Tejun,
>>
>>
>> commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14 (sched, cgroup: replace
>> signal_struct->group_rwsem with a global percpu_rwsem) causes some noticably
>> hick
Hello,
On Tue, Sep 15, 2015 at 03:36:34PM +0200, Christian Borntraeger wrote:
> >> The problem seems to be that the newly used percpu_rwsem does a
> >> rcu_synchronize_sched_expedited for all write downs/ups.
> >
> > Can you try:
> >
> > git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linu
On 15/09/2015 15:36, Christian Borntraeger wrote:
> I am wondering why the old code behaved in such fatal ways. Is there
> some interaction between waiting for a reschedule in the
> synchronize_sched writer and some fork code actually waiting for the
> read side to get the lock together with some
On Tue, Sep 15, 2015 at 06:42:19PM +0200, Paolo Bonzini wrote:
>
>
> On 15/09/2015 15:36, Christian Borntraeger wrote:
> > I am wondering why the old code behaved in such fatal ways. Is there
> > some interaction between waiting for a reschedule in the
> > synchronize_sched writer and some fork c
Am 15.09.2015 um 18:42 schrieb Paolo Bonzini:
>
>
> On 15/09/2015 15:36, Christian Borntraeger wrote:
>> I am wondering why the old code behaved in such fatal ways. Is there
>> some interaction between waiting for a reschedule in the
>> synchronize_sched writer and some fork code actually waiting
Hello,
On Tue, Sep 15, 2015 at 11:11:45PM +0200, Christian Borntraeger wrote:
> > In fact, I would say that any userspace-controlled call to *_expedited()
> > is a bug waiting to happen and a bad idea---because userspace can, with
> > little effort, end up calling it in a loop.
>
> Right. This al
On Tue, Sep 15, 2015 at 05:26:22PM -0400, Tejun Heo wrote:
> Hello,
>
> On Tue, Sep 15, 2015 at 11:11:45PM +0200, Christian Borntraeger wrote:
> > > In fact, I would say that any userspace-controlled call to *_expedited()
> > > is a bug waiting to happen and a bad idea---because userspace can, wit
Hello,
On Tue, Sep 15, 2015 at 02:38:30PM -0700, Paul E. McKenney wrote:
> I did take a shot at adding the rcu_sync stuff during this past merge
> window, but it did not converge quickly enough to make it. It looks
> quite good for the next merge window. There have been changes in most
> of the
On Tue, Sep 15, 2015 at 06:28:11PM -0400, Tejun Heo wrote:
> Hello,
>
> On Tue, Sep 15, 2015 at 02:38:30PM -0700, Paul E. McKenney wrote:
> > I did take a shot at adding the rcu_sync stuff during this past merge
> > window, but it did not converge quickly enough to make it. It looks
> > quite goo
Hello, Paul.
On Tue, Sep 15, 2015 at 04:38:18PM -0700, Paul E. McKenney wrote:
> Well, the decision as to what is too big for -stable is owned by the
> -stable maintainers, not by me.
Is it tho? Usually the subsystem maintainer knows the best and has
most say in it. I was mostly curious whether
On Tue, Sep 15, 2015 at 09:24:15PM -0400, Tejun Heo wrote:
> Hello, Paul.
>
> On Tue, Sep 15, 2015 at 04:38:18PM -0700, Paul E. McKenney wrote:
> > Well, the decision as to what is too big for -stable is owned by the
> > -stable maintainers, not by me.
>
> Is it tho? Usually the subsystem mainta
Am 16.09.2015 um 03:24 schrieb Tejun Heo:
> Hello, Paul.
>
> On Tue, Sep 15, 2015 at 04:38:18PM -0700, Paul E. McKenney wrote:
>> Well, the decision as to what is too big for -stable is owned by the
>> -stable maintainers, not by me.
>
> Is it tho? Usually the subsystem maintainer knows the best
On 15/09/2015 19:38, Paul E. McKenney wrote:
> Excellent points!
>
> Other options in such situations include the following:
>
> o Rework so that the code uses call_rcu*() instead of *_expedited().
>
> o Maintain a per-task or per-CPU counter so that every so many
> *_expedited()
Am 16.09.2015 um 10:32 schrieb Paolo Bonzini:
>
>
> On 15/09/2015 19:38, Paul E. McKenney wrote:
>> Excellent points!
>>
>> Other options in such situations include the following:
>>
>> oRework so that the code uses call_rcu*() instead of *_expedited().
>>
>> oMaintain a per-task or per-C
On 16/09/2015 10:57, Christian Borntraeger wrote:
> Am 16.09.2015 um 10:32 schrieb Paolo Bonzini:
>>
>>
>> On 15/09/2015 19:38, Paul E. McKenney wrote:
>>> Excellent points!
>>>
>>> Other options in such situations include the following:
>>>
>>> o Rework so that the code uses call_rcu*() instea
Am 16.09.2015 um 09:44 schrieb Christian Borntraeger:
> Am 16.09.2015 um 03:24 schrieb Tejun Heo:
>> Hello, Paul.
>>
>> On Tue, Sep 15, 2015 at 04:38:18PM -0700, Paul E. McKenney wrote:
>>> Well, the decision as to what is too big for -stable is owned by the
>>> -stable maintainers, not by me.
>>
>
Hello,
On Wed, Sep 16, 2015 at 12:58:00PM +0200, Christian Borntraeger wrote:
> FWIW, I added a printk to percpu_down_write. With KVM and uprobes disabled,
> just booting up a fedora20 gives me __6749__ percpu_down_write calls on 4.2.
> systemd seems to do that for the processes.
>
> So a revert
Hello,
On Tue, Sep 15, 2015 at 09:35:47PM -0700, Paul E. McKenney wrote:
> > > I am suggesting trying the options and seeing what works best, then
> > > working to convince people as needed.
> >
> > Yeah, sure thing. Let's wait for Christian.
>
> Indeed. Is there enough benefit to risk jamming
Am 16.09.2015 um 13:03 schrieb Tejun Heo:
> Hello,
>
> On Wed, Sep 16, 2015 at 12:58:00PM +0200, Christian Borntraeger wrote:
>> FWIW, I added a printk to percpu_down_write. With KVM and uprobes disabled,
>> just booting up a fedora20 gives me __6749__ percpu_down_write calls on 4.2.
>> systemd se
On 09/16, Paolo Bonzini wrote:
>
>
> On 16/09/2015 10:57, Christian Borntraeger wrote:
> > Am 16.09.2015 um 10:32 schrieb Paolo Bonzini:
> >>
> >>
> >> On 15/09/2015 19:38, Paul E. McKenney wrote:
> >>> Excellent points!
> >>>
> >>> Other options in such situations include the following:
> >>>
> >>
On 16/09/2015 14:22, Oleg Nesterov wrote:
> > The issue is that rcu_sync doesn't eliminate synchronize_sched,
>
> Yes, but it eliminates _expedited(). This is good, but otoh this means
> that (say) individual __cgroup_procs_write() can take much more time.
> However, it won't block the readers
On 09/16, Paolo Bonzini wrote:
>
>
> On 16/09/2015 14:22, Oleg Nesterov wrote:
> > > The issue is that rcu_sync doesn't eliminate synchronize_sched,
> >
> > Yes, but it eliminates _expedited(). This is good, but otoh this means
> > that (say) individual __cgroup_procs_write() can take much more ti
Am 16.09.2015 um 14:22 schrieb Oleg Nesterov:
>> The issue is that rcu_sync doesn't eliminate synchronize_sched,
>
> Yes, but it eliminates _expedited(). This is good, but otoh this means
> that (say) individual __cgroup_procs_write() can take much more time.
> However, it won't block the readers
Hello,
On Wed, Sep 16, 2015 at 02:22:49PM +0200, Oleg Nesterov wrote:
> > If the revert isn't easy, I think backporting rcu_sync is the best bet.
>
> I leave this to Paul and Tejun... at least I think this is not v4.2 material.
Will route reverts through cgroup branch. Should be pretty painless
On 16/09/2015 16:16, Tejun Heo wrote:
> On Wed, Sep 16, 2015 at 02:22:49PM +0200, Oleg Nesterov wrote:
>>> > > If the revert isn't easy, I think backporting rcu_sync is the best bet.
>> >
>> > I leave this to Paul and Tejun... at least I think this is not v4.2
>> > material.
> Will route revert
27 matches
Mail list logo