Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1217451 > unrolled thread

Only 1 cpu scheduled in 4.2.0

Started byMartin van Es <mrvanes@gmail.com>
First post2015-09-02 11:40 +0200
Last post2015-09-02 16:50 +0200
Articles 5 — 2 participants

Back to article view | Back to linux.kernel


Contents

  Only 1 cpu scheduled in 4.2.0 Martin van Es <mrvanes@gmail.com> - 2015-09-02 11:40 +0200
    Re: Only 1 cpu scheduled in 4.2.0 Mike Galbraith <umgwanakikbuti@gmail.com> - 2015-09-02 13:00 +0200
      Re: Only 1 cpu scheduled in 4.2.0 Martin van Es <mrvanes@gmail.com> - 2015-09-02 13:40 +0200
        Re: Only 1 cpu scheduled in 4.2.0 Mike Galbraith <umgwanakikbuti@gmail.com> - 2015-09-02 13:50 +0200
          Re: Only 1 cpu scheduled in 4.2.0 Martin van Es <mrvanes@gmail.com> - 2015-09-02 16:50 +0200

#1217451 — Only 1 cpu scheduled in 4.2.0

FromMartin van Es <mrvanes@gmail.com>
Date2015-09-02 11:40 +0200
SubjectOnly 1 cpu scheduled in 4.2.0
Message-ID<q4cGo-17b-41@gated-at.bofh.it>
Hi,

I recently compiled 4.2.0 based on my previous 4.1.6 config (make oldconfig).
On 4.1.6 all cores are equally scheduled.

This new 4.2.0 kernel however only schedules cpu0 on my 4 cpu i7-3537U
(which is actually 2 cores x 2HT, as far as I understand the specs).
CPU1 is scheduled for 0.5% now and then, so it's not completely 0.

I tried (re)enabling NUMA support, since that's adviced for 64bit/i7
cpu's according to the help text, but that didn't change anything.

Did I miss a new option for SMP scheduling in 4.2.0?

Best regards,
Martin
--
If 'but' was any useful, it would be a logic operator
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]


#1217519

FromMike Galbraith <umgwanakikbuti@gmail.com>
Date2015-09-02 13:00 +0200
Message-ID<q4dVM-2P4-7@gated-at.bofh.it>
In reply to#1217451
On Wed, 2015-09-02 at 11:38 +0200, Martin van Es wrote:
> Hi,
> 
> I recently compiled 4.2.0 based on my previous 4.1.6 config (make oldconfig).
> On 4.1.6 all cores are equally scheduled.

Do you have CONFIG_NO_HZ_FULL_ALL enabled?

	-Mike

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]


#1217538

FromMartin van Es <mrvanes@gmail.com>
Date2015-09-02 13:40 +0200
Message-ID<q4eyu-3NB-11@gated-at.bofh.it>
In reply to#1217519
On Wed, Sep 2, 2015 at 12:50 PM, Mike Galbraith
<umgwanakikbuti@gmail.com> wrote:
> On Wed, 2015-09-02 at 11:38 +0200, Martin van Es wrote:
>> Hi,
>>
>> I recently compiled 4.2.0 based on my previous 4.1.6 config (make oldconfig).
>> On 4.1.6 all cores are equally scheduled.
>
> Do you have CONFIG_NO_HZ_FULL_ALL enabled?

Yes, that's enabled.

Martin
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]


#1217542

FromMike Galbraith <umgwanakikbuti@gmail.com>
Date2015-09-02 13:50 +0200
Message-ID<q4eI9-3YQ-9@gated-at.bofh.it>
In reply to#1217538
On Wed, 2015-09-02 at 13:35 +0200, Martin van Es wrote:
> On Wed, Sep 2, 2015 at 12:50 PM, Mike Galbraith
> <umgwanakikbuti@gmail.com> wrote:
> > On Wed, 2015-09-02 at 11:38 +0200, Martin van Es wrote:
> >> Hi,
> >>
> >> I recently compiled 4.2.0 based on my previous 4.1.6 config (make oldconfig).
> >> On 4.1.6 all cores are equally scheduled.
> >
> > Do you have CONFIG_NO_HZ_FULL_ALL enabled?
> 
> Yes, that's enabled.

Turn it off and you'll get your CPUs back.

	-Mike

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]


#1217665

FromMartin van Es <mrvanes@gmail.com>
Date2015-09-02 16:50 +0200
Message-ID<q4hwm-81p-9@gated-at.bofh.it>
In reply to#1217542
On Wed, Sep 2, 2015 at 1:44 PM, Mike Galbraith <umgwanakikbuti@gmail.com> wrote:
> On Wed, 2015-09-02 at 13:35 +0200, Martin van Es wrote:
>> On Wed, Sep 2, 2015 at 12:50 PM, Mike Galbraith
>> <umgwanakikbuti@gmail.com> wrote:
>> > On Wed, 2015-09-02 at 11:38 +0200, Martin van Es wrote:
>> >> Hi,
>> >>
>> >> I recently compiled 4.2.0 based on my previous 4.1.6 config (make oldconfig).
>> >> On 4.1.6 all cores are equally scheduled.
>> >
>> > Do you have CONFIG_NO_HZ_FULL_ALL enabled?
>>
>> Yes, that's enabled.
>
> Turn it off and you'll get your CPUs back.

Yay, all my CPU's are rumbling again!
Thx!

Martin
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web