All of lore.kernel.org
 help / color / mirror / Atom feed
From: George Dunlap <george.dunlap@citrix.com>
To: Dario Faggioli <dario.faggioli@citrix.com>,
	xen-devel@lists.xenproject.org
Cc: Anshul Makkar <anshul.makkar@citrix.com>,
	Meng Xu <mengxu@cis.upenn.edu>, Jan Beulich <jbeulich@suse.com>
Subject: Re: [PATCH 2/3] xen: Have schedulers revise initial placement
Date: Mon, 25 Jul 2016 12:17:44 +0100	[thread overview]
Message-ID: <23a703ab-77d6-8b59-99da-1e3f7fad36b5@citrix.com> (raw)
In-Reply-To: <1468837713.13039.138.camel@citrix.com>

On 18/07/16 11:28, Dario Faggioli wrote:
> On Fri, 2016-07-15 at 19:02 +0100, George Dunlap wrote:
>> The generic domain creation logic in
>> xen/common/domctl.c:default_vcpu0_location() attempts to try to do
>> initial placement load-balancing by placing vcpu 0 on the least-busy
>> non-primary hyperthread available.  Unfortunately, the logic can end
>> up picking a pcpu that's not in the online mask.  When this is passed
>> to a scheduler such which assumes that the initial assignment is
>> valid, it causes a null pointer dereference looking up the runqueue.
>>
>> Furthermore, this initial placement doesn't take into account hard or
>> soft affinity, or any scheduler-specific knowledge (such as historic
>> runqueue load, as in credit2).
>>
>> To solve this, when inserting a vcpu, always call the per-scheduler
>> "pick" function to revise the initial placement.  This will
>> automatically take all knowledge the scheduler has into account.
>>
>> Signed-off-by: George Dunlap <george.dunlap@citrix.com>
>> ---
>> CC: Dario Faggioli <dario.faggioli@citrix.com>
>> CC: Anshul Makkar <anshul.makkar@citrix.com>
>> CC: Meng Xu <mengxu@cis.upenn.edu>
>> CC: Jan Beulich <jbeulich@suse.com>
>>
> Reviewed-by: Dario Faggioli <dario.faggioli@citrix.com>

Just to clarify - does this cover the sched_rt.c changes as well?

Thanks,
 -George

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

  reply	other threads:[~2016-07-25 11:17 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-15 18:02 [PATCH 1/3] xen: Some code motion to avoid having to do forward-declaration George Dunlap
2016-07-15 18:02 ` [PATCH 2/3] xen: Have schedulers revise initial placement George Dunlap
2016-07-15 18:07   ` Andrew Cooper
2016-07-16 14:12     ` Dario Faggioli
2016-07-18 18:10       ` Andrew Cooper
2016-07-18 18:55         ` Dario Faggioli
2016-07-18 21:36           ` Andrew Cooper
2016-07-19  7:14             ` Dario Faggioli
2016-07-18 10:28   ` Dario Faggioli
2016-07-25 11:17     ` George Dunlap [this message]
2016-07-25 14:36       ` Meng Xu
2016-07-26  9:17       ` Dario Faggioli
2016-07-25 14:35   ` Meng Xu
2016-08-01 10:40   ` Jan Beulich
2016-08-01 12:32     ` Dario Faggioli
2016-08-05 13:24       ` Jan Beulich
2016-08-05 14:09         ` Dario Faggioli
2016-08-05 14:44           ` Jan Beulich
2016-08-11 14:59         ` Dario Faggioli
2016-08-11 15:51           ` Andrew Cooper
2016-08-11 23:35             ` Dario Faggioli
2016-08-12  1:59         ` dependences for backporting to 4.6 [was: Re: [PATCH 2/3] xen: Have schedulers revise initial placement] Dario Faggioli
2016-08-12 13:53           ` Jan Beulich
2016-08-16 10:21             ` Dario Faggioli
2016-08-16 11:21               ` Jan Beulich
2016-08-12  8:58         ` dependences for backporting to 4.5 " Dario Faggioli
2016-07-15 18:02 ` [PATCH 3/3] xen: Remove buggy initial placement algorithm George Dunlap
2016-07-15 18:10   ` Andrew Cooper
2016-07-16 13:55   ` Dario Faggioli
2016-07-18 10:03     ` George Dunlap
2016-07-16 15:48 ` [PATCH 1/3] xen: Some code motion to avoid having to do forward-declaration Meng Xu
2016-07-18  9:58 ` Dario Faggioli
2016-07-18 10:06   ` George Dunlap

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=23a703ab-77d6-8b59-99da-1e3f7fad36b5@citrix.com \
    --to=george.dunlap@citrix.com \
    --cc=anshul.makkar@citrix.com \
    --cc=dario.faggioli@citrix.com \
    --cc=jbeulich@suse.com \
    --cc=mengxu@cis.upenn.edu \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.