From: Christian Borntraeger <borntraeger@de.ibm.com>
To: Paolo Bonzini <pbonzini@redhat.com>, paulmck@linux.vnet.ibm.com
Cc: Peter Zijlstra <peterz@infradead.org>, Tejun Heo <tj@kernel.org>,
Ingo Molnar <mingo@redhat.com>,
"linux-kernel@vger.kernel.org >> Linux Kernel Mailing List"
<linux-kernel@vger.kernel.org>, KVM list <kvm@vger.kernel.org>,
Oleg Nesterov <oleg@redhat.com>
Subject: Re: [4.2] commit d59cfc09c32 (sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem) causes regression for libvirt/kvm
Date: Wed, 16 Sep 2015 10:57:40 +0200 [thread overview]
Message-ID: <55F92F04.1040706@de.ibm.com> (raw)
In-Reply-To: <55F92904.4090206@redhat.com>
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*() instead of *_expedited().
>>
>> o Maintain a per-task or per-CPU counter so that every so many
>> *_expedited() invocations instead uses the non-expedited
>> counterpart. (For example, synchronize_rcu instead of
>> synchronize_rcu_expedited().)
>
> Or just use ratelimit (untested):
One of my tests was to always replace synchronize_sched_expedited with
synchronize_sched and things turned out to be even worse. Not sure if
it makes sense to test yopur in-the-middle approach?
Christian
next prev parent reply other threads:[~2015-09-16 8:57 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-15 12:05 [4.2] commit d59cfc09c32 (sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem) causes regression for libvirt/kvm Christian Borntraeger
2015-09-15 13:05 ` Peter Zijlstra
2015-09-15 13:36 ` Christian Borntraeger
2015-09-15 13:53 ` Tejun Heo
2015-09-15 16:42 ` Paolo Bonzini
2015-09-15 17:38 ` Paul E. McKenney
2015-09-16 8:32 ` Paolo Bonzini
2015-09-16 8:57 ` Christian Borntraeger [this message]
2015-09-16 9:12 ` Paolo Bonzini
2015-09-16 12:22 ` Oleg Nesterov
2015-09-16 12:35 ` Paolo Bonzini
2015-09-16 12:43 ` Oleg Nesterov
2015-09-16 12:56 ` Christian Borntraeger
2015-09-16 14:16 ` Tejun Heo
2015-09-16 14:19 ` Paolo Bonzini
2015-09-15 21:11 ` Christian Borntraeger
2015-09-15 21:26 ` Tejun Heo
2015-09-15 21:38 ` Paul E. McKenney
2015-09-15 22:28 ` Tejun Heo
2015-09-15 23:38 ` Paul E. McKenney
2015-09-16 1:24 ` Tejun Heo
2015-09-16 4:35 ` Paul E. McKenney
2015-09-16 11:06 ` Tejun Heo
2015-09-16 7:44 ` Christian Borntraeger
2015-09-16 10:58 ` Christian Borntraeger
2015-09-16 11:03 ` Tejun Heo
2015-09-16 11:50 ` Christian Borntraeger
2015-09-16 15:55 ` [PATCH cgroup/for-4.3-fixes 1/2] Revert "cgroup: simplify threadgroup locking" Tejun Heo
2015-09-16 15:56 ` [PATCH cgroup/for-4.3-fixes 2/2] Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem" Tejun Heo
2015-09-16 17:00 ` [PATCH cgroup/for-4.3-fixes 1/2] Revert "cgroup: simplify threadgroup locking" Oleg Nesterov
2015-09-16 18:45 ` Christian Borntraeger
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=55F92F04.1040706@de.ibm.com \
--to=borntraeger@de.ibm.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=oleg@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=tj@kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).