From mboxrd@z Thu Jan  1 00:00:00 1970
From: Luiz Capitulino <lcapitulino@redhat.com>
Subject: Re: [RFC] kvm: x86: export vCPU halted state to sysfs
Date: Fri, 2 Feb 2018 16:54:54 -0500
Message-ID: <20180202165454.13a5c8a2@redhat.com>
References: <96d66ae2-5c51-510f-06a5-cecdda74cfd4@linux.vnet.ibm.com>
        <20180202102231.7dc9a945@redhat.com>
        <86571633-ae6d-5678-7611-549ff41dccd8@linux.vnet.ibm.com>
        <20180202155415.GN15403@redhat.com>
        <20180202110137.2e2c1816@redhat.com>
        <597d7701-ea7b-524e-7632-10073284d060@linux.vnet.ibm.com>
        <20180202174249.GA22556@localhost.localdomain>
        <20180202135033.3ecfdd7b@redhat.com>
        <20180202200912.GP26425@localhost.localdomain>
        <20180202151945.52847f8e@redhat.com>
        <20180202204144.GQ26425@localhost.localdomain>
        <20180202164954.7586f4fd@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Cc: Viktor Mihajlovski <mihajlov@linux.vnet.ibm.com>,
        "Daniel P. =?UTF-8?B?QmVycmFuZ8Op?=" <berrange@redhat.com>,
        Radim =?UTF-8?B?S3LEjW0=?= =?UTF-8?B?w6HFmQ==?=
        <rkrcmar@redhat.com>, kvm@vger.kernel.org, pbonzini@redhat.com,
        Peter Krempa <pkrempa@redhat.com>,
        John Ferlan <jferlan@redhat.com>, libvir-list@redhat.com,
        Christian Borntraeger <borntraeger@de.ibm.com>
To: Eduardo Habkost <ehabkost@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:56426 "EHLO mx1.redhat.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1751544AbeBBVzH (ORCPT <rfc822;kvm@vger.kernel.org>);
        Fri, 2 Feb 2018 16:55:07 -0500
In-Reply-To: <20180202164954.7586f4fd@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Fri, 2 Feb 2018 16:49:54 -0500
Luiz Capitulino <lcapitulino@redhat.com> wrote:

> On Fri, 2 Feb 2018 18:41:44 -0200
> Eduardo Habkost <ehabkost@redhat.com> wrote:
> 
> > On Fri, Feb 02, 2018 at 03:19:45PM -0500, Luiz Capitulino wrote:  
> > > On Fri, 2 Feb 2018 18:09:12 -0200
> > > Eduardo Habkost <ehabkost@redhat.com> wrote:    
> > [...]  
> > > > Your plan above covers what will happen when using newer QEMU
> > > > versions, but libvirt still needs to work sanely if running QEMU
> > > > 2.11.  My suggestion is that libvirt do not run query-cpus to ask
> > > > for the "halted" field on any architecture except s390.    
> > > 
> > > My current plan is to ask libvirt to completely remove query-cpus
> > > usage, independent of the arch and use the new command instead.    
> > 
> > This would be a regression for people running QEMU 2.11 on s390.  
> 
> libvirt could use query-cpus on s390 if the new command is not
> available.

Btw, even on s390 query-cpus runs run_on_cpu(), which is what
causes vCPUs to go to user-space. So, s390 should suffer the same
performance problem. Pick your regression.

> 
> > 
> > (But maybe it would be an acceptable regression?  Viktor, what do
> > you think?  Are there production releases of management systems
> > that already rely on vcpu.<n>.halted?)
> >   
>