From: Marcelo Tosatti <mtosatti@redhat.com>
To: Wanpeng Li <kernellwp@gmail.com>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
LKML <linux-kernel@vger.kernel.org>, kvm <kvm@vger.kernel.org>,
"Radim Krčmář" <rkrcmar@redhat.com>,
"Linux PM" <linux-pm@vger.kernel.org>,
"Michael S. Tsirkin" <mst@redhat.com>
Subject: Re: [PATCH] cpuidle-haltpoll: Enable kvm guest polling when dedicated physical CPUs are available
Date: Thu, 29 Aug 2019 11:39:06 -0300 [thread overview]
Message-ID: <20190829143904.GA13983@amt.cnet> (raw)
In-Reply-To: <20190829125304.GA12214@amt.cnet>
On Thu, Aug 29, 2019 at 09:53:04AM -0300, Marcelo Tosatti wrote:
> On Thu, Aug 29, 2019 at 08:16:41PM +0800, Wanpeng Li wrote:
> > > Current situation regarding haltpoll driver is:
> > >
> > > overcommit group: haltpoll driver is not loaded by default, they are
> > > happy.
> > >
> > > non overcommit group: boots without "realtime hints" flag, loads haltpoll driver,
> > > happy.
> > >
> > > Situation with patch above:
> > >
> > > overcommit group: haltpoll driver is not loaded by default, they are
> > > happy.
> > >
> > > non overcommit group: boots without "realtime hints" flag, haltpoll driver
> > > cannot be loaded.
> >
> > non overcommit group, if they don't care latency/performance, they
> > don't need to enable haltpoll, "realtime hints" etc. Otherwise, they
> > should better tune.
>
> As mentioned before, "being overcommitted" is a property which is transitional.
>
> A static true/false scheme reflects this poorly.
>
> Therefore the OS should detect it and act accordingly.
Hi Wanpeng Li,
One suggestion for a dynamic "is overcommited" scheme:
If the amount of stolen time, in the past record_steal_time window,
is more than 20% of the time in that window, then mark system
as overcommitted. Otherwise, clear it.
Make that 20% configurable by as kvm module parameter.
Use that info to enable/disable overcommit features.
That should work, right?
next prev parent reply other threads:[~2019-08-29 14:42 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1564643196-7797-1-git-send-email-wanpengli@tencent.com>
2019-08-01 16:51 ` [PATCH] cpuidle-haltpoll: Enable kvm guest polling when dedicated physical CPUs are available Rafael J. Wysocki
2019-08-01 16:54 ` Paolo Bonzini
2019-08-03 20:21 ` Marcelo Tosatti
2019-08-13 0:55 ` Wanpeng Li
2019-08-13 7:55 ` Paolo Bonzini
2019-08-26 20:40 ` Marcelo Tosatti
2019-08-27 0:43 ` Wanpeng Li
2019-08-28 8:35 ` Wanpeng Li
2019-08-28 8:45 ` Rafael J. Wysocki
2019-08-28 8:48 ` Wanpeng Li
2019-08-28 14:39 ` Marcelo Tosatti
2019-08-28 23:37 ` Rafael J. Wysocki
2019-08-29 12:04 ` Marcelo Tosatti
2019-08-29 12:16 ` Wanpeng Li
2019-08-29 12:53 ` Marcelo Tosatti
2019-08-29 14:39 ` Marcelo Tosatti [this message]
2019-08-28 14:48 ` Marcelo Tosatti
2019-08-28 14:52 ` Marcelo Tosatti
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=20190829143904.GA13983@amt.cnet \
--to=mtosatti@redhat.com \
--cc=kernellwp@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=rafael.j.wysocki@intel.com \
--cc=rafael@kernel.org \
--cc=rkrcmar@redhat.com \
/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).