From: Marcelo Tosatti <mtosatti@redhat.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
kvm@vger.kernel.org, qemu-devel@nongnu.org,
Eduardo Habkost <ehabkost@redhat.com>,
Richard Henderson <rth@twiddle.net>
Subject: Re: [PATCH v2 0/2] kvm: x86 CPU power management
Date: Wed, 13 Jun 2018 19:34:53 -0300 [thread overview]
Message-ID: <20180613223449.GA18339@amt.cnet> (raw)
In-Reply-To: <20180612184616.90838-1-mst@redhat.com>
On Tue, Jun 12, 2018 at 09:47:11PM +0300, Michael S. Tsirkin wrote:
> This adds ability to expose host CPU power management capabilities to
> guests. For intel guests, this is sufficient for guest to enable
> low power CPU power management. For AMD guests it isn't sufficient,
> deeper C-states are entered using System-IO.
>
> mwait based power management is tied closely to specifics of CPUID,
> making migration challenging. At this point only the non-migrateable
> -cpu host is supported.
>
> With this patch applied, VM latency is within the noise of
> baremetal for some benchmarks.
>
> perf bench sched pipe results:
> Before:
> 6.452 sec
> After:
> 4.382 sec
> Baremetal:
> 4.136 sec
>
> Michael S. Tsirkin (2):
> kvm: support -realtime cpu-pm=on|off
> i386/cpu: make -cpu host support monitor/mwait
>
> include/sysemu/sysemu.h | 1 +
> target/i386/cpu.h | 9 +++++++++
> target/i386/cpu.c | 19 ++++++++++++++-----
> target/i386/kvm.c | 30 ++++++++++++++++++++++++++++++
> vl.c | 6 ++++++
> qemu-options.hx | 9 +++++++--
> 6 files changed, 67 insertions(+), 7 deletions(-)
>
> --
> MST
Hi Michael,
1) Command line option interface
Why is this not an optional cpu feature such as the other features?
-cpu CPU,+mwait
rather than a separate, architecture independent "-realtime cpu-pm=on|off"
command line option?
2) Migration
Isnt it sufficient to check that both CPUID leafs are the same,
to allow migration ?
1. Check that the processor supports MONITOR and MWAIT. If
CPUID.01H:ECX.MONITOR[bit 3] = 1, MONITOR and MWAIT are available at
ring 0.
2. Query the smallest and largest line size that MONITOR uses.
Use CPUID.05H:EAX.smallest[bits 15:0];EBX.largest[bits15:0].
WARNING: multiple messages have this Message-ID (diff)
From: Marcelo Tosatti <mtosatti@redhat.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: qemu-devel@nongnu.org, Paolo Bonzini <pbonzini@redhat.com>,
Richard Henderson <rth@twiddle.net>,
Eduardo Habkost <ehabkost@redhat.com>,
kvm@vger.kernel.org
Subject: Re: [Qemu-devel] [PATCH v2 0/2] kvm: x86 CPU power management
Date: Wed, 13 Jun 2018 19:34:53 -0300 [thread overview]
Message-ID: <20180613223449.GA18339@amt.cnet> (raw)
In-Reply-To: <20180612184616.90838-1-mst@redhat.com>
On Tue, Jun 12, 2018 at 09:47:11PM +0300, Michael S. Tsirkin wrote:
> This adds ability to expose host CPU power management capabilities to
> guests. For intel guests, this is sufficient for guest to enable
> low power CPU power management. For AMD guests it isn't sufficient,
> deeper C-states are entered using System-IO.
>
> mwait based power management is tied closely to specifics of CPUID,
> making migration challenging. At this point only the non-migrateable
> -cpu host is supported.
>
> With this patch applied, VM latency is within the noise of
> baremetal for some benchmarks.
>
> perf bench sched pipe results:
> Before:
> 6.452 sec
> After:
> 4.382 sec
> Baremetal:
> 4.136 sec
>
> Michael S. Tsirkin (2):
> kvm: support -realtime cpu-pm=on|off
> i386/cpu: make -cpu host support monitor/mwait
>
> include/sysemu/sysemu.h | 1 +
> target/i386/cpu.h | 9 +++++++++
> target/i386/cpu.c | 19 ++++++++++++++-----
> target/i386/kvm.c | 30 ++++++++++++++++++++++++++++++
> vl.c | 6 ++++++
> qemu-options.hx | 9 +++++++--
> 6 files changed, 67 insertions(+), 7 deletions(-)
>
> --
> MST
Hi Michael,
1) Command line option interface
Why is this not an optional cpu feature such as the other features?
-cpu CPU,+mwait
rather than a separate, architecture independent "-realtime cpu-pm=on|off"
command line option?
2) Migration
Isnt it sufficient to check that both CPUID leafs are the same,
to allow migration ?
1. Check that the processor supports MONITOR and MWAIT. If
CPUID.01H:ECX.MONITOR[bit 3] = 1, MONITOR and MWAIT are available at
ring 0.
2. Query the smallest and largest line size that MONITOR uses.
Use CPUID.05H:EAX.smallest[bits 15:0];EBX.largest[bits15:0].
next prev parent reply other threads:[~2018-06-13 22:34 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-12 18:47 [PATCH v2 0/2] kvm: x86 CPU power management Michael S. Tsirkin
2018-06-12 18:47 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-12 18:47 ` [PATCH v2 1/2] kvm: support -realtime cpu-pm=on|off Michael S. Tsirkin
2018-06-12 18:47 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-13 20:35 ` Eduardo Habkost
2018-06-13 20:35 ` [Qemu-devel] " Eduardo Habkost
2018-06-13 21:00 ` Eduardo Habkost
2018-06-13 21:00 ` [Qemu-devel] " Eduardo Habkost
2018-06-13 21:53 ` Michael S. Tsirkin
2018-06-13 21:53 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-12 18:47 ` [PATCH v2 2/2] i386/cpu: make -cpu host support monitor/mwait Michael S. Tsirkin
2018-06-12 18:47 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-13 21:24 ` Eduardo Habkost
2018-06-13 21:24 ` [Qemu-devel] " Eduardo Habkost
2018-06-12 19:18 ` [PATCH v2 0/2] kvm: x86 CPU power management no-reply
2018-06-12 19:18 ` [Qemu-devel] " no-reply
2018-06-12 20:29 ` Michael S. Tsirkin
2018-06-12 20:29 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-13 22:34 ` Marcelo Tosatti [this message]
2018-06-13 22:34 ` Marcelo Tosatti
2018-06-13 23:37 ` Michael S. Tsirkin
2018-06-13 23:37 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-15 18:32 ` Marcelo Tosatti
2018-06-15 18:32 ` [Qemu-devel] " Marcelo Tosatti
2018-06-15 21:53 ` Michael S. Tsirkin
2018-06-15 21:53 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-14 8:18 ` Daniel P. Berrangé
2018-06-14 8:18 ` [Qemu-devel] " Daniel P. Berrangé
2018-06-14 15:40 ` Paolo Bonzini
2018-06-14 15:40 ` [Qemu-devel] " Paolo Bonzini
2018-06-14 15:44 ` Daniel P. Berrangé
2018-06-14 15:44 ` [Qemu-devel] " Daniel P. Berrangé
2018-06-14 20:32 ` Paolo Bonzini
2018-06-14 20:32 ` [Qemu-devel] " Paolo Bonzini
2018-06-15 14:15 ` Michael S. Tsirkin
2018-06-15 14:15 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-14 16:53 ` Eduardo Habkost
2018-06-14 16:53 ` [Qemu-devel] " Eduardo Habkost
2018-06-14 21:21 ` Paolo Bonzini
2018-06-14 21:21 ` [Qemu-devel] " Paolo Bonzini
2018-06-15 13:52 ` Michael S. Tsirkin
2018-06-15 13:52 ` [Qemu-devel] " Michael S. Tsirkin
2018-06-22 13:06 ` Kashyap Chamarthy
2018-06-22 13:06 ` [Qemu-devel] " Kashyap Chamarthy
2018-06-22 19:18 ` Michael S. Tsirkin
2018-06-22 19:18 ` [Qemu-devel] " Michael S. Tsirkin
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=20180613223449.GA18339@amt.cnet \
--to=mtosatti@redhat.com \
--cc=ehabkost@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=rth@twiddle.net \
/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.