From: Gleb Natapov <gleb@redhat.com>
To: Alexander Graf <agraf@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>,
kvm@vger.kernel.org, "Michael S. Tsirkin" <mst@redhat.com>,
x86@kernel.org, Will Deacon <will.deacon@arm.com>,
linux-kernel@vger.kernel.org,
Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
Sasha Levin <sasha.levin@oracle.com>,
Thomas Gleixner <tglx@linutronix.de>,
Christoffer Dall <c.dall@virtualopensystems.com>,
virtualization@lists.linux-foundation.org,
Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Subject: Re: [PATCH RFC] kvm: add PV MMIO EVENTFD
Date: Thu, 4 Apr 2013 19:33:34 +0300 [thread overview]
Message-ID: <20130404163334.GE27672@redhat.com> (raw)
In-Reply-To: <14B443D5-5785-487D-9EA3-0AD20141BC06@suse.de>
On Thu, Apr 04, 2013 at 05:36:40PM +0200, Alexander Graf wrote:
> >
> > #define GOAL (1ull << 30)
> >
> > do {
> > iterations *= 2;
> > t1 = rdtsc();
> >
> > for (i = 0; i < iterations; ++i)
> > func();
> > t2 = rdtsc();
> > } while ((t2 - t1) < GOAL);
> > printf("%s %d\n", test->name, (int)((t2 - t1) / iterations));
>
> So it's the number of cycles per run.
>
> That means translated my numbers are:
>
> MMIO: 4307
> PIO: 3658
> HCALL: 1756
>
> MMIO - PIO = 649
>
> which aligns roughly with your PV MMIO callback.
>
> My MMIO benchmark was to poke the LAPIC version register. That does go through instruction emulation, no?
>
It should and PIO 'in' or string also goes through the emulator.
--
Gleb.
WARNING: multiple messages have this Message-ID (diff)
From: Gleb Natapov <gleb@redhat.com>
To: Alexander Graf <agraf@suse.de>
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
x86@kernel.org, Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>,
Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>,
Alex Williamson <alex.williamson@redhat.com>,
Will Deacon <will.deacon@arm.com>,
Christoffer Dall <c.dall@virtualopensystems.com>,
Sasha Levin <sasha.levin@oracle.com>,
Andrew Morton <akpm@linux-foundation.org>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
virtualization@lists.linux-foundation.org
Subject: Re: [PATCH RFC] kvm: add PV MMIO EVENTFD
Date: Thu, 4 Apr 2013 19:33:34 +0300 [thread overview]
Message-ID: <20130404163334.GE27672@redhat.com> (raw)
In-Reply-To: <14B443D5-5785-487D-9EA3-0AD20141BC06@suse.de>
On Thu, Apr 04, 2013 at 05:36:40PM +0200, Alexander Graf wrote:
> >
> > #define GOAL (1ull << 30)
> >
> > do {
> > iterations *= 2;
> > t1 = rdtsc();
> >
> > for (i = 0; i < iterations; ++i)
> > func();
> > t2 = rdtsc();
> > } while ((t2 - t1) < GOAL);
> > printf("%s %d\n", test->name, (int)((t2 - t1) / iterations));
>
> So it's the number of cycles per run.
>
> That means translated my numbers are:
>
> MMIO: 4307
> PIO: 3658
> HCALL: 1756
>
> MMIO - PIO = 649
>
> which aligns roughly with your PV MMIO callback.
>
> My MMIO benchmark was to poke the LAPIC version register. That does go through instruction emulation, no?
>
It should and PIO 'in' or string also goes through the emulator.
--
Gleb.
next prev parent reply other threads:[~2013-04-04 16:33 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-04 10:50 [PATCH RFC] kvm: add PV MMIO EVENTFD Michael S. Tsirkin
2013-04-04 10:50 ` Michael S. Tsirkin
2013-04-04 11:57 ` Alexander Graf
2013-04-04 11:57 ` Alexander Graf
2013-04-04 11:04 ` Michael S. Tsirkin
2013-04-04 11:04 ` Michael S. Tsirkin
2013-04-04 12:09 ` Alexander Graf
2013-04-04 12:09 ` Alexander Graf
2013-04-04 11:21 ` Michael S. Tsirkin
2013-04-04 11:21 ` Michael S. Tsirkin
2013-04-04 12:19 ` Gleb Natapov
2013-04-04 12:19 ` Gleb Natapov
2013-04-04 12:22 ` Alexander Graf
2013-04-04 12:22 ` Alexander Graf
2013-04-04 12:08 ` Gleb Natapov
2013-04-04 12:08 ` Gleb Natapov
2013-04-04 12:22 ` Alexander Graf
2013-04-04 12:22 ` Alexander Graf
2013-04-04 12:34 ` Gleb Natapov
2013-04-04 12:34 ` Gleb Natapov
2013-04-04 12:39 ` Alexander Graf
2013-04-04 12:39 ` Alexander Graf
2013-04-04 12:58 ` Michael S. Tsirkin
2013-04-04 12:58 ` Michael S. Tsirkin
2013-04-04 14:02 ` Alexander Graf
2013-04-04 14:02 ` Alexander Graf
2013-04-04 13:40 ` Michael S. Tsirkin
2013-04-04 13:40 ` Michael S. Tsirkin
2013-04-04 12:32 ` Alexander Graf
2013-04-04 12:32 ` Alexander Graf
2013-04-04 12:38 ` Gleb Natapov
2013-04-04 12:38 ` Gleb Natapov
2013-04-04 12:39 ` Alexander Graf
2013-04-04 12:39 ` Alexander Graf
2013-04-04 12:45 ` Gleb Natapov
2013-04-04 12:45 ` Gleb Natapov
2013-04-04 12:49 ` Alexander Graf
2013-04-04 12:49 ` Alexander Graf
2013-04-04 12:56 ` Gleb Natapov
2013-04-04 12:56 ` Gleb Natapov
2013-04-04 13:06 ` Alexander Graf
2013-04-04 13:06 ` Alexander Graf
2013-04-04 13:14 ` Gleb Natapov
2013-04-04 13:14 ` Gleb Natapov
2013-04-04 14:26 ` Michael S. Tsirkin
2013-04-04 14:26 ` Michael S. Tsirkin
2013-04-07 9:30 ` Gleb Natapov
2013-04-07 9:30 ` Gleb Natapov
2013-04-07 8:43 ` Michael S. Tsirkin
2013-04-07 8:43 ` Michael S. Tsirkin
2013-04-04 13:33 ` Michael S. Tsirkin
2013-04-04 13:33 ` Michael S. Tsirkin
2013-04-04 15:36 ` Alexander Graf
2013-04-04 15:36 ` Alexander Graf
2013-04-04 15:36 ` Michael S. Tsirkin
2013-04-04 15:36 ` Michael S. Tsirkin
2013-04-04 16:39 ` Gleb Natapov
2013-04-04 16:39 ` Gleb Natapov
2013-04-04 23:32 ` Christoffer Dall
2013-04-07 7:41 ` Michael S. Tsirkin
2013-04-07 7:41 ` Michael S. Tsirkin
2013-04-07 21:25 ` Christoffer Dall
2013-04-04 23:32 ` Christoffer Dall
2013-04-04 16:33 ` Gleb Natapov [this message]
2013-04-04 16:33 ` Gleb Natapov
2013-04-04 13:12 ` Michael S. Tsirkin
2013-04-04 13:12 ` Michael S. Tsirkin
2013-04-04 13:06 ` Michael S. Tsirkin
2013-04-04 13:06 ` Michael S. Tsirkin
2013-04-04 13:03 ` Michael S. Tsirkin
2013-04-04 13:03 ` 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=20130404163334.GE27672@redhat.com \
--to=gleb@redhat.com \
--cc=agraf@suse.de \
--cc=akpm@linux-foundation.org \
--cc=c.dall@virtualopensystems.com \
--cc=hpa@zytor.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=mst@redhat.com \
--cc=sasha.levin@oracle.com \
--cc=tglx@linutronix.de \
--cc=virtualization@lists.linux-foundation.org \
--cc=will.deacon@arm.com \
--cc=x86@kernel.org \
--cc=xiaoguangrong@linux.vnet.ibm.com \
--cc=yoshikawa_takuya_b1@lab.ntt.co.jp \
/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.