From: Scott Wood <scottwood@freescale.com>
To: Alexander Graf <agraf@suse.de>
Cc: Paul Mackerras <paulus@samba.org>, kvm list <kvm@vger.kernel.org>,
kvm-ppc <kvm-ppc@vger.kernel.org>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: [PATCH 2/2] KVM: PPC: Book3S: Call into C interrupt handlers
Date: Fri, 27 Apr 2012 16:37:25 +0000 [thread overview]
Message-ID: <4F9ACB45.3040803@freescale.com> (raw)
In-Reply-To: <DCEE0304-AD55-4522-814A-CB7B714D56C8@suse.de>
On 04/27/2012 06:23 AM, Alexander Graf wrote:
>
> On 27.04.2012, at 07:48, Paul Mackerras wrote:
>
>> Have you measured a performance improvement with this patch? If so
>> how big was it?
>
> Yeah, I tried things on 970 in an mfsprg/mtsprg busy loop. I measured 3 different variants:
>
> C irq handling: 1004944 exits/sec
> asm irq handling: 1001774 exits/sec
> asm + hsrr patch: 994719 exits/sec
>
> So as you can see, that code change does have quite an impact. But
> maybe the added complexity isn't worth it? Either way, we should try
> and find a solution that works the same way for booke and book3s - I
> don't want such an integral part to differ all that much.
Is it really added complexity, considering what you can remove from the
asm? I went with C handling on bookehv because it seemed simpler (the
original internal version had asm handling).
-Scott
WARNING: multiple messages have this Message-ID (diff)
From: Scott Wood <scottwood@freescale.com>
To: Alexander Graf <agraf@suse.de>
Cc: Paul Mackerras <paulus@samba.org>, kvm list <kvm@vger.kernel.org>,
kvm-ppc <kvm-ppc@vger.kernel.org>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: [PATCH 2/2] KVM: PPC: Book3S: Call into C interrupt handlers
Date: Fri, 27 Apr 2012 11:37:25 -0500 [thread overview]
Message-ID: <4F9ACB45.3040803@freescale.com> (raw)
In-Reply-To: <DCEE0304-AD55-4522-814A-CB7B714D56C8@suse.de>
On 04/27/2012 06:23 AM, Alexander Graf wrote:
>
> On 27.04.2012, at 07:48, Paul Mackerras wrote:
>
>> Have you measured a performance improvement with this patch? If so
>> how big was it?
>
> Yeah, I tried things on 970 in an mfsprg/mtsprg busy loop. I measured 3 different variants:
>
> C irq handling: 1004944 exits/sec
> asm irq handling: 1001774 exits/sec
> asm + hsrr patch: 994719 exits/sec
>
> So as you can see, that code change does have quite an impact. But
> maybe the added complexity isn't worth it? Either way, we should try
> and find a solution that works the same way for booke and book3s - I
> don't want such an integral part to differ all that much.
Is it really added complexity, considering what you can remove from the
asm? I went with C handling on bookehv because it seemed simpler (the
original internal version had asm handling).
-Scott
next prev parent reply other threads:[~2012-04-27 16:37 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-04-26 10:19 [PATCH 1/2] PPC: Export some interrupt handlers Alexander Graf
2012-04-26 10:19 ` Alexander Graf
2012-04-26 10:19 ` [PATCH 2/2] KVM: PPC: Book3S: Call into C " Alexander Graf
2012-04-26 10:19 ` Alexander Graf
2012-04-26 21:45 ` Benjamin Herrenschmidt
2012-04-26 21:45 ` Benjamin Herrenschmidt
2012-04-26 22:24 ` Alexander Graf
2012-04-26 22:24 ` Alexander Graf
2012-04-26 23:12 ` Benjamin Herrenschmidt
2012-04-26 23:12 ` Benjamin Herrenschmidt
2012-04-26 23:30 ` Alexander Graf
2012-04-26 23:30 ` Alexander Graf
2012-04-26 23:37 ` Benjamin Herrenschmidt
2012-04-26 23:37 ` Benjamin Herrenschmidt
2012-04-26 23:50 ` Alexander Graf
2012-04-26 23:50 ` Alexander Graf
2012-04-27 0:00 ` Benjamin Herrenschmidt
2012-04-27 0:00 ` Benjamin Herrenschmidt
2012-04-26 21:54 ` Scott Wood
2012-04-26 21:54 ` Scott Wood
2012-04-26 22:26 ` Alexander Graf
2012-04-26 22:26 ` Alexander Graf
2012-04-26 22:58 ` Benjamin Herrenschmidt
2012-04-26 22:58 ` Benjamin Herrenschmidt
2012-04-27 5:48 ` Paul Mackerras
2012-04-27 5:48 ` Paul Mackerras
2012-04-27 11:23 ` Alexander Graf
2012-04-27 11:23 ` Alexander Graf
2012-04-27 14:19 ` Alexander Graf
2012-04-27 14:19 ` Alexander Graf
2012-04-27 16:37 ` Scott Wood [this message]
2012-04-27 16:37 ` Scott Wood
2012-04-27 16:54 ` Alexander Graf
2012-04-27 16:54 ` Alexander Graf
2012-04-27 22:20 ` Benjamin Herrenschmidt
2012-04-27 22:20 ` Benjamin Herrenschmidt
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=4F9ACB45.3040803@freescale.com \
--to=scottwood@freescale.com \
--cc=agraf@suse.de \
--cc=benh@kernel.crashing.org \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=paulus@samba.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 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.