From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:40743)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <marc.zyngier@arm.com>) id 1aLwFP-0005y4-Rc
	for qemu-devel@nongnu.org; Wed, 20 Jan 2016 12:08:47 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <marc.zyngier@arm.com>) id 1aLwFL-00007I-R8
	for qemu-devel@nongnu.org; Wed, 20 Jan 2016 12:08:43 -0500
Received: from foss.arm.com ([217.140.101.70]:45492)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <marc.zyngier@arm.com>) id 1aLwFL-000069-Kt
	for qemu-devel@nongnu.org; Wed, 20 Jan 2016 12:08:39 -0500
References: <1453204158-11412-1-git-send-email-christoffer.dall@linaro.org>
	<20160119123716.GA10814@hawk.localdomain> <20160119124341.GA11756@cbox>
	<20160119133232.GA13745@hawk.localdomain> <569E3D6B.5030501@arm.com>
	<20160119184814.GC26962@hawk.localdomain>
	<20160120140121.GA3723@hawk.localdomain> <569F9975.90405@arm.com>
	<20160120150618.GB3723@hawk.localdomain> <569FB3B3.7040303@arm.com>
	<20160120164749.GC3723@hawk.localdomain>
From: Marc Zyngier <marc.zyngier@arm.com>
Message-ID: <569FBF14.20201@arm.com>
Date: Wed, 20 Jan 2016 17:08:36 +0000
MIME-Version: 1.0
In-Reply-To: <20160120164749.GC3723@hawk.localdomain>
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCH] hw/arm/virt: Add always-on property to the
 virt board timer
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Andrew Jones <drjones@redhat.com>
Cc: Mark Rutland <Mark.Rutland@arm.com>, qemu-devel@nongnu.org, Christoffer Dall <christoffer.dall@linaro.org>

On 20/01/16 16:47, Andrew Jones wrote:
> On Wed, Jan 20, 2016 at 04:20:03PM +0000, Marc Zyngier wrote:
>> Just tried on Seattle with a 64bit guest, and there is hardly any
>> difference indeed. Both host and guest are "mostly" defconfig as well.
>> So there is a kernel configuration difference.
>>
>> Running my 32bit guest on a 64bit host definitely shows a massive
>> difference (with 8 vcpus):
>>
>> Without "always-on": ~1200 interrupts per second
>> With "always-on": ~50 interrupts per second
>>
>> [Head scratching, poking Mark]
>>
>> Right, I now know what is going on: The arm64 kernel uses
>> tick_setup_hrtimer_broadcast() so that it can still use the arch timer
>> as a broadcast timer (forcing one CPU to remain on), while the 32bit
>> kernel relies on the presence of a backup timer (sp804 anyone?) or the
>> guarantee that the timer cannot go away (always-on).
>>
>> This is probably why I'm seeing such a gain with a 32bit guest, and none
>> with a 64bit guest (the kernel already does the right thing). As to why
>> there is such a difference between the two architectures, this is a
>> story for another day...
>>
> 
> Thanks Marc! I just confirmed with an AArch32 guest using QEMU, and the
> patch we've hijacked for this thread. Without the patch I get a megaton
> of interrupts (~14000/s). With the patch, after letting the guest chill
> for a while, I'm getting ~150/s (8 vcpus).
> 
> I guess I don't have a test case for the ACPI code though. afaik we only
> have UEFI for AArch64 guests, and we don't have ACPI boot without UEFI.
> Or maybe I can hack time_init to remove the tick_setup_hrtimer_broadcast
> call?

Yeah, that should work.

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny...