From mboxrd@z Thu Jan 1 00:00:00 1970 From: david.vrabel@citrix.com (David Vrabel) Date: Tue, 15 Sep 2015 14:14:09 +0100 Subject: [Xen-devel] [PATCH v4 00/20] xen/arm64: Add support for 64KB page in Linux In-Reply-To: <2415578.qstFX0Ux2G@wuerfel> References: <1441640038-23615-1-git-send-email-julien.grall@citrix.com> <55F6A437.3040403@citrix.com> <55F6A9DB.8040503@citrix.com> <2415578.qstFX0Ux2G@wuerfel> Message-ID: <55F819A1.8070609@citrix.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On 14/09/15 12:32, Arnd Bergmann wrote: > On Monday 14 September 2015 13:04:59 Roger Pau Monn? wrote: >>> TBH, I'm expecting a small impact to the performance. It would be hard >>> to get the exactly the same performance as today if we keep the helpers >>> to avoid the backend dealing himself with the splitting and page >>> granularity. >>> >>> Although, if the performance impact is not acceptable, it may be >>> possible to optimize gnttab_foreach_grant_in_range by moving the >>> function inline. The current way to the loop is the fastest I've found >>> (I've wrote a small program to test different way) and we will need it >>> when different of size will be supported. >> >> I don't expect the performance to drop massively with this patches >> applied, but it would be good to al least have an idea of the impact. > > Note that using 64kb pages in Linux tends to destroy performance > in Linux in any case, as the memory consumption for most workloads > explodes. In a virtualized environment you already tend to be > memory constrained, so any measurement should take that into account > and put the extra overhead into perspective to the massive overhead > of running 64kb pages when RAM is tight. If this is the case, why are some distros using 64 KiB pages then? David From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752260AbbIONOO (ORCPT ); Tue, 15 Sep 2015 09:14:14 -0400 Received: from smtp02.citrix.com ([66.165.176.63]:27747 "EHLO SMTP02.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751722AbbIONON (ORCPT ); Tue, 15 Sep 2015 09:14:13 -0400 X-IronPort-AV: E=Sophos;i="5.17,536,1437436800"; d="scan'208";a="303697780" Message-ID: <55F819A1.8070609@citrix.com> Date: Tue, 15 Sep 2015 14:14:09 +0100 From: David Vrabel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Icedove/31.8.0 MIME-Version: 1.0 To: Arnd Bergmann , CC: , , , , "Julien Grall" , , , , =?windows-1252?Q?Roger_Pau_Monn=E9?= Subject: Re: [Xen-devel] [PATCH v4 00/20] xen/arm64: Add support for 64KB page in Linux References: <1441640038-23615-1-git-send-email-julien.grall@citrix.com> <55F6A437.3040403@citrix.com> <55F6A9DB.8040503@citrix.com> <2415578.qstFX0Ux2G@wuerfel> In-Reply-To: <2415578.qstFX0Ux2G@wuerfel> Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: 8bit X-DLP: MIA2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 14/09/15 12:32, Arnd Bergmann wrote: > On Monday 14 September 2015 13:04:59 Roger Pau Monné wrote: >>> TBH, I'm expecting a small impact to the performance. It would be hard >>> to get the exactly the same performance as today if we keep the helpers >>> to avoid the backend dealing himself with the splitting and page >>> granularity. >>> >>> Although, if the performance impact is not acceptable, it may be >>> possible to optimize gnttab_foreach_grant_in_range by moving the >>> function inline. The current way to the loop is the fastest I've found >>> (I've wrote a small program to test different way) and we will need it >>> when different of size will be supported. >> >> I don't expect the performance to drop massively with this patches >> applied, but it would be good to al least have an idea of the impact. > > Note that using 64kb pages in Linux tends to destroy performance > in Linux in any case, as the memory consumption for most workloads > explodes. In a virtualized environment you already tend to be > memory constrained, so any measurement should take that into account > and put the extra overhead into perspective to the massive overhead > of running 64kb pages when RAM is tight. If this is the case, why are some distros using 64 KiB pages then? David