From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH] kvm tools: mmap guest kernel instead of reading it into memory Date: Mon, 12 Dec 2011 20:08:42 +0200 Message-ID: <4EE6432A.7010709@redhat.com> References: <1323701258-17443-1-git-send-email-levinsasha928@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: penberg@kernel.org, mingo@elte.hu, gorcunov@gmail.com, asias.hejun@gmail.com, kvm@vger.kernel.org, ajsween@sandia.gov To: Sasha Levin Return-path: Received: from mx1.redhat.com ([209.132.183.28]:33200 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752870Ab1LLSJC (ORCPT ); Mon, 12 Dec 2011 13:09:02 -0500 In-Reply-To: <1323701258-17443-1-git-send-email-levinsasha928@gmail.com> Sender: kvm-owner@vger.kernel.org List-ID: On 12/12/2011 04:47 PM, Sasha Levin wrote: > This patch mmaps guest kernel into it's own memory slot instead of reading > it into the memory. > > The advantages are: > - Smaller memory footprint (same effect as KSM if running multiple guests) > - Faster loading of larger kernels. > How many COW faults do you get when loading a kernel? Would be interesting to try both smp and up guests. Surprisingly, there is no tracepoint for that that I can see, but you can probe do_wp_page() and count it. -- error compiling committee.c: too many arguments to function