From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: Windows slow boot: contractor wanted Date: Wed, 22 Aug 2012 15:44:39 +0300 Message-ID: <5034D437.8070106@redhat.com> References: <20120816104727.GA17166@alpha.arachsys.com> <502CDC0D.9080004@redhat.com> <20120817123642.GA16736@alpha.arachsys.com> <5030F273.5080706@redhat.com> <20120820135656.GA16676@alpha.arachsys.com> <50334E13.8020100@redhat.com> <20120821152107.GA16363@alpha.arachsys.com> <5034A18B.5040408@redhat.com> <20120822124032.GA12647@alpha.arachsys.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org, Rik van Riel To: Richard Davies Return-path: Received: from mx1.redhat.com ([209.132.183.28]:35012 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932381Ab2HVMou (ORCPT ); Wed, 22 Aug 2012 08:44:50 -0400 In-Reply-To: <20120822124032.GA12647@alpha.arachsys.com> Sender: kvm-owner@vger.kernel.org List-ID: On 08/22/2012 03:40 PM, Richard Davies wrote: > > I can trigger the slow boots without KSM and they have the same profile, > with _raw_spin_lock_irqsave and isolate_freepages_block at the top. > > I reduced to 3x 20GB 8-core VMs on a 128GB host (rather than 3x 40GB 8-core > VMs), and haven't managed to get a really slow boot yet (>5 minutes). I'll > post agan when I get one. I think you can go higher than that. But 120GB on a 128GB host is pushing it. > > In the slowest boot that I have so far (1-2 minutes), this is the perf top > ouput: > > > PerfTop: 26741 irqs/sec kernel:97.5% exact: 0.0% [4000Hz cycles], (all, 16 CPUs) > --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- > > 53.94% [kernel] [k] clear_page_c > 2.77% [kernel] [k] svm_vcpu_put > 2.60% [kernel] [k] svm_vcpu_run > 1.79% [kernel] [k] sub_preempt_count > 1.56% [kernel] [k] svm_vcpu_load > 1.44% [kernel] [k] __schedule > 1.36% [kernel] [k] kvm_arch_vcpu_ioctl_run > 1.34% [kernel] [k] resched_task > 1.32% [kernel] [k] _raw_spin_lock > 0.98% [kernel] [k] trace_preempt_on > 0.95% [kernel] [k] get_parent_ip > 0.94% [kernel] [k] yield_to This is pretty normal, Widows is touching memory so clear_page_c() is called to scrub it. -- error compiling committee.c: too many arguments to function