From mboxrd@z Thu Jan 1 00:00:00 1970 From: Erik Jacobson Subject: Re: slow guest performance with build load, looking for ideas Date: Sun, 28 Jun 2009 14:05:00 -0500 Message-ID: <20090628190500.GA7347@sgi.com> References: <20090612210443.GA21840@sgi.com> <4A34C3D2.9020009@redhat.com> <20090618230744.GA19307@sgi.com> <4A477B8C.2010502@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Erik Jacobson , kvm@vger.kernel.org To: Avi Kivity Return-path: Received: from relay2.sgi.com ([192.48.179.30]:35368 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752167AbZF1TE6 (ORCPT ); Sun, 28 Jun 2009 15:04:58 -0400 Content-Disposition: inline In-Reply-To: <4A477B8C.2010502@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: >> * In some of the timing runs on this system, the "real time" reported by >> the time command was off by 10 to 11 times. Issues were found in >> the messages file that seemed to relate to this including HUGE time >> adjustments by NTP and kernel hrtimer 'interrupt too slow' messages. >> This specific problem seems to be intermittent. > This is on the host? It can easily ruin your day. This was in the guest. >> System: >> SGI XE270, 8-core, Xeon X5570 (Nehalem), Hyperthreading turned off > Shoot, was about to blame hyperthreading. I'll keep it off for the next attempted run. > kvm guests should have an accurate clock without ntp in the guest > (/sys/.../current_clocksource should say 'kvmclock'). OK thanks. > Can you post kvm_stat output during the run? Sure, I'll try to get time on the system again next week and post in to the thread again. We'll still have the issue with the non-sequential nodes and incorrect representation of memory for this two-socket Nehalem system. I don't think that patch has made it in to the kernel. Thanks for replying back. If you have any other things you'd suggest trying, I'm game to give it a whirl. Someone suggested trying to export a whole PCI device to the guest. I won't be able to do that on this machine, maybe later when I have physical access to the system. Besides, that exercise might not poke at what I'm interested in anyway. Others suggested some potential settings EPT (Extended Page Table) and VPID (Virtual Path Identifier?) but I don't see where these settings are exposed (they aren't, for example, in this system's BIOS). More to come then. Thanks. Erik