From mboxrd@z Thu Jan 1 00:00:00 1970 From: Igor Mammedov Subject: Re: x86: kvmclock: abstract save/restore sched_clock_state Date: Fri, 10 Feb 2012 13:43:05 +0100 Message-ID: <4F3510D9.8050204@redhat.com> References: <20120207210542.GC20618@amt.cnet> <20120209122742.GA25505@amit.redhat.com> <4F33E299.3090500@redhat.com> <20120210100211.GA2971@amit.redhat.com> <20120210123216.GA11137@amt.cnet> <20120210123337.GB11137@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Amit Shah , kvm@vger.kernel.org, tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com, x86@kernel.org, johnstul@us.ibm.com, riel@redhat.com, avi@redhat.com To: Marcelo Tosatti Return-path: Received: from mx1.redhat.com ([209.132.183.28]:64361 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754727Ab2BJMnS (ORCPT ); Fri, 10 Feb 2012 07:43:18 -0500 In-Reply-To: <20120210123337.GB11137@amt.cnet> Sender: kvm-owner@vger.kernel.org List-ID: On 02/10/2012 01:33 PM, Marcelo Tosatti wrote: > On Fri, Feb 10, 2012 at 10:32:16AM -0200, Marcelo Tosatti wrote: >> On Fri, Feb 10, 2012 at 03:32:11PM +0530, Amit Shah wrote: >>> On (Thu) 09 Feb 2012 [16:13:29], Igor Mammedov wrote: >>> >>>> Stalls are probably caused by uninitialized percpu hv_clock, with >>>> following patch I don't see stalls. Although I might be just lucky. >>>> http://git.kernel.org/?p=virt/kvm/kvm.git;a=commit;h=e2971ac7e1d186af059e088d305496c5cb47d487 >>> >>> Your commit does make things better, I don't see any stalls on the >>> first resume. >>> >>> However, a subsequent s4 causes the stall to re-appear on resume, and >>> this time there are no stall messages; the kernel just sits there >>> spinning on something. I've not found the solution to this one yet (I >>> had a commit similar to Marcelo's in the works, which got me to the >>> previous works-but-stalls behaviour). >> >> I cannot reproduce it here. Suspend/resume are operating normally after >> several iterations. Igor do you see anything similar? I wasn't able to reproduce it either but I haven't tried with Amit's config yet. >> >> Amit, can you please enable CONFIG_PRINTK_TIME=y and post a full dmesg >> (both during suspend and also the new kernel during resume). > > Also is it reproducible with UP guest? Another thing is to try smp guest without kvmclock and see if it helps. It might be just something else. > -- > To unsubscribe from this list: send the line "unsubscribe kvm" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- Thanks, Igor