Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1764892AbXHYQpH (ORCPT ); Sat, 25 Aug 2007 12:45:07 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753402AbXHYQow (ORCPT ); Sat, 25 Aug 2007 12:44:52 -0400 Received: from nf-out-0910.google.com ([64.233.182.190]:18438 "EHLO nf-out-0910.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761453AbXHYQom (ORCPT ); Sat, 25 Aug 2007 12:44:42 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; b=epwIdN4X4diDNifCVOW2t/puT/MWgAsq8tbEqVMlfhK5lX4hU3e1iTZc+pUqDFfnatL4nTtVm+O0G469COqMS+FixBZ/EC2gB7LaBaOqZxF7RDQ+tLP+1EwOt07/aEspZ3XtKagajujjhMV5Nq13kOK5sYG4VC30tRxpQL6CQic= Message-ID: <3c1737210708250944u7043c9e1j3be70674a1b55911@mail.gmail.com> Date: Sat, 25 Aug 2007 18:44:40 +0200 From: "Michael Smith" To: "john stultz" Subject: Re: gettimeofday() jumping into the future Cc: "Peter Zijlstra" , linux-kernel@vger.kernel.org, "Andy Wingo" , "Thomas Gleixner" , "Ingo Molnar" In-Reply-To: <1187894822.6024.8.camel@localhost.localdomain> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <3c1737210708230408i7a8049a9m5db49e6c4d89ab62@mail.gmail.com> <1187869632.6114.368.camel@twins> <3c1737210708230520l7dee896crc614f7fc60ac7a1a@mail.gmail.com> <1187894822.6024.8.camel@localhost.localdomain> X-Google-Sender-Auth: 9447366d6563c5c1 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 993 Lines: 25 > > Hmm. That does sound like unsycned TSCs. Normally Intel systems don't > skew unless they are NUMA systems or you're entering low power states. > We try to catch both of those cases, so I'm not sure how you box is > slipping through. > > Can you run the following test to verify that the TSCs are skewed? I ran this for the past two days, multiple copies to put some load on the system (the initial problem with gettimeofday() was easier to reproduce under load). Nothing. So, I guess that rules out unsynced TSCs as the cause? Or perhaps it only happens in other conditions, for some reason. I'm on holidays right now, but my coworkers should be able to continue investigating other possible causes. Thanks for the advice/test program. Mike - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/