From mboxrd@z Thu Jan 1 00:00:00 1970 From: Richard Cochran Subject: Re: [PATCH v2 net] igb: shorten maximum PHC timecounter update interval Date: Tue, 30 Oct 2018 19:30:56 -0700 Message-ID: <20181031023056.zqb5zl3wgl5fbbju@localhost> References: <20181026171300.12720-1-mlichvar@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@vger.kernel.org, intel-wired-lan@lists.osuosl.org, Jacob Keller , Thomas Gleixner To: Miroslav Lichvar Return-path: Received: from mail-pf1-f195.google.com ([209.85.210.195]:33470 "EHLO mail-pf1-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728645AbeJaL06 (ORCPT ); Wed, 31 Oct 2018 07:26:58 -0400 Received: by mail-pf1-f195.google.com with SMTP id a15-v6so6846070pfn.0 for ; Tue, 30 Oct 2018 19:30:59 -0700 (PDT) Content-Disposition: inline In-Reply-To: <20181026171300.12720-1-mlichvar@redhat.com> Sender: netdev-owner@vger.kernel.org List-ID: On Fri, Oct 26, 2018 at 07:13:00PM +0200, Miroslav Lichvar wrote: > The timecounter needs to be updated at least once per ~550 seconds in > order to avoid a 40-bit SYSTIM timestamp to be misinterpreted as an old > timestamp. > > Since commit 500462a9de65 ("timers: Switch to a non-cascading wheel"), > scheduling of delayed work seems to be less accurate and a requested > delay of 540 seconds may actually be longer than 550 seconds. Also, the > PHC may be adjusted to run up to 6% faster than real time and the system > clock up to 10% slower. Shorten the delay to 360 seconds to be sure the > timecounter is updated in time. > > This fixes an issue with HW timestamps on 82580/I350/I354 being off by > ~1100 seconds for few seconds every ~9 minutes. Acked-by: Richard Cochran