From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934198AbZAOXjX (ORCPT ); Thu, 15 Jan 2009 18:39:23 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756266AbZAOXjK (ORCPT ); Thu, 15 Jan 2009 18:39:10 -0500 Received: from yw-out-2324.google.com ([74.125.46.29]:45099 "EHLO yw-out-2324.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753782AbZAOXjI (ORCPT ); Thu, 15 Jan 2009 18:39:08 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=Z2aMXN0R0dxOhGyI17oCKfIpVVg7WUfmk/Ax3A6VcPSeuUzSBU9o02WytEeRbnd+z/ pGPbsLXdYcK7+dI6Jq25BlJHUTpapZ6PuHLb56qhBAtWPt+YPhlpQph/oP6ShTg4Hujn wU+5pyK2QdIIWn5+EJTE8LZtnKmOmxii6IkNQ= MIME-Version: 1.0 In-Reply-To: <496FBF2B.4010809@linux.intel.com> References: <20081227155019.GA15493@elte.hu> <20081227225102.GA17822@elte.hu> <49594411.60000@linux.intel.com> <20090113174522.GA26965@elte.hu> <496DB067.6060402@linux.intel.com> <496E297B.6010100@linux.intel.com> <496FBF2B.4010809@linux.intel.com> Date: Thu, 15 Jan 2009 15:39:07 -0800 Message-ID: Subject: Re: x86/mce merge, integration hickup + crash, design thoughts From: Tim Hockin To: Andi Kleen Cc: Ingo Molnar , Thomas Gleixner , linux-kernel@vger.kernel.org, "H. Peter Anvin" , ying.huang@intel.com, Aaron Durbin , priyankag@google.com Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Jan 15, 2009 at 2:56 PM, Andi Kleen wrote: > Tim Hockin wrote: >> >> Yeah, no offense, but that's horrible :) > > I'm not sure it's worse than the XML like format proposals that seem to > get thrown around. That is I am the only one who mentioned the > X word yet, but the structured ASCII records that have been hinted > at would be exactly like that. Yeah, if anyone proposes XML, I'll punch them :) I'm not that firm on it being ASCII myself, but it would be OK. Google's protocol buffers are a good example of a very efficient encoding of flexible data. This is not an unsolvable problem. >> SATA >> disk timeouts. > > Now that's a different issue. Generalized driver error reporting for > everyone. > > There was a lot of discussion some years ago from a IBM proposal to do > in general structured error reporting. But that was quite unpopular > and no-one really liked it. > > What came out of it was the dev_printk() stuff that allows > to match error messages to devices. So you already have some > baby steps in this direction. I remember - I was at Sun at the time. We wanted the same thing. > I suspect doing this fully generalized would be quite difficult > because there would be so many people you have to convince. Yes, it will be hard. But I think it will not be impossible. >> Now I know there are different conduits for some events - netlink >> tells me about netif link up/down events I think. I would settle for >> a small number of interfaces. What I don't want is what we have today >> - EVERYTHING has a different interface. Some are poll()-able. Some >> have to be actively polled. Some have to have a daemon listening or >> else messages are dropped. > > Well the kernel will always have limited buffers, so the someone > needs to listen problem will be always there. Sure, but just having a small buffer, like mcelog, and being poll()able goes a log way. >> Put it this way: Given a thousand machines, I want to gather, >> collate, and correlate all these events. I want to be able to produce >> a "life story" of sorts for a machine and for a data center. Once I >> can do that, I can start to make predictive diagnoses more accurately, >> and I can know how much these things actually COST us. > > Sure sounds nice. But frankly I don't see it happening. It would > be just too radical a change of too much code. We do a lot of this now, but it's far less accurate than it could be, because we drop so many events. And programming to all the different interfaces is difficult and error-prone. I'm hoping we can find a solution that makes everyone only a little bit unhappy. Tim