Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1764138AbZFOQ70 (ORCPT ); Mon, 15 Jun 2009 12:59:26 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1763098AbZFOQ7N (ORCPT ); Mon, 15 Jun 2009 12:59:13 -0400 Received: from one.firstfloor.org ([213.235.205.2]:52454 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763204AbZFOQ7M (ORCPT ); Mon, 15 Jun 2009 12:59:12 -0400 Date: Mon, 15 Jun 2009 19:07:26 +0200 From: Andi Kleen To: Alan Cox Cc: Andi Kleen , Hugh Dickins , Wu Fengguang , Balbir Singh , Andrew Morton , LKML , Ingo Molnar , Mel Gorman , Thomas Gleixner , "H. Peter Anvin" , Peter Zijlstra , Nick Piggin , "riel@redhat.com" , "chris.mason@oracle.com" , "linux-mm@kvack.org" Subject: Re: [PATCH 00/22] HWPOISON: Intro (v5) Message-ID: <20090615170726.GI31969@one.firstfloor.org> References: <4A35BD7A.9070208@linux.vnet.ibm.com> <20090615042753.GA20788@localhost> <20090615140019.4e405d37@lxorguk.ukuu.org.uk> <20090615132934.GE31969@one.firstfloor.org> <20090615154832.73c89733@lxorguk.ukuu.org.uk> <20090615152427.GF31969@one.firstfloor.org> <20090615162804.4cb75b30@lxorguk.ukuu.org.uk> <20090615161904.GH31969@one.firstfloor.org> <20090615172816.707bff0a@lxorguk.ukuu.org.uk> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090615172816.707bff0a@lxorguk.ukuu.org.uk> User-Agent: Mutt/1.4.2.1i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 929 Lines: 24 > But then if you > can't sort the resulting mess out because your patches are too limited > its not useful yet is it. With "too limited" you refer to unpoisioning? Again very slowly: - If you have a lot of errors you die eventually anyways. - If you have a very low rate of errors (which is the normal case) you don't need unpoisioning because the memory lost for each error is miniscule. - In the case of a hypervisor it's actually not memory lost, but only guest physical address space, which is plenty on a 64bit system. You can eventually replace it by readding memory to a guest, but that's unlikely to be needed. -Andi -- ak@linux.intel.com -- Speaking for myself only. -- 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/