From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Wed, 24 Jun 2015 14:11:52 +0200 From: Christoph Hellwig Subject: Re: [PATCH 14/15] libnvdimm: support read-only btt backing devices Message-ID: <20150624121152.GD17542@lst.de> References: <20150617235209.12943.24419.stgit@dwillia2-desk3.amr.corp.intel.com> <20150617235602.12943.24958.stgit@dwillia2-desk3.amr.corp.intel.com> <20150621101346.GF5915@lst.de> <20150621135406.GA9572@lst.de> <20150622063028.GA30434@lst.de> <20150623193043.GE1971@linux.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150623193043.GE1971@linux.intel.com> Sender: linux-kernel-owner@vger.kernel.org To: Matthew Wilcox Cc: Christoph Hellwig , Dan Williams , Jens Axboe , "linux-nvdimm@lists.01.org" , "linux-kernel@vger.kernel.org" , Linux ACPI , linux-fsdevel , Ingo Molnar List-ID: On Tue, Jun 23, 2015 at 03:30:43PM -0400, Matthew Wilcox wrote: > > I can't make any guarantees, especially not without verification. But > > if correctly implemented any filesystems that does out of place metadata > > writes (and that includes a traditional log) and uses checksum to ensure > > the integrity of these updates it should be fine. You'd still have > > the issue of sector atomicy of file I/O though. > > Is ext4 one of the filesystems that copes with torn updates to the log? > I see there's a checksum in the tail of at least some blocks, but I'd > like someone who understands ext4 to reassure me that it also doesn't > need the ability to put its log on a BTT. In theory it should if the log checksums are enabled, but I wouldn't rely on it without without confirmation and validation from the ext4 folks. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752532AbbFXMMA (ORCPT ); Wed, 24 Jun 2015 08:12:00 -0400 Received: from verein.lst.de ([213.95.11.211]:50686 "EHLO newverein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752662AbbFXMLx (ORCPT ); Wed, 24 Jun 2015 08:11:53 -0400 Date: Wed, 24 Jun 2015 14:11:52 +0200 From: Christoph Hellwig To: Matthew Wilcox Cc: Christoph Hellwig , Dan Williams , Jens Axboe , "linux-nvdimm@lists.01.org" , "linux-kernel@vger.kernel.org" , Linux ACPI , linux-fsdevel , Ingo Molnar Subject: Re: [PATCH 14/15] libnvdimm: support read-only btt backing devices Message-ID: <20150624121152.GD17542@lst.de> References: <20150617235209.12943.24419.stgit@dwillia2-desk3.amr.corp.intel.com> <20150617235602.12943.24958.stgit@dwillia2-desk3.amr.corp.intel.com> <20150621101346.GF5915@lst.de> <20150621135406.GA9572@lst.de> <20150622063028.GA30434@lst.de> <20150623193043.GE1971@linux.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150623193043.GE1971@linux.intel.com> User-Agent: Mutt/1.5.17 (2007-11-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jun 23, 2015 at 03:30:43PM -0400, Matthew Wilcox wrote: > > I can't make any guarantees, especially not without verification. But > > if correctly implemented any filesystems that does out of place metadata > > writes (and that includes a traditional log) and uses checksum to ensure > > the integrity of these updates it should be fine. You'd still have > > the issue of sector atomicy of file I/O though. > > Is ext4 one of the filesystems that copes with torn updates to the log? > I see there's a checksum in the tail of at least some blocks, but I'd > like someone who understands ext4 to reassure me that it also doesn't > need the ability to put its log on a BTT. In theory it should if the log checksums are enabled, but I wouldn't rely on it without without confirmation and validation from the ext4 folks.