From: "Martin K. Petersen" Subject: Re: [RFC] fadvise: add more flags to provide a hint for block allocation Date: Wed, 07 Mar 2012 00:02:19 -0500 Message-ID: References: <20120305125029.GA5121@gmail.com> <20120307005130.GH3592@dastard> Mime-Version: 1.0 Content-Type: text/plain Cc: Dave Chinner , linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org To: Andreas Dilger Return-path: Received: from acsinet15.oracle.com ([141.146.126.227]:28048 "EHLO acsinet15.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750805Ab2CGFCm (ORCPT ); Wed, 7 Mar 2012 00:02:42 -0500 In-Reply-To: (Andreas Dilger's message of "Wed, 7 Mar 2012 12:14:43 +0800") Sender: linux-ext4-owner@vger.kernel.org List-ID: >>>>> "Andreas" == Andreas Dilger writes: Andreas> This proposal definitely needs to have some clear explanation Andreas> of how the flags are intended to be used by applications, and Andreas> why they will help filesystems to improve allocation. This goes a bit deeper than just filesystem block allocation strategy. With SMR drives lurking on the horizon it is becoming increasingly important for us to classify anticipated future access patterns as we send I/Os out to storage. We'll need something much smarter than just REQ_META for these devices. Tiered storage arrays and tiered flash also benefit from this information. There's lots of work going on in the standards space in this department right now and I was hoping we could spend some time discussing the current proposals in one of the plenary sessions at LSF. Ideally we'd tie fadvise() and any filesystem internal knowledge into appropriate storage hints at the bottom of the stack. -- Martin K. Petersen Oracle Linux Engineering