From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754567AbaBJTtb (ORCPT ); Mon, 10 Feb 2014 14:49:31 -0500 Received: from mail-pb0-f51.google.com ([209.85.160.51]:46974 "EHLO mail-pb0-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752463AbaBJTt2 (ORCPT ); Mon, 10 Feb 2014 14:49:28 -0500 Date: Mon, 10 Feb 2014 12:49:25 -0700 From: Jens Axboe To: Christoph Hellwig Cc: linux-kernel@vger.kernel.org Subject: Re: [PATCH 0/3] blk-mq: rework I/O completions Message-ID: <20140210194923.GA3784@kernel.dk> References: <20140210112437.858399303@bombadil.infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20140210112437.858399303@bombadil.infradead.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Feb 10 2014, Christoph Hellwig wrote: > This series reworks how the blk-mq core handles I/O completion. The > prime motivation was that the current code does not work when using > a timeout handler that needs to complete requests after doing error > handling. A fallout from fixing that by making the completions more > similar to the old request model is that we now can use the remote > IPIs for driver-internal completions as well instead of just the final > completion and thus get rid of duplicate code both in null_blk and > the pending scsi work. Thanks Christoph, applied all 3. -- Jens Axboe