From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752604AbcBOIdg (ORCPT ); Mon, 15 Feb 2016 03:33:36 -0500 Received: from mail-wm0-f51.google.com ([74.125.82.51]:36878 "EHLO mail-wm0-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752263AbcBOIdd (ORCPT ); Mon, 15 Feb 2016 03:33:33 -0500 Subject: Re: [PATCH 0/4] block: fix bio_will_gap() To: Ming Lei , Jens Axboe , linux-kernel@vger.kernel.org References: <1455519687-23873-1-git-send-email-ming.lei@canonical.com> Cc: linux-block@vger.kernel.org, Christoph Hellwig From: Sagi Grimberg Message-ID: <56C18D59.5050704@dev.mellanox.co.il> Date: Mon, 15 Feb 2016 10:33:29 +0200 User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101 Thunderbird/38.5.1 MIME-Version: 1.0 In-Reply-To: <1455519687-23873-1-git-send-email-ming.lei@canonical.com> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > Hi, > > After bio splitting is introduced, the splitted bio can be fast-cloned, > which is correct because biovecs has become immutable since v3.13. > > Unfortunately bio_will_gap() isn't ready for this kind of change, > because it figures out the last bvec via 'bi_io_vec[prev->bi_vcnt - 1]' > directly. > > It is observed that lots of BIOs are merges even the virt boundary > limit is violated, and the issue is reported from Sagi Grimberg. This set makes the virt_boundary violation go away...