From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754472Ab3KTQWV (ORCPT ); Wed, 20 Nov 2013 11:22:21 -0500 Received: from merlin.infradead.org ([205.233.59.134]:45992 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754114Ab3KTQWS (ORCPT ); Wed, 20 Nov 2013 11:22:18 -0500 Message-ID: <528CE19B.8020004@kernel.dk> Date: Wed, 20 Nov 2013 09:21:47 -0700 From: Jens Axboe User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.1.0 MIME-Version: 1.0 To: Christoph Hellwig CC: Shaohua Li , Dave Chinner , linux-kernel@vger.kernel.org Subject: Re: [Regression x2, 3.13-git] virtio block mq hang, iostat busted on virtio devices References: <20131119212042.GB4094@kernel.dk> <20131119213429.GQ11434@dastard> <528BDB97.8090608@kernel.dk> <528BE967.9070506@kernel.dk> <528BEB6F.8040704@kernel.dk> <20131119232308.GS11434@dastard> <20131119235937.GC4094@kernel.dk> <20131120000858.GD4094@kernel.dk> <20131120014425.GA15287@kernel.org> <20131120015426.GE4094@kernel.dk> <20131120080702.GB13147@infradead.org> In-Reply-To: <20131120080702.GB13147@infradead.org> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 11/20/2013 01:07 AM, Christoph Hellwig wrote: >> Just stumbled on that too. You need one more, btw, for the sg failure >> case: >> >> >> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c >> index 588479d58f52..6a680d4de7f1 100644 >> --- a/drivers/block/virtio_blk.c >> +++ b/drivers/block/virtio_blk.c >> @@ -199,15 +199,16 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req) >> >> spin_lock_irqsave(&vblk->vq_lock, flags); >> if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) { >> + virtqueue_kick(vblk->vq); >> spin_unlock_irqrestore(&vblk->vq_lock, flags); >> blk_mq_stop_hw_queue(hctx); >> - virtqueue_kick(vblk->vq); >> return BLK_MQ_RQ_QUEUE_BUSY; >> } >> - spin_unlock_irqrestore(&vblk->vq_lock, flags); >> >> if (last) >> virtqueue_kick(vblk->vq); >> + >> + spin_unlock_irqrestore(&vblk->vq_lock, flags); > > Note that virtqueue_kick can be split into a virtqueue_prepare_split > that needs the lock, and a virtqueue_notify that doesn't, but it might > not be nessecary to do that optimization right now. Right, that would be easily doable. Seems it's in the realm of micro optimizations, but worth doing next time it's touched. > Btw, how much do I need to bribe you to send mails where I don't have > step over 500 lines of dead quotes to find the actual patch? Sorry, the next one was trimmed :-) -- Jens Axboe