Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0E140EB64DA for ; Thu, 20 Jul 2023 05:41:02 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229566AbjGTFlB (ORCPT ); Thu, 20 Jul 2023 01:41:01 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43634 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229517AbjGTFlA (ORCPT ); Thu, 20 Jul 2023 01:41:00 -0400 Received: from verein.lst.de (verein.lst.de [213.95.11.211]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A35941724 for ; Wed, 19 Jul 2023 22:40:59 -0700 (PDT) Received: by verein.lst.de (Postfix, from userid 2407) id 193DC68AFE; Thu, 20 Jul 2023 07:40:57 +0200 (CEST) Date: Thu, 20 Jul 2023 07:40:56 +0200 From: Christoph Hellwig To: Bart Van Assche Cc: Jens Axboe , linux-block@vger.kernel.org, Christoph Hellwig , "Martin K . Petersen" , "James E.J. Bottomley" Subject: Re: [PATCH v2 2/3] scsi: Remove a blk_mq_run_hw_queues() call Message-ID: <20230720054056.GB2450@lst.de> References: <20230719182243.2810134-1-bvanassche@acm.org> <20230719182243.2810134-3-bvanassche@acm.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20230719182243.2810134-3-bvanassche@acm.org> User-Agent: Mutt/1.5.17 (2007-11-01) Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org On Wed, Jul 19, 2023 at 11:22:41AM -0700, Bart Van Assche wrote: > blk_mq_kick_requeue_list() calls blk_mq_run_hw_queues() asynchronously. > Leave out the direct blk_mq_run_hw_queues() call. This patch causes > scsi_run_queue() to call blk_mq_run_hw_queues() asynchronously instead > of synchronously. Since scsi_run_queue() is not called from the hot I/O > submission path, this patch does not affect the hot path. I think this looks good, but a comment in the code that we now rely on blk_mq_kick_requeue_list to run the queue for us might be useful as that is a little counter-intuitive.