From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751542AbdLNCO4 (ORCPT ); Wed, 13 Dec 2017 21:14:56 -0500 Received: from aserp2130.oracle.com ([141.146.126.79]:50666 "EHLO aserp2130.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751029AbdLNCOz (ORCPT ); Wed, 13 Dec 2017 21:14:55 -0500 Subject: Re: [PATCH 6/6] blk-mq: remove REQ_ATOM_STARTED To: Tejun Heo Cc: axboe@kernel.dk, linux-kernel@vger.kernel.org, oleg@redhat.com, peterz@infradead.org, kernel-team@fb.com, osandov@fb.com References: <20171209192525.982030-1-tj@kernel.org> <20171209192525.982030-7-tj@kernel.org> <8c52269a-d5a9-d13c-bdb6-8f47cdaed982@oracle.com> <20171212172629.GF3919388@devbig577.frc2.facebook.com> <9e9452b1-5756-71fc-f7f9-2a90aceccf01@oracle.com> <20171213160913.GR3919388@devbig577.frc2.facebook.com> From: "jianchao.wang" Message-ID: Date: Thu, 14 Dec 2017 10:14:31 +0800 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.5.0 MIME-Version: 1.0 In-Reply-To: <20171213160913.GR3919388@devbig577.frc2.facebook.com> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit X-Proofpoint-Virus-Version: vendor=nai engine=5900 definitions=8744 signatures=668646 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 suspectscore=2 malwarescore=0 phishscore=0 bulkscore=0 spamscore=0 mlxscore=0 mlxlogscore=775 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1711220000 definitions=main-1712140027 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 12/14/2017 12:09 AM, Tejun Heo wrote: > Hello, > > On Wed, Dec 13, 2017 at 11:05:11AM +0800, jianchao.wang wrote: >> Just don't quite understand the strict definition of "generation" you said. >> A allocation->free cycle is a generation ? or a idle->in-flight cycle is a >> generation? The idle->in-flight cycle could include the requeue case as above. >> Can you clarify this? > > So, a request is > > * IN_FLIGHT, if it can be completed by the lower level driver > > * COMPLETE, if the lower level driver indicated completion but block > layer is still processing. > > * IDLE, if neither of the above two. > > and generation is bumped up on IDLE -> IN_FLIGHT to distinguish > different IN_FLIGHT instances. > So a generation means a cycle from IDLE -> IN_FLIGHT. Thanks for your response. That's really appreciated. Jianchao > Thanks. >