From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [PATCH 1/2] block: introduce polling on bio level Date: Sat, 1 Feb 2020 00:20:34 -0800 Message-ID: <20200201082034.GA8423@infradead.org> References: <20200126044138.5066-1-andrzej.jakowski@linux.intel.com> <20200126044138.5066-2-andrzej.jakowski@linux.intel.com> <20200131063407.GB6267@infradead.org> <081badca-ab0f-f666-1e5e-71992f93a157@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <081badca-ab0f-f666-1e5e-71992f93a157@linux.intel.com> Sender: linux-block-owner@vger.kernel.org To: Andrzej Jakowski Cc: Christoph Hellwig , axboe@kernel.dk, song@kernel.org, linux-block@vger.kernel.org, linux-raid@vger.kernel.org, Artur Paszkiewicz List-Id: linux-raid.ids On Fri, Jan 31, 2020 at 11:51:43AM -0700, Andrzej Jakowski wrote: > On 1/30/20 11:34 PM, Christoph Hellwig wrote: > > Can you explain this check? This looks weird to me I think we need > > a generalized check if a make_request based driver supports REQ_NOWAIT > > instead (and as a separate patch / patchset). > > Original check used to reject polled IO for stackable block devices as "not > supported". To solve that situation I introduced additional check to reject > all non REQ_HIPRI requests. That check is not intended to generalize, like > you indicated, but to conservatively select which requests to accept. > Perhaps there is better way to do that. Any suggestions? REQ_NOWAIT and REQ_HIPRI are completley unrelated concepts and they need to be dealt with entirely separately.