From mboxrd@z Thu Jan 1 00:00:00 1970 From: hch@lst.de (Christoph Hellwig) Date: Wed, 12 Dec 2018 08:21:32 +0100 Subject: [PATCH RFC 4/4] nvme-multipath: disable polling for underlying namespace request queue In-Reply-To: References: <20181211233652.9705-1-sagi@grimberg.me> <20181211233652.9705-5-sagi@grimberg.me> <20181212071140.GD28461@lst.de> Message-ID: <20181212072132.GA28850@lst.de> On Tue, Dec 11, 2018@11:19:22PM -0800, Sagi Grimberg wrote: >> So we need to make sure in the block layer or I/O submitter that >> REQ_HIPRI is only set if QUEUE_FLAG_POLL is supported. I think it would >> also help if we rename it to REQ_POLL to make this more obvious. > > It used to check for it, but was changed to look at nr_maps instead... > So I think this is a regression... blk_mq_map_queue looks at both QUEUE_FLAG_POLL and nr_maps for the queue selection, but that doesn't help with the problem that we should never pass poll requests through stacking devices.