From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bart.VanAssche@sandisk.com (Bart Van Assche) Date: Mon, 10 Apr 2017 15:27:14 +0000 Subject: [PATCH v2] nvme-rdma: support devices with queue size < 32 In-Reply-To: <20170410151657.GA15173@lst.de> References: <1519881025.363156294.1491837154312.JavaMail.zimbra@kalray.eu> <20170410151657.GA15173@lst.de> Message-ID: <1491838033.4199.3.camel@sandisk.com> On Mon, 2017-04-10@17:16 +0200, Christoph Hellwig wrote: > > +static inline nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue) > > +{ > > + int sig_limit; > > + > > + /* We signal completion every queue depth/2 and also > > + * handle the case of possible device with queue_depth=1, > > + * where we would need to signal every message. > > + */ > > + sig_limit = max(queue->queue_size / 2, 1); > > + return (++queue->sig_count % sig_limit) == 0; > > +} > > I would love if we could do this at the ib_qp level. Hello Christoph, Please keep in mind that some but not all RDMA drivers need a construct like this. Bart. From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bart Van Assche Subject: Re: [PATCH v2] nvme-rdma: support devices with queue size < 32 Date: Mon, 10 Apr 2017 15:27:14 +0000 Message-ID: <1491838033.4199.3.camel@sandisk.com> References: <1519881025.363156294.1491837154312.JavaMail.zimbra@kalray.eu> <20170410151657.GA15173@lst.de> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <20170410151657.GA15173-jcswGhMUV9g@public.gmane.org> Content-Language: en-US Content-ID: <72ABBB6A77B9894D93F8B2E635ED2937-+cFlbfsKLD6cE4WynfumptQqCkab/8FMAL8bYrjMMd8@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: "hch-jcswGhMUV9g@public.gmane.org" , "mrybczyn-FNhOzJFKnXGHXe+LvDLADg@public.gmane.org" Cc: "leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org" , "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" , "axboe-b10kYP2dOMg@public.gmane.org" , "linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org" , "maxg-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org" , "samuel.jones-FNhOzJFKnXGHXe+LvDLADg@public.gmane.org" , "jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org" , "keith.busch-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org" , "dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org" List-Id: linux-rdma@vger.kernel.org On Mon, 2017-04-10 at 17:16 +0200, Christoph Hellwig wrote: > > +static inline nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue) > > +{ > > + int sig_limit; > > + > > + /* We signal completion every queue depth/2 and also > > + * handle the case of possible device with queue_depth=3D1, > > + * where we would need to signal every message. > > + */ > > + sig_limit =3D max(queue->queue_size / 2, 1); > > + return (++queue->sig_count % sig_limit) =3D=3D 0; > > +} >=20 > I would love if we could do this at the ib_qp level. Hello Christoph, Please keep in mind that some but not all RDMA drivers need a construct lik= e this. Bart.= -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html