From mboxrd@z Thu Jan 1 00:00:00 1970 From: Doug Ledford Subject: Re: [PATCH v2 0/3] new ib_drain_qp() API Date: Thu, 11 Feb 2016 10:22:41 -0500 Message-ID: <56BCA741.6020800@redhat.com> References: <010901d16375$1a023210$4e069630$@opengridcomputing.com> <011601d1637b$8c01a3e0$a404eba0$@opengridcomputing.com> <56BA540B.4040405@sandisk.com> <011901d1637d$b5286400$1f792c00$@opengridcomputing.com> <012801d16384$f68884f0$e3998ed0$@opengridcomputing.com> <56BB11F0.9090203@dev.mellanox.co.il> <00ca01d16417$9e9fc030$dbdf4090$@opengridcomputing.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="6WSvBTWtJSAwaqHAL2A5Q4eWEQFBCt8CK" Return-path: In-Reply-To: <00ca01d16417$9e9fc030$dbdf4090$@opengridcomputing.com> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Steve Wise , 'Sagi Grimberg' , 'Bart Van Assche' , linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org Cc: 'Sagi Grimberg' , 'Christoph Hellwig' , 'Chuck Lever' List-Id: linux-rdma@vger.kernel.org This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --6WSvBTWtJSAwaqHAL2A5Q4eWEQFBCt8CK Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable On 02/10/2016 10:27 AM, Steve Wise wrote: >>>>> Hello Steve, >>>>> >>>>> How about creating three functions - one that drains the receive qu= eue, >>>>> one that drains the send queue and a third function that drains bot= h ? >>>>> The latter function then can call the two former functions. And sin= ce >>>>> only one of these three functions will have a user in your patch se= ries >>>>> (the function that drains the RQ), how about only introducing only = that >>>>> function now and to wait with introducing the two other functions u= ntil >>>>> these have a user ? >>>> >>>> That sounds reasonable. Simpler too perhaps. We'll see if anyone e= lse >>>> has an opinion. >>> >>> Another option is for ib_drain_qp() to just skip queues with IB_POLL_= DIRECT CQ processing. >> >> I'd rather not skip silently anything. ib_drain_qp() semantics is that= >> it drains all the pending posts on the queue-pair (i.e. both send and >> receive queues). >> >> We can split to send and receive, but the fact that srp uses direct >> polling CQ is not sufficient for that, most if not all will benefit fr= om >> both. >> >=20 > If we split it into ib_drain_rq(), ib_drain_sq(), and ib_drain_qp(), th= en srp would only call ib_drain_rq(). Others can call > ib_drain_qp() if they want both SQ and RQ drained. I'm in favor of this kind of flexibility at the API level. --=20 Doug Ledford GPG KeyID: 0E572FDD --6WSvBTWtJSAwaqHAL2A5Q4eWEQFBCt8CK Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iQIcBAEBCAAGBQJWvKdBAAoJELgmozMOVy/dBHUP/2DUleENpBMnnWJVD7MRDLKf RIX9RUj13e4xUhyXopIlcPbhRONQ36QHC8PRzL+ONtVXSQrfsHIV4QIpGC0asrZQ usBoAntU6IAVV/exreVlQoTdIBvfHBsiwTffLXmJ0kkXNdaZI6Ovk/Wk91kTAGsc e9SurAxwcl/xUqEDWmRvNLQyRhIoTksTiIDKaa2FupLpDUCXz0ZkTPW+JukcJK5w QMrPvlVV9NIXeBg9IOFp53D/AEUls7fWbtkR0WkKkKX870wqqxFwGs9EMYm00FdG GndYjuvOAMXVUB0sA3K2v1vCMXhXtTNGD+pwWK0PAHqEXsjBXqHbkNOeANqfY1TQ YHwORd3DG9gBRVqgOIJ1RE/YtthkmWuuTC248QG2J8hW+YEmdGBIjVYrywhd2yWW gyR5DJ73YuO7QDFxY7EjM2aaTVHowge1QOFHvvnV9Idu0DW0d8MWslSVfXW2qGVy FWVwB1i9PNQLizP+ll4aPMvbjClMyGAx/ZJO6kybrbBrgQHW7GRfwmx2lVAsnLLT wuBKqSVwCLHgecimrgndpTk5H2swUS/owOojKHb1wrjkr6vIKMd+6nKNYhZFDfJp cpvdjoqqV+oulb5ZkdJZPYXPRzrPRHyxDAPXY16KQgxan+rejnpuKlHPR6S2M40z 9A0yq/YBPL6EdcgObuF5 =pfqv -----END PGP SIGNATURE----- --6WSvBTWtJSAwaqHAL2A5Q4eWEQFBCt8CK-- -- 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