From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sagi Grimberg Subject: Re: [PATCH] IB/core: Don't drain the receive queue for srq attached queue-pair Date: Tue, 26 Apr 2016 22:24:01 +0300 Message-ID: <571FC051.7020009@grimberg.me> References: <1461682538-19647-1-git-send-email-sagi@grimberg.me> <571F841D.3010909@opengridcomputing.com> <20160426154328.GA12398@lst.de> <912C9E71-05E3-4ED9-9B41-137E131E3A71@oracle.com> <571F9084.2040506@opengridcomputing.com> <571F917C.40008@sandisk.com> <571F972B.6030904@opengridcomputing.com> <571FA4E5.2030501@sandisk.com> <571FA6D5.2060607@opengridcomputing.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <571FA6D5.2060607-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Steve Wise , Bart Van Assche , Chuck Lever , Christoph Hellwig Cc: "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" List-Id: linux-rdma@vger.kernel.org > Actually, after thinking more about this, posting anything to the SRQ > will not force it to complete. The only reason that works for a QP with > an RQ is that the QP is in ERR state and thus the RECV WR gets completed > with FLUSHED status. Exactly... > So SRQ drain would require some other method... I still don't understand the meaning of draining a SRQ. There are no QP associated post recvs, the QP and contexts (wc->qp) are assigned at completion processing time. When we have a SRQ the recv contexts are not bound to a session/connection/QP... Can you well-define what are you trying to do? -- 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