From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sreedhar Kodali Subject: RE: [PATCH v2 4/4] rsockets: acknowledge completion queue events in batch Date: Sat, 06 Sep 2014 07:52:39 +0530 Message-ID: References: <1828884A29C6694DAF28B7E6B8A8237399DC1B64@ORSMSX109.amr.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1828884A29C6694DAF28B7E6B8A8237399DC1B64-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: "Hefty, Sean" Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, pradeeps-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org List-Id: linux-rdma@vger.kernel.org On 2014-09-05 23:31, Hefty, Sean wrote: >> Expose '/unackcqe_default' variable so completion event >> acknowledgment can be done in batch instead of singles >> to minimize locking overheads. >> >> The default value of this variable is 1 so the existing >> functionality is preserved. Having a higher value delays >> acknowledging until the specified limit is reached for >> retrieved completion events. > > I would rather just change the default behavior, rather than introduce > more checks and options into the code. Hi Sean, That's indeed a good approach. But, we need to have an upper limit before a batch of events is flushed. Can we decide limit based on completion event queue size? Thank You. - Sreedhar -- 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