From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Paul E. McKenney" Subject: Measurable performance improvements from RCU_INIT_POINTER()? Date: Sat, 19 Jul 2014 01:12:40 -0700 Message-ID: <20140719081240.GA13806@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@vger.kernel.org To: edumazet@google.com, davem@davemloft.net, brouer@redhat.com Return-path: Received: from e36.co.us.ibm.com ([32.97.110.154]:47571 "EHLO e36.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754118AbaGSRmn (ORCPT ); Sat, 19 Jul 2014 13:42:43 -0400 Received: from /spool/local by e36.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Sat, 19 Jul 2014 11:42:43 -0600 Received: from b03cxnp07029.gho.boulder.ibm.com (b03cxnp07029.gho.boulder.ibm.com [9.17.130.16]) by d03dlp01.boulder.ibm.com (Postfix) with ESMTP id 873341FF003B for ; Sat, 19 Jul 2014 11:42:39 -0600 (MDT) Received: from d03av06.boulder.ibm.com (d03av06.boulder.ibm.com [9.17.195.245]) by b03cxnp07029.gho.boulder.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id s6JFcx982883974 for ; Sat, 19 Jul 2014 17:38:59 +0200 Received: from d03av06.boulder.ibm.com (loopback [127.0.0.1]) by d03av06.boulder.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id s6JHklwo015547 for ; Sat, 19 Jul 2014 11:46:47 -0600 Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: Hello! Did the replacement of selected calls to rcu_assign_pointer() by RCU_INIT_POINTER() in the networking stack result in measurable system-level performance improvements? The reason I ask is that some of the compiler guys on the C and C++ standards committees are suggesting changes that would add barriers in some cases. I suspect that this is a very bad idea, and was hoping that you guys would have some hard numbers on the system-level effects of barriers. ;-) Thanx, Paul