Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755773AbdCTQex (ORCPT ); Mon, 20 Mar 2017 12:34:53 -0400 Received: from mail-pg0-f67.google.com ([74.125.83.67]:34987 "EHLO mail-pg0-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755736AbdCTQer (ORCPT ); Mon, 20 Mar 2017 12:34:47 -0400 Message-ID: <1490027684.16816.63.camel@edumazet-glaptop3.roam.corp.google.com> Subject: Re: [PATCH 07/17] net: convert sock.sk_refcnt from atomic_t to refcount_t From: Eric Dumazet To: Peter Zijlstra Cc: Herbert Xu , David Miller , elena.reshetova@intel.com, keescook@chromium.org, netdev@vger.kernel.org, bridge@lists.linux-foundation.org, linux-kernel@vger.kernel.org, kuznet@ms2.inr.ac.ru, jmorris@namei.org, kaber@trash.net, stephen@networkplumber.org, ishkamiel@gmail.com, dwindsor@gmail.com, akpm@linux-foundation.org Date: Mon, 20 Mar 2017 09:34:44 -0700 In-Reply-To: <1490026735.16816.58.camel@edumazet-glaptop3.roam.corp.google.com> References: <1489767196.28631.305.camel@edumazet-glaptop3.roam.corp.google.com> <20170318164759.GA23837@gondor.apana.org.au> <20170318.182121.439615057765380575.davem@davemloft.net> <20170320103937.lq7nfnutupr3gkn7@hirez.programming.kicks-ass.net> <20170320131629.GA26405@gondor.apana.org.au> <20170320132357.acygo3umw6fiwb4p@hirez.programming.kicks-ass.net> <20170320132713.GA26954@gondor.apana.org.au> <20170320134017.h3c2jrsnd4guuyu7@hirez.programming.kicks-ass.net> <1490021461.16816.52.camel@edumazet-glaptop3.roam.corp.google.com> <1490021946.16816.54.camel@edumazet-glaptop3.roam.corp.google.com> <1490026735.16816.58.camel@edumazet-glaptop3.roam.corp.google.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.10.4-0ubuntu2 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 499 Lines: 19 On Mon, 2017-03-20 at 09:18 -0700, Eric Dumazet wrote: > Interesting. > > UDP ipv4 xmit path gets a ~25 % improvement on PPC with this patch. > > ( 20 concurrent netperf -t UDP_STREAM : 2.45 Mpps -> 3.07 Mpps ) Well, there _is_ a difference, but not 25 % (this was probably caused by different queues on TX or RX between my reboots). I added a sysctl hack to be able to dynamically change on a given workload, and we hit other bottlenecks (mainly qdisc locks and driver tx locks) anyway.