From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH v2] tcp: tsq: restore minimal amount of queueing Date: Wed, 13 Nov 2013 14:41:25 -0800 Message-ID: <1384382485.28458.133.camel@edumazet-glaptop2.roam.corp.google.com> References: <8761s0cqhh.fsf@natisbad.org> <87y54u59zq.fsf@natisbad.org> <1384267141.28458.24.camel@edumazet-glaptop2.roam.corp.google.com> <1384353174.28458.110.camel@edumazet-glaptop2.roam.corp.google.com> <8738n0ngq3.fsf@natisbad.org> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: David Miller , Sujith Manoharan , Cong Wang , netdev@vger.kernel.org, Felix Fietkau To: Arnaud Ebalard Return-path: Received: from mail-pa0-f50.google.com ([209.85.220.50]:57744 "EHLO mail-pa0-f50.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750992Ab3KMWla (ORCPT ); Wed, 13 Nov 2013 17:41:30 -0500 Received: by mail-pa0-f50.google.com with SMTP id hz1so1131841pad.9 for ; Wed, 13 Nov 2013 14:41:29 -0800 (PST) In-Reply-To: <8738n0ngq3.fsf@natisbad.org> Sender: netdev-owner@vger.kernel.org List-ID: On Wed, 2013-11-13 at 22:18 +0100, Arnaud Ebalard wrote: > Hi Eric, > > Eric Dumazet writes: > > > From: Eric Dumazet > > > > After commit c9eeec26e32e ("tcp: TSQ can use a dynamic limit"), several > > users reported throughput regressions, notably on mvneta and wifi > > adapters. > > > > 802.11 AMPDU requires a fair amount of queueing to be effective. > > > > This patch partially reverts the change done in tcp_write_xmit() > > so that the minimal amount is sysctl_tcp_limit_output_bytes. > > I just tested the fix on current linux tree with the same setup > on which I observed the regression: it also fixes it on my side > on my RN102. Thanks for the quick fix, Eric. > It would be nice you find the 'right value' for the sysctl, to give a hint to mvneta maintainers ;) Thanks