From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pf0-x243.google.com (mail-pf0-x243.google.com [IPv6:2607:f8b0:400e:c00::243]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 138183B2A3 for ; Fri, 27 Jan 2017 10:00:01 -0500 (EST) Received: by mail-pf0-x243.google.com with SMTP id e4so18691437pfg.0 for ; Fri, 27 Jan 2017 07:00:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=message-id:subject:from:to:cc:date:in-reply-to:references :mime-version:content-transfer-encoding; bh=sn8QloArX8o/K9wovB7FhKiZ2n2O1FpIg8Pd7EwCFS0=; b=n0ZvkQRL/zCUAZYEpuT3UQhv2MJFgC1Rczw/ADf3brP+ZWnHXSsRuEQmEbYVzMEqin 8q+OFhOZARhdQTjxAvmuSZH4zocpc+UBV6jfTmVIjslOTT1J7mJ90oI3qtF+5vgMBIie n2fBvj4z8cG3/YAnQb1QyHnnR5ZlinB+admVFBhCbfNYDLrz74oQOSOzS44DRFfundOE fzJq6wml8D9LY0heVep8Ap7yqLaNZiAEppa+Oc0njFR47MfZ+Y/hldbeoJuxPFOxHSu1 vzvephHeXM5ERi0E/lxy3RyiwMkBxNE6yaSKzPHg4oCHAJciZcGH/AIPpqXO/FSSzaAG QzSA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:message-id:subject:from:to:cc:date:in-reply-to :references:mime-version:content-transfer-encoding; bh=sn8QloArX8o/K9wovB7FhKiZ2n2O1FpIg8Pd7EwCFS0=; b=a1V4B0Gavh5Yoqp5l1d/4tOsfy5U34r9UgPNOEx39Vos21re4UaxOVpnQbYxryZiOi aEo1TBzJv/2rKMpk1q7zsmv/qo+P7+EhfKvuKWCwOo4wNFXcmQEL2aJod8/QzwJRwm23 tdBxD4Ql5ZOQRKhbrWqbpyVf6yNBegwgxrAKo0BWUuw9UejUMKUV74U5NVhFC/4X5pCK iN5lwVwaMX2QkpwlceUd+CLHbzqEwcPC7s7aoP5EIY4w6ROXAIuUp/t5KfZEJ8L6o+Hj JzcxixLVndpQAskt0jp+rmjpTqcIoLn8H8Xav1TE5FDhd+t6igBk+xC8cz+zCCeYn90H V46A== X-Gm-Message-State: AIkVDXKc/W63A9KJl5EHwtKvNcE8Jn0NMv/vb27YbQVAfARUplx2D43CzTaonP8YKHmOwA== X-Received: by 10.99.138.201 with SMTP id y192mr9877286pgd.146.1485529201085; Fri, 27 Jan 2017 07:00:01 -0800 (PST) Received: from [172.29.160.201] ([172.29.160.201]) by smtp.googlemail.com with ESMTPSA id u75sm12107905pgc.31.2017.01.27.07.00.00 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 27 Jan 2017 07:00:00 -0800 (PST) Message-ID: <1485529199.6360.46.camel@edumazet-glaptop3.roam.corp.google.com> From: Eric Dumazet To: Sebastian Moeller Cc: Dave =?ISO-8859-1?Q?T=E4ht?= , bloat@lists.bufferbloat.net Date: Fri, 27 Jan 2017 06:59:59 -0800 In-Reply-To: References: <0496946b-827a-8527-643d-0b186f52e192@taht.net> <1485528030.6360.35.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: 8bit Subject: Re: [Bloat] Recommendations for fq_codel and tso/gso in 2017 X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 Jan 2017 15:00:02 -0000 On Fri, 2017-01-27 at 15:49 +0100, Sebastian Moeller wrote: > Hi Eric, > > quick question from the peanut gallery: on a typical home router with > 1Gbps internal and <<100Mbps external interfaces, will giant packets > will be generated by the 1Gbps interface (with acceptable latency)? I > ask, as what makes sense on a 1000Mbps ingress link, might still block > an 20Mbps wan egress link slightly longer than one would like (to the > tune of 50ms, just based on the bandwidth ratio?). It depends if the switching on the 1Gbps involves the linux cpu or not. If switching is not passing around packets through linux stack, or you have a single station using the 1Gbit interface to the home router, then probably GRO is not needed at all. Also, we have ways to control packet sizes quite easily, stacking a virtual device before the 100Mbit external interface, as shown by this thread. bond0 - external0 If you disable TSO on bond0, GRO packets will automatically be segmented (Dave calls that peeling) before reaching external0 qdisc. So using a bonding is probably the way, leaving GRO enabled in internal0 1Gbit (or 10Gbits soon ?) interface. > > Best Regards > Sebastian > > > > > On Jan 27, 2017, at 15:40, Eric Dumazet wrote: > > > > On Thu, 2017-01-26 at 23:55 -0800, Dave Täht wrote: > >> > >> On 1/26/17 11:21 PM, Hans-Kristian Bakke wrote: > >>> Hi > >>> > >>> After having had some issues with inconcistent tso/gso configuration > >>> causing performance issues for sch_fq with pacing in one of my systems, > >>> I wonder if is it still recommended to disable gso/tso for interfaces > >>> used with fq_codel qdiscs and shaping using HTB etc. > >> > >> At lower bandwidths gro can do terrible things. Say you have a 1Mbit > >> uplink, and IW10. (At least one device (mvneta) will synthesise 64k of > >> gro packets) > >> > >> a single IW10 burst from one flow injects 130ms of latency. > > > > That is simply a sign of something bad happening from the source. > > > > The router will spend too much time trying to fix the TCP sender by > > smoothing things. > > > > Lets fix the root cause, instead of making everything slow or burn mega > > watts. > > > > GRO aggregates trains of packets for the same flow, in sub ms window. > > > > Why ? Because GRO can not predict the future : It can not know when next > > interrupt might come from the device telling : here is some additional > > packet(s). Maybe next packet is coming in 5 seconds. > > > > Take a look at napi_poll() > > > > 1) If device driver called napi_complete(), all packets are flushed > > (given) to upper stack. No packet will wait in GRO for additional > > segments. > > > > 2) Under flood (we exhausted the napi budget and did not call > > napi_complete()), we make sure no packet can sit in GRO for more than 1 > > ms. > > > > Only when the device is under flood and cpu can not drain fast enough RX > > queue, GRO can aggregate packets more aggressively, and the size of GRO > > packets exactly fits the CPU budget. > > > > In a nutshell, GRO is exactly the mechanism that adapts the packet sizes > > to available cpu power. > > > > If your cpu is really fast, then it will dequeue one packet at a time > > and GRO wont kick in. > > > > So the real problem here is that some device drivers implemented a poor > > interrupt mitigation logic, inherited from other OS that had not GRO and > > _had_ to implement their own crap, hurting latencies. > > > > Make sure you disable interrupt mitigation, and leave GRO enabled. > > > > e1000e is notoriously bad for interrupt mitigation. > > > > At Google, we let the NIC sends its RX interrupt ASAP. > > > > Every usec matters. > > > > So the model for us is very clear : Use GRO and TSO as much as we can, > > but make sure the producers (TCP senders) are smart and control their > > burst sizes. > > > > Think about 50Gbit and 100Gbit, and really the question of having or not > > TSO and GRO is simply moot. > > > > > > Even at 1Gbit, GRO is helping to reduce cpu cycles and thus reduce > > latencies. > > > > Adding a sysctl to limit GRO max size would be trivial, I already > > mentioned that, but nobody cared enough to send a patch. > > > >> > >>> > >>> If there is a trade off, at which bandwith does it generally make more > >>> sense to enable tso/gso than to have it disabled when doing HTB shaped > >>> fq_codel qdiscs? > >> > >> I stopped caring about tuning params at > 40Mbit. < 10 gbit, or rather, > >> trying get below 200usec of jitter|latency. (Others care) > >> > >> And: My expectation was generally that people would ignore our > >> recommendations on disabling offloads! > >> > >> Yes, we should revise the sample sqm code and recommendations for a post > >> gigabit era to not bother with changing network offloads. Were you > >> modifying the old debloat script? > >> > >> TBF & sch_Cake do peeling of gro/tso/gso back into packets, and then > >> interleave their scheduling, so GRO is both helpful (transiting the > >> stack faster) and harmless, at all bandwidths. > >> > >> HTB doesn't peel. We just ripped out hsfc for sqm-scripts (too buggy), > >> alsp. Leaving: tbf + fq_codel, htb+fq_codel, and cake models there. > >> > > > > > > > >> ... > >> > >> Cake is coming along nicely. I'd love a test in your 2Gbit bonding > >> scenario, particularly in a per host fairness test, at line or shaped > >> rates. We recently got cake working well with nat. > >> > >> http://blog.cerowrt.org/flent/steam/down_working.svg (ignore the latency > >> figure, the 6 flows were to spots all over the world) > >> > >>> Regards, > >>> Hans-Kristian > >>> > >>> > >>> _______________________________________________ > >>> Bloat mailing list > >>> Bloat@lists.bufferbloat.net > >>> https://lists.bufferbloat.net/listinfo/bloat > >>> > >> _______________________________________________ > >> Bloat mailing list > >> Bloat@lists.bufferbloat.net > >> https://lists.bufferbloat.net/listinfo/bloat > > > > > > _______________________________________________ > > Bloat mailing list > > Bloat@lists.bufferbloat.net > > https://lists.bufferbloat.net/listinfo/bloat >