From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp126.iad3a.emailsrvr.com (smtp126.iad3a.emailsrvr.com [173.203.187.126]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 742DD3B2A4 for ; Mon, 18 Sep 2023 12:57:42 -0400 (EDT) Received: from app37.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by smtp8.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id C74841B91; Mon, 18 Sep 2023 12:57:41 -0400 (EDT) Received: from deepplum.com (localhost.localdomain [127.0.0.1]) by app37.wa-webapps.iad3a (Postfix) with ESMTP id C32AD612E8; Mon, 18 Sep 2023 12:57:41 -0400 (EDT) Received: by apps.rackspace.com (Authenticated sender: dpreed@deepplum.com, from: dpreed@deepplum.com) with HTTP; Mon, 18 Sep 2023 12:57:41 -0400 (EDT) X-Auth-ID: dpreed@deepplum.com Date: Mon, 18 Sep 2023 12:57:41 -0400 (EDT) From: "David P. Reed" To: "Dave Taht" Cc: "Cake List" MIME-Version: 1.0 Content-Type: text/plain;charset=UTF-8 Content-Transfer-Encoding: quoted-printable Importance: Normal X-Priority: 3 (Normal) X-Type: plain In-Reply-To: References: X-Client-IP: 209.6.168.128 Message-ID: <1695056261.795419240@apps.rackspace.com> X-Mailer: webmail/19.0.24-RC X-Classification-ID: 1bdef6dc-ea6d-4ee5-aa65-ca79327139be-1-1 Subject: Re: [Cake] some comprehensive arm64 w/cake results X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 18 Sep 2023 16:57:42 -0000 I appreciate the effort that went into this testing. However, there are som= e signficant concerns regarding saying that this is typical ARM64 performan= ce. (ARM64 easily beats many Intel x86_64 CPUs, if the motherboards are des= igned for that - I have a very nice SolidRun 16 core ARM64 board based on t= he NXP ARMs, and the Chinese make a lot of servers)=0A=0AIt should be noted= that all the Pi's tested are configured with the *lousy* Ethernet interfac= e that is standard on Pi's (USB). I don't know about the Jetsons (I own a J= etson, but have never tested its networking or even looked at the design of= the I/O).=0A=0ANow the Pi CM4 *module* is capable of connecting to a PCIe = Ethernet adapter (using 1 lane PCIe gen 2 x1, which supports 4 Gb/sec trans= fers, enough for GigE wirespeed). Jeff Geerling has demonstrated various ca= rds get superior performance.=0Ahttps://www.hackster.io/news/jeff-geerling-= squeezes-4-15gb-s-from-a-raspberry-pi-compute-module-4-using-a-pcie-network= -card-bb373ca52966=0A=0Ahttps://www.tomshardware.com/news/raspberry-pi-comp= ute-module-4-four-pcie-slots is a nice "motherboard" for the CM4 module tha= t carries 4 PCIe slots.=0A=0ASo even the Pi CM4 should be able to beat up t= he Intel processors in a fair fight!=0A=0AI should also note that Armbian's= kernel isn't a particularly high performance kernel build.=0A=0AAgain, goo= d job on getting results, but as somebody who has worked on measuring Linu= x OS performance on various CPU architectures, I'd be very, very cautious a= bout drawing conclusions about *ARM* from this.=0A=0AIf you want to test Ca= ke on ARM64, you should perhaps set up an AWS ARM64 machine (Graviton CPUs,= and good Ethernet adapters) which won't cost much money when you are charg= ed by the hour.=0A=0AThe same caution applies to RISC-V systems. It's NOT t= he cpu architecture that you want to measure - it's tne networking architec= tures that are almost always crippled in some way on small boards.=0A=0ALet= 's not reinforce the distortion that Intel is so great!=0A=0ABTW, I don't k= now if a Pi CM4 with a couple of GigE ports would make a good home router a= t a reasonable price point. But it seems to me it could be a great candidat= e. It's a pretty fast machine and its network can definitely support two Gi= gE ports.=0A=0A=0AOn Sunday, September 17, 2023 9:05pm, "Dave Taht via Cake= " said:=0A=0A> _______________________________= ________________=0A> Cake mailing list=0A> Cake@lists.bufferbloat.net=0A> h= ttps://lists.bufferbloat.net/listinfo/cake=0A> A huge thanks to dave seddon= for buckling down and doing some comprehensive=0A> testing of a variety of= arm64 gear!=0A> =0A> https://docs.google.com/document/d/1HxIU_TEBI6xG9jRHl= r8rzyyxFEN43zMcJXUFlRuhiUI/edit#heading=3Dh.bpvv3vr500nw=0A> =0A> --=0A> Oc= t 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html= =0A> Dave T=C3=A4ht CSO, LibreQos=0A> =0A