From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.lixid.net (lixid.tarent.de [193.107.123.118]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id B5E2F3B29D for ; Sat, 22 Oct 2022 19:39:43 -0400 (EDT) Received: from localhost (localhost [127.0.0.1]) by mail.lixid.net (MTA) with ESMTP id 80741141221; Sun, 23 Oct 2022 01:39:42 +0200 (CEST) Received: from mail.lixid.net ([127.0.0.1]) by localhost (mail.lixid.net [127.0.0.1]) (MFA, port 10024) with LMTP id PyfUo1TFXNrd; Sun, 23 Oct 2022 01:39:36 +0200 (CEST) Received: from x61w.mirbsd.org (vpn-172-34-0-14.dynamic.tarent.de [172.34.0.14]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.lixid.net (MTA) with ESMTPS id 5F27A1410F2; Sun, 23 Oct 2022 01:39:36 +0200 (CEST) Received: by x61w.mirbsd.org (Postfix, from userid 1000) id EEF9D6112E; Sun, 23 Oct 2022 01:39:35 +0200 (CEST) Received: from localhost (localhost [127.0.0.1]) by x61w.mirbsd.org (Postfix) with ESMTP id E9800610FD; Sun, 23 Oct 2022 01:39:35 +0200 (CEST) Date: Sun, 23 Oct 2022 01:39:35 +0200 (CEST) From: Thorsten Glaser To: Dave Taht cc: libreqos@lists.bufferbloat.net In-Reply-To: Message-ID: <12c7ec6-dce1-4411-98b6-fecd4e5c46e9@tarent.de> References: <44a7e82b-0fe9-d6ba-ee12-02dfa4980966@gmail.com> <2b195a93-a88b-33c2-661a-85fa8513c063@gmail.com> <9c1bb95b-3933-2b33-b8c6-ddefc8459afa@tarent.de> Content-Language: de-DE-1901 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE X-Mailman-Approved-At: Sun, 23 Oct 2022 00:34:46 -0400 Subject: Re: [LibreQoS] qdisc_watchdog_schedule_range_ns granularity X-BeenThere: libreqos@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Many ISPs need the kinds of quality shaping cake can do List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 22 Oct 2022 23:39:43 -0000 On Sat, 22 Oct 2022, Dave Taht wrote: > I'm rather interested in your work because I don't understand how well > cake's shaper interacts with all the other loads, neither, htb. We're Interesting. Do keep in mind that this experimental qdisc will not become a generally useful one; rather one that attempts to mirror what an L4S slice in the 5G network does for *one* UE. We=E2=80=99re using this, on Intel NUCs acting as routers, so people can develop/test and possibly fine-tune their final application algorithms that will then be useful out in the field, where you don=E2=80=99t have this much ins= ight or debugging info. > hacking on this, running at speeds (10gbps) that are hard to measure OK, that=E2=80=99s tricky indeed. > at... with tools that don't exist yet, with kernel dependencies we > don't understand. Hey, that=E2=80=99s also where I am ;-) > How are you measuring, below? ebpf? No, relayfs again. The commit to add that was rather small even: > > See commit 2a61f1ea843dc767d291074eee9b2f1b8d3992a7 in > > git@github.com:tarent/sch_jens.git branch master for the Basically save away the time we expect the watchdog to call us, then compare that with now the next time we=E2=80=99re called. As for packages=E2=80=99 qdisc latency, same as fq_codel basically, just (now) in ns. The model here is: extralatency is simulated =E2=80=9Cbefore=E2=80=9D the p= ackets enter the qdisc, so while they=E2=80=99re put into the FIFO they are not considered arrived there yet. That=E2=80=99s (again) to help debugging the end user algorithms (turns out that BBR2 is no worse than L4S-based things at very small latencies). Then we have the normal queue delay, controlled by the arrival time of the packet (if extralatency is used, with that added) and its eventual departure time, no earlier than the previous packet=E2=80=99s departure plus ns_per_byte times its size. We ECN CE mark based on that as well, which (and the dropping of too old packets) is what Ericsson tells us is what the RAN does. I have absolutely no idea how to even begin to use eBPF, tbh=E2=80=A6 I=E2=80=99ve never encountered this Linux-specific tech before. bye, //mirabilos --=20 Infrastrukturexperte =E2=80=A2 tarent solutions GmbH Am Dickobskreuz 10, D-53121 Bonn =E2=80=A2 http://www.tarent.de/ Telephon +49 228 54881-393 =E2=80=A2 Fax: +49 228 54881-235 HRB AG Bonn 5168 =E2=80=A2 USt-ID (VAT): DE122264941 Gesch=C3=A4ftsf=C3=BChrer: Dr. Stefan Barth, Kai Ebenrett, Boris Esser, Ale= xander Steeg ***************************************************= * /=E2=81=80\ The UTF-8 Ribbon =E2=95=B2=C2=A0=E2=95=B1 Campaign against Mit dem tarent-Newsletter ni= chts mehr verpassen: =C2=A0=E2=95=B3=C2=A0 HTML eMail! Also, https://www.tarent.de/newslette= r =E2=95=B1=C2=A0=E2=95=B2 header encryption! ***************************************************= *