From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: mail.toke.dk; spf=pass smtp.mailfrom=; dkim=pass header.d=networkplumber-org.20230601.gappssmtp.com; arc=none (Message is not ARC signed); dmarc=fail (Used From Domain Record) header.from=networkplumber.org policy.dmarc=quarantine Received: from mail-wm1-x335.google.com (mail-wm1-x335.google.com [IPv6:2a00:1450:4864:20::335]) by mail.toke.dk (Postfix) with ESMTPS id 64C8DD239AC for ; Tue, 17 Feb 2026 15:34:17 +0100 (CET) Received: by mail-wm1-x335.google.com with SMTP id 5b1f17b1804b1-4806bf39419so45350665e9.1 for ; Tue, 17 Feb 2026 06:34:17 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=networkplumber-org.20230601.gappssmtp.com; s=20230601; t=1771338857; x=1771943657; darn=lists.bufferbloat.net; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:from:to:cc:subject:date :message-id:reply-to; bh=8D4chJSReAyvNAGhX3+B5YhoZaQ/FVNWXFPc8WsJRrc=; b=maXPATidSyIOekmNW0cIUhQ0FXpwcLp4Onp2AaRcgcnvPCxX7Tcq1atrOrdRKOGGNk GSaITQv0b5mxS6UryjXkih8YllAW51iAOgDv0FgB7R4o7gv32z0Yr3WsVNlYc0TkcbHv ohu8V+w4II/y7ZBJD7waowoczlQHCQXYnytPSrS2/VS1iJT8X+dO3DmDqXRvVJOY1kyi 4J3xao1Q32bI58EMUMCt1vCEHepJbXGwDnc1AZ7XTvQgP5V+p56bmTdyFWErUgEc2y2l xhL/39oKzSELen0TSftf4cgL1tzaPVOq2C/aBbal55zQBZ2dMzdefIW5HOAJ/Ar0xGep IG1w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1771338857; x=1771943657; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=8D4chJSReAyvNAGhX3+B5YhoZaQ/FVNWXFPc8WsJRrc=; b=DcjbWbnE6DBbF/mhwMg8Y774tlSjjusjYYVu/rXM307gCsI27PzASJFopPN7G1rOUs UFAChbRNwQTwYrCn6qBBs5FNJ0gHWIH3K49Rnp4MmXqh55FjZNZKARU7SiLo/6zi8qgx fYCm2fj1c8dHR3J7TXgJRR6VP9/R5iHCnpBRecEoiM1zHSukNbczgQzn2Hzt6tqokGDu 9C9T8eQDRggS9QupQ+yuWK+VVr3ckKX1WIOePbSMS0n8O7BMJq3e4QS9bhHFTULSRuTT hM4OO48U78tufVlIczEYSJDJvSrAF2Y6anxWnsSNkIgV3B7xVS098iltwWlFSPg2ezcO X8Ag== X-Gm-Message-State: AOJu0YyR5pzT2ZGtJ/lAfFbdq93wV5zQWK4JW7Au6bL0kzskZz2Sjno4 VWzA82+PEzC0DZaesuE+uxHQIDKf5kRfsLt1yIzWJqqMjfxy/fgDqQXJtTr2xHXDoZpm+DWFvIR UGNeU X-Gm-Gg: AZuq6aKNG13fS2xrMWEfhygFFbLuDaKOTNDsHVqKPlAL/8A/m1jfPCaugeifQDFNIZv 9k+csVwsi6bSMlPf3E3ly645V7S+L0T8KmF+yC4QS1ef+1AqgEYtyzREPmPyoL2EmpAReYHrf7x nLxy/Ta0Pm4Ow6mCOdKToXeN+IuMuhiSdKxI5HwQustTmoiuh41psLgUYkQROBTe6KAQXI6bzCZ 2/B4xFbiSjraQNRCzM+IL79YbDXDciQMuXURxej12W5P3tWTYMdPjXX0x3BcyRXtgjTILYonuu7 fAlVG0jNpmhb/WS7QMjgGCEvn0FojpLVzLjbi6KqVj0l/CIew3TYHsoR9EIqLZXk9nXK+pJu/eh q8IyJC4j1HYHS1rQSd2Hh6GVApUlCvnZ4UD+emGmGsIgMvmvyZQkwpSlJteG0QfAT2HVzCi4eWu d5jvg0qmHrjMcah7iO2y3adQ2pLVr6L0ite18ki+qeMXLuloaaPy5cWGhPCKpZK0pv X-Received: by 2002:a05:600c:858a:b0:47a:8383:f2b2 with SMTP id 5b1f17b1804b1-48378daa04fmr142556475e9.17.1771338856640; Tue, 17 Feb 2026 06:34:16 -0800 (PST) Received: from phoenix.local (204-195-96-226.wavecable.com. [204.195.96.226]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-437969fd36dsm36831444f8f.0.2026.02.17.06.34.14 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 17 Feb 2026 06:34:16 -0800 (PST) Date: Tue, 17 Feb 2026 06:34:10 -0800 From: Stephen Hemminger To: Toke =?UTF-8?B?SMO4aWxhbmQtSsO4cmdlbnNlbg==?= via Cake Cc: Toke =?UTF-8?B?SMO4aWxhbmQtSsO4cmdlbnNlbg==?= , dave seddon , Frantisek Borsik , codel@lists.bufferbloat.net, bloat , Jeremy Austin via Rpm , Make-Wifi-fast , ryan@rkhtech.org Message-ID: <20260217063410.47b59cd8@phoenix.local> In-Reply-To: <87ecmjpkpj.fsf@toke.dk> References: <87ecmjpkpj.fsf@toke.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Message-ID-Hash: SXSEESKPWXFLL6X6OA5QZ5SEJLX5UXKV X-Message-ID-Hash: SXSEESKPWXFLL6X6OA5QZ5SEJLX5UXKV X-MailFrom: stephen@networkplumber.org X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; loop; banned-address; emergency; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header X-Mailman-Version: 3.3.10 Precedence: list Subject: [Cake] Re: [Bloat] Re: CAKE-MQ merged to OpenWrt 25.12 today (February 15) List-Id: Cake - FQ_codel the next generation Archived-At: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: On Tue, 17 Feb 2026 14:23:52 +0100 Toke H=C3=B8iland-J=C3=B8rgensen via Cake wrot= e: > dave seddon writes: >=20 > > =3D=3D=3D Pre-flight Complete =3D=3D=3D > > Running 6 test points > > > > [1/6] qdisc=3Dfq_codel flows=3D1 tool=3Diperf2 > > Switching qdisc to fq_codel... > > Throughput: 9.41 Gbps > > [2/6] qdisc=3Dfq_codel flows=3D10 tool=3Diperf2 > > Throughput: 9.43 Gbps > > [3/6] qdisc=3Dcake flows=3D1 tool=3Diperf2 > > Switching qdisc to cake... > > Throughput: 6.93 Gbps > > [4/6] qdisc=3Dcake flows=3D10 tool=3Diperf2 > > Throughput: 4.37 Gbps <---- cake > > [5/6] qdisc=3Dmq-cake flows=3D1 tool=3Diperf2 > > Switching qdisc to mq-cake... > > Throughput: 7.17 Gbps > > [6/6] qdisc=3Dmq-cake flows=3D10 tool=3Diperf2 > > Throughput: 9.44 Gbps <----- > > mq-cake ... Actually, that's interesting. higher than fq_codel =20 >=20 > Are you running fq_codel as the root qdisc? Because in that case you're > running through the single qdisc lock, which could explain the > difference. Try running separate fq_codel instances beneath an 'mq' > qdisc as the root. >=20 > Also, if you're not setting a shaping rate, cake_mq is basically the > same as just installing an mq qdisc at the root and having separate cake > instances beneath that. So to test the multi-core shaper algorithm > you'll need to set a rate ('bandwidth' parameter). >=20 This is what the OpenWrt SQM scripts seem to favor. I probably need to tune the adaption overhead # tc qdisc show dev wan qdisc htb 1: root refcnt 2 r2q 10 default 0x12 direct_packets_stat 0 direct= _qlen 1000 qdisc fq_codel 120: parent 1:12 limit 1001p flows 1024 quantum 300 target 5= ms interval 100ms memory_limit 4Mb drop_batch 64=20 qdisc fq_codel 130: parent 1:13 limit 1001p flows 1024 quantum 300 target 5= ms interval 100ms memory_limit 4Mb drop_batch 64=20 qdisc fq_codel 110: parent 1:11 limit 1001p flows 1024 quantum 300 target 5= ms interval 100ms memory_limit 4Mb drop_batch 64=20 It is dumb that in US it is standard to offer 1G down and 10M up!