From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qk0-x233.google.com (mail-qk0-x233.google.com [IPv6:2607:f8b0:400d:c09::233]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 7904021F220 for ; Sun, 12 Apr 2015 15:11:52 -0700 (PDT) Received: by qkgx75 with SMTP id x75so144863527qkg.1 for ; Sun, 12 Apr 2015 15:11:51 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:date:message-id:subject:from:to:content-type :content-transfer-encoding; bh=OIwdhIWzFJHd28cT0dMliPDjw7wARr8uaDwDe6rxQR4=; b=NazvW0TDZXOum577LByrGU11NQ5uznyQpABpUvUkM2hhTx1UQUNP1CjEPBxN0r1GFX EOoR2eOATNYxQbR0zzfpEkfDVLq7Al1DKAdubRapMys/1+mHLCZqb4xJ0X3coTcU+XsS 78BmiIX2yXRQ4hPTYXpeZ1bNfO2NBVFKlZxD4ttU4UgjkurmXK+6WpATQU+foRthfYqf mDbqpwiXvPFH2HRlg/mETuRrt/b3lLutRVfLkFfdSdvRPoVRt2CdIIEZ9FFkfimyqelA HtCJOW+kAIZVV+UpJzkUzQ9ITtMjmvuxdYTq5mjU6C6v1VJ4p353iCA9TtYIJNn/Tmkj 8UDA== MIME-Version: 1.0 X-Received: by 10.182.78.101 with SMTP id a5mr8144398obx.45.1428876711396; Sun, 12 Apr 2015 15:11:51 -0700 (PDT) Received: by 10.202.51.66 with HTTP; Sun, 12 Apr 2015 15:11:51 -0700 (PDT) Date: Sun, 12 Apr 2015 15:11:51 -0700 Message-ID: From: Dave Taht To: cake@lists.bufferbloat.net Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Subject: [Cake] single softirq handler for shaping? X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 12 Apr 2015 22:12:21 -0000 All the new routers are multicore - the mt72 is 4 cores, I think the linksys 1900ac is dual core. And it is not clear to me if we are single threaded on the softirq handler or other parts of the shaping side of all this. ? I seem to only see one softirq handler running on the edgerouter pro with htb + fq_codel, for example. We usually run two instances of the shaper - one on inbound - the hard task, and the other on outbound (usually much less hard on cpu) So one thread per shaper (if sufficient cpus are available) queue might scale better, if we are presently only using one. --=20 Dave T=C3=A4ht Open Networking needs **Open Source Hardware** https://plus.google.com/u/0/+EricRaymond/posts/JqxCe2pFr67