From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-vn0-x234.google.com (mail-vn0-x234.google.com [IPv6:2607:f8b0:400c:c0f::234]) (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 1AE4B21F44F for ; Wed, 3 Jun 2015 09:25:30 -0700 (PDT) Received: by vnbg129 with SMTP id g129so1788381vnb.9 for ; Wed, 03 Jun 2015 09:25:29 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=mNny/wttF647la0NFsXuBGEw1dNJUE8/cF5lxNQeV+s=; b=Av+ZfEZiSn6SNsewnq9KaygJd7Nts/DwSn4A2X9CXRlzW3JYCByeidcQ4dcpILH7sf avu/J51+vLA0yynmgf6Qjo9xWdlPJZViVGwvwP7r/qjXQS8xi88UjJBXP3v0qqUBvIJu QrOgU/1CfgP678NYYCjUHNL+3I/3MlRh/azRb8fi5mxw5b0q2ivHZtTHV6aVTnWn+lMi MffszxUISYHxrUx62m9F1lr6QXX0FEQkYFUuGYba1QehuJ4P7yOP4Z10cJXZUKnVp5PD 7SXV26bafImuv8ZAj7ZZxPGf7JJ1xu2uGaoAu2d0/mmrRhw/ERWRgpUp5VluV+EaO3V6 +Pfg== MIME-Version: 1.0 X-Received: by 10.52.89.174 with SMTP id bp14mr48017816vdb.58.1433348729709; Wed, 03 Jun 2015 09:25:29 -0700 (PDT) Received: by 10.52.12.167 with HTTP; Wed, 3 Jun 2015 09:25:29 -0700 (PDT) Received: by 10.52.12.167 with HTTP; Wed, 3 Jun 2015 09:25:29 -0700 (PDT) In-Reply-To: References: Date: Wed, 3 Jun 2015 19:25:29 +0300 Message-ID: From: Jonathan Morton To: Aaron Wood Content-Type: multipart/alternative; boundary=20cf307abdc9dfa95405179f81c3 Cc: cerowrt-devel Subject: Re: [Cerowrt-devel] ingress rate limiting falling short X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 03 Jun 2015 16:25:59 -0000 --20cf307abdc9dfa95405179f81c3 Content-Type: text/plain; charset=UTF-8 Remind me: does HTB have a divide in the fast path? ARMv6 and ARMv7-A CPUs don't have a hardware integer divide, so that can really hurt. This is fixed I think in ARMv8 and definitely in AArch64, but divides are still expensive instructions on any CPU. - Jonathan Morton --20cf307abdc9dfa95405179f81c3 Content-Type: text/html; charset=UTF-8

Remind me: does HTB have a divide in the fast path? ARMv6 and ARMv7-A CPUs don't have a hardware integer divide, so that can really hurt.

This is fixed I think in ARMv8 and definitely in AArch64, but divides are still expensive instructions on any CPU.

- Jonathan Morton

--20cf307abdc9dfa95405179f81c3--