From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jarek Poplawski Subject: Re: HTB - What's the minimal value for 'rate' parameter? Date: Fri, 9 Apr 2010 23:26:57 +0200 Message-ID: <20100409212657.GA3560@del.dom.local> References: <4BBE4BB4.1060209@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@vger.kernel.org, kaber@trash.net, davem@davemloft.net, devik@cdi.cz To: Antonio Almeida Return-path: Received: from mail-fx0-f223.google.com ([209.85.220.223]:64869 "EHLO mail-fx0-f223.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757371Ab0DIV1F (ORCPT ); Fri, 9 Apr 2010 17:27:05 -0400 Received: by fxm23 with SMTP id 23so3108393fxm.21 for ; Fri, 09 Apr 2010 14:27:02 -0700 (PDT) Content-Disposition: inline In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On Fri, Apr 09, 2010 at 04:40:44PM +0100, Antonio Almeida wrote: > So, what about the rate limit miss? > As you can see the ceil of class 1:2 is set to 4096Kbit but its > sending rate is actually 8071Kbit! > It looks like classes 1:10 and 1:11 are ignoring hierarchical rate > restrictions of class 1:2 > Here: > class htb 1:2 parent 1:1 rate 4096Kbit ceil 4096Kbit burst 3655b cburst 3655b > Sent 84285894 bytes 55671 pkt (dropped 0, overlimits 0 requeues 0) > rate 8071Kbit 666pps backlog 0b 0p requeues 0 > lended: 0 borrowed: 0 giants: 0 > tokens: -937499999 ctokens: -937499999 Yes, since 1:2 has grandchildren with overflown rate tables, they could behave as if they had set rates higher than their parents or grandparent (and HTB doesn't restrict it hierarchically). Jarek P.