From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from g2t2353.austin.hp.com (g2t2353.austin.hp.com [15.217.128.52]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "smtp.hp.com", Issuer "VeriSign Class 3 Secure Server CA - G3" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 02E0721F34E for ; Tue, 12 May 2015 16:46:33 -0700 (PDT) Received: from g2t2360.austin.hp.com (g2t2360.austin.hp.com [16.197.8.247]) by g2t2353.austin.hp.com (Postfix) with ESMTP id 9CBEEA1 for ; Tue, 12 May 2015 23:46:31 +0000 (UTC) Received: from [16.103.148.51] (tardy.usa.hp.com [16.103.148.51]) by g2t2360.austin.hp.com (Postfix) with ESMTP id 7BEDD4E for ; Tue, 12 May 2015 23:46:31 +0000 (UTC) Message-ID: <555290D7.7040508@hp.com> Date: Tue, 12 May 2015 16:46:31 -0700 From: Rick Jones User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.6.0 MIME-Version: 1.0 To: bloat@lists.bufferbloat.net References: <20150512231330.GA30054@sesse.net> In-Reply-To: <20150512231330.GA30054@sesse.net> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Bloat] [Cerowrt-devel] better business bufferbloat monitoring tools? X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 X-List-Received-Date: Tue, 12 May 2015 23:47:02 -0000 On 05/12/2015 04:13 PM, Steinar H. Gunderson wrote: > On Tue, May 12, 2015 at 03:17:34PM -0700, David Lang wrote: >> I always set my graphs for 1 min samples (and am very tempted to go shorter) >> just because 5 min hides so much. > > Just be aware that there are many devices (in particular switches) that only > update SNMP counters now and then (say, every 17th second or whatever).[1] > The shorter your polling interval, the greater your noise will be from that > effect. > > [1] This used to be especially great in combination with devices that were too > stupid to have 64-bit SNMP counters, but were fast enough to have 32-bit > counters wraparound in 35 seconds or less. If you want to get more extreme, even sFlow can have troubles (or at least could): ftp://ftp.netperf.org/papers/high_freq_sflow/hf_sflow_counters.html Of course, not everyone is chasing after the grail of stats every second :) rick jones