From owner-freebsd-wireless@FreeBSD.ORG Sun Mar 25 19:51:43 2012 Return-Path: Delivered-To: freebsd-wireless@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4C084106564A for ; Sun, 25 Mar 2012 19:51:43 +0000 (UTC) (envelope-from lytboris@gmail.com) Received: from mail-we0-f182.google.com (mail-we0-f182.google.com [74.125.82.182]) by mx1.freebsd.org (Postfix) with ESMTP id BA08D8FC1D for ; Sun, 25 Mar 2012 19:51:42 +0000 (UTC) Received: by wern13 with SMTP id n13so5010274wer.13 for ; Sun, 25 Mar 2012 12:51:41 -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:content-transfer-encoding; bh=z8Yj0Ok/bIvN+c4lw/vxq3YPezHe11BjT7st4AWJ25Y=; b=OHYS57FD9USZ5qNNQz3XAekGeUFnDjZ/yPQVl2BpJOek04neDMHzhObjQdtw86HiNX zp9MNX/xghA5jZnqLoxI/c5oljtW3y9yM1ZqALQSfo3HJoAXvfvJlkD6avd33RRANat5 ot/bE17yxcvHgDqcllMA/EFqkhxO+QHrLTfQ5oK89YrwmoDeD++8Ew3sPMjok2dY7WDA kjT7RLsPN0W7Z/gD5oIZSrzol3QVgFa7HAdjeXrp3A5Wd9X00375cHBJ1G9EUDK+GKkp /FfcOVvToMo8b4ZxyKt+JsXJv9QupWhtk4LWA+q2VVhEPzF8YuaFiaC64d2WwL1X94H+ vIhg== MIME-Version: 1.0 Received: by 10.180.94.33 with SMTP id cz1mr12846186wib.13.1332705101795; Sun, 25 Mar 2012 12:51:41 -0700 (PDT) Received: by 10.223.72.6 with HTTP; Sun, 25 Mar 2012 12:51:41 -0700 (PDT) In-Reply-To: References: <4f6f67a7.4a0c440a.3941.ffffc865@mx.google.com> Date: Sun, 25 Mar 2012 23:51:41 +0400 Message-ID: From: Lytochkin Boris To: Adrian Chadd Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: "freebsd-wireless@freebsd.org" Subject: Re: [ath][CURRENT] Triangle-shaped network performance X-BeenThere: freebsd-wireless@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: "Discussions of 802.11 stack, tools device driver development." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 25 Mar 2012 19:51:43 -0000 On Sun, Mar 25, 2012 at 11:36 PM, Adrian Chadd wro= te: > Well, you changed both the OS _and_ the NIC. How are we supposed to > debug this? :-) Let's forget about past :) I would have to change my OS back unless this madness is fixed :( > >> =A0Some more facts: ping triangles for two laptops connected to server >> =A0are not synchronized and roll-over independently. > > I still don't know what's causing this. Try running athstats a little > more and try to correlate changes in latency with changes in the > output of athstats. Here it is. Transfer initiation (you can see when it boosts): >athstats 1 input output altrate short long xretry crcerr crypt phyerr rssi = rate 608153 1085770 74 0 30727 2591 2749 0 0 62 = MCS11 4 3 0 0 0 0 0 0 0 62 = MCS11 7 4 0 0 0 0 0 0 0 62 MCS11 <--- transfer initiated 4 5 0 0 0 0 0 0 0 61 = MCS11 4 4 0 0 0 0 0 0 0 62 = MCS11 7 8 0 0 0 0 0 0 0 59 = MCS15 9 8 0 0 14 3 0 0 0 54 = 48M 6 6 0 0 4 1 0 0 0 57 = 36M 21 17 0 0 78 15 0 0 0 54 = MCS11 8 6 0 0 0 0 0 0 0 55 = 36M 10 6 0 0 0 0 0 0 0 50 = 36M 12 8 0 0 0 0 0 0 0 59 = 36M 10 13 0 0 0 0 0 0 0 58 = 36M 7 8 0 0 1 0 0 0 0 60 = 36M 6 6 0 0 0 0 0 0 0 61 = 36M 5 5 0 0 0 0 0 0 0 61 = 36M 6 8 0 0 1 0 0 0 0 61 = 36M 8 7 0 0 1 0 0 0 0 59 = 54M 12 28 0 0 0 0 0 0 0 61 = 36M 26 31 0 0 5 0 0 0 0 57 = 36M 6 10 0 0 0 0 0 0 0 59 = 36M input output altrate short long xretry crcerr crypt phyerr rssi = rate 608336 1085966 74 0 30831 2610 2749 0 0 60 = 36M 6 6 0 0 0 0 0 0 0 65 = 36M 22 53 0 0 0 0 0 0 0 61 = 36M 28 48 0 0 0 0 0 0 0 61 = 36M 28 48 0 0 1 0 0 0 0 59 = 12M 28 49 0 0 8 0 0 0 0 59 = MCS12 30 49 0 0 2 0 0 0 0 62 = MCS12 29 49 0 0 5 0 0 0 0 59 = MCS12 24 39 0 0 1 0 0 0 0 60 = MCS12 33 45 0 0 1 0 0 0 0 58 = MCS12 31 52 0 0 3 0 0 0 0 59 = MCS11 32 52 0 0 2 0 0 0 0 66 = MCS11 28 51 0 0 1 0 0 0 0 59 = MCS11 29 50 0 0 3 0 0 0 0 60 = MCS12 28 53 0 0 3 0 0 0 0 57 = MCS11 28 50 0 0 1 0 0 0 0 60 = MCS12 37 56 0 0 3 0 0 0 0 58 = MCS11 36 50 0 0 0 0 0 0 0 63 = MCS11 31 55 0 0 2 0 0 0 0 65 = MCS11 31 54 0 0 3 0 0 0 0 62 = MCS12 35 51 0 0 3 0 0 0 0 60 = MCS12 input output altrate short long xretry crcerr crypt phyerr rssi = rate 608941 1086977 74 0 30875 2610 2749 0 0 59 = MCS11 29 52 0 0 1 0 0 0 0 62 = MCS12 28 50 0 0 3 0 0 0 0 61 = MCS12 28 50 0 0 0 0 0 0 0 62 = MCS11 32 58 0 0 7 0 0 0 0 57 = MCS12 40 55 0 0 2 0 0 0 0 62 = MCS12 30 56 0 0 2 0 0 0 0 63 = MCS12 35 60 0 0 1 0 0 0 0 64 = MCS12 32 57 0 0 1 0 0 0 0 63 = MCS12 29 52 0 0 1 0 0 0 0 61 = MCS12 17 31 0 0 0 0 0 0 0 62 = 36M 33 53 0 0 3 0 0 0 0 63 = 18M 30 50 0 0 2 0 0 0 0 64 = 36M 31 50 0 0 2 0 0 0 0 63 = 36M 28 50 0 0 4 0 0 0 0 62 = 36M 29 52 0 0 3 0 0 0 0 62 = 36M 29 52 0 0 3 0 0 0 0 62 = 36M 37 55 0 0 2 0 0 0 0 56 = MCS11 30 54 0 0 3 0 0 0 0 60 = 36M 31 53 0 0 4 0 0 0 0 60 = 36M 36 55 0 0 1 0 0 0 0 63 = 36M input output altrate short long xretry crcerr crypt phyerr rssi = rate 609586 1088075 74 0 30923 2610 2749 0 0 54 = 36M 30 53 0 0 2 0 0 0 0 56 = 24M 34 56 0 0 3 0 0 0 0 51 = 36M 33 54 0 0 25 5 0 0 0 64 = 36M 32 53 0 0 2 0 0 0 0 54 = 36M 35 52 0 0 4 0 0 0 0 59 = MCS15 30 50 0 0 2 0 0 0 0 60 = MCS15 30 54 0 0 5 0 0 0 0 53 = MCS15 34 55 0 0 3 0 0 0 0 63 = MCS15 518 981 0 0 11 0 0 0 0 44 = MCS15 1398 2659 1 0 29 0 0 0 0 20 = MCS15 3051 5716 1 0 64 0 2 0 0 24 = MCS15 661 1210 1 0 43 3 0 0 0 27 = MCS15 563 1024 0 0 128 11 0 0 0 32 = MCS15 25 39 0 0 0 0 0 0 0 38 = MCS12 5 10 0 0 1 0 0 0 0 47 = 36M 7 10 0 0 0 0 0 0 0 49 = MCS12 8 6 0 0 0 0 0 0 0 56 = MCS11 63 26 0 0 1 0 0 0 0 44 = MCS11 1586 3000 0 0 37 0 0 0 0 20 = MCS12 2210 4150 0 0 61 0 0 0 0 15 = MCS12 input output altrate short long xretry crcerr crypt phyerr rssi = rate 622148 1111497 78 0 31400 2629 2751 0 0 22 = MCS12 2203 4145 0 0 63 2 0 0 0 23 = MCS12 2144 4022 0 0 64 2 0 0 0 23 = MCS12 2222 4169 0 0 45 0 0 0 0 18 = MCS12 2270 4245 0 0 45 0 0 0 0 27 = MCS12 2227 4150 0 0 62 0 0 0 0 25 = MCS12 2200 4120 0 0 56 0 0 0 0 27 = MCS12 2189 4122 0 0 59 0 0 0 0 21 = MCS12 2195 4136 0 0 57 0 0 0 0 24 = MCS12 2205 4146 0 0 55 0 0 0 0 23 = MCS12 2225 4187 0 0 63 0 2 0 0 31 = MCS12 2192 4114 0 0 48 0 0 0 0 26 = MCS12 2206 4150 0 0 47 0 1 0 0 30 = MCS12 Transfer abortion: 1551 2931 1 0 58 1 4 0 0 28 = MCS12 1657 3111 0 0 29 0 0 0 0 29 = MCS12 1361 2576 0 0 19 0 0 0 0 30 = MCS12 1564 2962 0 0 24 0 0 0 0 31 = MCS12 input output altrate short long xretry crcerr crypt phyerr rssi = rate 840750 1522646 89 0 36373 2664 2834 0 0 21 = MCS12 1623 3030 0 0 38 0 0 0 0 30 = MCS12 1497 2827 0 0 37 0 5 0 0 42 = MCS12 1450 2749 0 0 31 0 0 0 0 36 = MCS12 1381 2576 1 0 41 1 0 0 0 28 MCS12 <-- stop transfer, pings still are ok 119 201 0 0 11 1 0 0 0 47 = 1M 10 9 0 0 0 0 0 0 0 53 = 54M 5 4 0 0 0 0 0 0 0 56 = 54M 21 18 0 0 1 0 0 0 0 59 = MCS15 5 3 0 0 0 0 0 0 0 58 = 54M 6 4 0 0 0 0 0 0 0 59 = 54M 13 13 0 0 0 0 0 0 0 54 = 54M 8 8 0 0 8 2 0 0 0 56 = 54M 3 3 0 0 0 0 0 0 0 57 = 54M 5 5 0 0 0 0 0 0 0 58 = 54M 8 7 0 0 1 0 0 0 0 59 = 54M 8 6 0 0 0 0 0 0 0 60 = 54M 3 3 0 0 0 0 0 0 0 60 = 54M 6 6 0 0 1 0 0 0 0 60 = MCS15 3 3 0 0 0 0 0 0 0 61 = 54M 7 7 0 0 0 0 0 0 0 62 = 54M input output altrate short long xretry crcerr crypt phyerr rssi = rate 846937 1534134 90 0 36542 2668 2839 0 0 62 = MCS15 5 5 0 0 0 0 0 0 0 62 = MCS15 6 5 0 0 0 0 0 0 0 62 = MCS15 6 6 0 0 0 0 0 0 0 62 MCS12 <-- ping triangles start 7 6 0 0 0 0 0 0 0 62 = MCS15 6 9 0 0 1 0 0 0 0 66 = MCS12 11 8 0 0 0 0 0 0 0 62 = 48M --=20 Boris Lytochkin