From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f175.google.com (mail-wi0-f175.google.com [209.85.212.175]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 5BEF321F0A7 for ; Tue, 4 Sep 2012 00:22:31 -0700 (PDT) Received: by wibhm2 with SMTP id hm2so3419900wib.10 for ; Tue, 04 Sep 2012 00:22:29 -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=rKAXveUoe2ecs4Yq35Oohz4u/FbxJQz9c0t0FIXrrvI=; b=s6mm7sEI1wpVjo6uwZIKNeqJT4NZ+RJJRH09PU97EfT5UmvzG3dKaId37fBlA0PBwv R3URrgRCHTCXZLEKS8X5vVJ5P5KM+EAY45FnXyr8rZ1du/8YBCrCewvKqBiXSZHQwH0j kzHCukUVsuuJdXDA/P15HimIsnm8B01uH3dt2j/C24E4dfjLwsxjZHVnX0WGKgnBL5WX /Lv5kfYZUdIkGgHAUnLRE0cpllvmmW3jKIRR5Q9CwdMXiD7QfWiTuNLxJWKoF5JnKN0G lg2bfqA6JzW4AEOghrOS0DYkY5lMZHsXjIUZYmXEkCofhJW3pCQB69+Bq/0mfSi+SkqT owvQ== MIME-Version: 1.0 Received: by 10.216.181.67 with SMTP id k45mr10312809wem.17.1346743349158; Tue, 04 Sep 2012 00:22:29 -0700 (PDT) Received: by 10.223.159.134 with HTTP; Tue, 4 Sep 2012 00:22:29 -0700 (PDT) Date: Tue, 4 Sep 2012 00:22:29 -0700 Message-ID: From: Dave Taht To: cerowrt-devel@lists.bufferbloat.net Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Subject: [Cerowrt-devel] quick update 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: Tue, 04 Sep 2012 07:22:32 -0000 If you can't tell, I have been trying for a stable-ish release of cero once a month, around the 15th. I'm not sure if I'm going to make it this time. Some good things have been happening... I THINK, but am not sure, the skb shrinkage thing I was doing needs some headroom added in some cases. I am hoping this would account some of the introduced flakyness on wifi we encountered in the last dev release. This little bit in ath9k/xmit.c looks suspicious: /* Add the padding after the header if this is not already done */ padpos =3D ath9k_cmn_padpos(hdr->frame_control); padsize =3D padpos & 3; if (padsize && skb->len > padpos) { if (skb_headroom(skb) < padsize) return -ENOMEM; Also found a few improvements to make to fq_codel at low bandwidths (below 10Mbit) and something of a theoretical problem with queue occupancy with tons of flows, and there's been some good threads on the codel list. But finding these has been kind of tedious and slow, and my non-bloat, and trying to make eating money, workload has been a bit much of late. So I will try to polish up the latest set of cero patches and get them out there after a great deal more testing on x86. --=20 Dave T=E4ht