From owner-freebsd-stable@FreeBSD.ORG Fri Oct 23 20:52:28 2009 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id EE3741065693 for ; Fri, 23 Oct 2009 20:52:28 +0000 (UTC) (envelope-from jbozza@mindsites.com) Received: from mail.thinkburst.com (mail.thinkburst.com [204.49.104.46]) by mx1.freebsd.org (Postfix) with ESMTP id BE3128FC1A for ; Fri, 23 Oct 2009 20:52:28 +0000 (UTC) Received: from mailgate.mindsites.net (gateway.mindsites.net [204.49.104.36]) by mail.thinkburst.com (Postfix) with ESMTP id 43EF11CC27; Fri, 23 Oct 2009 15:52:28 -0500 (CDT) Received: from remote.mindsites.com (unknown [10.1.1.5]) by mailgate.mindsites.net (Postfix) with ESMTP id 16BCB17040; Fri, 23 Oct 2009 15:52:28 -0500 (CDT) Received: from ATLAS.msg.local ([fe80::48f5:88b0:6093:4f67]) by ATLAS.msg.local ([fe80::48f5:88b0:6093:4f67%10]) with mapi; Fri, 23 Oct 2009 15:52:27 -0500 From: Jaime Bozza To: Scott Ullrich Date: Fri, 23 Oct 2009 15:52:26 -0500 Thread-Topic: Possible scheduler (SCHED_ULE) bug? Thread-Index: AcpUEZweeAagGkZhStWsbB7216svTwABY4Ag Message-ID: References: In-Reply-To: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: acceptlanguage: en-US Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "freebsd-stable@freebsd.org" , "jacob@whotookspaz.org" Subject: RE: Possible scheduler (SCHED_ULE) bug? X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Oct 2009 20:52:29 -0000 > Try adding this or changing these items in lighttpd.conf: >=20 > ## FreeBSD! > server.event-handler =3D "freebsd-kqueue" > server.network-backend =3D "writev" Scott, Lighttpd was already using freebsd-kqueue, but I added the writev network-b= ackend and the problem went away. With this additional information I was = able to track down kern/138999, which seems to be the exact issue I'm havin= g. The additional information I have (over the PR) is that: 1) Files over 64K cause the problem, not just larger files 2) switching over to SCHED_4BSD eliminates the problem - system no longer l= ocks. =20 3) 7.2 amd64 doesn't have the problem - Tested a similar configuration and = was not able to duplicate on amd64 at all. I'm CC'ing the original submitter of the PR to give him an update to see if= he had any additional luck. Jaime=20