From owner-freebsd-questions@FreeBSD.ORG Sat Feb 23 07:24:35 2008 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 01E0416A400 for ; Sat, 23 Feb 2008 07:24:35 +0000 (UTC) (envelope-from wojtek@wojtek.tensor.gdynia.pl) Received: from wojtek.tensor.gdynia.pl (wojtek.tensor.gdynia.pl [IPv6:2001:4070:101:2::1]) by mx1.freebsd.org (Postfix) with ESMTP id 97B1813C468 for ; Sat, 23 Feb 2008 07:24:30 +0000 (UTC) (envelope-from wojtek@wojtek.tensor.gdynia.pl) Received: from wojtek.tensor.gdynia.pl (localhost [IPv6:::1]) by wojtek.tensor.gdynia.pl (8.13.8/8.13.8) with ESMTP id m1N7N6P6001336 for ; Sat, 23 Feb 2008 08:23:06 +0100 (CET) (envelope-from wojtek@wojtek.tensor.gdynia.pl) Received: from localhost (wojtek@localhost) by wojtek.tensor.gdynia.pl (8.13.8/8.13.8/Submit) with ESMTP id m1N7N6lx001333 for ; Sat, 23 Feb 2008 08:23:06 +0100 (CET) (envelope-from wojtek@wojtek.tensor.gdynia.pl) Date: Sat, 23 Feb 2008 08:23:06 +0100 (CET) From: Wojciech Puchar To: freebsd-questions@freebsd.org Message-ID: <20080223081622.T1326@wojtek.tensor.gdynia.pl> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Subject: CRASH:sleeping thread owns a non-sleepable lock X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 23 Feb 2008 07:24:35 -0000 i'm running my program (bash script to be exact), that does process URL list by fetching each one with curl and then process etc.. to make it faster i run 30-40 of them in parallel to maximize speed, as often there are network stalls and doing many transfers in parallel speed it up. all is run with nice -n 20 to not interfere too much with other tasks. it runs on Core2Duo SMP system with 6.2p11/amd64 the script takes some CPU time so system it's quite loaded. when i first start it it takes about 25% user time and 20% system time. after half a day doing exactly the same thing, network having same load, after processing few millions URL, system time jumps to over 50%, idle gets close to zero, system load goes up. that's strange but it goes on, after about next half a day system crashes with "sleeping thread owns a non-sleepable lock". no core dump, after panic kernel hangs. is there a fix for that? unix is for running multiple parallel tasks, so it should not cause crashes!