From owner-freebsd-bugs@FreeBSD.ORG Tue Jan 8 01:28:52 2008 Return-Path: Delivered-To: freebsd-bugs@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 7417E16A41A for ; Tue, 8 Jan 2008 01:28:52 +0000 (UTC) (envelope-from jin@george.lbl.gov) Received: from smtp120.sbc.mail.sp1.yahoo.com (smtp120.sbc.mail.sp1.yahoo.com [69.147.64.93]) by mx1.freebsd.org (Postfix) with SMTP id 3EBB213C44B for ; Tue, 8 Jan 2008 01:28:52 +0000 (UTC) (envelope-from jin@george.lbl.gov) Received: (qmail 10754 invoked from network); 8 Jan 2008 01:02:12 -0000 Received: from unknown (HELO ?192.168.1.238?) (jinmtb@sbcglobal.net@67.111.218.125 with plain) by smtp120.sbc.mail.sp1.yahoo.com with SMTP; 8 Jan 2008 01:02:11 -0000 X-YMail-OSG: JsUmm48VM1ndYTBeC0DYmAWJNL2RPufUrO8mrrT3xR.dsowM4.83Wl4WEijUnpJLGCRA4rCMh3ZavoQoVLc5LeUq5WDmRDIL9TmDw3CqpP_JG6.JMchkZNMJY1.q Message-ID: <4782CB8D.2040401@george.lbl.gov> Date: Mon, 07 Jan 2008 17:02:05 -0800 From: Jin Guojun User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.13) Gecko/20061027 X-Accept-Language: zh, zh-CN, en MIME-Version: 1.0 To: kmacy@FreeBSD.org References: <200711170119.lAH1Jokl048803@freefall.freebsd.org> In-Reply-To: <200711170119.lAH1Jokl048803@freefall.freebsd.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-bugs@FreeBSD.org Subject: Re: kern/37436: [hang] accept dead loop when out of file descriptors X-BeenThere: freebsd-bugs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Bug reports List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Jan 2008 01:28:52 -0000 kmacy@FreeBSD.org wrote: >Synopsis: [hang] accept dead loop when out of file descriptors > >State-Changed-From-To: open->feedback >State-Changed-By: kmacy >State-Changed-When: Sat Nov 17 01:19:37 UTC 2007 >State-Changed-Why: > >Is this still an issue? > >http://www.freebsd.org/cgi/query-pr.cgi?pr=37436 > > This is no longer an issue in both 6.x and 7.0, but some other harder problem comes up :-( I have not been able to determine what is the root yet, and keep digging right now. Brief description to new problem: When a large number of threads (around 1K) created to communicate to a remote server via TCP sockets, if data tranmitted per thread (probably caused by aggregated data) exceed a certain amount, the Tx session will hang. If Tx runs on a terminal session, the terminal hangs. Cannot kill the Tx process. Open another V console term is ok. If Tx runs on a Xterm, the entire X window hangs, although the Xclock is still ticking, but even a top program stops running on another xterm. Samba serve is dead. CTL-ALT-BS can kill X window, but no way to kill the hanging process, thus if testing this multiple times, system dies. Anyway, this is a different problem. Case 37436 can be closed, and thanks for all efforts. -Jin