From owner-freebsd-questions@FreeBSD.ORG Wed Jul 29 15:21:57 2009 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 9C7D3106564A for ; Wed, 29 Jul 2009 15:21:57 +0000 (UTC) (envelope-from psteele@webmail.maxiscale.com) Received: from k2smtpout01-01.prod.mesa1.secureserver.net (k2smtpout01-01.prod.mesa1.secureserver.net [64.202.189.88]) by mx1.freebsd.org (Postfix) with SMTP id 6B70D8FC15 for ; Wed, 29 Jul 2009 15:21:57 +0000 (UTC) (envelope-from psteele@webmail.maxiscale.com) Received: (qmail 30617 invoked from network); 29 Jul 2009 15:14:44 -0000 Received: from unknown (HELO owa.webmail.maxiscale.com) (72.167.52.135) by k2smtpout01-01.prod.mesa1.secureserver.net (64.202.189.88) with ESMTP; 29 Jul 2009 15:14:44 -0000 X-MimeOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Date: Wed, 29 Jul 2009 08:19:49 -0700 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: Diablo JDK threads implementation Thread-Index: AcoQX0wMTm+02060RNCtUxXAeAY6Aw== From: "Peter Steele" To: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Subject: Diablo JDK threads implementation 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: Wed, 29 Jul 2009 15:21:57 -0000 We've developed a server platform around FreeBSD 7.0 consisting of several applications written in C and one primary application written in Java (JDK 1.6). We're seeing cases in some of ouor stress tests where some threads in our JAVA application appear to get no CPU time for extended periods of time (sometimes over a minute), even though the box has lots of idle time available and all of the C threads are running without a glitch. We thought originally it might be memory related and the GC was kicking in and freezing the JDK. That's not the case though, and in fact the memory footprint of the Java application is very small.=20 =20 I know I've read that some ports of Java do not always use native threads for the JDK thread model. Does anyone know the story with the Diablo JDK port? Is there another explanation what might be causing this problem? =20