From owner-freebsd-java@FreeBSD.ORG  Mon Sep 17 02:34:10 2007
Return-Path: <owner-freebsd-java@FreeBSD.ORG>
Delivered-To: java@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id D875D16A417;
	Mon, 17 Sep 2007 02:34:10 +0000 (UTC)
	(envelope-from davidxu@freebsd.org)
Received: from freefall.freebsd.org (freefall.freebsd.org
	[IPv6:2001:4f8:fff6::28])
	by mx1.freebsd.org (Postfix) with ESMTP id C6F3B13C457;
	Mon, 17 Sep 2007 02:34:10 +0000 (UTC)
	(envelope-from davidxu@freebsd.org)
Received: from [127.0.0.1] (root@localhost [127.0.0.1])
	by freefall.freebsd.org (8.14.1/8.14.1) with ESMTP id l8H2Y77C017951;
	Mon, 17 Sep 2007 02:34:08 GMT (envelope-from davidxu@freebsd.org)
Message-ID: <46EDE7CF.8060100@freebsd.org>
Date: Mon, 17 Sep 2007 10:34:55 +0800
From: David Xu <davidxu@freebsd.org>
User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.13) Gecko/20070516
X-Accept-Language: en-us, en
MIME-Version: 1.0
To: Kris Kennaway <kris@freebsd.org>
References: <46EC1B55.4060202@FreeBSD.org>
In-Reply-To: <46EC1B55.4060202@FreeBSD.org>
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Transfer-Encoding: 7bit
Cc: java@freebsd.org, performance@freebsd.org
Subject: Re: Massive performance loss from OS::sleep hack
X-BeenThere: freebsd-java@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Porting Java to FreeBSD <freebsd-java.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-java>,
	<mailto:freebsd-java-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-java>
List-Post: <mailto:freebsd-java@freebsd.org>
List-Help: <mailto:freebsd-java-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-java>,
	<mailto:freebsd-java-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Mon, 17 Sep 2007 02:34:11 -0000

Kris Kennaway wrote:
> Hi,
> 
> I have been running the volano java benchmark 
> (http://www.volano.com/benchmarks.html) on an 8-core i386 system, and 
> out of the box jdk15 on FreeBSD performs extremely poorly.  The system 
> is more than 90% idle, and profiling shows that the ~800 threads in the 
> benchmark are spending most of their time doing short nanosleep() calls.
> 
> 
> I traced it to the following FreeBSD-specific hack in the jdk:
> 
> // XXXBSD: understand meaning and workaround related to yield
> ...
> // XXXBSD: done differently in 1.3.1, take a look
> int os::sleep(Thread* thread, jlong millis, bool interruptible) {
>   assert(thread == Thread::current(),  "thread consistency check");
> ...
> 
>   if (millis <= 0) {
>     // NOTE: workaround for bug 4338139
>     if (thread->is_Java_thread()) {
>       ThreadBlockInVM tbivm((JavaThread*) thread);
> // BSDXXX: Only use pthread_yield here and below if the system thread
> // scheduler gives time slices to lower priority threads when yielding.
> #ifdef __FreeBSD__
>       os_sleep(MinSleepInterval, interruptible);
> #else
>       pthread_yield();
> #endif
> 
> When I removed this hack (i.e. revert to pthread_yield()) I got an 
> immediate 7-fold performance increase, which brings FreeBSD performance 
> on par with Solaris.
> 
> What is the reason why this code is necessary?  Does FreeBSD's 
> sched_yield() really have different semantics to the other operating 
> systems, or was this a libkse bug that was being worked around?
> 
> Kris

Yeah, our sched_yield() really works well, in kernel, if the thread
scheduling policy is SCHED_OTHER (time-sharing), scheduler temporarily
lowers its priority to PRI_MAX_TIMESHARE, it is enough to give some CPU
time to other threads. Why doesn't the UNIX time-sharing work for java ?

Regards,
David Xu