From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1MQhg7-0002PJ-3Q for qemu-devel@nongnu.org; Tue, 14 Jul 2009 09:04:15 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1MQhg2-0002NH-Ih for qemu-devel@nongnu.org; Tue, 14 Jul 2009 09:04:14 -0400 Received: from [199.232.76.173] (port=37415 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1MQhg2-0002NC-4K for qemu-devel@nongnu.org; Tue, 14 Jul 2009 09:04:10 -0400 Received: from mow300.securemx.jp ([210.130.202.48]:35660 helo=mow.securemx.jp) by monty-python.gnu.org with esmtps (TLS-1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.60) (envelope-from ) id 1MQhg0-00071Q-N3 for qemu-devel@nongnu.org; Tue, 14 Jul 2009 09:04:09 -0400 Received: from [192.168.128.141] (xdsl-205-43.nblnetworks.fi [83.145.205.43]) by smtp.securemx.jp (mx-mbox300) id n6ED3xtW001080 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT) for ; Tue, 14 Jul 2009 22:04:03 +0900 Message-ID: <4A5C8239.2060509@acrodea.co.jp> Date: Tue, 14 Jul 2009 16:03:53 +0300 From: Timo Suoranta MIME-Version: 1.0 Subject: Re: [Qemu-devel] ARM multithreading status References: <3646AB84-79BE-4327-A732-57661E3C8919@acrodea.co.jp> <94a0d4530907091440i65d16776vc1b575f9c5a8d454@mail.gmail.com> <4A56EF1B.8010803@acrodea.co.jp> <4A5C402F.6060209@acrodea.co.jp> In-Reply-To: <4A5C402F.6060209@acrodea.co.jp> Content-Type: text/plain; charset=ISO-2022-JP Content-Transfer-Encoding: 7bit List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Qemu-devel Some additional information: - Using clone() instead of pthreads results similar behavior. - Running simple main(){ for(;;){}; } application inside QEMU ARM Linux effectively blocks a lot of stuff, like ls (unless cached). Timo Suoranta wrote: > Using qemu-system-arm, pthread_create() does not seem to return if I > give it function which simply has empty infinite loop. Is that supposed > to work? I used this: > > http://people.debian.org/~aurel32/qemu/armel/ > > Funny thing is, such test actually works fine if I run it through GDB. > No need to step, just run. I've attached my test code below as it is not > very long. > > Any ideas? To me it looks like scheduler is not preempting :/ > Thanks! ... -- timo