From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:45961) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZUtSS-0004UG-Oz for qemu-devel@nongnu.org; Thu, 27 Aug 2015 05:26:57 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ZUtSP-0004S5-EG for qemu-devel@nongnu.org; Thu, 27 Aug 2015 05:26:56 -0400 Received: from mx-v6.kamp.de ([2a02:248:0:51::16]:53995 helo=mx01.kamp.de) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZUtSP-0004QB-2n for qemu-devel@nongnu.org; Thu, 27 Aug 2015 05:26:53 -0400 From: Peter Lieven Message-ID: <55DED7D1.3020101@kamp.de> Date: Thu, 27 Aug 2015 11:26:41 +0200 MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Subject: [Qemu-devel] coroutine pool memory usage List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu block , "qemu-devel@nongnu.org" Cc: Kevin Wolf , Paolo Bonzini , Stefan Hajnoczi Hi, i was debugging increased memory footprint of qemu over the past time and found that the coroutine pool heap usage can grow up to 70MB by just booting an Ubuntu Live CD. And those 70MB are never freed. Is this expected? Wouldn't it make sense to asynchronically throw some coroutines (or at least their stack) away if there is no I/O? Does anyone have a pointer to benchmarks of coroutine performance for NAS (iSCSI / NFS) with and without freelist? I would think that it only has significant impact for local (SSD) storage? Thanks, Peter