From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:51344) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UcwtD-00011H-Hy for qemu-devel@nongnu.org; Thu, 16 May 2013 08:02:33 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Ucwt9-0000W6-0p for qemu-devel@nongnu.org; Thu, 16 May 2013 08:02:31 -0400 Received: from mx1.redhat.com ([209.132.183.28]:38642) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Ucwt8-0000W2-Px for qemu-devel@nongnu.org; Thu, 16 May 2013 08:02:26 -0400 Message-ID: <5194CAC3.9040908@redhat.com> Date: Thu, 16 May 2013 14:02:11 +0200 From: Paolo Bonzini MIME-Version: 1.0 References: <5194ABFD.8040200@cn.fujitsu.com> In-Reply-To: <5194ABFD.8040200@cn.fujitsu.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] QEMU NUMA and memory allocation problem List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: gaowanlong@cn.fujitsu.com Cc: qemu-devel , ehabkost@redhat.com Il 16/05/2013 11:50, Wanlong Gao ha scritto: > To see that this 300M memory is allocated from host node0 again, but not host node1 as > I expected. > > We think that QEMU can't handled this numa memory allocation well, and it will cause the > cross node memory access performance regression. > > Any thoughts? Or, am I missing something? Pinning memory to host NUMA nodes is not implemented. Something like AutoNUMA would be able to balance the memory the right way. Paolo