From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alex Williamson Subject: Can't boot guest with more than 3585MB when using large pages Date: Tue, 24 Mar 2009 15:06:46 -0600 Message-ID: <1237928806.6124.39.camel@bling> Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit To: kvm-devel Return-path: Received: from g1t0027.austin.hp.com ([15.216.28.34]:6118 "EHLO g1t0027.austin.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750976AbZCXVGx (ORCPT ); Tue, 24 Mar 2009 17:06:53 -0400 Received: from g4t0009.houston.hp.com (g4t0009.houston.hp.com [16.234.32.26]) by g1t0027.austin.hp.com (Postfix) with ESMTP id 81A883827A for ; Tue, 24 Mar 2009 21:06:52 +0000 (UTC) Received: from ldl.fc.hp.com (ldl.fc.hp.com [15.11.146.30]) by g4t0009.houston.hp.com (Postfix) with ESMTP id 6A646C039 for ; Tue, 24 Mar 2009 21:06:52 +0000 (UTC) Received: from localhost (ldl.fc.hp.com [127.0.0.1]) by ldl.fc.hp.com (Postfix) with ESMTP id 1170B39C07B for ; Tue, 24 Mar 2009 15:06:52 -0600 (MDT) Received: from ldl.fc.hp.com ([127.0.0.1]) by localhost (ldl.fc.hp.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id rLXd87XdqOAq for ; Tue, 24 Mar 2009 15:06:49 -0600 (MDT) Received: from [192.168.1.60] (g3t0027.americas.hpqcorp.net [16.232.34.131]) by ldl.fc.hp.com (Postfix) with ESMTP id 42A9B39C07A for ; Tue, 24 Mar 2009 15:06:49 -0600 (MDT) Sender: kvm-owner@vger.kernel.org List-ID: On a 2.6.29, x86_64 host/guest, what's special about specifying a guest size of -m 3586 when using -mem-path backed by hugetlbfs? 3585 works, 3586 hangs here: ... PCI-DMA: Using software bounce buffering for IO (SWIOTLB) Placing 64MB software IO TLB between ffff880020000000 - ffff880024000000 software IO TLB at phys 0x20000000 - 0x24000000 Memory: 3504832k/4196352k available (2926k kernel code, 524740k absent, 166780k reserved, 1260k data, 496k init) I can back -mem-path by tmpfs or disk and it works fine. Also works with no -mem-path, but it would obviously be nice to benefit from large pages on big guests. The system has plenty of huge pages to back the request, and booting with -mem-prealloc makes no difference. Tested on latest git as of today. Thanks, Alex