From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:42677) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Vsx9w-0008Ae-9L for qemu-devel@nongnu.org; Tue, 17 Dec 2013 11:06:18 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Vsx9q-0006Vh-7v for qemu-devel@nongnu.org; Tue, 17 Dec 2013 11:06:12 -0500 Received: from mx1.redhat.com ([209.132.183.28]:20456) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Vsx9p-0006Vb-UN for qemu-devel@nongnu.org; Tue, 17 Dec 2013 11:06:06 -0500 Received: from int-mx01.intmail.prod.int.phx2.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id rBHG64vt012913 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Tue, 17 Dec 2013 11:06:04 -0500 From: Juan Quintela In-Reply-To: <1387293974-24718-39-git-send-email-quintela@redhat.com> (Juan Quintela's message of "Tue, 17 Dec 2013 16:26:14 +0100") References: <1387293974-24718-1-git-send-email-quintela@redhat.com> <1387293974-24718-39-git-send-email-quintela@redhat.com> Date: Tue, 17 Dec 2013 17:05:47 +0100 Message-ID: <87r49bxy1w.fsf@elfo.mitica> MIME-Version: 1.0 Content-Type: text/plain Subject: Re: [Qemu-devel] [PATCH 38/38] ram: align ram_addr_t's regions in multiples of 64 Reply-To: quintela@redhat.com List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org, Paolo Bonzini Juan Quintela wrote: > This allows us to use fastest path for bitmap operations. > This was based on Paolo idea/code. > > Signed-off-by: Juan Quintela > --- > exec.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/exec.c b/exec.c > index be421e5..faf3f59 100644 > --- a/exec.c > +++ b/exec.c > @@ -1108,7 +1108,7 @@ static ram_addr_t find_ram_offset(ram_addr_t size) > QTAILQ_FOREACH(block, &ram_list.blocks, next) { > ram_addr_t end, next = RAM_ADDR_MAX; > > - end = block->offset + block->length; > + end = ROUND_UP(block->offset + block->length, TARGET_PAGE_SIZE * 64); > > QTAILQ_FOREACH(next_block, &ram_list.blocks, next) { > if (next_block->offset >= end) { NAK This patch is giving me trouble. iht stays at 868kbytes forever, removing this patch makes things work again. Paolo, any idea? will drop it until I found what/where the problem is. Later, Juan. 16:51:10 DEBUG| (monitor hmp1) Response to 'info migrate' 16:51:10 DEBUG| (monitor hmp1) capabilities: xbzrle: off x-rdma-pin-all: off auto-converge: off zero-blocks: off 16:51:10 DEBUG| (monitor hmp1) Migration status: active 16:51:10 DEBUG| (monitor hmp1) total time: 1515704 milliseconds 16:51:10 DEBUG| (monitor hmp1) expected downtime: 30 milliseconds 16:51:10 DEBUG| (monitor hmp1) setup: 6 milliseconds 16:51:10 DEBUG| (monitor hmp1) transferred ram: 5168004 kbytes 16:51:10 DEBUG| (monitor hmp1) throughput: 44.17 mbps 16:51:10 DEBUG| (monitor hmp1) remaining ram: 868 kbytes 16:51:10 DEBUG| (monitor hmp1) total ram: 1065688 kbytes 16:51:10 DEBUG| (monitor hmp1) duplicate: 228523 pages 16:51:10 DEBUG| (monitor hmp1) skipped: 0 pages 16:51:10 DEBUG| (monitor hmp1) normal: 37899 pages 16:51:10 DEBUG| (monitor hmp1) normal bytes: 151596 kbytes 16:51:11 DEBUG| (monitor hmp1) Sending command 'cont' 16:51:11 DEBUG| Send command: cont 16:51:11 DEBUG| Host does not support