From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH] qemu-kvm: Speed up of the dirty-bitmap-traveling Date: Wed, 10 Feb 2010 12:24:30 +0200 Message-ID: <4B72895E.7050006@redhat.com> References: <4B6BF06D.1090909@lab.ntt.co.jp> <4B70065B.1010401@redhat.com> <4B7130E9.7060809@lab.ntt.co.jp> <4B713839.30301@redhat.com> <4B7282A5.7090500@lab.ntt.co.jp> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-2022-JP Content-Transfer-Encoding: 7bit Cc: kvm@vger.kernel.org, qemu-devel@nongnu.org, mtosatti@redhat.com To: OHMURA Kei Return-path: Received: from mx1.redhat.com ([209.132.183.28]:18568 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754033Ab0BJKYl (ORCPT ); Wed, 10 Feb 2010 05:24:41 -0500 In-Reply-To: <4B7282A5.7090500@lab.ntt.co.jp> Sender: kvm-owner@vger.kernel.org List-ID: On 02/10/2010 11:55 AM, OHMURA Kei wrote: > >> Instead of using a nested loop if bitmap_ul[i] != 0, it is possible to >> use just a single loop (while (c> 0)), and process a long's worth of data. >> >> The only trickery is with big endian hosts, where the conversion from >> bit number to page number is a bit complicated. >> > To convert the bitmap from big endian to little endian, le_bswap macro in > bswap.h seems useful, which is now undefined. What do you think about this > approach? > > This is an example bitmap-traveling code using le_bswap: > /* > * bitmap-traveling is faster than memory-traveling (for addr...) > * especially when most of the memory is not dirty. > */ > for (i = 0; i < len; i++) { > if (bitmap_ul[i] != 0) { > c = le_bswap(bitmap_ul[i], HOST_LONG_BITS); > while (c > 0) { > j = ffsl(c) - 1; > c &= ~(1ul << j); > page_number = i * HOST_LONG_BITS + j; > addr1 = page_number * TARGET_PAGE_SIZE; > addr = offset + addr1; > ram_addr = cpu_get_physical_page_desc(addr); > cpu_physical_memory_set_dirty(ram_addr); > } > } > } > Yes, that solves the problem very neatly. -- error compiling committee.c: too many arguments to function