From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:35516) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Um4nZ-0007hE-PH for qemu-devel@nongnu.org; Mon, 10 Jun 2013 12:18:27 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Um4nX-0004gk-Lk for qemu-devel@nongnu.org; Mon, 10 Jun 2013 12:18:25 -0400 Sender: fluxion Date: Mon, 10 Jun 2013 11:17:13 -0500 From: mdroth Message-ID: <20130610161713.GA24919@vm> References: <1370859260-8183-1-git-send-email-pl@kamp.de> <1370859260-8183-3-git-send-email-pl@kamp.de> <20130610161029.GB5727@vm> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130610161029.GB5727@vm> Subject: Re: [Qemu-devel] [PATCHv2 2/2] migration: do not overwrite zero pages List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Lieven Cc: quintela@redhat.com, aik@ozlabs.ru, qemu-devel@nongnu.org, qemu-stable@nongnu.org, owasserm@redhat.com, pbonzini@redhat.com, xiawenc@linux.vnet.ibm.com, david@gibson.dropbear.id.au On Mon, Jun 10, 2013 at 11:10:29AM -0500, mdroth wrote: > On Mon, Jun 10, 2013 at 12:14:20PM +0200, Peter Lieven wrote: > > on incoming migration do not memset pages to zero if they already read as zero. > > this will allocate a new zero page and consume memory unnecessarily. even > > if we madvise a MADV_DONTNEED later this will only deallocate the memory > > asynchronously. > > > > Signed-off-by: Peter Lieven > > --- > > arch_init.c | 14 ++++++++------ > > 1 file changed, 8 insertions(+), 6 deletions(-) > > > > diff --git a/arch_init.c b/arch_init.c > > index 08fccf6..cf4e1d5 100644 > > --- a/arch_init.c > > +++ b/arch_init.c > > @@ -832,14 +832,16 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) > > } > > > > ch = qemu_get_byte(f); > > - memset(host, ch, TARGET_PAGE_SIZE); > > + if (ch != 0 || !is_zero_page(host)) { > > + memset(host, ch, TARGET_PAGE_SIZE); > > #ifndef _WIN32 > > - if (ch == 0 && > > - (!kvm_enabled() || kvm_has_sync_mmu()) && > > - getpagesize() <= TARGET_PAGE_SIZE) { > > - qemu_madvise(host, TARGET_PAGE_SIZE, QEMU_MADV_DONTNEED); > > - } > > + if (ch == 0 && > > + (!kvm_enabled() || kvm_has_sync_mmu()) && > > + getpagesize() <= TARGET_PAGE_SIZE) { > > + qemu_madvise(host, TARGET_PAGE_SIZE, QEMU_MADV_DONTNEED); > > + } > > Reviewed-by: Michael Roth > > Also CC'ing qemu-stable, but from what I gather this just mitigates the *actually* CC'ing qemu-stable this time :)