From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:38921) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yx7oI-0006Nq-Dn for qemu-devel@nongnu.org; Tue, 26 May 2015 01:53:55 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Yx7oF-0003N2-0w for qemu-devel@nongnu.org; Tue, 26 May 2015 01:53:54 -0400 Received: from mx-v6.kamp.de ([2a02:248:0:51::16]:53889 helo=mx01.kamp.de) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yx7oE-0003MZ-Mk for qemu-devel@nongnu.org; Tue, 26 May 2015 01:53:50 -0400 Message-ID: <55640A63.4040809@kamp.de> Date: Tue, 26 May 2015 07:53:39 +0200 From: Peter Lieven MIME-Version: 1.0 References: <1432611383-3779-1-git-send-email-famz@redhat.com> <1432611383-3779-4-git-send-email-famz@redhat.com> In-Reply-To: <1432611383-3779-4-git-send-email-famz@redhat.com> Content-Type: text/plain; charset=iso-8859-15; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [Qemu-stable] [PATCH v5 3/8] mirror: Do zero write on target if sectors not allocated List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Fam Zheng , qemu-devel@nongnu.org Cc: Kevin Wolf , qemu-block@nongnu.org, jsnow@redhat.com, Jeff Cody , qemu-stable@nongnu.org, Stefan Hajnoczi , pbonzini@redhat.com, wangxiaolong@ucloud.cn Am 26.05.2015 um 05:36 schrieb Fam Zheng: > If guest discards a source cluster, mirroring with bdrv_aio_readv is overkill. > Some protocols do zero upon discard, where it's best to use > bdrv_aio_write_zeroes, otherwise, bdrv_aio_discard will be enough. > > Signed-off-by: Fam Zheng > --- > block/mirror.c | 20 ++++++++++++++++++-- > 1 file changed, 18 insertions(+), 2 deletions(-) > > diff --git a/block/mirror.c b/block/mirror.c > index 85995b2..ba33254 100644 > --- a/block/mirror.c > +++ b/block/mirror.c > @@ -164,6 +164,8 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) > int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector; > uint64_t delay_ns = 0; > MirrorOp *op; > + int pnum; > + int64_t ret; > > s->sector_num = hbitmap_iter_next(&s->hbi); > if (s->sector_num < 0) { > @@ -290,8 +292,22 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) > s->in_flight++; > s->sectors_in_flight += nb_sectors; > trace_mirror_one_iteration(s, sector_num, nb_sectors); > - bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors, > - mirror_read_complete, op); > + > + ret = bdrv_get_block_status_above(source, NULL, sector_num, > + nb_sectors, &pnum); > + if (ret < 0 || pnum < nb_sectors || > + (ret & BDRV_BLOCK_DATA && !(ret & BDRV_BLOCK_ZERO))) { > + bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors, > + mirror_read_complete, op); > + } else if (ret & BDRV_BLOCK_ZERO) { > + bdrv_aio_write_zeroes(s->target, sector_num, op->nb_sectors, > + s->unmap ? BDRV_REQ_MAY_UNMAP : 0, > + mirror_write_complete, op); > + } else { > + assert(!(ret & BDRV_BLOCK_DATA)); > + bdrv_aio_discard(s->target, sector_num, op->nb_sectors, > + mirror_write_complete, op); > + } I wonder what happens if on the destination the discard is a NOP which is legal (at least in SCSI). In this case we might end up having different contents and source and destination. Or is this not a problem? Peter