From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:35906) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bD14H-0001hy-CY for qemu-devel@nongnu.org; Tue, 14 Jun 2016 23:00:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bD14E-0002wO-Vm for qemu-devel@nongnu.org; Tue, 14 Jun 2016 23:00:36 -0400 References: <1465917916-22348-1-git-send-email-den@openvz.org> <1465917916-22348-5-git-send-email-den@openvz.org> From: Eric Blake Message-ID: <5760C4CB.6080703@redhat.com> Date: Tue, 14 Jun 2016 21:00:27 -0600 MIME-Version: 1.0 In-Reply-To: <1465917916-22348-5-git-send-email-den@openvz.org> Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="NP3XBdjuHu3fIU97HxuJlDGOKHDTSwqSg" Subject: Re: [Qemu-devel] [PATCH 4/9] mirror: efficiently zero out target List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Denis V. Lunev" , qemu-devel@nongnu.org, qemu-block@nongnu.org Cc: vsementsov@virtuozzo.com, Stefan Hajnoczi , Fam Zheng , Kevin Wolf , Max Reitz , Jeff Cody This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --NP3XBdjuHu3fIU97HxuJlDGOKHDTSwqSg Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable On 06/14/2016 09:25 AM, Denis V. Lunev wrote: > With a bdrv_co_write_zeroes method on a target BDS zeroes will not be p= laced > into the wire. Thus the target could be very efficiently zeroed out. Th= is > is should be done with the largest chunk possible. >=20 > This improves the performance of the live migration of the empty disk b= y > 150 times if NBD supports write_zeroes. >=20 > Signed-off-by: Denis V. Lunev > Reviewed-by: Vladimir Sementsov-Ogievskiy > CC: Stefan Hajnoczi > CC: Fam Zheng > CC: Kevin Wolf > CC: Max Reitz > CC: Jeff Cody > CC: Eric Blake > --- > block/mirror.c | 32 +++++++++++++++++++++++++++++++- > 1 file changed, 31 insertions(+), 1 deletion(-) >=20 > diff --git a/block/mirror.c b/block/mirror.c > index c7b3639..c2f8773 100644 > --- a/block/mirror.c > +++ b/block/mirror.c > @@ -21,6 +21,7 @@ > #include "qemu/ratelimit.h" > #include "qemu/bitmap.h" > =20 > +#define MIRROR_ZERO_CHUNK (3u << (29 - BDRV_SECTOR_BITS)) /* 1.= 5 Gb */ Probably nicer to track this in bytes. And do you really want a hard-coded arbitrary limit, or is it better to live with MIN_NON_ZERO(target_bs->bl.max_pwrite_zeroes, INT_MAX)? > @@ -512,7 +513,8 @@ static int mirror_dirty_init(MirrorBlockJob *s) > =20 > end =3D s->bdev_length / BDRV_SECTOR_SIZE; > =20 > - if (base =3D=3D NULL && !bdrv_has_zero_init(target_bs)) { > + if (base =3D=3D NULL && !bdrv_has_zero_init(target_bs) && > + target_bs->drv->bdrv_co_write_zeroes =3D=3D NULL) { Indentation is off, although if checkpatch.pl doesn't complain I guess it doesn't matter that much. Why should you care whether the target_bs->drv implements a callback? Can't you just rely on the normal bdrv_*() functions to do the dirty work of picking the most efficient implementation without you having to bypass the block layer? In fact, isn't that the whole goal of bdrv_make_zero() - why not call that instead of reimplementing it? Patch needs rebasing - we've redone this into bdrv_co_pwrite_zeroes and a byte interface, since upstream commit c1499a5e. > bdrv_set_dirty_bitmap(s->dirty_bitmap, 0, end); > return 0; > } > @@ -546,6 +548,34 @@ static int mirror_dirty_init(MirrorBlockJob *s) > } > sector_num +=3D n; > } > + > + if (base !=3D NULL || bdrv_has_zero_init(target_bs)) { You're now repeating the conditional that used to be 'bool mark_all_dirty' (well, this is !mark_all_dirty); is it worth keeping the simpler bool around? > + /* no need to zero out entire disk */ > + return 0; > + } > + > + for (sector_num =3D 0; sector_num < end; ) { > + int nb_sectors =3D MIN(MIRROR_ZERO_CHUNK, end - sector_num); Why limit yourself to 1.5G? It's either too small for what you can really do, or too large for what the device permits. See my above comment about MIN_NON_ZERO. > + int64_t now =3D qemu_clock_get_ns(QEMU_CLOCK_REALTIME); > + > + if (now - last_pause_ns > SLICE_TIME) { > + last_pause_ns =3D now; > + block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, 0); > + } > + > + if (block_job_is_cancelled(&s->common)) { > + return -EINTR; > + } > + > + if (s->in_flight =3D=3D MAX_IN_FLIGHT) { > + trace_mirror_yield(s, s->in_flight, s->buf_free_count, -1)= ; > + mirror_wait_for_io(s); > + continue; > + } Hmm - I guess your mirror yield points are why you couldn't just directly use bdrv_make_zero(); but is that something where some code refactoring can share more code rather than duplicating it? > + > + mirror_do_zero_or_discard(s, sector_num, nb_sectors, false); > + sector_num +=3D nb_sectors; > + } > return 0; > } > =20 >=20 --=20 Eric Blake eblake redhat com +1-919-301-3266 Libvirt virtualization library http://libvirt.org --NP3XBdjuHu3fIU97HxuJlDGOKHDTSwqSg Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 Comment: Public key at http://people.redhat.com/eblake/eblake.gpg Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iQEcBAEBCAAGBQJXYMTLAAoJEKeha0olJ0NqaA4H/A3Lo1RVXvDm7FNxxrb1+iPK n+kfEnTvH9ntL5XV3V9pGqR/N2tgw0OsjMRAC2E+3z9scnrC8zHJZKIlajH4S5oR kYNW2XHXw0ipW4sLwfnXP33mdosM4plGAqNS4ZMw4VYT2VtqhxFXKpezc3uFtfUu BsbyAV4VZj7Dhu2jH9UocxpAkKH++ESV6YDZ5VNycb4E+ZDfH3bt3xcff4o2RE6z t6ZckJxTraczxYEfI+crR7GzP2y10WB/JqYFMSf3eNJYmHmiI5l0pEGg7Px+deU4 sXJtpWFoWl+9wGkn2HbIwQn2O60WWTe9NgPenYvR2rkzGqYcAA3E82HzBlCPKNY= =Tb0E -----END PGP SIGNATURE----- --NP3XBdjuHu3fIU97HxuJlDGOKHDTSwqSg--