From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:56531) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bQdW5-0000CM-Ja for qemu-devel@nongnu.org; Fri, 22 Jul 2016 12:41:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bQdW3-0003i6-MN for qemu-devel@nongnu.org; Fri, 22 Jul 2016 12:41:36 -0400 References: <1468516741-82174-1-git-send-email-vsementsov@virtuozzo.com> From: Max Reitz Message-ID: <46037124-db08-b60a-912c-75b81994801b@redhat.com> Date: Fri, 22 Jul 2016 18:41:24 +0200 MIME-Version: 1.0 In-Reply-To: <1468516741-82174-1-git-send-email-vsementsov@virtuozzo.com> Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="hLJlvvi0rrrAma4OxhqOKMoqSV1Bo9gQS" Subject: Re: [Qemu-devel] [PATCH v2] mirror: double performance of the bulk stage if the disc is full List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Vladimir Sementsov-Ogievskiy , qemu-block@nongnu.org, qemu-devel@nongnu.org Cc: stefanha@redhat.com, famz@redhat.com, jcody@redhat.com, eblake@redhat.com, pbonzini@redhat.com, "Denis V. Lunev" , Kevin Wolf This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --hLJlvvi0rrrAma4OxhqOKMoqSV1Bo9gQS From: Max Reitz To: Vladimir Sementsov-Ogievskiy , qemu-block@nongnu.org, qemu-devel@nongnu.org Cc: stefanha@redhat.com, famz@redhat.com, jcody@redhat.com, eblake@redhat.com, pbonzini@redhat.com, "Denis V. Lunev" , Kevin Wolf Message-ID: <46037124-db08-b60a-912c-75b81994801b@redhat.com> Subject: Re: [PATCH v2] mirror: double performance of the bulk stage if the disc is full References: <1468516741-82174-1-git-send-email-vsementsov@virtuozzo.com> In-Reply-To: <1468516741-82174-1-git-send-email-vsementsov@virtuozzo.com> Content-Type: text/plain; charset=iso-8859-15 Content-Transfer-Encoding: quoted-printable On 14.07.2016 19:19, Vladimir Sementsov-Ogievskiy wrote: > Mirror can do up to 16 in-flight requests, but actually on full copy > (the whole source disk is non-zero) in-flight is always 1. This happens= > as the request is not limited in size: the data occupies maximum availa= ble > capacity of s->buf. >=20 > The patch limits the size of the request to some artificial constant > (1 Mb here), which is not that big or small. This effectively enables > back parallelism in mirror code as it was designed. >=20 > The result is important: the time to migrate 10 Gb disk is reduced from= > ~350 sec to 170 sec. >=20 > Signed-off-by: Vladimir Sementsov-Ogievskiy > Signed-off-by: Denis V. Lunev > CC: Stefan Hajnoczi > CC: Fam Zheng > CC: Kevin Wolf > CC: Max Reitz > CC: Jeff Cody > CC: Eric Blake > --- >=20 > v2: in case of s->buf_size larger than default use it to limit io_secto= rs >=20 > block/mirror.c | 10 ++++++++-- > 1 file changed, 8 insertions(+), 2 deletions(-) Reviewed-by: Max Reitz I think that this can be considered a bugfix, but strictly speaking it's a patch for Jeff's tree, so I'm hesitant to take it. Max --hLJlvvi0rrrAma4OxhqOKMoqSV1Bo9gQS 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 iQEvBAEBCAAZBQJXkky1EhxtcmVpdHpAcmVkaGF0LmNvbQAKCRA7sUIC6Disreaa CACKBRUIsSxFNXsObvUbTk35Ghv5FNH+pdVy8nqg+fNJK6VrRCVETjBnnJftH922 aI+GTTKOk17b7Y4QRF+BTGafpIhMTMZgn8yvQk28maKAO/yyWfenAPE9HIhaKwCj n7i77TmxJIA0SHzEBHdOetYJVnUbg4frX6CwTClPv5vea2IW9PNT/5w65cEO/1R+ vXefFxOkK00jH7aZl+/+VODA5l8s6kgIk+uxk4gCO4pLiX2KS9M+TF+9LU27k7o3 Bgn24Hg/hbBPCgnryxl/H7t80vS3ySqDrPoniwf2v+FTpaI7JAUDBV70ii3f5Rl5 YRW9hKPazpdFbOjCT49v84Ak =8jPT -----END PGP SIGNATURE----- --hLJlvvi0rrrAma4OxhqOKMoqSV1Bo9gQS--