From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:47286) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cVbz5-0007CJ-4s for qemu-devel@nongnu.org; Mon, 23 Jan 2017 05:36:23 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cVbz4-0007z1-Cm for qemu-devel@nongnu.org; Mon, 23 Jan 2017 05:36:23 -0500 Received: from mail-wm0-x244.google.com ([2a00:1450:400c:c09::244]:35003) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1cVbz4-0007yw-6T for qemu-devel@nongnu.org; Mon, 23 Jan 2017 05:36:22 -0500 Received: by mail-wm0-x244.google.com with SMTP id d140so25420429wmd.2 for ; Mon, 23 Jan 2017 02:36:22 -0800 (PST) Date: Mon, 23 Jan 2017 10:36:18 +0000 From: Stefan Hajnoczi Message-ID: <20170123103618.GF29186@stefanha-x1.localdomain> References: <20170113131731.1246-1-pbonzini@redhat.com> <20170118160315.GS30347@stefanha-x1.localdomain> <08705645-17e8-1ffa-4199-c962f7198ab3@redhat.com> <20170119170128.GD27032@stefanha-x1.localdomain> <0969c169-772e-d213-675a-30aee616f8a8@redhat.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="8JPrznbw0YAQ/KXy" Content-Disposition: inline In-Reply-To: <0969c169-772e-d213-675a-30aee616f8a8@redhat.com> Subject: Re: [Qemu-devel] [PATCH 00/16] aio_context_acquire/release pushdown, part 2 List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Paolo Bonzini Cc: Stefan Hajnoczi , famz@redhat.com, qemu-devel@nongnu.org --8JPrznbw0YAQ/KXy Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Jan 20, 2017 at 05:39:40PM +0100, Paolo Bonzini wrote: >=20 >=20 > On 19/01/2017 18:01, Stefan Hajnoczi wrote: > >>> This is a big and somewhat risky change. Have you run any performance > >>> benchmarks? > >> > >> Not recently; I ran them a year ago and there was no measurable differ= ence. > >=20 > > Good, please re-run for the final version. >=20 > Done, went better than expected. :) >=20 > base > 4k-1 null READ: io=3D6646.8MB, aggrb=3D226852KB/s, minb=3D226852KB/s, m= axb=3D226852KB/s, mint=3D30000msec, maxt=3D30000msec > 4k-1 nvme READ: io=3D3086.4MB, aggrb=3D105342KB/s, minb=3D105342KB/s, m= axb=3D105342KB/s, mint=3D30001msec, maxt=3D30001msec > 4k-32 nvme READ: io=3D14246MB, aggrb=3D486241KB/s, minb=3D486241KB/s, ma= xb=3D486241KB/s, mint=3D30001msec, maxt=3D30001msec >=20 > patched: > 4k-1 null READ: io=3D7044.5MB, aggrb=3D240436KB/s, minb=3D240436KB/s, m= axb=3D240436KB/s, mint=3D30000msec, maxt=3D30000msec > 4k-1 nvme READ: io=3D3463.3MB, aggrb=3D118208KB/s, minb=3D118208KB/s, m= axb=3D118208KB/s, mint=3D30001msec, maxt=3D30001msec > 4k-32 nvme READ: io=3D15217MB, aggrb=3D519378KB/s, minb=3D519378KB/s, ma= xb=3D519378KB/s, mint=3D30001msec, maxt=3D30001msec >=20 > null is null-co://, nvme is a fast (180kIOPS on bare-metal) NVMe SSD. >=20 > So it seems to be some 5-10% faster. No idea why so I would not give too > much importance on the numbers, but at least it's not worse. Nice, thank you! Stefan --8JPrznbw0YAQ/KXy Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iQEcBAEBAgAGBQJYhdyiAAoJEJykq7OBq3PIEMMIAL7c/kwIftq3eY5XcHi3mXFu v4cGuWDO9rpSr66mUpBTJxaYq83Q4ygJghElMtmedZ5LQc4paY5sMP/D64wHomjC YlKgW6QPRgRlr/Vd+Nmjf9Z+cBRYxblFwDnAS19c63f4VAbOaXdGrEbeFQWpInhl pGcBUp5xeXe0JSNeabJP1YqtjsGTQK9hj0AdaEXv/Lk7ywvsMV/Y2QOxSbEbaGjC qEI6a/am/MzzITgVXafO0bkhNEINmGsutTUe5i8bokoMWO70173AdL1YB2BGfA2/ PmDN3qvkT4NZYsUeDvdFbAlp6UB/dA4n5uKkKJPLXGid7V5oN1DmN6lShUR/S5Y= =+3bt -----END PGP SIGNATURE----- --8JPrznbw0YAQ/KXy--