From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:34715) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1c6KrO-0003zQ-5a for qemu-devel@nongnu.org; Mon, 14 Nov 2016 12:15:59 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1c6KrK-0001Dx-2W for qemu-devel@nongnu.org; Mon, 14 Nov 2016 12:15:58 -0500 Received: from mx1.redhat.com ([209.132.183.28]:47586) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1c6KrJ-0001Dm-Ra for qemu-devel@nongnu.org; Mon, 14 Nov 2016 12:15:54 -0500 References: <1478711602-12620-1-git-send-email-stefanha@redhat.com> <5826231D.7070208@redhat.com> <20161114152642.GE26198@stefanha-x1.localdomain> <90b5f81f-eab0-72dc-63b8-143477cb5286@redhat.com> <20161114170611.GE1352@stefanha-x1.localdomain> From: Paolo Bonzini Message-ID: Date: Mon, 14 Nov 2016 18:15:46 +0100 MIME-Version: 1.0 In-Reply-To: <20161114170611.GE1352@stefanha-x1.localdomain> Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="X33IRcJOqcTPccG6l5BlPBAnMCW3S0Apk" Subject: Re: [Qemu-devel] [RFC 0/3] aio: experimental virtio-blk polling mode List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Stefan Hajnoczi Cc: Karl Rister , Stefan Hajnoczi , qemu-devel@nongnu.org, Andrew Theurer , Fam Zheng This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --X33IRcJOqcTPccG6l5BlPBAnMCW3S0Apk From: Paolo Bonzini To: Stefan Hajnoczi Cc: Karl Rister , Stefan Hajnoczi , qemu-devel@nongnu.org, Andrew Theurer , Fam Zheng Message-ID: Subject: Re: [Qemu-devel] [RFC 0/3] aio: experimental virtio-blk polling mode References: <1478711602-12620-1-git-send-email-stefanha@redhat.com> <5826231D.7070208@redhat.com> <20161114152642.GE26198@stefanha-x1.localdomain> <90b5f81f-eab0-72dc-63b8-143477cb5286@redhat.com> <20161114170611.GE1352@stefanha-x1.localdomain> In-Reply-To: <20161114170611.GE1352@stefanha-x1.localdomain> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable On 14/11/2016 18:06, Stefan Hajnoczi wrote: >>> > > Very interesting that QEMU_AIO_POLL_MAX_NS=3D1 performs so well w= ithout >>> > > much CPU overhead. >> >=20 >> > That basically means "avoid a syscall if you already know there's >> > something to do", so in retrospect it's not that surprising. Still >> > interesting though, and it means that the feature is useful even if = you >> > don't have CPU to waste. > Can you spell out which syscall you mean? Reading the ioeventfd? I mean ppoll. If ppoll succeeds without ever going to sleep, you can achieve the same result with QEMU_AIO_POLL_MAX_NS=3D1, but cheaper. Paolo > The benchmark uses virtio-blk dataplane and iodepth=3D1 so there should= n't > be much IOThread event loop activity besides the single I/O request. >=20 > The reason this puzzles me is that I wouldn't expect poll to succeed > with QEMU_AIO_POLL_MAX_NS and iodepth=3D1. --X33IRcJOqcTPccG6l5BlPBAnMCW3S0Apk 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 iQEcBAEBCAAGBQJYKfFCAAoJEL/70l94x66DEkEH/37zz8D41oISurfo8BsHjmcV HYXnLVBtso1i49l8yR7mwPsBMP67HzGMTp/JgOlOsApnrwTAE1O4JZpB0riEZ1bn oBYi55UlovcaI/QWzdirBWSIwo4Rz7taR3dpQOQpIPlHjBrIJhCwdQ7a8r1kuc3w WMfTOlPuGHSpmwhndD7iGbB0ZrLvqxAjdxcDb2WLf/zibj9/G4l8JAh6go+vqef3 +a/vi3GblwdIQhbi+7fAASvH3c6fXWs93e84Pw9GnOoibZMzAGFw4hk4FSEukBjn KBHMsRYzCKwqSE6rvkoFCLG+xZXjh5c0JALpP5Uh6hQt/C4cisd51zCQwg4yDT8= =mM9x -----END PGP SIGNATURE----- --X33IRcJOqcTPccG6l5BlPBAnMCW3S0Apk--