From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: arm64: Approach for DT based NUMA and issues Date: Fri, 16 Dec 2016 11:18:28 +0100 Message-ID: <1481883508.3445.441.camel@citrix.com> References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1382344215915539467==" Return-path: Received: from mail6.bemta6.messagelabs.com ([193.109.254.103]) by lists.xenproject.org with esmtp (Exim 4.84_2) (envelope-from ) id 1cHpbC-0002Wu-3g for xen-devel@lists.xenproject.org; Fri, 16 Dec 2016 10:18:46 +0000 In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xen.org Sender: "Xen-devel" To: Julien Grall , Vijay Kilari Cc: Andre Przywara , "prasun.kapoor" , Stefano Stabellini , xen-devel List-Id: xen-devel@lists.xenproject.org --===============1382344215915539467== Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="=-81HV3C4gcAgppoYOXdyf" --=-81HV3C4gcAgppoYOXdyf Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Fri, 2016-12-16 at 09:40 +0000, Julien Grall wrote: > Hi Vijay, > On 16/12/2016 07:39, Vijay Kilari wrote: > > If we drop numa-node-id from memory node generated to dom0, then > > dom0 will > > assume all the memory is from node0. So eventually node1 device > > intialization fails. >=20 > I suggested to drop the property numa-node-id from every node (not > only=C2=A0 > memory one). So DOM0 will think it is running a non-NUMA platform. >=20 > =C2=A0From my knowledge this is working on x86, and I don't understand > why=C2=A0 > this would be an issue on ARM. If you think the device may not work,=C2= =A0 > please explain why. >=20 Yes, I confirm that what you said works and any x86 NUMA system I've seen. AFAIUI, since Vijay is talking about "devices", the x86 equivalent of what would be an "IONUMA system", i.e. a platform where I/O devices are physically attached to more than just one I/O hub, which in turn are attached to different nodes. I don't have first hand experience with these systems on the x86 world, but I'm quite sure they also function with the configuration Julien is suggesting to use. Boris did some work to _improve_ the situation (namely, to make it possible for *Xen* to report to the toolstack, to which NUMA node a specific device is attached to). But: =C2=A0- things were working already before this =C2=A0- that does involve Xen and toolstack, while Dom0 remains totally=C2= =A0 =C2=A0 =C2=A0NUMA _unaware_. And I indeed think that doing what Julien says (i.e., keep dom0 NUMA- ignorant) is, if possible, best as a first step. Regards, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-81HV3C4gcAgppoYOXdyf Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIcBAABCAAGBQJYU792AAoJEBZCeImluHPu/ZcQANscM3kSDnbmE/o4pf79/W31 54Q+okC5tx1N1K06EjPDSemeWleTntf+C1rQRmRmYDvGaSY47V5owqJPBderbcPS CubycwSE2sLPuIWxUKSpkmun+/c59beuvpInB+e4meE97PmTBAl0Q9WZTuLLBCUv Pm/gXTJ9ysM3wbTEJ00jHDImGZsf6kytq3niSDKVh8AhZbBfXDtfOTTWoNpOWKtC p/Qky7jQqTyjRqruAROHgqtEXn1aP2EiI8vyBJhBmU6pkKu8tu++sevpDYtm5nQW K62aabl6oDEvog3KZ5zYLnTQ2Tn5UFMpYc5SZ3ehkXIhAKSQNTzKqkVc+7TwCYe9 u3sxuudXsjkmLvrP7T8ryXPAQixwIpyyhIqFufPh943KB5HySlwcLbK4fn1cXR2t 0Hyqd14qn4HiBdwJ0fDP143zJjKjfuD8U6JEbQSQtR78cb24kdqpI/gK/8Y/81ov A6D6pSDvxQvLDKbOEgAzQAgADy7SSLsOry2NcYe8yGdw7C6OFA2IqWG+kFMfb+O6 nfACfv5qCpwy9IjLfuzpVEiFv3zxLunjK/A6eBv6XTbeoY6ETv/qgUnx7hSgUdR7 Xbj8morfEmSAdmkdQoAVXo1Vh276O5uLN7ZqhlzNKYfSgGTeHvyWdB4xeKiOAF+r NxBpYORDs7j1Ff2aNad2 =HIxv -----END PGP SIGNATURE----- --=-81HV3C4gcAgppoYOXdyf-- --===============1382344215915539467== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KWGVuLWRldmVs IG1haWxpbmcgbGlzdApYZW4tZGV2ZWxAbGlzdHMueGVuLm9yZwpodHRwczovL2xpc3RzLnhlbi5v cmcveGVuLWRldmVsCg== --===============1382344215915539467==--