From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751317AbeFDUF6 (ORCPT ); Mon, 4 Jun 2018 16:05:58 -0400 Received: from shelob.surriel.com ([96.67.55.147]:53898 "EHLO shelob.surriel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751091AbeFDUF5 (ORCPT ); Mon, 4 Jun 2018 16:05:57 -0400 Message-ID: <1528142755.7898.122.camel@surriel.com> Subject: Re: [PATCH 16/19] sched/numa: Detect if node actively handling migration From: Rik van Riel To: Srikar Dronamraju , Ingo Molnar , Peter Zijlstra Cc: LKML , Mel Gorman , Thomas Gleixner Date: Mon, 04 Jun 2018 16:05:55 -0400 In-Reply-To: <1528106428-19992-17-git-send-email-srikar@linux.vnet.ibm.com> References: <1528106428-19992-1-git-send-email-srikar@linux.vnet.ibm.com> <1528106428-19992-17-git-send-email-srikar@linux.vnet.ibm.com> Content-Type: multipart/signed; micalg="pgp-sha256"; protocol="application/pgp-signature"; boundary="=-QvcmWrj+G+DSdPGPn/WV" X-Mailer: Evolution 3.26.6 (3.26.6-1.fc27) Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --=-QvcmWrj+G+DSdPGPn/WV Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Mon, 2018-06-04 at 15:30 +0530, Srikar Dronamraju wrote: > @@ -1554,6 +1562,9 @@ static void task_numa_compare(struct > task_numa_env *env, > if (READ_ONCE(dst_rq->numa_migrate_on)) > return; > =20 > + if (*move && READ_ONCE(pgdat->active_node_migrate)) > + *move =3D false; Why not do this check in task_numa_find_cpu? That way you won't have to pass this in as a pointer, and you also will not have to recalculate NODE_DATA(cpu_to_node(env->dst_cpu)) for every CPU. > /* > + * If the numa importance is less than SMALLIMP, ^^^ numa improvement > + * task migration might only result in ping pong > + * of tasks and also hurt performance due to cache > + * misses. > + */ > + if (imp < SMALLIMP || imp <=3D env->best_imp + SMALLIMP / 2) > + goto unlock; I can see a use for the first test, but why limit the search for the best score once you are past the threshold? I don't understand the use for that second test. What workload benefits from it? --=20 All Rights Reversed. --=-QvcmWrj+G+DSdPGPn/WV Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- iQEzBAABCAAdFiEEKR73pCCtJ5Xj3yADznnekoTE3oMFAlsVm6MACgkQznnekoTE 3oOSnwf/bbTYHVhtD7SxCuBW1Fl5XvQVaF+EgGecbI9e1HkXEthcT/HVQC58WIWR 8a0lgBmcrmSOnIRIJX6fbSOcaQrR2OWUdV29S6sznZm/sf7W/0YMh3lEudJNDy/E E9BcFMBnkIaq5b2e/pgIfeYnw802OowC0/gOXQ8xD8OUA2eHIhEaflFX20Xw7zPG L4jW2UP7GprEYBGiGcakhu+qL/MdQCLJbdS89ANKBDykoWVdRtdhp983oIFuZ0TB ysGv/IdOoMXu9ojb1Wp+0390MoLhcjO5dBUaxi0rFOWTgzpTIBg5cWldDYM2a6WN 5qaI5dnnHaKcLjDjjYlWgXHelHDvVQ== =pR+q -----END PGP SIGNATURE----- --=-QvcmWrj+G+DSdPGPn/WV--