From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1762736Ab2ERKkH (ORCPT ); Fri, 18 May 2012 06:40:07 -0400 Received: from terminus.zytor.com ([198.137.202.10]:42625 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760701Ab2ERKkD (ORCPT ); Fri, 18 May 2012 06:40:03 -0400 Date: Fri, 18 May 2012 03:39:38 -0700 From: tip-bot for Peter Zijlstra Message-ID: Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@kernel.org, torvalds@linux-foundation.org, a.p.zijlstra@chello.nl, pjt@google.com, cl@linux.com, riel@redhat.com, akpm@linux-foundation.org, bharata.rao@gmail.com, aarcange@redhat.com, Lee.Schermerhorn@hp.com, suresh.b.siddha@intel.com, danms@us.ibm.com, tglx@linutronix.de Reply-To: mingo@kernel.org, hpa@zytor.com, linux-kernel@vger.kernel.org, a.p.zijlstra@chello.nl, torvalds@linux-foundation.org, pjt@google.com, cl@linux.com, riel@redhat.com, bharata.rao@gmail.com, akpm@linux-foundation.org, Lee.Schermerhorn@hp.com, aarcange@redhat.com, danms@us.ibm.com, suresh.b.siddha@intel.com, tglx@linutronix.de To: linux-tip-commits@vger.kernel.org Subject: [tip:sched/numa] sched/numa: Add {mems,cpus}_allowed tests Git-Commit-ID: 42cfa9f3166fe9eb5a8b31ca01cdfd2c275161f8 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.6 (terminus.zytor.com [127.0.0.1]); Fri, 18 May 2012 03:39:43 -0700 (PDT) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 42cfa9f3166fe9eb5a8b31ca01cdfd2c275161f8 Gitweb: http://git.kernel.org/tip/42cfa9f3166fe9eb5a8b31ca01cdfd2c275161f8 Author: Peter Zijlstra AuthorDate: Tue, 8 May 2012 13:12:07 +0200 Committer: Ingo Molnar CommitDate: Fri, 18 May 2012 08:16:25 +0200 sched/numa: Add {mems,cpus}_allowed tests Make the NUMA balancer respect task_struct::{mems,cpus}_allowed. Since these are per task we require all tasks in the process/group to allow the target node otherwise we fail the migration. Signed-off-by: Peter Zijlstra Cc: Suresh Siddha Cc: Paul Turner Cc: Dan Smith Cc: Bharata B Rao Cc: Lee Schermerhorn Cc: Christoph Lameter Cc: Rik van Riel Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Linus Torvalds Link: http://lkml.kernel.org/n/tip-zm9pzuxeiebax9vrhx9bbt3i@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/numa.c | 51 ++++++++++++++++++++++++++++----------------------- 1 files changed, 28 insertions(+), 23 deletions(-) diff --git a/kernel/sched/numa.c b/kernel/sched/numa.c index 7712744..1d2837d 100644 --- a/kernel/sched/numa.c +++ b/kernel/sched/numa.c @@ -27,7 +27,7 @@ struct numa_ops { void (*mem_migrate)(struct numa_entity *ne, int node); void (*cpu_migrate)(struct numa_entity *ne, int node); - u64 (*cpu_runtime)(struct numa_entity *ne); + bool (*can_migrate)(struct numa_entity *ne, int node); bool (*tryget)(struct numa_entity *ne); void (*put)(struct numa_entity *ne); @@ -210,19 +210,41 @@ static void process_mem_migrate(struct numa_entity *ne, int node) lazy_migrate_process(ne_mm(ne), node); } -static u64 process_cpu_runtime(struct numa_entity *ne) +static bool __task_can_migrate(struct task_struct *t, u64 *runtime, int node) +{ +#ifdef CONFIG_CPUSETS + if (!node_isset(node, t->mems_allowed)) + return false; +#endif + + if (!cpumask_intersects(cpumask_of_node(node), tsk_cpus_allowed(t))) + return false; + + *runtime += t->se.sum_exec_runtime; // @#$#@ 32bit + + return true; +} + +static bool process_can_migrate(struct numa_entity *ne, int node) { struct task_struct *p, *t; + bool allowed = false; u64 runtime = 0; rcu_read_lock(); t = p = ne_owner(ne); if (p) do { - runtime += t->se.sum_exec_runtime; // @#$#@ 32bit + allowed = __task_can_migrate(t, &runtime, node); + if (!allowed) + break; } while ((t = next_thread(t)) != p); rcu_read_unlock(); - return runtime; + /* + * Don't bother migrating memory if there's less than 1 second + * of runtime on the tasks. + */ + return allowed && runtime > NSEC_PER_SEC; } static bool process_tryget(struct numa_entity *ne) @@ -248,7 +270,7 @@ static const struct numa_ops process_numa_ops = { .mem_migrate = process_mem_migrate, .cpu_migrate = process_cpu_migrate, - .cpu_runtime = process_cpu_runtime, + .can_migrate = process_can_migrate, .tryget = process_tryget, .put = process_put, @@ -624,23 +646,6 @@ calc_imb: return node; } -static bool can_move_ne(struct numa_entity *ne) -{ - /* - * XXX: consider mems_allowed, stinking cpusets has mems_allowed - * per task and it can actually differ over a whole process, la-la-la. - */ - - /* - * Don't bother migrating memory if there's less than 1 second - * of runtime on the tasks. - */ - if (ne->nops->cpu_runtime(ne) < NSEC_PER_SEC) - return false; - - return true; -} - static void move_processes(struct node_queue *busiest_nq, struct node_queue *this_nq, struct numa_imbalance *imb) @@ -679,7 +684,7 @@ static void move_processes(struct node_queue *busiest_nq, goto next; } - if (!can_move_ne(ne)) + if (!ne->nops->can_migrate(ne, this_nq->node)) goto next; __dequeue_ne(busiest_nq, ne);