| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 8 Aug 2013 15:00:38 +0100
From: Mel Gorman <mgorman@...e.de>
To: Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Rik van Riel <riel@...hat.com>
Cc: Srikar Dronamraju <srikar@...ux.vnet.ibm.com>,
Ingo Molnar <mingo@...nel.org>,
Andrea Arcangeli <aarcange@...hat.com>,
Johannes Weiner <hannes@...xchg.org>,
Linux-MM <linux-mm@...ck.org>,
LKML <linux-kernel@...r.kernel.org>, Mel Gorman <mgorman@...e.de>
Subject: [PATCH 26/27] sched: Avoid overloading CPUs on a preferred NUMA node
This patch replaces find_idlest_cpu_node with task_numa_find_cpu.
find_idlest_cpu_node has two critical limitations. It does not take the
scheduling class into account when calculating the load and it is unsuitable
for using when comparing loads between NUMA nodes.
task_numa_find_cpu uses similar load calculations to wake_affine() when
selecting the least loaded CPU within a scheduling domain common to the
source and destimation nodes. It avoids causing CPU load imbalances in
the machine by refusing to migrate if the relative load on the target
CPU is higher than the source CPU.
Signed-off-by: Peter Zijlstra <peterz@...radead.org>
Signed-off-by: Mel Gorman <mgorman@...e.de>
---
kernel/sched/fair.c | 105 +++++++++++++++++++++++++++++++++++++++++-----------
1 file changed, 83 insertions(+), 22 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9d8b5cb..9ea4d5c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -901,28 +901,92 @@ static inline unsigned long task_faults(struct task_struct *p, int nid)
}
static unsigned long weighted_cpuload(const int cpu);
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static unsigned long power_of(int cpu);
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
+
+static int task_numa_find_cpu(struct task_struct *p, int nid)
+{
+ int node_cpu = cpumask_first(cpumask_of_node(nid));
+ int cpu, src_cpu = task_cpu(p), dst_cpu = src_cpu;
+ unsigned long src_load, dst_load;
+ unsigned long min_load = ULONG_MAX;
+ struct task_group *tg = task_group(p);
+ s64 src_eff_load, dst_eff_load;
+ struct sched_domain *sd;
+ unsigned long weight;
+ bool balanced;
+ int imbalance_pct, idx = -1;
+ /* No harm being optimistic */
+ if (idle_cpu(node_cpu))
+ return node_cpu;
-static int
-find_idlest_cpu_node(int this_cpu, int nid)
-{
- unsigned long load, min_load = ULONG_MAX;
- int i, idlest_cpu = this_cpu;
+ /*
+ * Find the lowest common scheduling domain covering the nodes of both
+ * the CPU the task is currently running on and the target NUMA node.
+ */
+ rcu_read_lock();
+ for_each_domain(src_cpu, sd) {
+ if (cpumask_test_cpu(node_cpu, sched_domain_span(sd))) {
+ /*
+ * busy_idx is used for the load decision as it is the
+ * same index used by the regular load balancer for an
+ * active cpu.
+ */
+ idx = sd->busy_idx;
+ imbalance_pct = sd->imbalance_pct;
+ break;
+ }
+ }
+ rcu_read_unlock();
- BUG_ON(cpu_to_node(this_cpu) == nid);
+ if (WARN_ON_ONCE(idx == -1))
+ return src_cpu;
- rcu_read_lock();
- for_each_cpu(i, cpumask_of_node(nid)) {
- load = weighted_cpuload(i);
+ /*
+ * XXX the below is mostly nicked from wake_affine(); we should
+ * see about sharing a bit if at all possible; also it might want
+ * some per entity weight love.
+ */
+ weight = p->se.load.weight;
- if (load < min_load) {
- min_load = load;
- idlest_cpu = i;
+ src_load = source_load(src_cpu, idx);
+
+ src_eff_load = 100 + (imbalance_pct - 100) / 2;
+ src_eff_load *= power_of(src_cpu);
+ src_eff_load *= src_load + effective_load(tg, src_cpu, -weight, -weight);
+
+ for_each_cpu(cpu, cpumask_of_node(nid)) {
+ dst_load = target_load(cpu, idx);
+
+ /* If the CPU is idle, use it */
+ if (!dst_load)
+ return cpu;
+
+ /* Otherwise check the target CPU load */
+ dst_eff_load = 100;
+ dst_eff_load *= power_of(cpu);
+ dst_eff_load *= dst_load + effective_load(tg, cpu, weight, weight);
+
+ /*
+ * Destination is considered balanced if the destination CPU is
+ * less loaded than the source CPU. Unfortunately there is a
+ * risk that a task running on a lightly loaded CPU will not
+ * migrate to its preferred node due to load imbalances.
+ */
+ balanced = (dst_eff_load <= src_eff_load);
+ if (!balanced)
+ continue;
+
+ if (dst_load < min_load) {
+ min_load = dst_load;
+ dst_cpu = cpu;
}
}
- rcu_read_unlock();
- return idlest_cpu;
+ return dst_cpu;
}
static void task_numa_placement(struct task_struct *p)
@@ -969,14 +1033,12 @@ static void task_numa_placement(struct task_struct *p)
int preferred_cpu;
/*
- * If the task is not on the preferred node then find the most
- * idle CPU to migrate to.
+ * If the task is not on the preferred node then find
+ * a suitable CPU to migrate to.
*/
preferred_cpu = task_cpu(p);
- if (cpu_to_node(preferred_cpu) != max_nid) {
- preferred_cpu = find_idlest_cpu_node(preferred_cpu,
- max_nid);
- }
+ if (cpu_to_node(preferred_cpu) != max_nid)
+ preferred_cpu = task_numa_find_cpu(p, max_nid);
/* Update the preferred nid and migrate task if possible */
p->numa_preferred_nid = max_nid;
@@ -3326,8 +3388,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
}
#else
-static inline unsigned long effective_load(struct task_group *tg, int cpu,
- unsigned long wl, unsigned long wg)
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
return wl;
}
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists