Thread (2 messages) 2 messages, 2 authors, 2015-01-31

Re: [PATCH v2] cpuset: Fix cpuset sched_relax_domain_level

From: Zefan Li <hidden>
Date: 2015-01-31 00:31:29
Also in: lkml, stable

On 2015/1/31 2:54, Jason Low wrote:
The cpuset.sched_relax_domain_level can control how far we do
immediate load balancing on a system. However, it was found on recent
kernels that echo'ing a value into cpuset.sched_relax_domain_level
did not reduce any immediate load balancing.

The reason this occurred was because the update_domain_attr_tree() traversal
did not update for the "top_cpuset". This resulted in nothing being changed
when modifying the sched_relax_domain_level parameter.

This patch is able to address that problem by having update_domain_attr_tree()
allow updates for the root in the cpuset traversal.

Fixes: fc560a26acce ("cpuset: replace cpuset->stack_list with cpuset_for_each_descendant_pre()")
Cc: <redacted> # 3.9+
Signed-off-by: Jason Low <redacted>
Acked-by: Zefan Li <redacted>
quoted hunk ↗ jump to hunk
---
 kernel/cpuset.c |    3 ---
 1 files changed, 0 insertions(+), 3 deletions(-)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 64b257f..b589e57 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -548,9 +548,6 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
 
 	rcu_read_lock();
 	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		if (cp == root_cs)
-			continue;
-
 		/* skip the whole subtree if @cp doesn't have any CPU */
 		if (cpumask_empty(cp->cpus_allowed)) {
 			pos_css = css_rightmost_descendant(pos_css);
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help