浏览代码

powerpc/numa: Disable NEWIDLE balancing at node level

On big POWER7 boxes we see large amounts of CPU time in system
processes like workqueue and watchdog kernel threads.

We currently rebalance the entire machine each time a task goes
idle and this is very expensive on large machines. Disable newidle
balancing at the node level and rely on the scheduler tick to
rebalance across nodes.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Anton Blanchard 14 年之前
父节点
当前提交
7bebcf0925
共有 1 个文件被更改,包括 1 次插入1 次删除
  1. 1 1
      arch/powerpc/include/asm/topology.h

+ 1 - 1
arch/powerpc/include/asm/topology.h

@@ -75,7 +75,7 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 	.forkexec_idx		= 0,					\
 									\
 	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
+				| 0*SD_BALANCE_NEWIDLE			\
 				| 1*SD_BALANCE_EXEC			\
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\