sched/numa: Rewrite the CONFIG_NUMA sched domain support

The current code groups up to 16 nodes in a level and then puts an ALLNODES domain spanning the entire tree on top of that. This doesn't reflect the numa topology and esp for the smaller not-fully-connected machines out there today this might make a difference. Therefore, build a proper numa topology based on node_distance(). Since there's no fixed numa layers anymore, the static SD_NODE_INIT and SD_ALLNODES_INIT aren't usable anymore, the new code tries to construct something similar and scales some values either on the number of cpus in the domain and/or the node_distance() ratio. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: linux-alpha@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-sh@vger.kernel.org Cc: Matt Turner <mattst88@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: sparclinux@vger.kernel.org Cc: Tony Luck <tony.luck@intel.com> Cc: x86@kernel.org Cc: Dimitri Sivanich <sivanich@sgi.com> Cc: Greg Pearson <greg.pearson@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: bob.picco@oracle.com Cc: chris.mason@oracle.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/n/tip-r74n3n8hhuc2ynbrnp3vt954@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
torvalds · May 9, 2012 · cb83b62 · cb83b62
1 parent bd939f4
commit cb83b62
Show file tree

Hide file tree

Showing 9 changed files with 185 additions and 318 deletions.
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
@@ -70,31 +70,6 @@ void build_cpu_to_node_map(void);
 	.nr_balance_failed	= 0,			\
 }
 
-/* sched_domains SD_NODE_INIT for IA64 NUMA machines */
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 8,			\
-	.max_interval		= 8*(min(num_online_cpus(), 32U)), \
-	.busy_factor		= 64,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 3,			\
-	.idle_idx		= 2,			\
-	.newidle_idx		= 0,			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_FORK	\
-				| SD_SERIALIZE,		\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 64,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_SMP

diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h
@@ -36,23 +36,6 @@ extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
 
 #define node_distance(from, to)	(__node_distances[(from)][(to)])
 
-/* sched_domains SD_NODE_INIT for SGI IP27 machines */
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 8,			\
-	.max_interval		= 32,			\
-	.busy_factor		= 32,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 1,			\
-	.flags			= SD_LOAD_BALANCE |	\
-				  SD_BALANCE_EXEC,	\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_MACH_TOPOLOGY_H */
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
@@ -18,12 +18,6 @@ struct device_node;
  */
 #define RECLAIM_DISTANCE 10
 
-/*
- * Avoid creating an extra level of balancing (SD_ALLNODES) on the largest
- * POWER7 boxes which have a maximum of 32 nodes.
- */
-#define SD_NODES_PER_DOMAIN 32
-
 #include <asm/mmzone.h>
 
 static inline int cpu_to_node(int cpu)
@@ -51,36 +45,6 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
 
-/* sched_domains SD_NODE_INIT for PPC64 machines */
-#define SD_NODE_INIT (struct sched_domain) {				\
-	.min_interval		= 8,					\
-	.max_interval		= 32,					\
-	.busy_factor		= 32,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 3,					\
-	.idle_idx		= 1,					\
-	.newidle_idx		= 0,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 0*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 0*SD_PREFER_LOCAL			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_POWERSAVINGS_BALANCE		\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-}
-
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 

diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
@@ -3,31 +3,6 @@
 
 #ifdef CONFIG_NUMA
 
-/* sched_domains SD_NODE_INIT for sh machines */
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 8,			\
-	.max_interval		= 32,			\
-	.busy_factor		= 32,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 3,			\
-	.idle_idx		= 2,			\
-	.newidle_idx		= 0,			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_FORK	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_SERIALIZE,		\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #define cpu_to_node(cpu)	((void)(cpu),0)
 #define parent_node(node)	((void)(node),0)
 

diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
@@ -31,25 +31,6 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 	 cpu_all_mask : \
 	 cpumask_of_node(pcibus_to_node(bus)))
 
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.min_interval		= 8,			\
-	.max_interval		= 32,			\
-	.busy_factor		= 32,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 3,			\
-	.idle_idx		= 2,			\
-	.newidle_idx		= 0, 			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_FORK	\
-				| SD_BALANCE_EXEC	\
-				| SD_SERIALIZE,		\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-}
-
 #else /* CONFIG_NUMA */
 
 #include <asm-generic/topology.h>

diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
@@ -78,32 +78,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
 	.balance_interval	= 32,					\
 }
 
-/* sched_domains SD_NODE_INIT for TILE architecture */
-#define SD_NODE_INIT (struct sched_domain) {				\
-	.min_interval		= 16,					\
-	.max_interval		= 512,					\
-	.busy_factor		= 32,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 3,					\
-	.idle_idx		= 1,					\
-	.newidle_idx		= 2,					\
-	.wake_idx		= 1,					\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 0*SD_WAKE_AFFINE			\
-				| 0*SD_PREFER_LOCAL			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 128,					\
-}
-
 /* By definition, we create nodes based on online memory. */
 #define node_has_online_mem(nid) 1
 

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
@@ -92,44 +92,6 @@ extern void setup_node_to_cpumask_map(void);
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 
-#ifdef CONFIG_X86_32
-# define SD_CACHE_NICE_TRIES	1
-# define SD_IDLE_IDX		1
-#else
-# define SD_CACHE_NICE_TRIES	2
-# define SD_IDLE_IDX		2
-#endif
-
-/* sched_domains SD_NODE_INIT for NUMA machines */
-#define SD_NODE_INIT (struct sched_domain) {				\
-	.min_interval		= 8,					\
-	.max_interval		= 32,					\
-	.busy_factor		= 32,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= SD_CACHE_NICE_TRIES,			\
-	.busy_idx		= 3,					\
-	.idle_idx		= SD_IDLE_IDX,				\
-	.newidle_idx		= 0,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 0*SD_PREFER_LOCAL			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_POWERSAVINGS_BALANCE		\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-}
-
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 

diff --git a/include/linux/topology.h b/include/linux/topology.h
@@ -70,7 +70,6 @@ int arch_update_cpu_topology(void);
  * Below are the 3 major initializers used in building sched_domains:
  * SD_SIBLING_INIT, for SMT domains
  * SD_CPU_INIT, for SMP domains
- * SD_NODE_INIT, for NUMA domains
  *
  * Any architecture that cares to do any tuning to these values should do so
  * by defining their own arch-specific initializer in include/asm/topology.h.
@@ -176,48 +175,12 @@ int arch_update_cpu_topology(void);
 }
 #endif
 
-/* sched_domains SD_ALLNODES_INIT for NUMA machines */
-#define SD_ALLNODES_INIT (struct sched_domain) {			\
-	.min_interval		= 64,					\
-	.max_interval		= 64*num_online_cpus(),			\
-	.busy_factor		= 128,					\
-	.imbalance_pct		= 133,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 3,					\
-	.idle_idx		= 3,					\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 0*SD_BALANCE_EXEC			\
-				| 0*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 0*SD_WAKE_AFFINE			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_POWERSAVINGS_BALANCE		\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 64,					\
-}
-
-#ifndef SD_NODES_PER_DOMAIN
-#define SD_NODES_PER_DOMAIN 16
-#endif
-
 #ifdef CONFIG_SCHED_BOOK
 #ifndef SD_BOOK_INIT
 #error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
 #endif
 #endif /* CONFIG_SCHED_BOOK */
 
-#ifdef CONFIG_NUMA
-#ifndef SD_NODE_INIT
-#error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!!
-#endif
-
-#endif /* CONFIG_NUMA */
-
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DECLARE_PER_CPU(int, numa_node);