From 143e1e28cb40bed836b0a06567208bd7347c9672 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:37 +0200 Subject: sched: Rework sched_domain topology definition We replace the old way to configure the scheduler topology with a new method which enables a platform to declare additionnal level (if needed). We still have a default topology table definition that can be used by platform that don't want more level than the SMT, MC, CPU and NUMA ones. This table can be overwritten by an arch which either wants to add new level where a load balance make sense like BOOK or powergating level or wants to change the flags configuration of some levels. For each level, we need a function pointer that returns cpumask for each cpu, a function pointer that returns the flags for the level and a name. Only flags that describe topology, can be set by an architecture. The current topology flags are: SD_SHARE_CPUPOWER SD_SHARE_PKG_RESOURCES SD_NUMA SD_ASYM_PACKING Then, each level must be a subset on the next one. The build sequence of the sched_domain will take care of removing useless levels like those with 1 CPU and those with the same CPU span and no more relevant information for load balancing than its children. Signed-off-by: Vincent Guittot Tested-by: Dietmar Eggemann Reviewed-by: Preeti U Murthy Reviewed-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Chris Metcalf Cc: Christoph Lameter Cc: David S. Miller Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: Hanjun Guo Cc: Heiko Carstens Cc: Jason Low Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Tony Luck Cc: linux390@de.ibm.com Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Link: http://lkml.kernel.org/r/1397209481-28542-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/topology.h | 128 +++++------------------------------------------ 1 file changed, 13 insertions(+), 115 deletions(-) (limited to 'include/linux/topology.h') diff --git a/include/linux/topology.h b/include/linux/topology.h index 7062330a1329..973671ff9e7d 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -66,121 +66,6 @@ int arch_update_cpu_topology(void); #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif -/* - * Below are the 3 major initializers used in building sched_domains: - * SD_SIBLING_INIT, for SMT domains - * SD_CPU_INIT, for SMP 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. - * A definition there will automagically override these default initializers - * and allow arch-specific performance tuning of sched_domains. - * (Only non-zero and non-null fields need be specified.) - */ - -#ifdef CONFIG_SCHED_SMT -/* MCD - Do we really need this? It is always on if CONFIG_SCHED_SMT is, - * so can't we drop this in favor of CONFIG_SCHED_SMT? - */ -#define ARCH_HAS_SCHED_WAKE_IDLE -/* Common values for SMT siblings */ -#ifndef SD_SIBLING_INIT -#define SD_SIBLING_INIT (struct sched_domain) { \ - .min_interval = 1, \ - .max_interval = 2, \ - .busy_factor = 64, \ - .imbalance_pct = 110, \ - \ - .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 \ - | 1*SD_SHARE_CPUPOWER \ - | 1*SD_SHARE_PKG_RESOURCES \ - | 0*SD_SERIALIZE \ - | 0*SD_PREFER_SIBLING \ - | arch_sd_sibling_asym_packing() \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .smt_gain = 1178, /* 15% */ \ - .max_newidle_lb_cost = 0, \ - .next_decay_max_lb_cost = jiffies, \ -} -#endif -#endif /* CONFIG_SCHED_SMT */ - -#ifdef CONFIG_SCHED_MC -/* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */ -#ifndef SD_MC_INIT -#define SD_MC_INIT (struct sched_domain) { \ - .min_interval = 1, \ - .max_interval = 4, \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .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_SHARE_CPUPOWER \ - | 1*SD_SHARE_PKG_RESOURCES \ - | 0*SD_SERIALIZE \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .max_newidle_lb_cost = 0, \ - .next_decay_max_lb_cost = jiffies, \ -} -#endif -#endif /* CONFIG_SCHED_MC */ - -/* Common values for CPUs */ -#ifndef SD_CPU_INIT -#define SD_CPU_INIT (struct sched_domain) { \ - .min_interval = 1, \ - .max_interval = 4, \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .idle_idx = 1, \ - .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_SHARE_CPUPOWER \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 0*SD_SERIALIZE \ - | 1*SD_PREFER_SIBLING \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .max_newidle_lb_cost = 0, \ - .next_decay_max_lb_cost = jiffies, \ -} -#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_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); @@ -295,4 +180,17 @@ static inline int cpu_to_mem(int cpu) #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif +#ifdef CONFIG_SCHED_SMT +static inline const struct cpumask *cpu_smt_mask(int cpu) +{ + return topology_thread_cpumask(cpu); +} +#endif + +static inline const struct cpumask *cpu_cpu_mask(int cpu) +{ + return cpumask_of_node(cpu_to_node(cpu)); +} + + #endif /* _LINUX_TOPOLOGY_H */ -- cgit v1.2.3 From 4f9b16a64753d0bb607454347036dc997fd03b82 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:07:14 -0700 Subject: mm: disable zone_reclaim_mode by default When it was introduced, zone_reclaim_mode made sense as NUMA distances punished and workloads were generally partitioned to fit into a NUMA node. NUMA machines are now common but few of the workloads are NUMA-aware and it's routine to see major performance degradation due to zone_reclaim_mode being enabled but relatively few can identify the problem. Those that require zone_reclaim_mode are likely to be able to detect when it needs to be enabled and tune appropriately so lets have a sensible default for the bulk of users. This patch (of 2): zone_reclaim_mode causes processes to prefer reclaiming memory from local node instead of spilling over to other nodes. This made sense initially when NUMA machines were almost exclusively HPC and the workload was partitioned into nodes. The NUMA penalties were sufficiently high to justify reclaiming the memory. On current machines and workloads it is often the case that zone_reclaim_mode destroys performance but not all users know how to detect this. Favour the common case and disable it by default. Users that are sophisticated enough to know they need zone_reclaim_mode will detect it. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Reviewed-by: Zhang Yanfei Acked-by: Michal Hocko Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 17 +++++++++-------- arch/ia64/include/asm/topology.h | 3 ++- arch/powerpc/include/asm/topology.h | 8 ++------ include/linux/topology.h | 3 ++- mm/page_alloc.c | 2 -- 5 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux/topology.h') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index dd9d0e33b443..5b6da0fb5fbf 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -772,16 +772,17 @@ This is value ORed together of 2 = Zone reclaim writes dirty pages out 4 = Zone reclaim swaps pages -zone_reclaim_mode is set during bootup to 1 if it is determined that pages -from remote zones will cause a measurable performance reduction. The -page allocator will then reclaim easily reusable pages (those page -cache pages that are currently not used) before allocating off node pages. - -It may be beneficial to switch off zone reclaim if the system is -used for a file server and all of memory should be used for caching files -from disk. In that case the caching effect is more important than +zone_reclaim_mode is disabled by default. For file servers or workloads +that benefit from having their data cached, zone_reclaim_mode should be +left disabled as the caching effect is likely to be more important than data locality. +zone_reclaim may be enabled if it's known that the workload is partitioned +such that each partition fits within a NUMA node and that accessing remote +memory would cause a measurable performance reduction. The page allocator +will then reclaim easily reusable pages (those page cache pages that are +currently not used) before allocating off node pages. + Allowing zone reclaim to write out pages stops processes that are writing large amounts of data from dirtying pages on other nodes. Zone reclaim will write out dirty pages if a zone fills up and so effectively diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 3202aa74e0d6..6437ca21f61b 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -21,7 +21,8 @@ #define PENALTY_FOR_NODE_WITH_CPUS 255 /* - * Distance above which we begin to use zone reclaim + * Nodes within this distance are eligible for reclaim by zone_reclaim() when + * zone_reclaim_mode is enabled. */ #define RECLAIM_DISTANCE 15 diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index c9202151079f..6c8a8c5a37a1 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -9,12 +9,8 @@ struct device_node; #ifdef CONFIG_NUMA /* - * Before going off node we want the VM to try and reclaim from the local - * node. It does this if the remote distance is larger than RECLAIM_DISTANCE. - * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of - * 20, we never reclaim and go off node straight away. - * - * To fix this we choose a smaller value of RECLAIM_DISTANCE. + * If zone_reclaim_mode is enabled, a RECLAIM_DISTANCE of 10 will mean that + * all zones on all nodes will be eligible for zone_reclaim(). */ #define RECLAIM_DISTANCE 10 diff --git a/include/linux/topology.h b/include/linux/topology.h index 973671ff9e7d..dda6ee521e74 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -58,7 +58,8 @@ int arch_update_cpu_topology(void); /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) - * then switch on zone reclaim on boot. + * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim() + * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7cfdcd808f52..dfe954fbb48a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1860,8 +1860,6 @@ static void __paginginit init_zone_allows_reclaim(int nid) for_each_node_state(i, N_MEMORY) if (node_distance(nid, i) <= RECLAIM_DISTANCE) node_set(i, NODE_DATA(nid)->reclaim_nodes); - else - zone_reclaim_mode = 1; } #else /* CONFIG_NUMA */ -- cgit v1.2.3