linux_dsm_epyc7002/include/linux/sched/topology.h
Peter Zijlstra d153b15344 sched/core: Fix wake_affine() performance regression
Eric reported a sysbench regression against commit:

  3fed382b46 ("sched/numa: Implement NUMA node level wake_affine()")

Similarly, Rik was looking at the NAS-lu.C benchmark, which regressed
against his v3.10 enterprise kernel.

PRE (current tip/master):

 ivb-ep sysbench:

   2: [30 secs]     transactions:                        64110  (2136.94 per sec.)
   5: [30 secs]     transactions:                        143644 (4787.99 per sec.)
  10: [30 secs]     transactions:                        274298 (9142.93 per sec.)
  20: [30 secs]     transactions:                        418683 (13955.45 per sec.)
  40: [30 secs]     transactions:                        320731 (10690.15 per sec.)
  80: [30 secs]     transactions:                        355096 (11834.28 per sec.)

 hsw-ex NAS:

 OMP_PROC_BIND/lu.C.x_threads_144_run_1.log: Time in seconds =                    18.01
 OMP_PROC_BIND/lu.C.x_threads_144_run_2.log: Time in seconds =                    17.89
 OMP_PROC_BIND/lu.C.x_threads_144_run_3.log: Time in seconds =                    17.93
 lu.C.x_threads_144_run_1.log: Time in seconds =                   434.68
 lu.C.x_threads_144_run_2.log: Time in seconds =                   405.36
 lu.C.x_threads_144_run_3.log: Time in seconds =                   433.83

POST (+patch):

 ivb-ep sysbench:

   2: [30 secs]     transactions:                        64494  (2149.75 per sec.)
   5: [30 secs]     transactions:                        145114 (4836.99 per sec.)
  10: [30 secs]     transactions:                        278311 (9276.69 per sec.)
  20: [30 secs]     transactions:                        437169 (14571.60 per sec.)
  40: [30 secs]     transactions:                        669837 (22326.73 per sec.)
  80: [30 secs]     transactions:                        631739 (21055.88 per sec.)

 hsw-ex NAS:

 lu.C.x_threads_144_run_1.log: Time in seconds =                    23.36
 lu.C.x_threads_144_run_2.log: Time in seconds =                    22.96
 lu.C.x_threads_144_run_3.log: Time in seconds =                    22.52

This patch takes out all the shiny wake_affine() stuff and goes back to
utter basics. Between the two CPUs involved with the wakeup (the CPU
doing the wakeup and the CPU we ran on previously) pick the CPU we can
run on _now_.

This restores much of the regressions against the older kernels,
but leaves some ground in the overloaded case. The default-enabled
WA_WEIGHT (which will be introduced in the next patch) is an attempt
to address the overloaded situation.

Reported-by: Eric Farman <farman@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: jinpuwang@gmail.com
Cc: vcaputo@pengaru.com
Fixes: 3fed382b46 ("sched/numa: Implement NUMA node level wake_affine()")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-10 10:14:02 +02:00

227 lines
6.1 KiB
C

#ifndef _LINUX_SCHED_TOPOLOGY_H
#define _LINUX_SCHED_TOPOLOGY_H
#include <linux/topology.h>
#include <linux/sched/idle.h>
/*
* sched-domains (multiprocessor balancing) declarations:
*/
#ifdef CONFIG_SMP
#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */
#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */
#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */
#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
#define SD_ASYM_CPUCAPACITY 0x0040 /* Groups have different max cpu capacities */
#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */
#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */
#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
#define SD_NUMA 0x4000 /* cross-node balancing */
/*
* Increase resolution of cpu_capacity calculations
*/
#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT
#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
#ifdef CONFIG_SCHED_SMT
static inline int cpu_smt_flags(void)
{
return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
}
#endif
#ifdef CONFIG_SCHED_MC
static inline int cpu_core_flags(void)
{
return SD_SHARE_PKG_RESOURCES;
}
#endif
#ifdef CONFIG_NUMA
static inline int cpu_numa_flags(void)
{
return SD_NUMA;
}
#endif
extern int arch_asym_cpu_priority(int cpu);
struct sched_domain_attr {
int relax_domain_level;
};
#define SD_ATTR_INIT (struct sched_domain_attr) { \
.relax_domain_level = -1, \
}
extern int sched_domain_level_max;
struct sched_group;
struct sched_domain_shared {
atomic_t ref;
atomic_t nr_busy_cpus;
int has_idle_cores;
};
struct sched_domain {
/* These fields must be setup */
struct sched_domain *parent; /* top domain must be null terminated */
struct sched_domain *child; /* bottom domain must be null terminated */
struct sched_group *groups; /* the balancing groups of the domain */
unsigned long min_interval; /* Minimum balance interval ms */
unsigned long max_interval; /* Maximum balance interval ms */
unsigned int busy_factor; /* less balancing by factor if busy */
unsigned int imbalance_pct; /* No balance until over watermark */
unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */
unsigned int busy_idx;
unsigned int idle_idx;
unsigned int newidle_idx;
unsigned int wake_idx;
unsigned int forkexec_idx;
unsigned int smt_gain;
int nohz_idle; /* NOHZ IDLE status */
int flags; /* See SD_* */
int level;
/* Runtime fields. */
unsigned long last_balance; /* init to jiffies. units in jiffies */
unsigned int balance_interval; /* initialise to 1. units in ms. */
unsigned int nr_balance_failed; /* initialise to 0 */
/* idle_balance() stats */
u64 max_newidle_lb_cost;
unsigned long next_decay_max_lb_cost;
u64 avg_scan_cost; /* select_idle_sibling */
#ifdef CONFIG_SCHEDSTATS
/* load_balance() stats */
unsigned int lb_count[CPU_MAX_IDLE_TYPES];
unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
/* Active load balancing */
unsigned int alb_count;
unsigned int alb_failed;
unsigned int alb_pushed;
/* SD_BALANCE_EXEC stats */
unsigned int sbe_count;
unsigned int sbe_balanced;
unsigned int sbe_pushed;
/* SD_BALANCE_FORK stats */
unsigned int sbf_count;
unsigned int sbf_balanced;
unsigned int sbf_pushed;
/* try_to_wake_up() stats */
unsigned int ttwu_wake_remote;
unsigned int ttwu_move_affine;
unsigned int ttwu_move_balance;
#endif
#ifdef CONFIG_SCHED_DEBUG
char *name;
#endif
union {
void *private; /* used during construction */
struct rcu_head rcu; /* used during destruction */
};
struct sched_domain_shared *shared;
unsigned int span_weight;
/*
* Span of all CPUs in this domain.
*
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
*/
unsigned long span[0];
};
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
return to_cpumask(sd->span);
}
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new);
/* Allocate an array of sched domains, for partition_sched_domains(). */
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
bool cpus_share_cache(int this_cpu, int that_cpu);
typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
typedef int (*sched_domain_flags_f)(void);
#define SDTL_OVERLAP 0x01
struct sd_data {
struct sched_domain **__percpu sd;
struct sched_domain_shared **__percpu sds;
struct sched_group **__percpu sg;
struct sched_group_capacity **__percpu sgc;
};
struct sched_domain_topology_level {
sched_domain_mask_f mask;
sched_domain_flags_f sd_flags;
int flags;
int numa_level;
struct sd_data data;
#ifdef CONFIG_SCHED_DEBUG
char *name;
#endif
};
extern void set_sched_topology(struct sched_domain_topology_level *tl);
#ifdef CONFIG_SCHED_DEBUG
# define SD_INIT_NAME(type) .name = #type
#else
# define SD_INIT_NAME(type)
#endif
#else /* CONFIG_SMP */
struct sched_domain_attr;
static inline void
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
}
static inline bool cpus_share_cache(int this_cpu, int that_cpu)
{
return true;
}
#endif /* !CONFIG_SMP */
static inline int task_node(const struct task_struct *p)
{
return cpu_to_node(task_cpu(p));
}
#endif /* _LINUX_SCHED_TOPOLOGY_H */