mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Matt Fleming](/assets/img/avatar_default.png)
SD_BALANCE_{FORK,EXEC} and SD_WAKE_AFFINE are stripped in sd_init()
for any sched domains with a NUMA distance greater than 2 hops
(RECLAIM_DISTANCE). The idea being that it's expensive to balance
across domains that far apart.
However, as is rather unfortunately explained in:
commit 32e45ff43e
("mm: increase RECLAIM_DISTANCE to 30")
the value for RECLAIM_DISTANCE is based on node distance tables from
2011-era hardware.
Current AMD EPYC machines have the following NUMA node distances:
node distances:
node 0 1 2 3 4 5 6 7
0: 10 16 16 16 32 32 32 32
1: 16 10 16 16 32 32 32 32
2: 16 16 10 16 32 32 32 32
3: 16 16 16 10 32 32 32 32
4: 32 32 32 32 10 16 16 16
5: 32 32 32 32 16 10 16 16
6: 32 32 32 32 16 16 10 16
7: 32 32 32 32 16 16 16 10
where 2 hops is 32.
The result is that the scheduler fails to load balance properly across
NUMA nodes on different sockets -- 2 hops apart.
For example, pinning 16 busy threads to NUMA nodes 0 (CPUs 0-7) and 4
(CPUs 32-39) like so,
$ numactl -C 0-7,32-39 ./spinner 16
causes all threads to fork and remain on node 0 until the active
balancer kicks in after a few seconds and forcibly moves some threads
to node 4.
Override node_reclaim_distance for AMD Zen.
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Suravee.Suthikulpanit@amd.com
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas.Lendacky@amd.com
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20190808195301.13222-3-matt@codeblueprint.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
230 lines
5.5 KiB
C
230 lines
5.5 KiB
C
/*
|
|
* include/linux/topology.h
|
|
*
|
|
* Written by: Matthew Dobson, IBM Corporation
|
|
*
|
|
* Copyright (C) 2002, IBM Corp.
|
|
*
|
|
* All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
|
|
* NON INFRINGEMENT. See the GNU General Public License for more
|
|
* details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
*
|
|
* Send feedback to <colpatch@us.ibm.com>
|
|
*/
|
|
#ifndef _LINUX_TOPOLOGY_H
|
|
#define _LINUX_TOPOLOGY_H
|
|
|
|
#include <linux/cpumask.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/percpu.h>
|
|
#include <asm/topology.h>
|
|
|
|
#ifndef nr_cpus_node
|
|
#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
|
|
#endif
|
|
|
|
#define for_each_node_with_cpus(node) \
|
|
for_each_online_node(node) \
|
|
if (nr_cpus_node(node))
|
|
|
|
int arch_update_cpu_topology(void);
|
|
|
|
/* Conform to ACPI 2.0 SLIT distance definitions */
|
|
#define LOCAL_DISTANCE 10
|
|
#define REMOTE_DISTANCE 20
|
|
#ifndef node_distance
|
|
#define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE)
|
|
#endif
|
|
#ifndef RECLAIM_DISTANCE
|
|
/*
|
|
* If the distance between nodes in a system is larger than RECLAIM_DISTANCE
|
|
* (in whatever arch specific measurement units returned by node_distance())
|
|
* and node_reclaim_mode is enabled then the VM will only call node_reclaim()
|
|
* on nodes within this distance.
|
|
*/
|
|
#define RECLAIM_DISTANCE 30
|
|
#endif
|
|
|
|
/*
|
|
* The following tunable allows platforms to override the default node
|
|
* reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are
|
|
* sufficiently fast that the default value actually hurts
|
|
* performance.
|
|
*
|
|
* AMD EPYC machines use this because even though the 2-hop distance
|
|
* is 32 (3.2x slower than a local memory access) performance actually
|
|
* *improves* if allowed to reclaim memory and load balance tasks
|
|
* between NUMA nodes 2-hops apart.
|
|
*/
|
|
extern int __read_mostly node_reclaim_distance;
|
|
|
|
#ifndef PENALTY_FOR_NODE_WITH_CPUS
|
|
#define PENALTY_FOR_NODE_WITH_CPUS (1)
|
|
#endif
|
|
|
|
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
|
|
DECLARE_PER_CPU(int, numa_node);
|
|
|
|
#ifndef numa_node_id
|
|
/* Returns the number of the current Node. */
|
|
static inline int numa_node_id(void)
|
|
{
|
|
return raw_cpu_read(numa_node);
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_node
|
|
static inline int cpu_to_node(int cpu)
|
|
{
|
|
return per_cpu(numa_node, cpu);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_numa_node
|
|
static inline void set_numa_node(int node)
|
|
{
|
|
this_cpu_write(numa_node, node);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_cpu_numa_node
|
|
static inline void set_cpu_numa_node(int cpu, int node)
|
|
{
|
|
per_cpu(numa_node, cpu) = node;
|
|
}
|
|
#endif
|
|
|
|
#else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */
|
|
|
|
/* Returns the number of the current Node. */
|
|
#ifndef numa_node_id
|
|
static inline int numa_node_id(void)
|
|
{
|
|
return cpu_to_node(raw_smp_processor_id());
|
|
}
|
|
#endif
|
|
|
|
#endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */
|
|
|
|
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
|
|
|
|
/*
|
|
* N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
|
|
* It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
|
|
* Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem().
|
|
*/
|
|
DECLARE_PER_CPU(int, _numa_mem_);
|
|
extern int _node_numa_mem_[MAX_NUMNODES];
|
|
|
|
#ifndef set_numa_mem
|
|
static inline void set_numa_mem(int node)
|
|
{
|
|
this_cpu_write(_numa_mem_, node);
|
|
_node_numa_mem_[numa_node_id()] = node;
|
|
}
|
|
#endif
|
|
|
|
#ifndef node_to_mem_node
|
|
static inline int node_to_mem_node(int node)
|
|
{
|
|
return _node_numa_mem_[node];
|
|
}
|
|
#endif
|
|
|
|
#ifndef numa_mem_id
|
|
/* Returns the number of the nearest Node with memory */
|
|
static inline int numa_mem_id(void)
|
|
{
|
|
return raw_cpu_read(_numa_mem_);
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_mem
|
|
static inline int cpu_to_mem(int cpu)
|
|
{
|
|
return per_cpu(_numa_mem_, cpu);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_cpu_numa_mem
|
|
static inline void set_cpu_numa_mem(int cpu, int node)
|
|
{
|
|
per_cpu(_numa_mem_, cpu) = node;
|
|
_node_numa_mem_[cpu_to_node(cpu)] = node;
|
|
}
|
|
#endif
|
|
|
|
#else /* !CONFIG_HAVE_MEMORYLESS_NODES */
|
|
|
|
#ifndef numa_mem_id
|
|
/* Returns the number of the nearest Node with memory */
|
|
static inline int numa_mem_id(void)
|
|
{
|
|
return numa_node_id();
|
|
}
|
|
#endif
|
|
|
|
#ifndef node_to_mem_node
|
|
static inline int node_to_mem_node(int node)
|
|
{
|
|
return node;
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_mem
|
|
static inline int cpu_to_mem(int cpu)
|
|
{
|
|
return cpu_to_node(cpu);
|
|
}
|
|
#endif
|
|
|
|
#endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */
|
|
|
|
#ifndef topology_physical_package_id
|
|
#define topology_physical_package_id(cpu) ((void)(cpu), -1)
|
|
#endif
|
|
#ifndef topology_die_id
|
|
#define topology_die_id(cpu) ((void)(cpu), -1)
|
|
#endif
|
|
#ifndef topology_core_id
|
|
#define topology_core_id(cpu) ((void)(cpu), 0)
|
|
#endif
|
|
#ifndef topology_sibling_cpumask
|
|
#define topology_sibling_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
#ifndef topology_core_cpumask
|
|
#define topology_core_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
#ifndef topology_die_cpumask
|
|
#define topology_die_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
|
|
#ifdef CONFIG_SCHED_SMT
|
|
static inline const struct cpumask *cpu_smt_mask(int cpu)
|
|
{
|
|
return topology_sibling_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 */
|