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 32e45ff43eaf ("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 <m...@codeblueprint.co.uk> Cc: "Suthikulpanit, Suravee" <suravee.suthikulpa...@amd.com> Cc: Mel Gorman <mgor...@techsingularity.net> Cc: "Lendacky, Thomas" <thomas.lenda...@amd.com> Cc: Borislav Petkov <b...@alien8.de> --- arch/x86/kernel/cpu/amd.c | 3 +++ include/linux/topology.h | 14 ++++++++++++++ kernel/sched/topology.c | 3 ++- mm/khugepaged.c | 2 +- mm/page_alloc.c | 2 +- 5 files changed, 21 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8d4e50428b68..d94bf83d5ee6 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/random.h> +#include <linux/topology.h> #include <asm/processor.h> #include <asm/apic.h> #include <asm/cacheinfo.h> @@ -824,6 +825,8 @@ static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); + node_reclaim_distance = 32; + /* * Fix erratum 1076: CPB feature bit not being set in CPUID. * Always set it, except when running under a hypervisor. diff --git a/include/linux/topology.h b/include/linux/topology.h index 47a3e3c08036..579522ec446c 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -59,6 +59,20 @@ int arch_update_cpu_topology(void); */ #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 diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f751ce0b783e..f684fde00536 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1284,6 +1284,7 @@ static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; #endif /* @@ -1402,7 +1403,7 @@ sd_init(struct sched_domain_topology_level *tl, sd->flags &= ~SD_PREFER_SIBLING; sd->flags |= SD_SERIALIZE; - if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + if (sched_domains_numa_distance[tl->numa_level] > node_reclaim_distance) { sd->flags &= ~(SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index eaaa21b23215..ccede2425c3f 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -710,7 +710,7 @@ static bool khugepaged_scan_abort(int nid) for (i = 0; i < MAX_NUMNODES; i++) { if (!khugepaged_node_load[i]) continue; - if (node_distance(nid, i) > RECLAIM_DISTANCE) + if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 272c6de1bf4e..0d54cd2c43a4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3522,7 +3522,7 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order, static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= - RECLAIM_DISTANCE; + node_reclaim_distance; } #else /* CONFIG_NUMA */ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) -- 2.13.7