Numa Programming

# Hardware topology summary
numactl --hardware

# Detailed topology with distances
lstopo --of console

# sysfs nodes
ls /sys/devices/system/node/
cat /sys/devices/system/node/node0/meminfo
cat /sys/devices/system/node/node0/cpulist

available: 2 nodes (0-1)
node 0 cpus: 0-15
node 0 size: 65536 MB
node 1 cpus: 16-31
node 1 size: 65536 MB
node distances:
node   0   1
  0:  10  21
  1:  21  10

# Bind to node 0 CPUs and memory
numactl --cpunodebind=0 --membind=0 ./myapp

# Interleave memory across all nodes
numactl --interleave=all ./myapp

# Preferred node (fallback if full)
numactl --preferred=0 ./myapp

# Show process NUMA policy
numactl --show
cat /proc/self/numa_maps

#include <numa.h>
#include <numaif.h>
#include <stdio.h>

int main(void) {
    if (numa_available() < 0) {
        fprintf(stderr, "NUMA not available\n");
        return 1;
    }
    int node = numa_node_of_cpu(0);
    printf("CPU 0 on node %d\n", node);

    // Allocate on specific node
    size_t size = 1024 * 1024 * 1024;
    void *mem = numa_alloc_onnode(size, 0);
    if (!mem) return 1;

    // Bind existing memory
    unsigned long nodemask = 1UL << 0;
    mbind(mem, size, MPOL_BIND, &nodemask, sizeof(nodemask) * 8, 0);

    numa_free(mem, size);
    return 0;
}

gcc -o numa_test numa_test.c -lnuma

// Per-node freelist — avoids cross-node synchronization
#define MAX_NODES 8
struct per_node_pool {
    void *free_list[MAX_NODES];
    int   node_count;
};

void *pool_alloc_numa(struct per_node_pool *p) {
    int node = numa_node_of_cpu(sched_getcpu());
    void *blk = p->free_list[node];
    if (blk) {
        p->free_list[node] = *(void **)blk;
        return blk;
    }
    return numa_alloc_onnode(BLOCK_SIZE, node);
}

# Pin thread 0 to CPU 0 (node 0), allocate on node 0
numactl --cpunodebind=0 --membind=0 ./worker --id 0
numactl --cpunodebind=1 --membind=1 ./worker --id 1

#include <pthread.h>
#include <sched.h>

cpu_set_t cpuset;
CPU_ZERO(&cpuset);
CPU_SET(target_cpu, &cpuset);
pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);

# Cache misses often spike with remote memory
perf stat -e cache-misses,cache-references,node-load-misses \
    numactl --cpunodebind=0 --membind=1 ./myapp

# Compare local vs remote binding
perf stat numactl --cpunodebind=0 --membind=0 ./myapp
perf stat numactl --cpunodebind=0 --membind=1 ./myapp

# NUMA hit/miss stats (if available)
perf stat -e node-loads,node-load-misses,node-stores ./myapp

// Microbenchmark: touch 1GB on local vs remote node
clock_t start = clock();
for (size_t i = 0; i < size; i += 4096)
    sum += ((char *)mem)[i];

# Graphical (if X11)
lstopo

# Text with memory/PCI
lstopo --of ascii

# Export for documentation
lstopo file.png

Poor scaling on multi-socket?
├── Check numactl --hardware
├── Verify thread and memory on same node
├── perf stat node-load-misses
├── Remote misses high?
│   ├── numactl --membind=local
│   └── Per-node data partitioning
└── Still slow → memory bandwidth bound; reduce sharing