5db58faf98
This patch has some unit tests and a test_lru_dist. The test_lru_dist reads in the numeric keys from a file. The files used here are generated by a modified fio-genzipf tool originated from the fio test suit. The sample data file can be found here: https://github.com/iamkafai/bpf-lru The zipf.* data files have 100k numeric keys and the key is also ranged from 1 to 100k. The test_lru_dist outputs the number of unique keys (nr_unique). F.e. The following means, 61239 of them is unique out of 100k keys. nr_misses means it cannot be found in the LRU map, so nr_misses must be >= nr_unique. test_lru_dist also simulates a perfect LRU map as a comparison: [root@arch-fb-vm1 ~]# ~/devshare/fb-kernel/linux/samples/bpf/test_lru_dist \ /root/zipf.100k.a1_01.out 4000 1 ... test_parallel_lru_dist (map_type:9 map_flags:0x0): task:0 BPF LRU: nr_unique:23093(/100000) nr_misses:31603(/100000) task:0 Perfect LRU: nr_unique:23093(/100000 nr_misses:34328(/100000) .... test_parallel_lru_dist (map_type:9 map_flags:0x2): task:0 BPF LRU: nr_unique:23093(/100000) nr_misses:31710(/100000) task:0 Perfect LRU: nr_unique:23093(/100000 nr_misses:34328(/100000) [root@arch-fb-vm1 ~]# ~/devshare/fb-kernel/linux/samples/bpf/test_lru_dist \ /root/zipf.100k.a0_01.out 40000 1 ... test_parallel_lru_dist (map_type:9 map_flags:0x0): task:0 BPF LRU: nr_unique:61239(/100000) nr_misses:67054(/100000) task:0 Perfect LRU: nr_unique:61239(/100000 nr_misses:66993(/100000) ... test_parallel_lru_dist (map_type:9 map_flags:0x2): task:0 BPF LRU: nr_unique:61239(/100000) nr_misses:67068(/100000) task:0 Perfect LRU: nr_unique:61239(/100000 nr_misses:66993(/100000) LRU map has also been added to map_perf_test: /* Global LRU */ [root@kerneltest003.31.prn1 ~]# for i in 1 4 8; do echo -n "$i cpus: "; \ ./map_perf_test 16 $i | awk '{r += $3}END{print r " updates"}'; done 1 cpus: 2934082 updates 4 cpus: 7391434 updates 8 cpus: 6500576 updates /* Percpu LRU */ [root@kerneltest003.31.prn1 ~]# for i in 1 4 8; do echo -n "$i cpus: "; \ ./map_perf_test 32 $i | awk '{r += $3}END{print r " updates"}'; done 1 cpus: 2896553 updates 4 cpus: 9766395 updates 8 cpus: 17460553 updates Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
189 lines
4.0 KiB
C
189 lines
4.0 KiB
C
/* Copyright (c) 2016 Facebook
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#define _GNU_SOURCE
|
|
#include <sched.h>
|
|
#include <stdio.h>
|
|
#include <sys/types.h>
|
|
#include <asm/unistd.h>
|
|
#include <unistd.h>
|
|
#include <assert.h>
|
|
#include <sys/wait.h>
|
|
#include <stdlib.h>
|
|
#include <signal.h>
|
|
#include <linux/bpf.h>
|
|
#include <string.h>
|
|
#include <time.h>
|
|
#include <sys/resource.h>
|
|
#include "libbpf.h"
|
|
#include "bpf_load.h"
|
|
|
|
#define MAX_CNT 1000000
|
|
|
|
static __u64 time_get_ns(void)
|
|
{
|
|
struct timespec ts;
|
|
|
|
clock_gettime(CLOCK_MONOTONIC, &ts);
|
|
return ts.tv_sec * 1000000000ull + ts.tv_nsec;
|
|
}
|
|
|
|
#define HASH_PREALLOC (1 << 0)
|
|
#define PERCPU_HASH_PREALLOC (1 << 1)
|
|
#define HASH_KMALLOC (1 << 2)
|
|
#define PERCPU_HASH_KMALLOC (1 << 3)
|
|
#define LRU_HASH_PREALLOC (1 << 4)
|
|
#define PERCPU_LRU_HASH_PREALLOC (1 << 5)
|
|
|
|
static int test_flags = ~0;
|
|
|
|
static void test_hash_prealloc(int cpu)
|
|
{
|
|
__u64 start_time;
|
|
int i;
|
|
|
|
start_time = time_get_ns();
|
|
for (i = 0; i < MAX_CNT; i++)
|
|
syscall(__NR_getuid);
|
|
printf("%d:hash_map_perf pre-alloc %lld events per sec\n",
|
|
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
|
|
}
|
|
|
|
static void test_lru_hash_prealloc(int cpu)
|
|
{
|
|
__u64 start_time;
|
|
int i;
|
|
|
|
start_time = time_get_ns();
|
|
for (i = 0; i < MAX_CNT; i++)
|
|
syscall(__NR_getpid);
|
|
printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
|
|
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
|
|
}
|
|
|
|
static void test_percpu_lru_hash_prealloc(int cpu)
|
|
{
|
|
__u64 start_time;
|
|
int i;
|
|
|
|
start_time = time_get_ns();
|
|
for (i = 0; i < MAX_CNT; i++)
|
|
syscall(__NR_getppid);
|
|
printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
|
|
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
|
|
}
|
|
|
|
static void test_percpu_hash_prealloc(int cpu)
|
|
{
|
|
__u64 start_time;
|
|
int i;
|
|
|
|
start_time = time_get_ns();
|
|
for (i = 0; i < MAX_CNT; i++)
|
|
syscall(__NR_geteuid);
|
|
printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n",
|
|
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
|
|
}
|
|
|
|
static void test_hash_kmalloc(int cpu)
|
|
{
|
|
__u64 start_time;
|
|
int i;
|
|
|
|
start_time = time_get_ns();
|
|
for (i = 0; i < MAX_CNT; i++)
|
|
syscall(__NR_getgid);
|
|
printf("%d:hash_map_perf kmalloc %lld events per sec\n",
|
|
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
|
|
}
|
|
|
|
static void test_percpu_hash_kmalloc(int cpu)
|
|
{
|
|
__u64 start_time;
|
|
int i;
|
|
|
|
start_time = time_get_ns();
|
|
for (i = 0; i < MAX_CNT; i++)
|
|
syscall(__NR_getegid);
|
|
printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n",
|
|
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
|
|
}
|
|
|
|
static void loop(int cpu)
|
|
{
|
|
cpu_set_t cpuset;
|
|
|
|
CPU_ZERO(&cpuset);
|
|
CPU_SET(cpu, &cpuset);
|
|
sched_setaffinity(0, sizeof(cpuset), &cpuset);
|
|
|
|
if (test_flags & HASH_PREALLOC)
|
|
test_hash_prealloc(cpu);
|
|
|
|
if (test_flags & PERCPU_HASH_PREALLOC)
|
|
test_percpu_hash_prealloc(cpu);
|
|
|
|
if (test_flags & HASH_KMALLOC)
|
|
test_hash_kmalloc(cpu);
|
|
|
|
if (test_flags & PERCPU_HASH_KMALLOC)
|
|
test_percpu_hash_kmalloc(cpu);
|
|
|
|
if (test_flags & LRU_HASH_PREALLOC)
|
|
test_lru_hash_prealloc(cpu);
|
|
|
|
if (test_flags & PERCPU_LRU_HASH_PREALLOC)
|
|
test_percpu_lru_hash_prealloc(cpu);
|
|
}
|
|
|
|
static void run_perf_test(int tasks)
|
|
{
|
|
pid_t pid[tasks];
|
|
int i;
|
|
|
|
for (i = 0; i < tasks; i++) {
|
|
pid[i] = fork();
|
|
if (pid[i] == 0) {
|
|
loop(i);
|
|
exit(0);
|
|
} else if (pid[i] == -1) {
|
|
printf("couldn't spawn #%d process\n", i);
|
|
exit(1);
|
|
}
|
|
}
|
|
for (i = 0; i < tasks; i++) {
|
|
int status;
|
|
|
|
assert(waitpid(pid[i], &status, 0) == pid[i]);
|
|
assert(status == 0);
|
|
}
|
|
}
|
|
|
|
int main(int argc, char **argv)
|
|
{
|
|
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
|
|
char filename[256];
|
|
int num_cpu = 8;
|
|
|
|
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
|
|
setrlimit(RLIMIT_MEMLOCK, &r);
|
|
|
|
if (argc > 1)
|
|
test_flags = atoi(argv[1]) ? : test_flags;
|
|
|
|
if (argc > 2)
|
|
num_cpu = atoi(argv[2]) ? : num_cpu;
|
|
|
|
if (load_bpf_file(filename)) {
|
|
printf("%s", bpf_log_buf);
|
|
return 1;
|
|
}
|
|
|
|
run_perf_test(num_cpu);
|
|
|
|
return 0;
|
|
}
|