linux/samples/bpf/map_perf_test_kern.c

203 lines
4.4 KiB
C
Raw Normal View History

/* 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.
*/
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#define MAX_ENTRIES 1000
struct bpf_map_def SEC("maps") hash_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = MAX_ENTRIES,
};
bpf: Add tests for the LRU bpf_htab 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>
2016-11-11 19:55:11 +01:00
struct bpf_map_def SEC("maps") lru_hash_map = {
.type = BPF_MAP_TYPE_LRU_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = 10000,
};
struct bpf_map_def SEC("maps") percpu_lru_hash_map = {
.type = BPF_MAP_TYPE_LRU_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = 10000,
.map_flags = BPF_F_NO_COMMON_LRU,
};
struct bpf_map_def SEC("maps") percpu_hash_map = {
.type = BPF_MAP_TYPE_PERCPU_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = MAX_ENTRIES,
};
struct bpf_map_def SEC("maps") hash_map_alloc = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = MAX_ENTRIES,
.map_flags = BPF_F_NO_PREALLOC,
};
struct bpf_map_def SEC("maps") percpu_hash_map_alloc = {
.type = BPF_MAP_TYPE_PERCPU_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = MAX_ENTRIES,
.map_flags = BPF_F_NO_PREALLOC,
};
struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
.type = BPF_MAP_TYPE_LPM_TRIE,
.key_size = 8,
.value_size = sizeof(long),
.max_entries = 10000,
.map_flags = BPF_F_NO_PREALLOC,
};
samples/bpf: add map_lookup microbenchmark $ map_perf_test 128 speed of HASH bpf_map_lookup_elem() in lookups per second w/o JIT w/JIT before 46M 58M after 42M 74M perf report before: 54.23% map_perf_test [kernel.kallsyms] [k] __htab_map_lookup_elem 14.24% map_perf_test [kernel.kallsyms] [k] lookup_elem_raw 8.84% map_perf_test [kernel.kallsyms] [k] htab_map_lookup_elem 5.93% map_perf_test [kernel.kallsyms] [k] bpf_map_lookup_elem 2.30% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 1.49% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler after: 60.03% map_perf_test [kernel.kallsyms] [k] __htab_map_lookup_elem 18.07% map_perf_test [kernel.kallsyms] [k] lookup_elem_raw 2.91% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 1.94% map_perf_test [kernel.kallsyms] [k] _einittext 1.90% map_perf_test [kernel.kallsyms] [k] __audit_syscall_exit 1.72% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler Notice that bpf_map_lookup_elem() and htab_map_lookup_elem() are trivial functions, yet they take sizeable amount of cpu time. htab_map_gen_lookup() removes bpf_map_lookup_elem() and converts htab_map_lookup_elem() into three BPF insns which causing cpu time for bpf_prog_da4fc6a3f41761a2() slightly increase. $ map_perf_test 256 speed of ARRAY bpf_map_lookup_elem() in lookups per second w/o JIT w/JIT before 97M 174M after 64M 280M before: 37.33% map_perf_test [kernel.kallsyms] [k] array_map_lookup_elem 13.95% map_perf_test [kernel.kallsyms] [k] bpf_map_lookup_elem 6.54% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 4.57% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler after: 32.86% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 6.54% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler array_map_gen_lookup() removes calls to array_map_lookup_elem() and bpf_map_lookup_elem() and replaces them with 7 bpf insns. The performance without JIT is slower, since executing extra insns in the interpreter is slower than running native C code, but with JIT the performance gains are obvious, since native C->x86 code is replaced with fewer bpf->x86 instructions. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-16 02:26:44 +01:00
struct bpf_map_def SEC("maps") array_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = MAX_ENTRIES,
};
SEC("kprobe/sys_getuid")
int stress_hmap(struct pt_regs *ctx)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
long *value;
bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY);
value = bpf_map_lookup_elem(&hash_map, &key);
if (value)
bpf_map_delete_elem(&hash_map, &key);
bpf: Add tests for the LRU bpf_htab 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>
2016-11-11 19:55:11 +01:00
return 0;
}
SEC("kprobe/sys_geteuid")
int stress_percpu_hmap(struct pt_regs *ctx)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
long *value;
bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY);
value = bpf_map_lookup_elem(&percpu_hash_map, &key);
if (value)
bpf_map_delete_elem(&percpu_hash_map, &key);
return 0;
}
SEC("kprobe/sys_getgid")
int stress_hmap_alloc(struct pt_regs *ctx)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
long *value;
bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY);
value = bpf_map_lookup_elem(&hash_map_alloc, &key);
if (value)
bpf_map_delete_elem(&hash_map_alloc, &key);
return 0;
}
SEC("kprobe/sys_getegid")
int stress_percpu_hmap_alloc(struct pt_regs *ctx)
{
u32 key = bpf_get_current_pid_tgid();
long init_val = 1;
long *value;
bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY);
value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key);
if (value)
bpf_map_delete_elem(&percpu_hash_map_alloc, &key);
return 0;
}
bpf: Add tests for the LRU bpf_htab 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>
2016-11-11 19:55:11 +01:00
SEC("kprobe/sys_getpid")
int stress_lru_hmap_alloc(struct pt_regs *ctx)
{
u32 key = bpf_get_prandom_u32();
long val = 1;
bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
return 0;
}
SEC("kprobe/sys_getppid")
int stress_percpu_lru_hmap_alloc(struct pt_regs *ctx)
{
u32 key = bpf_get_prandom_u32();
long val = 1;
bpf_map_update_elem(&percpu_lru_hash_map, &key, &val, BPF_ANY);
return 0;
}
SEC("kprobe/sys_gettid")
int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
{
union {
u32 b32[2];
u8 b8[8];
} key;
unsigned int i;
key.b32[0] = 32;
key.b8[4] = 192;
key.b8[5] = 168;
key.b8[6] = 0;
key.b8[7] = 1;
#pragma clang loop unroll(full)
for (i = 0; i < 32; ++i)
bpf_map_lookup_elem(&lpm_trie_map_alloc, &key);
return 0;
}
samples/bpf: add map_lookup microbenchmark $ map_perf_test 128 speed of HASH bpf_map_lookup_elem() in lookups per second w/o JIT w/JIT before 46M 58M after 42M 74M perf report before: 54.23% map_perf_test [kernel.kallsyms] [k] __htab_map_lookup_elem 14.24% map_perf_test [kernel.kallsyms] [k] lookup_elem_raw 8.84% map_perf_test [kernel.kallsyms] [k] htab_map_lookup_elem 5.93% map_perf_test [kernel.kallsyms] [k] bpf_map_lookup_elem 2.30% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 1.49% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler after: 60.03% map_perf_test [kernel.kallsyms] [k] __htab_map_lookup_elem 18.07% map_perf_test [kernel.kallsyms] [k] lookup_elem_raw 2.91% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 1.94% map_perf_test [kernel.kallsyms] [k] _einittext 1.90% map_perf_test [kernel.kallsyms] [k] __audit_syscall_exit 1.72% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler Notice that bpf_map_lookup_elem() and htab_map_lookup_elem() are trivial functions, yet they take sizeable amount of cpu time. htab_map_gen_lookup() removes bpf_map_lookup_elem() and converts htab_map_lookup_elem() into three BPF insns which causing cpu time for bpf_prog_da4fc6a3f41761a2() slightly increase. $ map_perf_test 256 speed of ARRAY bpf_map_lookup_elem() in lookups per second w/o JIT w/JIT before 97M 174M after 64M 280M before: 37.33% map_perf_test [kernel.kallsyms] [k] array_map_lookup_elem 13.95% map_perf_test [kernel.kallsyms] [k] bpf_map_lookup_elem 6.54% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 4.57% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler after: 32.86% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 6.54% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler array_map_gen_lookup() removes calls to array_map_lookup_elem() and bpf_map_lookup_elem() and replaces them with 7 bpf insns. The performance without JIT is slower, since executing extra insns in the interpreter is slower than running native C code, but with JIT the performance gains are obvious, since native C->x86 code is replaced with fewer bpf->x86 instructions. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-16 02:26:44 +01:00
SEC("kprobe/sys_getpgid")
int stress_hash_map_lookup(struct pt_regs *ctx)
{
u32 key = 1, i;
long *value;
#pragma clang loop unroll(full)
for (i = 0; i < 64; ++i)
value = bpf_map_lookup_elem(&hash_map, &key);
return 0;
}
SEC("kprobe/sys_getpgrp")
int stress_array_map_lookup(struct pt_regs *ctx)
{
u32 key = 1, i;
long *value;
#pragma clang loop unroll(full)
for (i = 0; i < 64; ++i)
value = bpf_map_lookup_elem(&array_map, &key);
return 0;
}
char _license[] SEC("license") = "GPL";
u32 _version SEC("version") = LINUX_VERSION_CODE;