Commit 89dc8d0c authored by Alexei Starovoitov's avatar Alexei Starovoitov Committed by Daniel Borkmann

samples/bpf: Reduce syscall overhead in map_perf_test.

Make map_perf_test for preallocated and non-preallocated hash map
spend more time inside bpf program to focus performance analysis
on the speed of update/lookup/delete operations performed by bpf program.

It makes 'perf report' of bpf_mem_alloc look like:
 11.76%  map_perf_test    [k] _raw_spin_lock_irqsave
 11.26%  map_perf_test    [k] htab_map_update_elem
  9.70%  map_perf_test    [k] _raw_spin_lock
  9.47%  map_perf_test    [k] htab_map_delete_elem
  8.57%  map_perf_test    [k] memcpy_erms
  5.58%  map_perf_test    [k] alloc_htab_elem
  4.09%  map_perf_test    [k] __htab_map_lookup_elem
  3.44%  map_perf_test    [k] syscall_exit_to_user_mode
  3.13%  map_perf_test    [k] lookup_nulls_elem_raw
  3.05%  map_perf_test    [k] migrate_enable
  3.04%  map_perf_test    [k] memcmp
  2.67%  map_perf_test    [k] unit_free
  2.39%  map_perf_test    [k] lookup_elem_raw

Reduce default iteration count as well to make 'map_perf_test' quick enough
even on debug kernels.
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Acked-by: default avatarKumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: default avatarAndrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220902211058.60789-5-alexei.starovoitov@gmail.com
parent 37521bff
...@@ -108,11 +108,14 @@ int stress_hmap(struct pt_regs *ctx) ...@@ -108,11 +108,14 @@ int stress_hmap(struct pt_regs *ctx)
u32 key = bpf_get_current_pid_tgid(); u32 key = bpf_get_current_pid_tgid();
long init_val = 1; long init_val = 1;
long *value; long *value;
int i;
bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY); for (i = 0; i < 10; i++) {
value = bpf_map_lookup_elem(&hash_map, &key); bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY);
if (value) value = bpf_map_lookup_elem(&hash_map, &key);
bpf_map_delete_elem(&hash_map, &key); if (value)
bpf_map_delete_elem(&hash_map, &key);
}
return 0; return 0;
} }
...@@ -123,11 +126,14 @@ int stress_percpu_hmap(struct pt_regs *ctx) ...@@ -123,11 +126,14 @@ int stress_percpu_hmap(struct pt_regs *ctx)
u32 key = bpf_get_current_pid_tgid(); u32 key = bpf_get_current_pid_tgid();
long init_val = 1; long init_val = 1;
long *value; long *value;
int i;
bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY); for (i = 0; i < 10; i++) {
value = bpf_map_lookup_elem(&percpu_hash_map, &key); bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY);
if (value) value = bpf_map_lookup_elem(&percpu_hash_map, &key);
bpf_map_delete_elem(&percpu_hash_map, &key); if (value)
bpf_map_delete_elem(&percpu_hash_map, &key);
}
return 0; return 0;
} }
...@@ -137,11 +143,14 @@ int stress_hmap_alloc(struct pt_regs *ctx) ...@@ -137,11 +143,14 @@ int stress_hmap_alloc(struct pt_regs *ctx)
u32 key = bpf_get_current_pid_tgid(); u32 key = bpf_get_current_pid_tgid();
long init_val = 1; long init_val = 1;
long *value; long *value;
int i;
bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY); for (i = 0; i < 10; i++) {
value = bpf_map_lookup_elem(&hash_map_alloc, &key); bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY);
if (value) value = bpf_map_lookup_elem(&hash_map_alloc, &key);
bpf_map_delete_elem(&hash_map_alloc, &key); if (value)
bpf_map_delete_elem(&hash_map_alloc, &key);
}
return 0; return 0;
} }
...@@ -151,11 +160,14 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx) ...@@ -151,11 +160,14 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
u32 key = bpf_get_current_pid_tgid(); u32 key = bpf_get_current_pid_tgid();
long init_val = 1; long init_val = 1;
long *value; long *value;
int i;
bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY); for (i = 0; i < 10; i++) {
value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key); bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY);
if (value) value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key);
bpf_map_delete_elem(&percpu_hash_map_alloc, &key); if (value)
bpf_map_delete_elem(&percpu_hash_map_alloc, &key);
}
return 0; return 0;
} }
......
...@@ -72,7 +72,7 @@ static int test_flags = ~0; ...@@ -72,7 +72,7 @@ static int test_flags = ~0;
static uint32_t num_map_entries; static uint32_t num_map_entries;
static uint32_t inner_lru_hash_size; static uint32_t inner_lru_hash_size;
static int lru_hash_lookup_test_entries = 32; static int lru_hash_lookup_test_entries = 32;
static uint32_t max_cnt = 1000000; static uint32_t max_cnt = 10000;
static int check_test_flags(enum test_type t) static int check_test_flags(enum test_type t)
{ {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment