diff mbox series

[v4,bpf-next,04/15] samples/bpf: Reduce syscall overhead in map_perf_test.

Message ID 20220826024430.84565-5-alexei.starovoitov@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf: BPF specific memory allocator. | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR fail PR summary
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 8 maintainers not CCed: john.fastabend@gmail.com jolsa@kernel.org song@kernel.org yhs@fb.com haoluo@google.com martin.lau@linux.dev kpsingh@kernel.org sdf@google.com
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning CHECK: Prefer kernel type 'u32' over 'uint32_t' WARNING: line length of 86 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-10 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for test_maps on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-4 success Logs for llvm-toolchain
bpf/vmtest-bpf-next-VM_Test-5 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-2 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-1 success Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-11 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-13 success Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-7 fail Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 fail Logs for test_maps on x86_64 with llvm-16

Commit Message

Alexei Starovoitov Aug. 26, 2022, 2:44 a.m. UTC 
From: Alexei Starovoitov <ast@kernel.org>

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.

Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/map_perf_test_kern.c | 44 ++++++++++++++++++++------------
 samples/bpf/map_perf_test_user.c |  2 +-
 2 files changed, 29 insertions(+), 17 deletions(-)
diff mbox series

Patch

diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 8773f22b6a98..7342c5b2f278 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -108,11 +108,14 @@  int stress_hmap(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	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);
+	for (i = 0; i < 10; i++) {
+		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);
+	}
 
 	return 0;
 }
@@ -123,11 +126,14 @@  int stress_percpu_hmap(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	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);
+	for (i = 0; i < 10; i++) {
+		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;
 }
 
@@ -137,11 +143,14 @@  int stress_hmap_alloc(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	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);
+	for (i = 0; i < 10; i++) {
+		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;
 }
 
@@ -151,11 +160,14 @@  int stress_percpu_hmap_alloc(struct pt_regs *ctx)
 	u32 key = bpf_get_current_pid_tgid();
 	long init_val = 1;
 	long *value;
+	int i;
 
-	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);
+	for (i = 0; i < 10; i++) {
+		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;
 }
 
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index b6fc174ab1f2..1bb53f4b29e1 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -72,7 +72,7 @@  static int test_flags = ~0;
 static uint32_t num_map_entries;
 static uint32_t inner_lru_hash_size;
 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)
 {