linux/tools/testing/selftests/bpf/bench.h
Dave Marchevsky 2b4b2621fd selftests/bpf: Add benchmark for local_storage RCU Tasks Trace usage
This benchmark measures grace period latency and kthread cpu usage of
RCU Tasks Trace when many processes are creating/deleting BPF
local_storage. Intent here is to quantify improvement on these metrics
after Paul's recent RCU Tasks patches [0].

Specifically, fork 15k tasks which call a bpf prog that creates/destroys
task local_storage and sleep in a loop, resulting in many
call_rcu_tasks_trace calls.

To determine grace period latency, trace time elapsed between
rcu_tasks_trace_pregp_step and rcu_tasks_trace_postgp; for cpu usage
look at rcu_task_trace_kthread's stime in /proc/PID/stat.

On my virtualized test environment (Skylake, 8 cpus) benchmark results
demonstrate significant improvement:

BEFORE Paul's patches:

  SUMMARY tasks_trace grace period latency        avg 22298.551 us stddev 1302.165 us
  SUMMARY ticks per tasks_trace grace period      avg 2.291 stddev 0.324

AFTER Paul's patches:

  SUMMARY tasks_trace grace period latency        avg 16969.197 us  stddev 2525.053 us
  SUMMARY ticks per tasks_trace grace period      avg 1.146 stddev 0.178

Note that since these patches are not in bpf-next benchmarking was done
by cherry-picking this patch onto rcu tree.

  [0] https://lore.kernel.org/rcu/20220620225402.GA3842369@paulmck-ThinkPad-P17-Gen-1/

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20220705190018.3239050-1-davemarchevsky@fb.com
2022-07-07 16:35:21 +02:00

104 lines
2.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#pragma once
#include <stdlib.h>
#include <stdbool.h>
#include <linux/err.h>
#include <errno.h>
#include <unistd.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include <math.h>
#include <time.h>
#include <sys/syscall.h>
struct cpu_set {
bool *cpus;
int cpus_len;
int next_cpu;
};
struct env {
char *bench_name;
int duration_sec;
int warmup_sec;
bool verbose;
bool list;
bool affinity;
int consumer_cnt;
int producer_cnt;
struct cpu_set prod_cpus;
struct cpu_set cons_cpus;
};
struct basic_stats {
double mean;
double stddev;
};
struct bench_res {
long hits;
long drops;
long false_hits;
long important_hits;
unsigned long gp_ns;
unsigned long gp_ct;
unsigned int stime;
};
struct bench {
const char *name;
void (*validate)(void);
void (*setup)(void);
void *(*producer_thread)(void *ctx);
void *(*consumer_thread)(void *ctx);
void (*measure)(struct bench_res* res);
void (*report_progress)(int iter, struct bench_res* res, long delta_ns);
void (*report_final)(struct bench_res res[], int res_cnt);
};
struct counter {
long value;
} __attribute__((aligned(128)));
extern struct env env;
extern const struct bench *bench;
void setup_libbpf(void);
void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
void hits_drops_report_final(struct bench_res res[], int res_cnt);
void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns);
void false_hits_report_final(struct bench_res res[], int res_cnt);
void ops_report_progress(int iter, struct bench_res *res, long delta_ns);
void ops_report_final(struct bench_res res[], int res_cnt);
void local_storage_report_progress(int iter, struct bench_res *res,
long delta_ns);
void local_storage_report_final(struct bench_res res[], int res_cnt);
void grace_period_latency_basic_stats(struct bench_res res[], int res_cnt,
struct basic_stats *gp_stat);
void grace_period_ticks_basic_stats(struct bench_res res[], int res_cnt,
struct basic_stats *gp_stat);
static inline __u64 get_time_ns(void)
{
struct timespec t;
clock_gettime(CLOCK_MONOTONIC, &t);
return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
}
static inline void atomic_inc(long *value)
{
(void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED);
}
static inline void atomic_add(long *value, long n)
{
(void)__atomic_add_fetch(value, n, __ATOMIC_RELAXED);
}
static inline long atomic_swap(long *value, long n)
{
return __atomic_exchange_n(value, n, __ATOMIC_RELAXED);
}