68a6772f11
Add 2 benchmarks: 1. Performance of thread creation/exiting in presence of breakpoints. 2. Performance of breakpoint modification in presence of threads. The benchmarks capture use cases that we are interested in: using inheritable breakpoints in large highly-threaded applications. The benchmarks show significant slowdown imposed by breakpoints (even when they don't fire). Testing on Intel 8173M with 112 HW threads show: perf bench --repeat=56 breakpoint thread --breakpoints=0 --parallelism=56 --threads=20 78.675000 usecs/op perf bench --repeat=56 breakpoint thread --breakpoints=4 --parallelism=56 --threads=20 12967.135714 usecs/op That's 165x slowdown due to presence of the breakpoints. perf bench --repeat=20000 breakpoint enable --passive=0 --active=0 1.433250 usecs/op perf bench --repeat=20000 breakpoint enable --passive=224 --active=0 585.318400 usecs/op perf bench --repeat=20000 breakpoint enable --passive=0 --active=111 635.953000 usecs/op That's 408x and 444x slowdown due to presence of threads. Profiles show some overhead in toggle_bp_slot, but also very high contention: 90.83% breakpoint-thre [kernel.kallsyms] [k] osq_lock 4.69% breakpoint-thre [kernel.kallsyms] [k] mutex_spin_on_owner 2.06% breakpoint-thre [kernel.kallsyms] [k] __reserve_bp_slot 2.04% breakpoint-thre [kernel.kallsyms] [k] toggle_bp_slot 79.01% breakpoint-enab [kernel.kallsyms] [k] smp_call_function_single 9.94% breakpoint-enab [kernel.kallsyms] [k] llist_add_batch 5.70% breakpoint-enab [kernel.kallsyms] [k] _raw_spin_lock_irq 1.84% breakpoint-enab [kernel.kallsyms] [k] event_function_call 1.12% breakpoint-enab [kernel.kallsyms] [k] send_call_function_single_ipi 0.37% breakpoint-enab [kernel.kallsyms] [k] generic_exec_single 0.24% breakpoint-enab [kernel.kallsyms] [k] __perf_event_disable 0.20% breakpoint-enab [kernel.kallsyms] [k] _perf_event_enable 0.18% breakpoint-enab [kernel.kallsyms] [k] toggle_bp_slot Committer notes: Fixup struct init for older compilers: 3 32.90 alpine:3.5 : FAIL clang version 3.8.1 (tags/RELEASE_381/final) bench/breakpoint.c:49:34: error: missing field 'size' initializer [-Werror,-Wmissing-field-initializers] struct perf_event_attr attr = {0}; ^ 1 error generated. 7 37.31 alpine:3.9 : FAIL gcc version 8.3.0 (Alpine 8.3.0) bench/breakpoint.c:49:34: error: missing field 'size' initializer [-Werror,-Wmissing-field-initializers] struct perf_event_attr attr = {0}; ^ 1 error generated. Signed-off-by: Dmitriy Vyukov <dvyukov@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Marco Elver <elver@google.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20220505155745.1690906-1-dvyukov@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
333 lines
8.6 KiB
C
333 lines
8.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* builtin-bench.c
|
|
*
|
|
* General benchmarking collections provided by perf
|
|
*
|
|
* Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
|
|
*/
|
|
|
|
/*
|
|
* Available benchmark collection list:
|
|
*
|
|
* sched ... scheduler and IPC performance
|
|
* syscall ... System call performance
|
|
* mem ... memory access performance
|
|
* numa ... NUMA scheduling and MM performance
|
|
* futex ... Futex performance
|
|
* epoll ... Event poll performance
|
|
*/
|
|
#include <subcmd/parse-options.h>
|
|
#include "builtin.h"
|
|
#include "bench/bench.h"
|
|
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <sys/prctl.h>
|
|
#include <linux/zalloc.h>
|
|
|
|
typedef int (*bench_fn_t)(int argc, const char **argv);
|
|
|
|
struct bench {
|
|
const char *name;
|
|
const char *summary;
|
|
bench_fn_t fn;
|
|
};
|
|
|
|
#ifdef HAVE_LIBNUMA_SUPPORT
|
|
static struct bench numa_benchmarks[] = {
|
|
{ "mem", "Benchmark for NUMA workloads", bench_numa },
|
|
{ "all", "Run all NUMA benchmarks", NULL },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
#endif
|
|
|
|
static struct bench sched_benchmarks[] = {
|
|
{ "messaging", "Benchmark for scheduling and IPC", bench_sched_messaging },
|
|
{ "pipe", "Benchmark for pipe() between two processes", bench_sched_pipe },
|
|
{ "all", "Run all scheduler benchmarks", NULL },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
|
|
static struct bench syscall_benchmarks[] = {
|
|
{ "basic", "Benchmark for basic getppid(2) calls", bench_syscall_basic },
|
|
{ "all", "Run all syscall benchmarks", NULL },
|
|
{ NULL, NULL, NULL },
|
|
};
|
|
|
|
static struct bench mem_benchmarks[] = {
|
|
{ "memcpy", "Benchmark for memcpy() functions", bench_mem_memcpy },
|
|
{ "memset", "Benchmark for memset() functions", bench_mem_memset },
|
|
{ "find_bit", "Benchmark for find_bit() functions", bench_mem_find_bit },
|
|
{ "all", "Run all memory access benchmarks", NULL },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
|
|
static struct bench futex_benchmarks[] = {
|
|
{ "hash", "Benchmark for futex hash table", bench_futex_hash },
|
|
{ "wake", "Benchmark for futex wake calls", bench_futex_wake },
|
|
{ "wake-parallel", "Benchmark for parallel futex wake calls", bench_futex_wake_parallel },
|
|
{ "requeue", "Benchmark for futex requeue calls", bench_futex_requeue },
|
|
/* pi-futexes */
|
|
{ "lock-pi", "Benchmark for futex lock_pi calls", bench_futex_lock_pi },
|
|
{ "all", "Run all futex benchmarks", NULL },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
|
|
#ifdef HAVE_EVENTFD_SUPPORT
|
|
static struct bench epoll_benchmarks[] = {
|
|
{ "wait", "Benchmark epoll concurrent epoll_waits", bench_epoll_wait },
|
|
{ "ctl", "Benchmark epoll concurrent epoll_ctls", bench_epoll_ctl },
|
|
{ "all", "Run all futex benchmarks", NULL },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
#endif // HAVE_EVENTFD_SUPPORT
|
|
|
|
static struct bench internals_benchmarks[] = {
|
|
{ "synthesize", "Benchmark perf event synthesis", bench_synthesize },
|
|
{ "kallsyms-parse", "Benchmark kallsyms parsing", bench_kallsyms_parse },
|
|
{ "inject-build-id", "Benchmark build-id injection", bench_inject_build_id },
|
|
{ "evlist-open-close", "Benchmark evlist open and close", bench_evlist_open_close },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
|
|
static struct bench breakpoint_benchmarks[] = {
|
|
{ "thread", "Benchmark thread start/finish with breakpoints", bench_breakpoint_thread},
|
|
{ "enable", "Benchmark breakpoint enable/disable", bench_breakpoint_enable},
|
|
{ "all", "Run all breakpoint benchmarks", NULL},
|
|
{ NULL, NULL, NULL },
|
|
};
|
|
|
|
struct collection {
|
|
const char *name;
|
|
const char *summary;
|
|
struct bench *benchmarks;
|
|
};
|
|
|
|
static struct collection collections[] = {
|
|
{ "sched", "Scheduler and IPC benchmarks", sched_benchmarks },
|
|
{ "syscall", "System call benchmarks", syscall_benchmarks },
|
|
{ "mem", "Memory access benchmarks", mem_benchmarks },
|
|
#ifdef HAVE_LIBNUMA_SUPPORT
|
|
{ "numa", "NUMA scheduling and MM benchmarks", numa_benchmarks },
|
|
#endif
|
|
{"futex", "Futex stressing benchmarks", futex_benchmarks },
|
|
#ifdef HAVE_EVENTFD_SUPPORT
|
|
{"epoll", "Epoll stressing benchmarks", epoll_benchmarks },
|
|
#endif
|
|
{ "internals", "Perf-internals benchmarks", internals_benchmarks },
|
|
{ "breakpoint", "Breakpoint benchmarks", breakpoint_benchmarks },
|
|
{ "all", "All benchmarks", NULL },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
|
|
/* Iterate over all benchmark collections: */
|
|
#define for_each_collection(coll) \
|
|
for (coll = collections; coll->name; coll++)
|
|
|
|
/* Iterate over all benchmarks within a collection: */
|
|
#define for_each_bench(coll, bench) \
|
|
for (bench = coll->benchmarks; bench && bench->name; bench++)
|
|
|
|
static void dump_benchmarks(struct collection *coll)
|
|
{
|
|
struct bench *bench;
|
|
|
|
printf("\n # List of available benchmarks for collection '%s':\n\n", coll->name);
|
|
|
|
for_each_bench(coll, bench)
|
|
printf("%14s: %s\n", bench->name, bench->summary);
|
|
|
|
printf("\n");
|
|
}
|
|
|
|
static const char *bench_format_str;
|
|
|
|
/* Output/formatting style, exported to benchmark modules: */
|
|
int bench_format = BENCH_FORMAT_DEFAULT;
|
|
unsigned int bench_repeat = 10; /* default number of times to repeat the run */
|
|
|
|
static const struct option bench_options[] = {
|
|
OPT_STRING('f', "format", &bench_format_str, "default|simple", "Specify the output formatting style"),
|
|
OPT_UINTEGER('r', "repeat", &bench_repeat, "Specify amount of times to repeat the run"),
|
|
OPT_END()
|
|
};
|
|
|
|
static const char * const bench_usage[] = {
|
|
"perf bench [<common options>] <collection> <benchmark> [<options>]",
|
|
NULL
|
|
};
|
|
|
|
static void print_usage(void)
|
|
{
|
|
struct collection *coll;
|
|
int i;
|
|
|
|
printf("Usage: \n");
|
|
for (i = 0; bench_usage[i]; i++)
|
|
printf("\t%s\n", bench_usage[i]);
|
|
printf("\n");
|
|
|
|
printf(" # List of all available benchmark collections:\n\n");
|
|
|
|
for_each_collection(coll)
|
|
printf("%14s: %s\n", coll->name, coll->summary);
|
|
printf("\n");
|
|
}
|
|
|
|
static int bench_str2int(const char *str)
|
|
{
|
|
if (!str)
|
|
return BENCH_FORMAT_DEFAULT;
|
|
|
|
if (!strcmp(str, BENCH_FORMAT_DEFAULT_STR))
|
|
return BENCH_FORMAT_DEFAULT;
|
|
else if (!strcmp(str, BENCH_FORMAT_SIMPLE_STR))
|
|
return BENCH_FORMAT_SIMPLE;
|
|
|
|
return BENCH_FORMAT_UNKNOWN;
|
|
}
|
|
|
|
/*
|
|
* Run a specific benchmark but first rename the running task's ->comm[]
|
|
* to something meaningful:
|
|
*/
|
|
static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
|
|
int argc, const char **argv)
|
|
{
|
|
int size;
|
|
char *name;
|
|
int ret;
|
|
|
|
size = strlen(coll_name) + 1 + strlen(bench_name) + 1;
|
|
|
|
name = zalloc(size);
|
|
BUG_ON(!name);
|
|
|
|
scnprintf(name, size, "%s-%s", coll_name, bench_name);
|
|
|
|
prctl(PR_SET_NAME, name);
|
|
argv[0] = name;
|
|
|
|
ret = fn(argc, argv);
|
|
|
|
free(name);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void run_collection(struct collection *coll)
|
|
{
|
|
struct bench *bench;
|
|
const char *argv[2];
|
|
|
|
argv[1] = NULL;
|
|
/*
|
|
* TODO:
|
|
*
|
|
* Preparing preset parameters for
|
|
* embedded, ordinary PC, HPC, etc...
|
|
* would be helpful.
|
|
*/
|
|
for_each_bench(coll, bench) {
|
|
if (!bench->fn)
|
|
break;
|
|
printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
|
|
|
|
argv[1] = bench->name;
|
|
run_bench(coll->name, bench->name, bench->fn, 1, argv);
|
|
printf("\n");
|
|
}
|
|
}
|
|
|
|
static void run_all_collections(void)
|
|
{
|
|
struct collection *coll;
|
|
|
|
for_each_collection(coll)
|
|
run_collection(coll);
|
|
}
|
|
|
|
int cmd_bench(int argc, const char **argv)
|
|
{
|
|
struct collection *coll;
|
|
int ret = 0;
|
|
|
|
/* Unbuffered output */
|
|
setvbuf(stdout, NULL, _IONBF, 0);
|
|
|
|
if (argc < 2) {
|
|
/* No collection specified. */
|
|
print_usage();
|
|
goto end;
|
|
}
|
|
|
|
argc = parse_options(argc, argv, bench_options, bench_usage,
|
|
PARSE_OPT_STOP_AT_NON_OPTION);
|
|
|
|
bench_format = bench_str2int(bench_format_str);
|
|
if (bench_format == BENCH_FORMAT_UNKNOWN) {
|
|
printf("Unknown format descriptor: '%s'\n", bench_format_str);
|
|
goto end;
|
|
}
|
|
|
|
if (bench_repeat == 0) {
|
|
printf("Invalid repeat option: Must specify a positive value\n");
|
|
goto end;
|
|
}
|
|
|
|
if (argc < 1) {
|
|
print_usage();
|
|
goto end;
|
|
}
|
|
|
|
if (!strcmp(argv[0], "all")) {
|
|
run_all_collections();
|
|
goto end;
|
|
}
|
|
|
|
for_each_collection(coll) {
|
|
struct bench *bench;
|
|
|
|
if (strcmp(coll->name, argv[0]))
|
|
continue;
|
|
|
|
if (argc < 2) {
|
|
/* No bench specified. */
|
|
dump_benchmarks(coll);
|
|
goto end;
|
|
}
|
|
|
|
if (!strcmp(argv[1], "all")) {
|
|
run_collection(coll);
|
|
goto end;
|
|
}
|
|
|
|
for_each_bench(coll, bench) {
|
|
if (strcmp(bench->name, argv[1]))
|
|
continue;
|
|
|
|
if (bench_format == BENCH_FORMAT_DEFAULT)
|
|
printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
|
|
ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
|
|
goto end;
|
|
}
|
|
|
|
if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
|
|
dump_benchmarks(coll);
|
|
goto end;
|
|
}
|
|
|
|
printf("Unknown benchmark: '%s' for collection '%s'\n", argv[1], argv[0]);
|
|
ret = 1;
|
|
goto end;
|
|
}
|
|
|
|
printf("Unknown collection: '%s'\n", argv[0]);
|
|
ret = 1;
|
|
|
|
end:
|
|
return ret;
|
|
}
|