8c292f1174
Pull perf changes from Ingo Molnar: "Main changes: Kernel side changes: - Add SNB/IVB/HSW client uncore memory controller support (Stephane Eranian) - Fix various x86/P4 PMU driver bugs (Don Zickus) Tooling, user visible changes: - Add several futex 'perf bench' microbenchmarks (Davidlohr Bueso) - Speed up thread map generation (Don Zickus) - Introduce 'perf kvm --list-cmds' command line option for use by scripts (Ramkumar Ramachandra) - Print the evsel name in the annotate stdio output, prep to fix support outputting annotation for multiple events, not just for the first one (Arnaldo Carvalho de Melo) - Allow setting preferred callchain method in .perfconfig (Jiri Olsa) - Show in what binaries/modules 'perf probe's are set (Masami Hiramatsu) - Support distro-style debuginfo for uprobe in 'perf probe' (Masami Hiramatsu) Tooling, internal changes and fixes: - Use tid in mmap/mmap2 events to find maps (Don Zickus) - Record the reason for filtering an address_location (Namhyung Kim) - Apply all filters to an addr_location (Namhyung Kim) - Merge al->filtered with hist_entry->filtered in report/hists (Namhyung Kim) - Fix memory leak when synthesizing thread records (Namhyung Kim) - Use ui__has_annotation() in 'report' (Namhyung Kim) - hists browser refactorings to reuse code accross UIs (Namhyung Kim) - Add support for the new DWARF unwinder library in elfutils (Jiri Olsa) - Fix build race in the generation of bison files (Jiri Olsa) - Further streamline the feature detection display, trimming it a bit to show just the libraries detected, using VF=1 gets a more verbose output, showing the less interesting feature checks as well (Jiri Olsa). - Check compatible symtab type before loading dso (Namhyung Kim) - Check return value of filename__read_debuglink() (Stephane Eranian) - Move some hashing and fs related code from tools/perf/util/ to tools/lib/ so that it can be used by more tools/ living utilities (Borislav Petkov) - Prepare DWARF unwinding code for using an elfutils alternative unwinding library (Jiri Olsa) - Fix DWARF unwind max_stack processing (Jiri Olsa) - Add dwarf unwind 'perf test' entry (Jiri Olsa) - 'perf probe' improvements including memory leak fixes, sharing the intlist class with other tools, uprobes/kprobes code sharing and use of ref_reloc_sym (Masami Hiramatsu) - Shorten sample symbol resolving by adding cpumode to struct addr_location (Arnaldo Carvalho de Melo) - Fix synthesizing mmaps for threads (Don Zickus) - Fix invalid output on event group stdio report (Namhyung Kim) - Fixup header alignment in 'perf sched latency' output (Ramkumar Ramachandra) - Fix off-by-one error in 'perf timechart record' argv handling (Ramkumar Ramachandra) Tooling, cleanups: - Remove unused thread__find_map function (Jiri Olsa) - Remove unused simple_strtoul() function (Ramkumar Ramachandra) Tooling, documentation updates: - Update function names in debug messages (Ramkumar Ramachandra) - Update some code references in design.txt (Ramkumar Ramachandra) - Clarify load-latency information in the 'perf mem' docs (Andi Kleen) - Clarify x86 register naming in 'perf probe' docs (Andi Kleen)" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (96 commits) perf tools: Remove unused simple_strtoul() function perf tools: Update some code references in design.txt perf evsel: Update function names in debug messages perf tools: Remove thread__find_map function perf annotate: Print the evsel name in the stdio output perf report: Use ui__has_annotation() perf tools: Fix memory leak when synthesizing thread records perf tools: Use tid in mmap/mmap2 events to find maps perf report: Merge al->filtered with hist_entry->filtered perf symbols: Apply all filters to an addr_location perf symbols: Record the reason for filtering an address_location perf sched: Fixup header alignment in 'latency' output perf timechart: Fix off-by-one error in 'record' argv handling perf machine: Factor machine__find_thread to take tid argument perf tools: Speed up thread map generation perf kvm: introduce --list-cmds for use by scripts perf ui hists: Pass evsel to hpp->header/width functions explicitly perf symbols: Introduce thread__find_cpumode_addr_location perf session: Change header.misc dump from decimal to hex perf ui/tui: Reuse generic __hpp__fmt() code ...
282 lines
6.5 KiB
C
282 lines
6.5 KiB
C
/*
|
|
* 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
|
|
* mem ... memory access performance
|
|
* numa ... NUMA scheduling and MM performance
|
|
* futex ... Futex performance
|
|
*/
|
|
#include "perf.h"
|
|
#include "util/util.h"
|
|
#include "util/parse-options.h"
|
|
#include "builtin.h"
|
|
#include "bench/bench.h"
|
|
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <sys/prctl.h>
|
|
|
|
typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix);
|
|
|
|
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", "Test 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", "Test all scheduler benchmarks", NULL },
|
|
{ NULL, NULL, NULL }
|
|
};
|
|
|
|
static struct bench mem_benchmarks[] = {
|
|
{ "memcpy", "Benchmark for memcpy()", bench_mem_memcpy },
|
|
{ "memset", "Benchmark for memset() tests", bench_mem_memset },
|
|
{ "all", "Test all memory 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 },
|
|
{ "requeue", "Benchmark for futex requeue calls", bench_futex_requeue },
|
|
{ "all", "Test all futex 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 },
|
|
{ "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 },
|
|
{ "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;
|
|
|
|
static const struct option bench_options[] = {
|
|
OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
|
|
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, const char *prefix)
|
|
{
|
|
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, prefix);
|
|
|
|
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);
|
|
fflush(stdout);
|
|
|
|
argv[1] = bench->name;
|
|
run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL);
|
|
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, const char *prefix __maybe_unused)
|
|
{
|
|
struct collection *coll;
|
|
int ret = 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 (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);
|
|
fflush(stdout);
|
|
ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix);
|
|
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;
|
|
}
|