WSL2-Linux-Kernel/tools/perf/builtin-bench.c

264 строки
5.2 KiB
C
Исходник Обычный вид История

/*
*
* builtin-bench.c
*
* General benchmarking subsystem provided by perf
*
* Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
*
*/
/*
*
* Available subsystem list:
* sched ... scheduler and IPC mechanism
* mem ... memory access 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>
struct bench_suite {
const char *name;
const char *summary;
int (*fn)(int, const char **, const char *);
};
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
\
/* sentinel: easy for help */
#define suite_all { "all", "Test all benchmark suites", NULL }
perf: Add 'perf bench numa mem' NUMA performance measurement suite Add a suite of NUMA performance benchmarks. The goal was simulate the behavior and access patterns of real NUMA workloads, via a wide range of parameters, so this tool goes well beyond simple bzero() measurements that most NUMA micro-benchmarks use: - It processes the data and creates a chain of data dependencies, like a real workload would. Neither the compiler, nor the kernel (via KSM and other optimizations) nor the CPU can eliminate parts of the workload. - It randomizes the initial state and also randomizes the target addresses of the processing - it's not a simple forward scan of addresses. - It provides flexible options to set process, thread and memory relationship information: -G sets "global" memory shared between all test processes, -P sets "process" memory shared by all threads of a process and -T sets "thread" private memory. - There's a NUMA convergence monitoring and convergence latency measurement option via -c and -m. - Micro-sleeps and synchronization can be injected to provoke lock contention and scheduling, via the -u and -S options. This simulates IO and contention. - The -x option instructs the workload to 'perturb' itself artificially every N seconds, by moving to the first and last CPU of the system periodically. This way the stability of convergence equilibrium and the number of steps taken for the scheduler to reach equilibrium again can be measured. - The amount of work can be specified via the -l loop count, and/or via a -s seconds-timeout value. - CPU and node memory binding options, to test hard binding scenarios. THP can be turned on and off via madvise() calls. - Live reporting of convergence progress in an 'at glance' output format. Printing of convergence and deconvergence events. The 'perf bench numa mem -a' option will start an array of about 30 individual tests that will each output such measurements: # Running 5x5-bw-thread, "perf bench numa mem -p 5 -t 5 -P 512 -s 20 -zZ0q --thp 1" 5x5-bw-thread, 20.276, secs, runtime-max/thread 5x5-bw-thread, 20.004, secs, runtime-min/thread 5x5-bw-thread, 20.155, secs, runtime-avg/thread 5x5-bw-thread, 0.671, %, spread-runtime/thread 5x5-bw-thread, 21.153, GB, data/thread 5x5-bw-thread, 528.818, GB, data-total 5x5-bw-thread, 0.959, nsecs, runtime/byte/thread 5x5-bw-thread, 1.043, GB/sec, thread-speed 5x5-bw-thread, 26.081, GB/sec, total-speed See the help text and the code for more details. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-12-06 16:51:59 +04:00
static struct bench_suite numa_suites[] = {
{ "mem",
"Benchmark for NUMA workloads",
bench_numa },
suite_all,
{ NULL,
NULL,
NULL }
};
static struct bench_suite sched_suites[] = {
{ "messaging",
"Benchmark for scheduler and IPC mechanisms",
bench_sched_messaging },
{ "pipe",
"Flood of communication over pipe() between two processes",
bench_sched_pipe },
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
suite_all,
{ NULL,
NULL,
NULL }
};
static struct bench_suite mem_suites[] = {
{ "memcpy",
"Simple memory copy in various ways",
bench_mem_memcpy },
{ "memset",
"Simple memory set in various ways",
bench_mem_memset },
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
suite_all,
{ NULL,
NULL,
NULL }
};
struct bench_subsys {
const char *name;
const char *summary;
struct bench_suite *suites;
};
static struct bench_subsys subsystems[] = {
perf: Add 'perf bench numa mem' NUMA performance measurement suite Add a suite of NUMA performance benchmarks. The goal was simulate the behavior and access patterns of real NUMA workloads, via a wide range of parameters, so this tool goes well beyond simple bzero() measurements that most NUMA micro-benchmarks use: - It processes the data and creates a chain of data dependencies, like a real workload would. Neither the compiler, nor the kernel (via KSM and other optimizations) nor the CPU can eliminate parts of the workload. - It randomizes the initial state and also randomizes the target addresses of the processing - it's not a simple forward scan of addresses. - It provides flexible options to set process, thread and memory relationship information: -G sets "global" memory shared between all test processes, -P sets "process" memory shared by all threads of a process and -T sets "thread" private memory. - There's a NUMA convergence monitoring and convergence latency measurement option via -c and -m. - Micro-sleeps and synchronization can be injected to provoke lock contention and scheduling, via the -u and -S options. This simulates IO and contention. - The -x option instructs the workload to 'perturb' itself artificially every N seconds, by moving to the first and last CPU of the system periodically. This way the stability of convergence equilibrium and the number of steps taken for the scheduler to reach equilibrium again can be measured. - The amount of work can be specified via the -l loop count, and/or via a -s seconds-timeout value. - CPU and node memory binding options, to test hard binding scenarios. THP can be turned on and off via madvise() calls. - Live reporting of convergence progress in an 'at glance' output format. Printing of convergence and deconvergence events. The 'perf bench numa mem -a' option will start an array of about 30 individual tests that will each output such measurements: # Running 5x5-bw-thread, "perf bench numa mem -p 5 -t 5 -P 512 -s 20 -zZ0q --thp 1" 5x5-bw-thread, 20.276, secs, runtime-max/thread 5x5-bw-thread, 20.004, secs, runtime-min/thread 5x5-bw-thread, 20.155, secs, runtime-avg/thread 5x5-bw-thread, 0.671, %, spread-runtime/thread 5x5-bw-thread, 21.153, GB, data/thread 5x5-bw-thread, 528.818, GB, data-total 5x5-bw-thread, 0.959, nsecs, runtime/byte/thread 5x5-bw-thread, 1.043, GB/sec, thread-speed 5x5-bw-thread, 26.081, GB/sec, total-speed See the help text and the code for more details. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-12-06 16:51:59 +04:00
{ "numa",
"NUMA scheduling and MM behavior",
numa_suites },
{ "sched",
"scheduler and IPC mechanism",
sched_suites },
{ "mem",
"memory access performance",
mem_suites },
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
{ "all", /* sentinel: easy for help */
"all benchmark subsystem",
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
NULL },
{ NULL,
NULL,
NULL }
};
static void dump_suites(int subsys_index)
{
int i;
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
printf("# List of available suites for %s...\n\n",
subsystems[subsys_index].name);
for (i = 0; subsystems[subsys_index].suites[i].name; i++)
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
printf("%14s: %s\n",
subsystems[subsys_index].suites[i].name,
subsystems[subsys_index].suites[i].summary);
printf("\n");
return;
}
static const char *bench_format_str;
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>] <subsystem> <suite> [<options>]",
NULL
};
static void print_usage(void)
{
int i;
printf("Usage: \n");
for (i = 0; bench_usage[i]; i++)
printf("\t%s\n", bench_usage[i]);
printf("\n");
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
printf("# List of available subsystems...\n\n");
for (i = 0; subsystems[i].name; i++)
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
printf("%14s: %s\n",
subsystems[i].name, subsystems[i].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;
}
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
static void all_suite(struct bench_subsys *subsys) /* FROM HERE */
{
int i;
const char *argv[2];
struct bench_suite *suites = subsys->suites;
argv[1] = NULL;
/*
* TODO:
* preparing preset parameters for
* embedded, ordinary PC, HPC, etc...
* will be helpful
*/
for (i = 0; suites[i].fn; i++) {
printf("# Running %s/%s benchmark...\n",
subsys->name,
suites[i].name);
fflush(stdout);
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
argv[1] = suites[i].name;
suites[i].fn(1, argv, NULL);
printf("\n");
}
}
static void all_subsystem(void)
{
int i;
for (i = 0; subsystems[i].suites; i++)
all_suite(&subsystems[i]);
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 02:15:03 +04:00
int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
{
int i, j, status = 0;
if (argc < 2) {
/* No subsystem 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;
}
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
if (!strcmp(argv[0], "all")) {
all_subsystem();
goto end;
}
for (i = 0; subsystems[i].name; i++) {
if (strcmp(subsystems[i].name, argv[0]))
continue;
if (argc < 2) {
/* No suite specified. */
dump_suites(i);
goto end;
}
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 11:01:59 +03:00
if (!strcmp(argv[1], "all")) {
all_suite(&subsystems[i]);
goto end;
}
for (j = 0; subsystems[i].suites[j].name; j++) {
if (strcmp(subsystems[i].suites[j].name, argv[1]))
continue;
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Running %s/%s benchmark...\n",
subsystems[i].name,
subsystems[i].suites[j].name);
fflush(stdout);
status = subsystems[i].suites[j].fn(argc - 1,
argv + 1, prefix);
goto end;
}
if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
dump_suites(i);
goto end;
}
printf("Unknown suite:%s for %s\n", argv[1], argv[0]);
status = 1;
goto end;
}
printf("Unknown subsystem:%s\n", argv[0]);
status = 1;
end:
return status;
}