[PATCH] perf bench: Add "all" pseudo subsystem and "all" pseudo suite

* [PATCH] perf bench: Add "all" pseudo subsystem and "all" pseudo suite
       [not found] <20091124152051.GA21821@elte.hu>
@ 2009-12-12 10:37 ` Hitoshi Mitake
  2009-12-12 10:55   ` Ingo Molnar
  0 siblings, 1 reply; 6+ messages in thread
From: Hitoshi Mitake @ 2009-12-12 10:37 UTC (permalink / raw)
  To: mingo
  Cc: linux-kernel, Hitoshi Mitake, Peter Zijlstra, Paul Mackerras,
	Frederic Weisbecker

This patch adds new "all" pseudo subsystem and "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 suite 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 suite of all subsystem
| # 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




Below is description of another issue.

As a matter of fact, I fixed output of "./perf bench all" a little.
Because the raw output is this,
| # 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
|
|
| # Running mem/memcpy benchmark...             # Second mem !?
| # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ...
|
|      841.042893 MB/Sec

mem subsystem was executed twice!
Something is going wrong, and I tested with the modification of all_subsystem() function,

original:
static void all_subsystem(void)
{
	int i;
	for (i = 0; subsystems[i].suites; i++)
		all_suite(&subsystems[i]);
}

modified,
static void all_subsystem(void)
{
	int i;
	for (i = 0; subsystems[i].suites; i++) {
	        printf("start of loop:%d\n", i);
		all_suite(&subsystems[i]);
	        printf("end of loop:%d\n", i);
	}
}

The result is,

| start of loop:0
| # Running sched/messaging benchmark...
| # 20 sender and receiver processes per group
| # 10 groups == 400 processes run
|
|      Total time: 0.459 [sec]
|
| # Running sched/pipe benchmark...
| # Extecuted 1000000 pipe operations between two tasks
|
|      Total time: 12.264 [sec]
|
|   12.264828 usecs/op
|           81533 ops/sec
|
| end of loop:0
| start of loop:1
| # Running mem/memcpy benchmark...
| # Copying 1MB Bytes from 0x7f2c5e526010 to 0x7f2c5fdb4010 ...
|
|      846.023689 MB/Sec
|
| end of loop:1               # !!!
|                             # !!!
| end of loop:0               # !!! <- WHAT IS THIS!!?
| start of loop:1
| # Running mem/memcpy benchmark...
| # Copying 1MB Bytes from 0x7f2c5e526010 to 0x7f2c5fdb4010 ...
|
|      839.630563 MB/Sec
|
| end of loop:1

Something terrible happend :-( Is this bug of gcc?
I disassembled builtin-bench.o, but highly optimized assembly was hard to read...
If you have some ideas to solve this problem,
or know issues similar to it, could you tell me?

My gcc's description:
| % gcc --version
| gcc (Debian 4.3.2-1.1) 4.3.2
| Copyright (C) 2008 Free Software Foundation, Inc.
| This is free software; see the source for copying conditions.  There is NO
| warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
| % gcc -v
| Using built-in specs.
| Target: x86_64-linux-gnu
| Configured with: ../src/configure -v --with-pkgversion='Debian 4.3.2-1.1' --with-bugurl=file:///usr/share/doc/gcc-4.3/README.Bugs --enable-languages=c,c++,fortran,objc,obj-c++ --prefix=/usr --enable-shared --with-system-zlib --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --enable-nls --with-gxx-include-dir=/usr/include/c++/4.3 --program-suffix=-4.3 --enable-clocale=gnu --enable-libstdcxx-debug --enable-objc-gc --enable-mpfr --enable-cld --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
| Thread model: posix
| gcc version 4.3.2 (Debian 4.3.2-1.1)

But I think that this patch has no problem and is commitable.
I'll work on this with gdb again...

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>
---
 tools/perf/bench/sched-messaging.c |    2 +-
 tools/perf/bench/sched-pipe.c      |    2 +-
 tools/perf/builtin-bench.c         |   57 +++++++++++++++++++++++++++++++++--
 3 files changed, 55 insertions(+), 6 deletions(-)

diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 605a2a9..e249eb2 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -1,6 +1,6 @@
 /*
  *
- * builtin-bench-messaging.c
+ * sched-messaging.c
  *
  * messaging: Benchmark for scheduler and IPC mechanisms
  *
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 238185f..260dca2 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -1,6 +1,6 @@
 /*
  *
- * builtin-bench-pipe.c
+ * sched-pipe.c
  *
  * pipe: Benchmark for pipe()
  *
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index e043eb8..4699677 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -31,6 +31,9 @@ struct bench_suite {
 	const char *summary;
 	int (*fn)(int, const char **, const char *);
 };
+						\
+/* sentinel: easy for help */
+#define suite_all { "all", "test all suite (pseudo suite)", NULL }
 
 static struct bench_suite sched_suites[] = {
 	{ "messaging",
@@ -39,6 +42,7 @@ static struct bench_suite sched_suites[] = {
 	{ "pipe",
 	  "Flood of communication over pipe() between two processes",
 	  bench_sched_pipe      },
+	suite_all,
 	{ NULL,
 	  NULL,
 	  NULL                  }
@@ -48,6 +52,7 @@ static struct bench_suite mem_suites[] = {
 	{ "memcpy",
 	  "Simple memory copy in various ways",
 	  bench_mem_memcpy },
+	suite_all,
 	{ NULL,
 	  NULL,
 	  NULL             }
@@ -66,6 +71,9 @@ static struct bench_subsys subsystems[] = {
 	{ "mem",
 	  "memory access performance",
 	  mem_suites },
+	{ "all",		/* sentinel: easy for help */
+	  "test all subsystem (pseudo subsystem)",
+	  NULL },
 	{ NULL,
 	  NULL,
 	  NULL       }
@@ -75,11 +83,11 @@ static void dump_suites(int subsys_index)
 {
 	int i;
 
-	printf("List of available suites for %s...\n\n",
+	printf("# List of available suites for %s...\n\n",
 	       subsystems[subsys_index].name);
 
 	for (i = 0; subsystems[subsys_index].suites[i].name; i++)
-		printf("\t%s: %s\n",
+		printf("%14s: %s\n",
 		       subsystems[subsys_index].suites[i].name,
 		       subsystems[subsys_index].suites[i].summary);
 
@@ -110,10 +118,10 @@ static void print_usage(void)
 		printf("\t%s\n", bench_usage[i]);
 	printf("\n");
 
-	printf("List of available subsystems...\n\n");
+	printf("# List of available subsystems...\n\n");
 
 	for (i = 0; subsystems[i].name; i++)
-		printf("\t%s: %s\n",
+		printf("%14s: %s\n",
 		       subsystems[i].name, subsystems[i].summary);
 	printf("\n");
 }
@@ -131,6 +139,37 @@ static int bench_str2int(char *str)
 	return BENCH_FORMAT_UNKNOWN;
 }
 
+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);
+
+		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]);
+}
+
 int cmd_bench(int argc, const char **argv, const char *prefix __used)
 {
 	int i, j, status = 0;
@@ -155,6 +194,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __used)
 		goto end;
 	}
 
+	if (!strcmp(argv[0], "all")) {
+		all_subsystem();
+		goto end;
+	}
+
 	for (i = 0; subsystems[i].name; i++) {
 		if (strcmp(subsystems[i].name, argv[0]))
 			continue;
@@ -165,6 +209,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __used)
 			goto end;
 		}
 
+		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;
-- 
1.6.5.2


^ permalink raw reply related	[flat|nested] 6+ messages in thread