Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/urgent

tools/perf/Documentation/perf-record.txt

@@ -83,6 +83,10 @@ OPTIONS
 --call-graph::
 	Do call-graph (stack chain/backtrace) recording.
 
+-q::
+--quiet::
+	Don't print any message, useful for scripting.
+
 -v::
 --verbose::
 	Be more verbose (show counter open errors, etc).

tools/perf/builtin-record.c

@@ -353,7 +353,7 @@ try_again:
 		}
 
 		if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
-			perror("Unable to read perf file descriptor\n");
+			perror("Unable to read perf file descriptor");
 			exit(-1);
 		}
 
@@ -626,7 +626,7 @@ static int __cmd_record(int argc, const char **argv)
 
 	nr_cpus = read_cpu_map(cpu_list);
 	if (nr_cpus < 1) {
-		perror("failed to collect number of CPUs\n");
+		perror("failed to collect number of CPUs");
 		return -1;
 	}
 
@@ -761,6 +761,9 @@ static int __cmd_record(int argc, const char **argv)
 		}
 	}
 
+	if (quiet)
+		return 0;
+
 	fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
 	/*
@@ -820,6 +823,7 @@ static const struct option options[] = {
 		    "do call-graph (stack chain/backtrace) recording"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
+	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
 	OPT_BOOLEAN('s', "stat", &inherit_stat,
 		    "per thread counts"),
 	OPT_BOOLEAN('d', "data", &sample_address,

tools/perf/builtin-trace.c

@@ -625,12 +625,13 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 			dup2(live_pipe[1], 1);
 			close(live_pipe[0]);
 
-			__argv = malloc(5 * sizeof(const char *));
+			__argv = malloc(6 * sizeof(const char *));
 			__argv[0] = "/bin/sh";
 			__argv[1] = record_script_path;
-			__argv[2] = "-o";
-			__argv[3] = "-";
-			__argv[4] = NULL;
+			__argv[2] = "-q";
+			__argv[3] = "-o";
+			__argv[4] = "-";
+			__argv[5] = NULL;
 
 			execvp("/bin/sh", (char **)__argv);
 			exit(-1);

tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py

@@ -8,6 +8,12 @@
 
 import errno, os
 
+FUTEX_WAIT = 0
+FUTEX_WAKE = 1
+FUTEX_PRIVATE_FLAG = 128
+FUTEX_CLOCK_REALTIME = 256
+FUTEX_CMD_MASK = ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
+
 NSECS_PER_SEC    = 1000000000
 
 def avg(total, n):
@@ -26,6 +32,18 @@ def nsecs_str(nsecs):
     str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
     return str
 
+def add_stats(dict, key, value):
+	if not dict.has_key(key):
+		dict[key] = (value, value, value, 1)
+	else:
+		min, max, avg, count = dict[key]
+		if value < min:
+			min = value
+		if value > max:
+			max = value
+		avg = (avg + value) / 2
+		dict[key] = (min, max, avg, count + 1)
+
 def clear_term():
     print("\x1b[H\x1b[2J")
 

tools/perf/scripts/python/bin/futex-contention-record

@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -a -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@

tools/perf/scripts/python/bin/futex-contention-report

@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: futext contention measurement
+
+perf trace $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py

tools/perf/scripts/python/futex-contention.py

@@ -0,0 +1,50 @@
+# futex contention
+# (c) 2010, Arnaldo Carvalho de Melo <acme@redhat.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Translation of:
+#
+# http://sourceware.org/systemtap/wiki/WSFutexContention
+#
+# to perf python scripting.
+#
+# Measures futex contention
+
+import os, sys
+sys.path.append(os.environ['PERF_EXEC_PATH'] + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+from Util import *
+
+process_names = {}
+thread_thislock = {}
+thread_blocktime = {}
+
+lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time
+process_names = {} # long-lived pid-to-execname mapping
+
+def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
+			      nr, uaddr, op, val, utime, uaddr2, val3):
+	cmd = op & FUTEX_CMD_MASK
+	if cmd != FUTEX_WAIT:
+		return # we don't care about originators of WAKE events
+
+	process_names[tid] = comm
+	thread_thislock[tid] = uaddr
+	thread_blocktime[tid] = nsecs(s, ns)
+
+def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm,
+			     nr, ret):
+	if thread_blocktime.has_key(tid):
+		elapsed = nsecs(s, ns) - thread_blocktime[tid]
+		add_stats(lock_waits, (tid, thread_thislock[tid]), elapsed)
+		del thread_blocktime[tid]
+		del thread_thislock[tid]
+
+def trace_begin():
+	print "Press control+C to stop and show the summary"
+
+def trace_end():
+	for (tid, lock) in lock_waits:
+		min, max, avg, count = lock_waits[tid, lock]
+		print "%s[%d] lock %x contended %d times, %d avg ns" % \
+		      (process_names[tid], tid, lock, count, avg)
+

tools/perf/scripts/python/sctop.py

@@ -17,7 +17,7 @@ from perf_trace_context import *
 from Core import *
 from Util import *
 
-usage = "perf trace -s syscall-counts.py [comm] [interval]\n";
+usage = "perf trace -s sctop.py [comm] [interval]\n";
 
 for_comm = None
 default_interval = 3

tools/perf/util/debug.c

@@ -12,8 +12,8 @@
 #include "debug.h"
 #include "util.h"
 
-int verbose = 0;
-bool dump_trace = false;
+int verbose;
+bool dump_trace = false, quiet = false;
 
 int eprintf(int level, const char *fmt, ...)
 {

tools/perf/util/debug.h

@@ -6,7 +6,7 @@
 #include "event.h"
 
 extern int verbose;
-extern bool dump_trace;
+extern bool quiet, dump_trace;
 
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(event_t *event);