From 0076d546b4f9b5c15121c6959d108a83fe43fa9a Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 8 Aug 2012 17:57:55 +0800
Subject: perf scripts python: Add event_analyzing_sample.py as a sample for
general event handling
Currently only trace point events are supported in perf/python script,
the first 3 patches of this serie add the support for all types of
events. This script is just a simple sample to show how to gather the
basic information of the events and analyze them.
This script will create one object for each event sample and insert them
into a table in a database, then leverage the simple SQL commands to
sort/group them. User can modify or write their brand new functions
according to their specific requirment.
Here is the sample of how to use the script:
$ perf record -a tree
$ perf script -s process_event.py
There is 100 records in gen_events table
Statistics about the general events grouped by thread/symbol/dso:
comm number histgram
==========================================
swapper 56 ######
tree 20 #####
perf 10 ####
sshd 8 ####
kworker/7:2 4 ###
ksoftirqd/7 1 #
plugin-containe 1 #
symbol number histgram
==========================================================
native_write_msr_safe 40 ######
__lock_acquire 8 ####
ftrace_graph_caller 4 ###
prepare_ftrace_return 4 ###
intel_idle 3 ##
native_sched_clock 3 ##
Unknown_symbol 2 ##
do_softirq 2 ##
lock_release 2 ##
lock_release_holdtime 2 ##
trace_graph_entry 2 ##
_IO_putc 1 #
__d_lookup_rcu 1 #
__do_fault 1 #
__schedule 1 #
_raw_spin_lock 1 #
delay_tsc 1 #
generic_exec_single 1 #
generic_fillattr 1 #
dso number histgram
==================================================================
[kernel.kallsyms] 95 #######
/lib/libc-2.12.1.so 5 ###
Signed-off-by: Feng Tang <feng.tang@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1344419875-21665-6-git-send-email-feng.tang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../perf/scripts/python/event_analyzing_sample.py | 193 +++++++++++++++++++++
1 file changed, 193 insertions(+)
create mode 100644 tools/perf/scripts/python/event_analyzing_sample.py
(limited to 'tools/perf/scripts/python/event_analyzing_sample.py')
diff --git a/tools/perf/scripts/python/event_analyzing_sample.py b/tools/perf/scripts/python/event_analyzing_sample.py
new file mode 100644
index 000000000000..46f05aad6d07
--- /dev/null
+++ b/tools/perf/scripts/python/event_analyzing_sample.py
@@ -0,0 +1,193 @@
+# process_event.py: general event handler in python
+#
+# Current perf report is alreay very powerful with the anotation integrated,
+# and this script is not trying to be as powerful as perf report, but
+# providing end user/developer a flexible way to analyze the events other
+# than trace points.
+#
+# The 2 database related functions in this script just show how to gather
+# the basic information, and users can modify and write their own functions
+# according to their specific requirment.
+#
+# The first sample "show_general_events" just does a baisc grouping for all
+# generic events with the help of sqlite, and the 2nd one "show_pebs_ll" is
+# for a x86 HW PMU event: PEBS with load latency data.
+#
+
+import os
+import sys
+import math
+import struct
+import sqlite3
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from EventClass import *
+
+#
+# If the perf.data has a big number of samples, then the insert operation
+# will be very time consuming (about 10+ minutes for 10000 samples) if the
+# .db database is on disk. Move the .db file to RAM based FS to speedup
+# the handling, which will cut the time down to several seconds.
+#
+con = sqlite3.connect("/dev/shm/perf.db")
+con.isolation_level = None
+
+def trace_begin():
+ print "In trace_begin:\n"
+
+ #
+ # Will create several tables at the start, pebs_ll is for PEBS data with
+ # load latency info, while gen_events is for general event.
+ #
+ con.execute("""
+ create table if not exists gen_events (
+ name text,
+ symbol text,
+ comm text,
+ dso text
+ );""")
+ con.execute("""
+ create table if not exists pebs_ll (
+ name text,
+ symbol text,
+ comm text,
+ dso text,
+ flags integer,
+ ip integer,
+ status integer,
+ dse integer,
+ dla integer,
+ lat integer
+ );""")
+
+#
+# Create and insert event object to a database so that user could
+# do more analysis with simple database commands.
+#
+def process_event(param_dict):
+ event_attr = param_dict["attr"]
+ sample = param_dict["sample"]
+ raw_buf = param_dict["raw_buf"]
+ comm = param_dict["comm"]
+ name = param_dict["ev_name"]
+
+ # Symbol and dso info are not always resolved
+ if (param_dict.has_key("dso")):
+ dso = param_dict["dso"]
+ else:
+ dso = "Unknown_dso"
+
+ if (param_dict.has_key("symbol")):
+ symbol = param_dict["symbol"]
+ else:
+ symbol = "Unknown_symbol"
+
+ # Creat the event object and insert it to the right table in database
+ event = create_event(name, comm, dso, symbol, raw_buf)
+ insert_db(event)
+
+def insert_db(event):
+ if event.ev_type == EVTYPE_GENERIC:
+ con.execute("insert into gen_events values(?, ?, ?, ?)",
+ (event.name, event.symbol, event.comm, event.dso))
+ elif event.ev_type == EVTYPE_PEBS_LL:
+ event.ip &= 0x7fffffffffffffff
+ event.dla &= 0x7fffffffffffffff
+ con.execute("insert into pebs_ll values (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
+ (event.name, event.symbol, event.comm, event.dso, event.flags,
+ event.ip, event.status, event.dse, event.dla, event.lat))
+
+def trace_end():
+ print "In trace_end:\n"
+ # We show the basic info for the 2 type of event classes
+ show_general_events()
+ show_pebs_ll()
+ con.close()
+
+#
+# As the event number may be very big, so we can't use linear way
+# to show the histgram in real number, but use a log2 algorithm.
+#
+
+def num2sym(num):
+ # Each number will have at least one '#'
+ snum = '#' * (int)(math.log(num, 2) + 1)
+ return snum
+
+def show_general_events():
+
+ # Check the total record number in the table
+ count = con.execute("select count(*) from gen_events")
+ for t in count:
+ print "There is %d records in gen_events table" % t[0]
+ if t[0] == 0:
+ return
+
+ print "Statistics about the general events grouped by thread/symbol/dso: \n"
+
+ # Group by thread
+ commq = con.execute("select comm, count(comm) from gen_events group by comm order by -count(comm)")
+ print "\n%16s %8s %16s\n%s" % ("comm", "number", "histgram", "="*42)
+ for row in commq:
+ print "%16s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by symbol
+ print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histgram", "="*58)
+ symbolq = con.execute("select symbol, count(symbol) from gen_events group by symbol order by -count(symbol)")
+ for row in symbolq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by dso
+ print "\n%40s %8s %16s\n%s" % ("dso", "number", "histgram", "="*74)
+ dsoq = con.execute("select dso, count(dso) from gen_events group by dso order by -count(dso)")
+ for row in dsoq:
+ print "%40s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+#
+# This function just shows the basic info, and we could do more with the
+# data in the tables, like checking the function parameters when some
+# big latency events happen.
+#
+def show_pebs_ll():
+
+ count = con.execute("select count(*) from pebs_ll")
+ for t in count:
+ print "There is %d records in pebs_ll table" % t[0]
+ if t[0] == 0:
+ return
+
+ print "Statistics about the PEBS Load Latency events grouped by thread/symbol/dse/latency: \n"
+
+ # Group by thread
+ commq = con.execute("select comm, count(comm) from pebs_ll group by comm order by -count(comm)")
+ print "\n%16s %8s %16s\n%s" % ("comm", "number", "histgram", "="*42)
+ for row in commq:
+ print "%16s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by symbol
+ print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histgram", "="*58)
+ symbolq = con.execute("select symbol, count(symbol) from pebs_ll group by symbol order by -count(symbol)")
+ for row in symbolq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by dse
+ dseq = con.execute("select dse, count(dse) from pebs_ll group by dse order by -count(dse)")
+ print "\n%32s %8s %16s\n%s" % ("dse", "number", "histgram", "="*58)
+ for row in dseq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by latency
+ latq = con.execute("select lat, count(lat) from pebs_ll group by lat order by lat")
+ print "\n%32s %8s %16s\n%s" % ("latency", "number", "histgram", "="*58)
+ for row in latq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+def trace_unhandled(event_name, context, event_fields_dict):
+ print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
+
+def print_header(event_name, cpu, secs, nsecs, pid, comm):
+ print "%-20s %5u %05u.%09u %8u %-20s " % \
+ (event_name, cpu, secs, nsecs, pid, comm),
--
cgit v1.2.3-70-g09d2
From 87b6a3ad40ba304ec468b972e979e7e410852476 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Thu, 9 Aug 2012 13:46:13 +0800
Subject: perf script python: Correct handler check and spelling errors
Correct the checking for handler returned by PyDict_GetItemString(),
also fix some spelling error and remove some data code in
event_analyzing_sample.py, as suggested by Namhyung Kim.
v2: restore back the wrongly removed trace_unhandled() func
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20120809134613.067104c4@feng-i7
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../Perf-Trace-Util/lib/Perf/Trace/EventClass.py | 4 +--
.../perf/scripts/python/event_analyzing_sample.py | 30 ++++++++++------------
.../util/scripting-engines/trace-event-python.c | 8 +++---
3 files changed, 18 insertions(+), 24 deletions(-)
(limited to 'tools/perf/scripts/python/event_analyzing_sample.py')
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 6372431188de..9e0985794e20 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -1,12 +1,12 @@
# EventClass.py
#
-# This is a libray defining some events typs classes, which could
+# This is a library defining some events types classes, which could
# be used by other scripts to analyzing the perf samples.
#
# Currently there are just a few classes defined for examples,
# PerfEvent is the base class for all perf event sample, PebsEvent
# is a HW base Intel x86 PEBS event, and user could add more SW/HW
-# event classes based on requriements.
+# event classes based on requirements.
import struct
diff --git a/tools/perf/scripts/python/event_analyzing_sample.py b/tools/perf/scripts/python/event_analyzing_sample.py
index 46f05aad6d07..163c39fa12d9 100644
--- a/tools/perf/scripts/python/event_analyzing_sample.py
+++ b/tools/perf/scripts/python/event_analyzing_sample.py
@@ -1,15 +1,15 @@
-# process_event.py: general event handler in python
+# event_analyzing_sample.py: general event handler in python
#
-# Current perf report is alreay very powerful with the anotation integrated,
+# Current perf report is already very powerful with the annotation integrated,
# and this script is not trying to be as powerful as perf report, but
# providing end user/developer a flexible way to analyze the events other
# than trace points.
#
# The 2 database related functions in this script just show how to gather
# the basic information, and users can modify and write their own functions
-# according to their specific requirment.
+# according to their specific requirement.
#
-# The first sample "show_general_events" just does a baisc grouping for all
+# The first function "show_general_events" just does a basic grouping for all
# generic events with the help of sqlite, and the 2nd one "show_pebs_ll" is
# for a x86 HW PMU event: PEBS with load latency data.
#
@@ -85,7 +85,7 @@ def process_event(param_dict):
else:
symbol = "Unknown_symbol"
- # Creat the event object and insert it to the right table in database
+ # Create the event object and insert it to the right table in database
event = create_event(name, comm, dso, symbol, raw_buf)
insert_db(event)
@@ -109,7 +109,7 @@ def trace_end():
#
# As the event number may be very big, so we can't use linear way
-# to show the histgram in real number, but use a log2 algorithm.
+# to show the histogram in real number, but use a log2 algorithm.
#
def num2sym(num):
@@ -130,18 +130,18 @@ def show_general_events():
# Group by thread
commq = con.execute("select comm, count(comm) from gen_events group by comm order by -count(comm)")
- print "\n%16s %8s %16s\n%s" % ("comm", "number", "histgram", "="*42)
+ print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)
for row in commq:
print "%16s %8d %s" % (row[0], row[1], num2sym(row[1]))
# Group by symbol
- print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histgram", "="*58)
+ print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)
symbolq = con.execute("select symbol, count(symbol) from gen_events group by symbol order by -count(symbol)")
for row in symbolq:
print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
# Group by dso
- print "\n%40s %8s %16s\n%s" % ("dso", "number", "histgram", "="*74)
+ print "\n%40s %8s %16s\n%s" % ("dso", "number", "histogram", "="*74)
dsoq = con.execute("select dso, count(dso) from gen_events group by dso order by -count(dso)")
for row in dsoq:
print "%40s %8d %s" % (row[0], row[1], num2sym(row[1]))
@@ -163,31 +163,27 @@ def show_pebs_ll():
# Group by thread
commq = con.execute("select comm, count(comm) from pebs_ll group by comm order by -count(comm)")
- print "\n%16s %8s %16s\n%s" % ("comm", "number", "histgram", "="*42)
+ print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)
for row in commq:
print "%16s %8d %s" % (row[0], row[1], num2sym(row[1]))
# Group by symbol
- print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histgram", "="*58)
+ print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)
symbolq = con.execute("select symbol, count(symbol) from pebs_ll group by symbol order by -count(symbol)")
for row in symbolq:
print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
# Group by dse
dseq = con.execute("select dse, count(dse) from pebs_ll group by dse order by -count(dse)")
- print "\n%32s %8s %16s\n%s" % ("dse", "number", "histgram", "="*58)
+ print "\n%32s %8s %16s\n%s" % ("dse", "number", "histogram", "="*58)
for row in dseq:
print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
# Group by latency
latq = con.execute("select lat, count(lat) from pebs_ll group by lat order by lat")
- print "\n%32s %8s %16s\n%s" % ("latency", "number", "histgram", "="*58)
+ print "\n%32s %8s %16s\n%s" % ("latency", "number", "histogram", "="*58)
for row in latq:
print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
def trace_unhandled(event_name, context, event_fields_dict):
print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
-
-def print_header(event_name, cpu, secs, nsecs, pid, comm):
- print "%-20s %5u %05u.%09u %8u %-20s " % \
- (event_name, cpu, secs, nsecs, pid, comm),
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 7e3f57656c55..afba09729183 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -343,7 +343,7 @@ static void python_process_general_event(union perf_event *perf_event __unused,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine __unused,
- struct addr_location *al __unused)
+ struct addr_location *al)
{
PyObject *handler, *retval, *t, *dict;
static char handler_name[64];
@@ -352,7 +352,7 @@ static void python_process_general_event(union perf_event *perf_event __unused,
/*
* Use the MAX_FIELDS to make the function expandable, though
- * currently there is only one itme for the tuple.
+ * currently there is only one item for the tuple.
*/
t = PyTuple_New(MAX_FIELDS);
if (!t)
@@ -365,10 +365,8 @@ static void python_process_general_event(union perf_event *perf_event __unused,
snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
handler = PyDict_GetItemString(main_dict, handler_name);
- if (handler && !PyCallable_Check(handler)) {
- handler = NULL;
+ if (!handler || !PyCallable_Check(handler))
goto exit;
- }
PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize(
--
cgit v1.2.3-70-g09d2