1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
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),
|
