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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
|
#!/usr/bin/env python
#
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
import os
import re
import datetime
import sys
import string
from optparse import OptionParser
from datetime import datetime, timedelta
import shutil
def showUsage():
log("./pT.py [-b|--broker-log-dir] <dir> [-t|--test-dir] <dir>")
ACCESS="Access"
MODIFY="Modify"
BROKER_LOG="broker.log"
BROKER_PID="broker.pid"
BROKER_CPU="broker_cpu.log"
BROKER_CPU_DATED="broker_cpu.log.dated"
BROKER_GC="gc.log"
GRAPH_DATA="graph.data"
_verbose = False
_debug = False
_brokerLogs = ""
def exitError(message):
log(message)
sys.exit(1)
def main():
global _log, _verbose, _debug, _brokerLogs
# Load the
parser = OptionParser()
parser.add_option("-v", "--verbose", dest="verbose",
action="store_true", default=False, help="enable verbose output")
parser.add_option("-d", "--debug", dest="debug",
action="store_true", default=False, help="enable debug output")
parser.add_option("-b", "--broker-log-dir", dest="brokerLogs",
action="store", default=True, help="Broker Logs")
parser.add_option("-t", "--test-dir", dest="testDir",
action="store", default="", help="Test Results")
(options, args) = parser.parse_args()
_verbose = options.verbose
_debug = options.debug
testDir = options.testDir
_brokerLogs = options.brokerLogs
if testDir == "" or _brokerLogs == "" :
log("Broker Log Dir and Test Dir are both requried.")
showUsage()
if not os.path.exists(testDir):
exitError("Test directory does not exist:" + testDir)
if not os.path.exists(_brokerLogs):
exitError("Broker log directory does not exist:" + _brokerLogs)
# Standardize the format of the broker logs
preProcessBrokerLogs(_brokerLogs)
# Get list of test results from test_dir
processTestResults(testDir)
#
# Process the log files we know of
#
def preProcessBrokerLogs(resultDir):
# Pre-Process GC - no pre processing required
# Process Log4j - no processing required as file is already time stamped.
# Pre-Process broker_cpu
processCPUUsage(resultDir)
#
# Process the broker CPU log file and create an output file of format
# <Date Time> <CPU Usage>
#
#
def processCPUUsage(resultDir):
logfile=resultDir+os.sep+BROKER_CPU
datedFile=resultDir+os.sep+BROKER_CPU_DATED
start = extractTime(ACCESS, logfile+".stat")
pid = getPID(BROKER_PID)
topRate = getFirstLine(_brokerLogs+os.sep+"top.rate")
#
# Calulate addition required per process line output
#
if topRate.find(".") == -1:
second = topRate
millis = 0
else:
split = topRate.split('.')
seconds = split[0]
# Convert
millis = float("0."+split[1]) * 1000
offset = timedelta(seconds=int(seconds),milliseconds=int(millis))
#
# Process the CPU log file and make a file of format:
# datetime <CPU% usage> <MEM% usage>
#
# Open log CPU file for reading
logfile = open(logfile, "r")
# Open the output file, erasing any existing version
output= open(datedFile, "w")
for line in logfile:
if line.find(pid) != -1:
# Split line on whitespace
data = line.split()
#
# Data format
# 0 1 2 3 4 5 6 7 8 9 10 11
# PID USER PR NI %CPU TIME+ %MEM VIRT RES SHR S COMMAND
#
#Write out the date time (ISO-8601 format)
output.write(str(start))
# Output the %CPU value
output.write(" "+str(data[4]))
# Output the %MEM value
output.write(" "+str(data[5]))
output.write('\n')
# Add the offset based on the logging rate
start = start + offset
# Close the files
logfile.close
output.close
log("Pre Process of CPU Log file '"+BROKER_CPU+"' complete")
#
# Give an known process type get the recorded PID.
#
def getPID(process):
return getFirstLine(_brokerLogs+os.sep+process)
#
# Get the first line of the file without EOL chars.
# NOTE: this will load the entire file into memory to do it.
#
def getFirstLine(fileName):
f = open(fileName,"r")
line = f.read().splitlines()[0]
f.close
return line
#
# Walk the directory given and process all csv test results
#
def processTestResults(resultDir):
for root, dirs, files in os.walk(resultDir, topdown=False):
if len(files) == 0:
exitError("Test result directory is empty:" + resultDir)
for file in files:
if file.endswith(".csv"):
processTestResult(root , file)
def processTestResult(root, resultFile):
# Open stat file and extract test times, we determine:
# -start time based on the 'Access' value
# -end time based on the 'Modify' value 'Change' would also work
statFile=root+os.sep+resultFile+".stat"
if not os.path.exists(statFile):
log("Unable to process : Unable to open stat file:" + statFile)
return
createResultSetPackage(root, resultFile)
def extractTime(field, statFile):
stats = open(statFile, "r")
for line in stats:
if line.startswith(field):
if line.find("(") == -1:
dt = lineToDate(" ".join(line.split()[1:]))
#
# TODO We need to handle time time zone issues as I'm sure we will have issues with the
# log4j matching.
stats.close
return dt
#
# Given a text line in ISO format convert it to a date object
#
def lineToDate(line):
#2009-06-22 17:04:44,320
#2009-06-22 17:04:44.320
pattern = re.compile(r'(?P<year>^[0-9][0-9][0-9][0-9])-(?P<month>[0-9][0-9])-(?P<day>[0-9][0-9]) (?P<hour>[0-9][0-9]):(?P<minute>[0-9][0-9]):(?P<seconds>[0-9][0-9])')
m = pattern.match(line)
if m:
year = int(m.group('year'))
month = int(m.group('month'))
day = int(m.group('day'))
hour = int(m.group('hour'))
minute = int(m.group('minute'))
seconds = int(m.group('seconds'))
pattern = re.compile(r'(?P<year>^[0-9][0-9][0-9][0-9])-(?P<month>[0-9][0-9])-(?P<day>[0-9][0-9]) (?P<hour>[0-9][0-9]):(?P<minute>[0-9][0-9]):(?P<seconds>[0-9][0-9])[.|,](?P<micro>[0-9]+)')
m = pattern.match(line)
micro = None
if m:
micro = m.group('micro')
if micro == None:
micro = 0
return datetime(year,month,day,hour,minute,seconds,int(micro))
else:
# Error we shouldn't get here
return null
def createResultSetPackage(root, resultFile):
# Get the Name of the test to make a directory with said name
testName = resultFile.split(".csv")[0]
resultDir = root+ os.sep + testName
log("Processing Result set for:"+ testName)
mkdir(resultDir)
# Move result file to new directory
shutil.move(root + os.sep + resultFile, resultDir)
# Move stat file to new directory
shutil.move(root + os.sep + resultFile + ".stat", resultDir)
statFile=resultDir + os.sep + resultFile + ".stat"
#
# Get start and end time for test run
#
start = extractTime(ACCESS, statFile)
end = extractTime(MODIFY, statFile)
sliceBrokerLogs(resultDir, start, end)
createGraphData(resultDir, testName)
log("Created Result Package for:"+ testName)
def sliceBrokerLogs(resultDir, start, end):
sliceCPULog(resultDir, start, end)
sliceLog4j(resultDir, start, end)
sliceGCLog(resultDir, start, end)
def sliceCPULog(resultDir, start, end):
global _brokerLogs
logfilePath=_brokerLogs+os.sep+BROKER_CPU_DATED
cpuSliceFile=resultDir+os.sep+BROKER_CPU
# Process the CPU log file and make a file of format:
# datetime <CPU% usage> <MEM% usage>
#
# Open log CPU file for reading
logFile = open(logfilePath, "r")
#
# Create outputfile
#
cpuslice = open(cpuSliceFile,"w")
for line in logFile:
data = line.split()
#
# //fixme remove tz addition.
#
lineTime = lineToDate(" ".join(data[0:2])+" +0000")
if lineTime > start:
if lineTime < end:
cpuslice.writelines(line)
logFile.close()
cpuslice.close()
log("Sliced CPU log")
def sliceGCLog(resultDir, start, end):
global _brokerLogs
logfilePath=_brokerLogs+os.sep+BROKER_GC
sliceFile=resultDir+os.sep+BROKER_GC
gcstart = extractTime(ACCESS, logfilePath+".stat")
# Open log GC file for reading
logFile = open(logfilePath, "r")
# Open the output file, erasing any existing version
output= open(sliceFile, "w")
# Use a regular expression to pull out the Seconds.Millis values from the
# Start of the gc log line.
pattern = re.compile(r'(?P<seconds>^[0-9]+)\.(?P<millis>[0-9]+):')
for line in logFile:
m = pattern.match(line)
if m:
seconds = m.group('seconds');
millis = m.group('millis');
offset = timedelta(seconds=int(seconds),milliseconds=int(millis))
lineTime = gcstart + offset
if lineTime > start:
if lineTime < end:
output.writelines(line)
# Close the files
logFile.close
output.close()
log("Sliced gc log")
def sliceLog4j(resultDir, start, end):
global _brokerLogs
logfilePath=_brokerLogs+os.sep+BROKER_LOG
log4jSliceFile=resultDir+os.sep+BROKER_LOG
log4jstart = extractTime(ACCESS, logfilePath+".stat")
#
# Say that first line is the start of the file,
# This value will give a time value to the initial
# logging before Log4j kicks in.
#
lineTime = log4jstart
# Process the broker log4j file
# Open log CPU file for reading
logFile = open(logfilePath, "r")
#
# Create outputfile
#
log4jslice = open(log4jSliceFile,"w")
for line in logFile:
data = line.split()
#
# If the line has a time at the start then process it
# otherwise use the previous time. This means if there is
# a stack trace in the middle of the log file then it will
# be copied over to the split file as long as it is in the
# split time.
#
if (hasTime(data)):
#
# //fixme remove tz addition.
#
lineTime = lineToDate(" ".join(data[0:2])+" +0000")
if lineTime > start:
if lineTime < end:
print line
log4jslice.writelines(line)
logFile.close()
log4jslice.close()
log("Sliced broker log")
#
# Check the first two entries of data can make a datetime object
#
def hasTime(data):
date = data[0]
time = data[1]
# Examples:
# 2009-06-22 17:04:44,246
# 2009-06-22 17:04:44.2464
# 2009-06-22 17:04:44
# ISO-8601 '-' format date
dateRE = re.compile('[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]')
#
# Check for times with/out millis
# e.g.
# 10:00:00,000 - log4j
# 10:00:00.0000 - generated in script for cpu time
#
timeRE = re.compile('[0-9][0-9]:[0-9][0-9]:[0-9][0-9]?[0-9]*')
return dateRE.match(date) and timeRE.match(time)
def createGraphData(resultDir, testName):
# Create graph.data file for process.sh
# Format two lines : Title and filename
# $version $type : $volume% volume
# $version-$brokerState-$type-$volume
version=getBrokerVersion()
test= extractTestValue("n",resultDir, testName)
volume = int(float(extractTestResult("Test * Size Throughput", resultDir, testName)) * 1000)
messageSize = extractTestValue("messageSize",resultDir, testName)
ackMode = ackModeToString(extractTestValue("consAckMode",resultDir, testName))
graphDataFile=resultDir+os.sep+GRAPH_DATA
graphData = open(graphDataFile, "w")
#
# Write Title
graphData.write(version+":"+test+":"+str(messageSize)+"kb x "+str(volume)+" msg/sec using "+ackMode)
graphData.write('\n')
#
# Write FileName
graphData.writelines(version+"-"+testName)
graphData.write('\n')
graphData.close
log("Created graph.data")
def getBrokerVersion():
global _brokerLogs
READY = "Qpid Broker Ready"
brokerLogFile = _brokerLogs + os.sep + BROKER_LOG
log = open(brokerLogFile, "r")
dataLine = ""
for line in log:
if line.find(READY) != -1:
dataLine = line
break
# Log Entry
#2009-06-19 17:04:02,493 INFO [main] server.Main (Main.java:456) - Qpid Broker Ready :2.3.0.1 build: 727403M
# Split on READY
data = dataLine.split(READY)
# So [1] should be
# :2.3.0.1 build: 727403M
readyEntries = data[1].split()
# so spliting on white space should give us ':version'
# and a quick split on ':' will give us the version
version = readyEntries[0].split(':')[1]
# Strip to ensure we have no whitespace
return version.strip()
def extractTestValue(property,resultDir,testName):
return extractTestData(property,resultDir,testName," =")
def extractTestResult(property,resultDir,testName):
return extractTestData(property,resultDir,testName,":")
def extractTestData(property,resultDir,testName,type):
resultFile = resultDir + os.sep + testName+".csv"
results = open(resultFile, "r")
dataLine = ""
for line in results:
if line.find("Total Tests:") == 0:
dataLine = line
results.close()
# Data is CSV
data = dataLine.split(',')
found = False
result = ""
searchProperty = property+type
for entry in data:
if found:
result = entry
break
if entry.strip() == searchProperty:
found=True
return result.strip()
def ackModeToString(ackMode):
if ackMode == '0':
return "Transacted"
elif ackMode == '1':
return "AutoAck"
elif ackMode == '2':
return "ClientAck"
elif ackMode == '3':
return "DupsOK"
elif ackMode == '257':
return "NoAck"
elif ackMode == '258':
return "PreAck"
else:
return str(ackMode)
def debug(msg):
global _debug
if _debug:
log(msg)
def log(msg):
print msg
def mkdir(dir):
if not os.path.exists(dir):
os.mkdir(dir)
if __name__ == "__main__":
main()
|