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
|
#!/bin/sh
#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.
""":"
work_dir=$(dirname $0)
base_name=$(basename $0)
cd $work_dir
if [ $HOD_PYTHON_HOME ]; then
exec $HOD_PYTHON_HOME -OO -u $base_name ${1+"$@"}
elif [ -e /usr/bin/python ]; then
exec /usr/bin/python -OO -u $base_name ${1+"$@"}
elif [ -e /usr/local/bin/python ]; then
exec /usr/local/bin/python -OO -u $base_name ${1+"$@"}
else
exec python -OO -u $base_name ${1+"$@"}
fi
":"""
from os import popen3
import os, sys
import re
import time
from datetime import datetime
from optparse import OptionParser
myName = os.path.basename(sys.argv[0])
myName = re.sub(".*/", "", myName)
reVersion = re.compile(".*(\d+_\d+).*")
VERSION = '$HeadURL: https://svn.apache.org/repos/asf/hadoop/core/branches/branch-0.20/src/contrib/hod/support/logcondense.py $'
reMatch = reVersion.match(VERSION)
if reMatch:
VERSION = reMatch.group(1)
VERSION = re.sub("_", ".", VERSION)
else:
VERSION = 'DEV'
options = ( {'short' : "-p",
'long' : "--package",
'type' : "string",
'action' : "store",
'dest' : "package",
'metavar' : " ",
'default' : 'hadoop',
'help' : "Bin file for hadoop"},
{'short' : "-d",
'long' : "--days",
'type' : "int",
'action' : "store",
'dest' : "days",
'metavar' : " ",
'default' : 7,
'help' : "Number of days before logs are deleted"},
{'short' : "-c",
'long' : "--config",
'type' : "string",
'action' : "store",
'dest' : "config",
'metavar' : " ",
'default' : None,
'help' : "config directory for hadoop"},
{'short' : "-l",
'long' : "--logs",
'type' : "string",
'action' : "store",
'dest' : "log",
'metavar' : " ",
'default' : "/user",
'help' : "directory prefix under which logs are stored per user"},
{'short' : "-n",
'long' : "--dynamicdfs",
'type' : "string",
'action' : "store",
'dest' : "dynamicdfs",
'metavar' : " ",
'default' : "false",
'help' : "'true', if the cluster is used to bring up dynamic dfs clusters, 'false' otherwise"}
)
def getDfsCommand(options, args):
if (options.config == None):
cmd = options.package + " " + "dfs " + args
else:
cmd = options.package + " " + "--config " + options.config + " dfs " + args
return cmd
def runcondense():
import shutil
options = process_args()
# if the cluster is used to bring up dynamic dfs, we must leave NameNode and JobTracker logs,
# otherwise only JobTracker logs. Likewise, in case of dynamic dfs, we must also look for
# deleting datanode logs
filteredNames = ['jobtracker']
deletedNamePrefixes = ['*-tasktracker-*']
if options.dynamicdfs == 'true':
filteredNames.append('namenode')
deletedNamePrefixes.append('*-datanode-*')
filepath = '%s/\*/hod-logs/' % (options.log)
cmd = getDfsCommand(options, "-lsr " + filepath)
(stdin, stdout, stderr) = popen3(cmd)
lastjobid = 'none'
toPurge = { }
for line in stdout:
try:
m = re.match("^.*\s(.*)\n$", line)
filename = m.group(1)
# file name format: <prefix>/<user>/hod-logs/<jobid>/[0-9]*-[jobtracker|tasktracker|datanode|namenode|]-hostname-YYYYMMDDtime-random.tar.gz
# first strip prefix:
if filename.startswith(options.log):
filename = filename.lstrip(options.log)
if not filename.startswith('/'):
filename = '/' + filename
else:
continue
# Now get other details from filename.
k = re.match("/(.*)/hod-logs/(.*)/.*-.*-([0-9][0-9][0-9][0-9])([0-9][0-9])([0-9][0-9]).*$", filename)
if k:
username = k.group(1)
jobid = k.group(2)
datetimefile = datetime(int(k.group(3)), int(k.group(4)), int(k.group(5)))
datetimenow = datetime.utcnow()
diff = datetimenow - datetimefile
filedate = k.group(3) + k.group(4) + k.group(5)
newdate = datetimenow.strftime("%Y%m%d")
print "%s %s %s %d" % (filename, filedate, newdate, diff.days)
# if the cluster is used to bring up dynamic dfs, we must also leave NameNode logs.
foundFilteredName = False
for name in filteredNames:
if filename.find(name) >= 0:
foundFilteredName = True
break
if foundFilteredName:
continue
if (diff.days > options.days):
desttodel = filename
if not toPurge.has_key(jobid):
toPurge[jobid] = options.log.rstrip("/") + "/" + username + "/hod-logs/" + jobid
except Exception, e:
print >> sys.stderr, e
for job in toPurge.keys():
try:
for prefix in deletedNamePrefixes:
cmd = getDfsCommand(options, "-rm " + toPurge[job] + '/' + prefix)
print cmd
ret = 0
ret = os.system(cmd)
if (ret != 0):
print >> sys.stderr, "Command failed to delete file " + cmd
except Exception, e:
print >> sys.stderr, e
def process_args():
global options, myName, VERSION
usage = "usage: %s <ARGS>" % (myName)
version = "%s %s" % (myName, VERSION)
argParser = OptionParser(usage=usage, version=VERSION)
for option_element in options:
argParser.add_option(option_element['short'], option_element['long'],
type=option_element['type'], action=option_element['action'],
dest=option_element['dest'], default=option_element['default'],
metavar=option_element['metavar'], help=option_element['help'])
(parsedOptions, args) = argParser.parse_args()
if not os.path.exists(parsedOptions.package):
argParser.error("Could not find path to hadoop binary: %s" % parsedOptions.package)
if not os.path.exists(parsedOptions.config):
argParser.error("Could not find config: %s" % parsedOptions.config)
if parsedOptions.days <= 0:
argParser.error("Invalid number of days specified, must be > 0: %s" % parsedOptions.config)
if parsedOptions.dynamicdfs!='true' and parsedOptions.dynamicdfs!='false':
argParser.error("Invalid option for dynamicdfs, must be true or false: %s" % parsedOptions.dynamicdfs)
return parsedOptions
if __name__ == '__main__':
runcondense()
|
