1 | <?xml version="1.0"?> |
---|
2 | <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> |
---|
3 | |
---|
4 | <!-- Do not modify this file directly. Instead, copy entries that you --> |
---|
5 | <!-- wish to modify from this file into core-site.xml and change them --> |
---|
6 | <!-- there. If core-site.xml does not already exist, create it. --> |
---|
7 | |
---|
8 | <configuration> |
---|
9 | |
---|
10 | <!--- global properties --> |
---|
11 | |
---|
12 | <property> |
---|
13 | <name>hadoop.tmp.dir</name> |
---|
14 | <value>/tmp/hadoop-${user.name}</value> |
---|
15 | <description>A base for other temporary directories.</description> |
---|
16 | </property> |
---|
17 | |
---|
18 | <property> |
---|
19 | <name>hadoop.native.lib</name> |
---|
20 | <value>true</value> |
---|
21 | <description>Should native hadoop libraries, if present, be used.</description> |
---|
22 | </property> |
---|
23 | |
---|
24 | <property> |
---|
25 | <name>hadoop.http.filter.initializers</name> |
---|
26 | <value></value> |
---|
27 | <description>A comma separated list of class names. Each class in the list |
---|
28 | must extend org.apache.hadoop.http.FilterInitializer. The corresponding |
---|
29 | Filter will be initialized. Then, the Filter will be applied to all user |
---|
30 | facing jsp and servlet web pages. The ordering of the list defines the |
---|
31 | ordering of the filters.</description> |
---|
32 | </property> |
---|
33 | |
---|
34 | <property> |
---|
35 | <name>hadoop.security.authorization</name> |
---|
36 | <value>false</value> |
---|
37 | <description>Is service-level authorization enabled?</description> |
---|
38 | </property> |
---|
39 | |
---|
40 | <!--- logging properties --> |
---|
41 | |
---|
42 | <property> |
---|
43 | <name>hadoop.logfile.size</name> |
---|
44 | <value>10000000</value> |
---|
45 | <description>The max size of each log file</description> |
---|
46 | </property> |
---|
47 | |
---|
48 | <property> |
---|
49 | <name>hadoop.logfile.count</name> |
---|
50 | <value>10</value> |
---|
51 | <description>The max number of log files</description> |
---|
52 | </property> |
---|
53 | |
---|
54 | <!-- i/o properties --> |
---|
55 | <property> |
---|
56 | <name>io.file.buffer.size</name> |
---|
57 | <value>4096</value> |
---|
58 | <description>The size of buffer for use in sequence files. |
---|
59 | The size of this buffer should probably be a multiple of hardware |
---|
60 | page size (4096 on Intel x86), and it determines how much data is |
---|
61 | buffered during read and write operations.</description> |
---|
62 | </property> |
---|
63 | |
---|
64 | <property> |
---|
65 | <name>io.bytes.per.checksum</name> |
---|
66 | <value>512</value> |
---|
67 | <description>The number of bytes per checksum. Must not be larger than |
---|
68 | io.file.buffer.size.</description> |
---|
69 | </property> |
---|
70 | |
---|
71 | <property> |
---|
72 | <name>io.skip.checksum.errors</name> |
---|
73 | <value>false</value> |
---|
74 | <description>If true, when a checksum error is encountered while |
---|
75 | reading a sequence file, entries are skipped, instead of throwing an |
---|
76 | exception.</description> |
---|
77 | </property> |
---|
78 | |
---|
79 | <property> |
---|
80 | <name>io.compression.codecs</name> |
---|
81 | <value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value> |
---|
82 | <description>A list of the compression codec classes that can be used |
---|
83 | for compression/decompression.</description> |
---|
84 | </property> |
---|
85 | |
---|
86 | <property> |
---|
87 | <name>io.serializations</name> |
---|
88 | <value>org.apache.hadoop.io.serializer.WritableSerialization</value> |
---|
89 | <description>A list of serialization classes that can be used for |
---|
90 | obtaining serializers and deserializers.</description> |
---|
91 | </property> |
---|
92 | |
---|
93 | <!-- file system properties --> |
---|
94 | |
---|
95 | <property> |
---|
96 | <name>fs.default.name</name> |
---|
97 | <value>file:///</value> |
---|
98 | <description>The name of the default file system. A URI whose |
---|
99 | scheme and authority determine the FileSystem implementation. The |
---|
100 | uri's scheme determines the config property (fs.SCHEME.impl) naming |
---|
101 | the FileSystem implementation class. The uri's authority is used to |
---|
102 | determine the host, port, etc. for a filesystem.</description> |
---|
103 | </property> |
---|
104 | |
---|
105 | <property> |
---|
106 | <name>fs.trash.interval</name> |
---|
107 | <value>0</value> |
---|
108 | <description>Number of minutes between trash checkpoints. |
---|
109 | If zero, the trash feature is disabled. |
---|
110 | </description> |
---|
111 | </property> |
---|
112 | |
---|
113 | <property> |
---|
114 | <name>fs.file.impl</name> |
---|
115 | <value>org.apache.hadoop.fs.LocalFileSystem</value> |
---|
116 | <description>The FileSystem for file: uris.</description> |
---|
117 | </property> |
---|
118 | |
---|
119 | <property> |
---|
120 | <name>fs.hdfs.impl</name> |
---|
121 | <value>org.apache.hadoop.hdfs.DistributedFileSystem</value> |
---|
122 | <description>The FileSystem for hdfs: uris.</description> |
---|
123 | </property> |
---|
124 | |
---|
125 | <property> |
---|
126 | <name>fs.s3.impl</name> |
---|
127 | <value>org.apache.hadoop.fs.s3.S3FileSystem</value> |
---|
128 | <description>The FileSystem for s3: uris.</description> |
---|
129 | </property> |
---|
130 | |
---|
131 | <property> |
---|
132 | <name>fs.s3n.impl</name> |
---|
133 | <value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value> |
---|
134 | <description>The FileSystem for s3n: (Native S3) uris.</description> |
---|
135 | </property> |
---|
136 | |
---|
137 | <property> |
---|
138 | <name>fs.kfs.impl</name> |
---|
139 | <value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value> |
---|
140 | <description>The FileSystem for kfs: uris.</description> |
---|
141 | </property> |
---|
142 | |
---|
143 | <property> |
---|
144 | <name>fs.hftp.impl</name> |
---|
145 | <value>org.apache.hadoop.hdfs.HftpFileSystem</value> |
---|
146 | </property> |
---|
147 | |
---|
148 | <property> |
---|
149 | <name>fs.hsftp.impl</name> |
---|
150 | <value>org.apache.hadoop.hdfs.HsftpFileSystem</value> |
---|
151 | </property> |
---|
152 | |
---|
153 | <property> |
---|
154 | <name>fs.ftp.impl</name> |
---|
155 | <value>org.apache.hadoop.fs.ftp.FTPFileSystem</value> |
---|
156 | <description>The FileSystem for ftp: uris.</description> |
---|
157 | </property> |
---|
158 | |
---|
159 | <property> |
---|
160 | <name>fs.ramfs.impl</name> |
---|
161 | <value>org.apache.hadoop.fs.InMemoryFileSystem</value> |
---|
162 | <description>The FileSystem for ramfs: uris.</description> |
---|
163 | </property> |
---|
164 | |
---|
165 | <property> |
---|
166 | <name>fs.har.impl</name> |
---|
167 | <value>org.apache.hadoop.fs.HarFileSystem</value> |
---|
168 | <description>The filesystem for Hadoop archives. </description> |
---|
169 | </property> |
---|
170 | |
---|
171 | <property> |
---|
172 | <name>fs.checkpoint.dir</name> |
---|
173 | <value>${hadoop.tmp.dir}/dfs/namesecondary</value> |
---|
174 | <description>Determines where on the local filesystem the DFS secondary |
---|
175 | name node should store the temporary images to merge. |
---|
176 | If this is a comma-delimited list of directories then the image is |
---|
177 | replicated in all of the directories for redundancy. |
---|
178 | </description> |
---|
179 | </property> |
---|
180 | |
---|
181 | <property> |
---|
182 | <name>fs.checkpoint.edits.dir</name> |
---|
183 | <value>${fs.checkpoint.dir}</value> |
---|
184 | <description>Determines where on the local filesystem the DFS secondary |
---|
185 | name node should store the temporary edits to merge. |
---|
186 | If this is a comma-delimited list of directoires then teh edits is |
---|
187 | replicated in all of the directoires for redundancy. |
---|
188 | Default value is same as fs.checkpoint.dir |
---|
189 | </description> |
---|
190 | </property> |
---|
191 | |
---|
192 | <property> |
---|
193 | <name>fs.checkpoint.period</name> |
---|
194 | <value>3600</value> |
---|
195 | <description>The number of seconds between two periodic checkpoints. |
---|
196 | </description> |
---|
197 | </property> |
---|
198 | |
---|
199 | <property> |
---|
200 | <name>fs.checkpoint.size</name> |
---|
201 | <value>67108864</value> |
---|
202 | <description>The size of the current edit log (in bytes) that triggers |
---|
203 | a periodic checkpoint even if the fs.checkpoint.period hasn't expired. |
---|
204 | </description> |
---|
205 | </property> |
---|
206 | |
---|
207 | |
---|
208 | |
---|
209 | <property> |
---|
210 | <name>fs.s3.block.size</name> |
---|
211 | <value>67108864</value> |
---|
212 | <description>Block size to use when writing files to S3.</description> |
---|
213 | </property> |
---|
214 | |
---|
215 | <property> |
---|
216 | <name>fs.s3.buffer.dir</name> |
---|
217 | <value>${hadoop.tmp.dir}/s3</value> |
---|
218 | <description>Determines where on the local filesystem the S3 filesystem |
---|
219 | should store files before sending them to S3 |
---|
220 | (or after retrieving them from S3). |
---|
221 | </description> |
---|
222 | </property> |
---|
223 | |
---|
224 | <property> |
---|
225 | <name>fs.s3.maxRetries</name> |
---|
226 | <value>4</value> |
---|
227 | <description>The maximum number of retries for reading or writing files to S3, |
---|
228 | before we signal failure to the application. |
---|
229 | </description> |
---|
230 | </property> |
---|
231 | |
---|
232 | <property> |
---|
233 | <name>fs.s3.sleepTimeSeconds</name> |
---|
234 | <value>10</value> |
---|
235 | <description>The number of seconds to sleep between each S3 retry. |
---|
236 | </description> |
---|
237 | </property> |
---|
238 | |
---|
239 | |
---|
240 | <property> |
---|
241 | <name>local.cache.size</name> |
---|
242 | <value>10737418240</value> |
---|
243 | <description>The limit on the size of cache you want to keep, set by default |
---|
244 | to 10GB. This will act as a soft limit on the cache directory for out of band data. |
---|
245 | </description> |
---|
246 | </property> |
---|
247 | |
---|
248 | <property> |
---|
249 | <name>io.seqfile.compress.blocksize</name> |
---|
250 | <value>1000000</value> |
---|
251 | <description>The minimum block size for compression in block compressed |
---|
252 | SequenceFiles. |
---|
253 | </description> |
---|
254 | </property> |
---|
255 | |
---|
256 | <property> |
---|
257 | <name>io.seqfile.lazydecompress</name> |
---|
258 | <value>true</value> |
---|
259 | <description>Should values of block-compressed SequenceFiles be decompressed |
---|
260 | only when necessary. |
---|
261 | </description> |
---|
262 | </property> |
---|
263 | |
---|
264 | <property> |
---|
265 | <name>io.seqfile.sorter.recordlimit</name> |
---|
266 | <value>1000000</value> |
---|
267 | <description>The limit on number of records to be kept in memory in a spill |
---|
268 | in SequenceFiles.Sorter |
---|
269 | </description> |
---|
270 | </property> |
---|
271 | |
---|
272 | <property> |
---|
273 | <name>io.mapfile.bloom.size</name> |
---|
274 | <value>1048576</value> |
---|
275 | <description>The size of BloomFilter-s used in BloomMapFile. Each time this many |
---|
276 | keys is appended the next BloomFilter will be created (inside a DynamicBloomFilter). |
---|
277 | Larger values minimize the number of filters, which slightly increases the performance, |
---|
278 | but may waste too much space if the total number of keys is usually much smaller |
---|
279 | than this number. |
---|
280 | </description> |
---|
281 | </property> |
---|
282 | |
---|
283 | <property> |
---|
284 | <name>io.mapfile.bloom.error.rate</name> |
---|
285 | <value>0.005</value> |
---|
286 | <description>The rate of false positives in BloomFilter-s used in BloomMapFile. |
---|
287 | As this value decreases, the size of BloomFilter-s increases exponentially. This |
---|
288 | value is the probability of encountering false positives (default is 0.5%). |
---|
289 | </description> |
---|
290 | </property> |
---|
291 | |
---|
292 | <property> |
---|
293 | <name>hadoop.util.hash.type</name> |
---|
294 | <value>murmur</value> |
---|
295 | <description>The default implementation of Hash. Currently this can take one of the |
---|
296 | two values: 'murmur' to select MurmurHash and 'jenkins' to select JenkinsHash. |
---|
297 | </description> |
---|
298 | </property> |
---|
299 | |
---|
300 | |
---|
301 | <!-- ipc properties --> |
---|
302 | |
---|
303 | <property> |
---|
304 | <name>ipc.client.idlethreshold</name> |
---|
305 | <value>4000</value> |
---|
306 | <description>Defines the threshold number of connections after which |
---|
307 | connections will be inspected for idleness. |
---|
308 | </description> |
---|
309 | </property> |
---|
310 | |
---|
311 | <property> |
---|
312 | <name>ipc.client.kill.max</name> |
---|
313 | <value>10</value> |
---|
314 | <description>Defines the maximum number of clients to disconnect in one go. |
---|
315 | </description> |
---|
316 | </property> |
---|
317 | |
---|
318 | <property> |
---|
319 | <name>ipc.client.connection.maxidletime</name> |
---|
320 | <value>10000</value> |
---|
321 | <description>The maximum time in msec after which a client will bring down the |
---|
322 | connection to the server. |
---|
323 | </description> |
---|
324 | </property> |
---|
325 | |
---|
326 | <property> |
---|
327 | <name>ipc.client.connect.max.retries</name> |
---|
328 | <value>10</value> |
---|
329 | <description>Indicates the number of retries a client will make to establish |
---|
330 | a server connection. |
---|
331 | </description> |
---|
332 | </property> |
---|
333 | |
---|
334 | <property> |
---|
335 | <name>ipc.server.listen.queue.size</name> |
---|
336 | <value>128</value> |
---|
337 | <description>Indicates the length of the listen queue for servers accepting |
---|
338 | client connections. |
---|
339 | </description> |
---|
340 | </property> |
---|
341 | |
---|
342 | <property> |
---|
343 | <name>ipc.server.tcpnodelay</name> |
---|
344 | <value>false</value> |
---|
345 | <description>Turn on/off Nagle's algorithm for the TCP socket connection on |
---|
346 | the server. Setting to true disables the algorithm and may decrease latency |
---|
347 | with a cost of more/smaller packets. |
---|
348 | </description> |
---|
349 | </property> |
---|
350 | |
---|
351 | <property> |
---|
352 | <name>ipc.client.tcpnodelay</name> |
---|
353 | <value>false</value> |
---|
354 | <description>Turn on/off Nagle's algorithm for the TCP socket connection on |
---|
355 | the client. Setting to true disables the algorithm and may decrease latency |
---|
356 | with a cost of more/smaller packets. |
---|
357 | </description> |
---|
358 | </property> |
---|
359 | |
---|
360 | |
---|
361 | <!-- Web Interface Configuration --> |
---|
362 | |
---|
363 | <property> |
---|
364 | <name>webinterface.private.actions</name> |
---|
365 | <value>false</value> |
---|
366 | <description> If set to true, the web interfaces of JT and NN may contain |
---|
367 | actions, such as kill job, delete file, etc., that should |
---|
368 | not be exposed to public. Enable this option if the interfaces |
---|
369 | are only reachable by those who have the right authorization. |
---|
370 | </description> |
---|
371 | </property> |
---|
372 | |
---|
373 | <!-- Proxy Configuration --> |
---|
374 | |
---|
375 | <property> |
---|
376 | <name>hadoop.rpc.socket.factory.class.default</name> |
---|
377 | <value>org.apache.hadoop.net.StandardSocketFactory</value> |
---|
378 | <description> Default SocketFactory to use. This parameter is expected to be |
---|
379 | formatted as "package.FactoryClassName". |
---|
380 | </description> |
---|
381 | </property> |
---|
382 | |
---|
383 | <property> |
---|
384 | <name>hadoop.rpc.socket.factory.class.ClientProtocol</name> |
---|
385 | <value></value> |
---|
386 | <description> SocketFactory to use to connect to a DFS. If null or empty, use |
---|
387 | hadoop.rpc.socket.class.default. This socket factory is also used by |
---|
388 | DFSClient to create sockets to DataNodes. |
---|
389 | </description> |
---|
390 | </property> |
---|
391 | |
---|
392 | |
---|
393 | |
---|
394 | <property> |
---|
395 | <name>hadoop.socks.server</name> |
---|
396 | <value></value> |
---|
397 | <description> Address (host:port) of the SOCKS server to be used by the |
---|
398 | SocksSocketFactory. |
---|
399 | </description> |
---|
400 | </property> |
---|
401 | |
---|
402 | <!-- Rack Configuration --> |
---|
403 | |
---|
404 | <property> |
---|
405 | <name>topology.node.switch.mapping.impl</name> |
---|
406 | <value>org.apache.hadoop.net.ScriptBasedMapping</value> |
---|
407 | <description> The default implementation of the DNSToSwitchMapping. It |
---|
408 | invokes a script specified in topology.script.file.name to resolve |
---|
409 | node names. If the value for topology.script.file.name is not set, the |
---|
410 | default value of DEFAULT_RACK is returned for all node names. |
---|
411 | </description> |
---|
412 | </property> |
---|
413 | |
---|
414 | <property> |
---|
415 | <name>topology.script.file.name</name> |
---|
416 | <value></value> |
---|
417 | <description> The script name that should be invoked to resolve DNS names to |
---|
418 | NetworkTopology names. Example: the script would take host.foo.bar as an |
---|
419 | argument, and return /rack1 as the output. |
---|
420 | </description> |
---|
421 | </property> |
---|
422 | |
---|
423 | <property> |
---|
424 | <name>topology.script.number.args</name> |
---|
425 | <value>100</value> |
---|
426 | <description> The max number of args that the script configured with |
---|
427 | topology.script.file.name should be run with. Each arg is an |
---|
428 | IP address. |
---|
429 | </description> |
---|
430 | </property> |
---|
431 | |
---|
432 | |
---|
433 | |
---|
434 | </configuration> |
---|