/
hdfs-default.xml
4261 lines (3789 loc) · 141 KB
/
hdfs-default.xml
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
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
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.
-->
<!-- Do not modify this file directly. Instead, copy entries that you -->
<!-- wish to modify from this file into hdfs-site.xml and change them -->
<!-- there. If hdfs-site.xml does not already exist, create it. -->
<configuration>
<property>
<name>hadoop.hdfs.configuration.version</name>
<value>1</value>
<description>version of this configuration file</description>
</property>
<property>
<name>dfs.namenode.rpc-address</name>
<value></value>
<description>
RPC address that handles all clients requests. In the case of HA/Federation where multiple namenodes exist,
the name service id is added to the name e.g. dfs.namenode.rpc-address.ns1
dfs.namenode.rpc-address.EXAMPLENAMESERVICE
The value of this property will take the form of nn-host1:rpc-port.
</description>
</property>
<property>
<name>dfs.namenode.rpc-bind-host</name>
<value></value>
<description>
The actual address the RPC server will bind to. If this optional address is
set, it overrides only the hostname portion of dfs.namenode.rpc-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node listen on all interfaces by
setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.servicerpc-address</name>
<value></value>
<description>
RPC address for HDFS Services communication. BackupNode, Datanodes and all other services should be
connecting to this address if it is configured. In the case of HA/Federation where multiple namenodes exist,
the name service id is added to the name e.g. dfs.namenode.servicerpc-address.ns1
dfs.namenode.rpc-address.EXAMPLENAMESERVICE
The value of this property will take the form of nn-host1:rpc-port.
If the value of this property is unset the value of dfs.namenode.rpc-address will be used as the default.
</description>
</property>
<property>
<name>dfs.namenode.servicerpc-bind-host</name>
<value></value>
<description>
The actual address the service RPC server will bind to. If this optional address is
set, it overrides only the hostname portion of dfs.namenode.servicerpc-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node listen on all interfaces by
setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.rpc-address</name>
<value></value>
<description>
NameNode RPC lifeline address. This is an optional separate RPC address
that can be used to isolate health checks and liveness to protect against
resource exhaustion in the main RPC handler pool. In the case of
HA/Federation where multiple NameNodes exist, the name service ID is added
to the name e.g. dfs.namenode.lifeline.rpc-address.ns1. The value of this
property will take the form of nn-host1:rpc-port. If this property is not
defined, then the NameNode will not start a lifeline RPC server. By
default, the property is not defined.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.rpc-bind-host</name>
<value></value>
<description>
The actual address the lifeline RPC server will bind to. If this optional
address is set, it overrides only the hostname portion of
dfs.namenode.lifeline.rpc-address. It can also be specified per name node
or name service for HA/Federation. This is useful for making the name node
listen on all interfaces by setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>0.0.0.0:50090</value>
<description>
The secondary namenode http server address and port.
</description>
</property>
<property>
<name>dfs.namenode.secondary.https-address</name>
<value>0.0.0.0:50091</value>
<description>
The secondary namenode HTTPS server address and port.
</description>
</property>
<property>
<name>dfs.datanode.address</name>
<value>0.0.0.0:50010</value>
<description>
The datanode server address and port for data transfer.
</description>
</property>
<property>
<name>dfs.datanode.http.address</name>
<value>0.0.0.0:50075</value>
<description>
The datanode http server address and port.
</description>
</property>
<property>
<name>dfs.datanode.ipc.address</name>
<value>0.0.0.0:50020</value>
<description>
The datanode ipc server address and port.
</description>
</property>
<property>
<name>dfs.datanode.handler.count</name>
<value>10</value>
<description>The number of server threads for the datanode.</description>
</property>
<property>
<name>dfs.namenode.http-address</name>
<value>0.0.0.0:50070</value>
<description>
The address and the base port where the dfs namenode web ui will listen on.
</description>
</property>
<property>
<name>dfs.namenode.http-bind-host</name>
<value></value>
<description>
The actual adress the HTTP server will bind to. If this optional address
is set, it overrides only the hostname portion of dfs.namenode.http-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node HTTP server listen on all
interfaces by setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.heartbeat.recheck-interval</name>
<value>300000</value>
<description>
This time decides the interval to check for expired datanodes.
With this value and dfs.heartbeat.interval, the interval of
deciding the datanode is stale or not is also calculated.
The unit of this configuration is millisecond.
</description>
</property>
<property>
<name>dfs.http.policy</name>
<value>HTTP_ONLY</value>
<description>Decide if HTTPS(SSL) is supported on HDFS
This configures the HTTP endpoint for HDFS daemons:
The following values are supported:
- HTTP_ONLY : Service is provided only on http
- HTTPS_ONLY : Service is provided only on https
- HTTP_AND_HTTPS : Service is provided both on http and https
</description>
</property>
<property>
<name>dfs.client.https.need-auth</name>
<value>false</value>
<description>Whether SSL client certificate authentication is required
</description>
</property>
<property>
<name>dfs.client.cached.conn.retry</name>
<value>3</value>
<description>The number of times the HDFS client will pull a socket from the
cache. Once this number is exceeded, the client will try to create a new
socket.
</description>
</property>
<property>
<name>dfs.https.server.keystore.resource</name>
<value>ssl-server.xml</value>
<description>Resource file from which ssl server keystore
information will be extracted
</description>
</property>
<property>
<name>dfs.client.https.keystore.resource</name>
<value>ssl-client.xml</value>
<description>Resource file from which ssl client keystore
information will be extracted
</description>
</property>
<property>
<name>dfs.datanode.https.address</name>
<value>0.0.0.0:50475</value>
<description>The datanode secure http server address and port.</description>
</property>
<property>
<name>dfs.namenode.https-address</name>
<value>0.0.0.0:50470</value>
<description>The namenode secure http server address and port.</description>
</property>
<property>
<name>dfs.namenode.https-bind-host</name>
<value></value>
<description>
The actual adress the HTTPS server will bind to. If this optional address
is set, it overrides only the hostname portion of dfs.namenode.https-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node HTTPS server listen on all
interfaces by setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.datanode.dns.interface</name>
<value>default</value>
<description>
The name of the Network Interface from which a data node should
report its IP address. e.g. eth2. This setting may be required for some
multi-homed nodes where the DataNodes are assigned multiple hostnames
and it is desirable for the DataNodes to use a non-default hostname.
Prefer using hadoop.security.dns.interface over
dfs.datanode.dns.interface.
</description>
</property>
<property>
<name>dfs.datanode.dns.nameserver</name>
<value>default</value>
<description>
The host name or IP address of the name server (DNS) which a DataNode
should use to determine its own host name.
Prefer using hadoop.security.dns.nameserver over
dfs.datanode.dns.nameserver.
</description>
</property>
<property>
<name>dfs.namenode.backup.address</name>
<value>0.0.0.0:50100</value>
<description>
The backup node server address and port.
If the port is 0 then the server will start on a free port.
</description>
</property>
<property>
<name>dfs.namenode.backup.http-address</name>
<value>0.0.0.0:50105</value>
<description>
The backup node http server address and port.
If the port is 0 then the server will start on a free port.
</description>
</property>
<property>
<name>dfs.namenode.replication.considerLoad</name>
<value>true</value>
<description>Decide if chooseTarget considers the target's load or not
</description>
</property>
<property>
<name>dfs.namenode.replication.considerLoad.factor</name>
<value>2.0</value>
<description>The factor by which a node's load can exceed the average
before being rejected for writes, only if considerLoad is true.
</description>
</property>
<property>
<name>dfs.default.chunk.view.size</name>
<value>32768</value>
<description>The number of bytes to view for a file on the browser.
</description>
</property>
<property>
<name>dfs.datanode.du.reserved</name>
<value>0</value>
<description>Reserved space in bytes per volume. Always leave this much space free for non dfs use.
Specific storage type based reservation is also supported. The property can be followed with
corresponding storage types ([ssd]/[disk]/[archive]/[ram_disk]) for cluster with heterogeneous storage.
For example, reserved space for RAM_DISK storage can be configured using property
'dfs.datanode.du.reserved.ram_disk'. If specific storage type reservation is not configured
then dfs.datanode.du.reserved will be used.
</description>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file://${hadoop.tmp.dir}/dfs/name</value>
<description>Determines where on the local filesystem the DFS name node
should store the name table(fsimage). If this is a comma-delimited list
of directories then the name table is replicated in all of the
directories, for redundancy. </description>
</property>
<property>
<name>dfs.namenode.name.dir.restore</name>
<value>false</value>
<description>Set to true to enable NameNode to attempt recovering a
previously failed dfs.namenode.name.dir. When enabled, a recovery of any
failed directory is attempted during checkpoint.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-component-length</name>
<value>255</value>
<description>Defines the maximum number of bytes in UTF-8 encoding in each
component of a path. A value of 0 will disable the check.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-directory-items</name>
<value>1048576</value>
<description>Defines the maximum number of items that a directory may
contain. Cannot set the property to a value less than 1 or more than
6400000.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.min-block-size</name>
<value>1048576</value>
<description>Minimum block size in bytes, enforced by the Namenode at create
time. This prevents the accidental creation of files with tiny block
sizes (and thus many blocks), which can degrade
performance.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-blocks-per-file</name>
<value>1048576</value>
<description>Maximum number of blocks per file, enforced by the Namenode on
write. This prevents the creation of extremely large files which can
degrade performance.</description>
</property>
<property>
<name>dfs.namenode.edits.dir</name>
<value>${dfs.namenode.name.dir}</value>
<description>Determines where on the local filesystem the DFS name node
should store the transaction (edits) file. If this is a comma-delimited list
of directories then the transaction file is replicated in all of the
directories, for redundancy. Default value is same as dfs.namenode.name.dir
</description>
</property>
<property>
<name>dfs.namenode.edits.dir.required</name>
<value></value>
<description>This should be a subset of dfs.namenode.edits.dir,
to ensure that the transaction (edits) file
in these places is always up-to-date.
</description>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value></value>
<description>A directory on shared storage between the multiple namenodes
in an HA cluster. This directory will be written by the active and read
by the standby in order to keep the namespaces synchronized. This directory
does not need to be listed in dfs.namenode.edits.dir above. It should be
left empty in a non-HA cluster.
</description>
</property>
<property>
<name>dfs.namenode.edits.journal-plugin.qjournal</name>
<value>org.apache.hadoop.hdfs.qjournal.client.QuorumJournalManager</value>
</property>
<property>
<name>dfs.permissions.enabled</name>
<value>true</value>
<description>
If "true", enable permission checking in HDFS.
If "false", permission checking is turned off,
but all other behavior is unchanged.
Switching from one parameter value to the other does not change the mode,
owner or group of files or directories.
</description>
</property>
<property>
<name>dfs.permissions.superusergroup</name>
<value>supergroup</value>
<description>The name of the group of super-users.
The value should be a single group name.
</description>
</property>
<property>
<name>dfs.cluster.administrators</name>
<value></value>
<description>ACL for the admins, this configuration is used to control
who can access the default servlets in the namenode, etc. The value
should be a comma separated list of users and groups. The user list
comes first and is separated by a space followed by the group list,
e.g. "user1,user2 group1,group2". Both users and groups are optional,
so "user1", " group1", "", "user1 group1", "user1,user2 group1,group2"
are all valid (note the leading space in " group1"). '*' grants access
to all users and groups, e.g. '*', '* ' and ' *' are all valid.
</description>
</property>
<property>
<name>dfs.namenode.acls.enabled</name>
<value>false</value>
<description>
Set to true to enable support for HDFS ACLs (Access Control Lists). By
default, ACLs are disabled. When ACLs are disabled, the NameNode rejects
all RPCs related to setting or getting ACLs.
</description>
</property>
<property>
<name>dfs.namenode.lazypersist.file.scrub.interval.sec</name>
<value>300</value>
<description>
The NameNode periodically scans the namespace for LazyPersist files with
missing blocks and unlinks them from the namespace. This configuration key
controls the interval between successive scans. Set it to a negative value
to disable this behavior.
</description>
</property>
<property>
<name>dfs.block.access.token.enable</name>
<value>false</value>
<description>
If "true", access tokens are used as capabilities for accessing datanodes.
If "false", no access tokens are checked on accessing datanodes.
</description>
</property>
<property>
<name>dfs.block.access.key.update.interval</name>
<value>600</value>
<description>
Interval in minutes at which namenode updates its access keys.
</description>
</property>
<property>
<name>dfs.block.access.token.lifetime</name>
<value>600</value>
<description>The lifetime of access tokens in minutes.</description>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file://${hadoop.tmp.dir}/dfs/data</value>
<description>Determines where on the local filesystem an DFS data node
should store its blocks. If this is a comma-delimited
list of directories, then data will be stored in all named
directories, typically on different devices. The directories should be tagged
with corresponding storage types ([SSD]/[DISK]/[ARCHIVE]/[RAM_DISK]) for HDFS
storage policies. The default storage type will be DISK if the directory does
not have a storage type tagged explicitly. Directories that do not exist will
be created if local filesystem permission allows.
</description>
</property>
<property>
<name>dfs.datanode.data.dir.perm</name>
<value>700</value>
<description>Permissions for the directories on on the local filesystem where
the DFS data node store its blocks. The permissions can either be octal or
symbolic.</description>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
<description>Default block replication.
The actual number of replications can be specified when the file is created.
The default is used if replication is not specified in create time.
</description>
</property>
<property>
<name>dfs.replication.max</name>
<value>512</value>
<description>Maximal block replication.
</description>
</property>
<property>
<name>dfs.namenode.replication.min</name>
<value>1</value>
<description>Minimal block replication.
</description>
</property>
<property>
<name>dfs.namenode.maintenance.replication.min</name>
<value>1</value>
<description>Minimal live block replication in existence of maintenance mode.
</description>
</property>
<property>
<name>dfs.namenode.safemode.replication.min</name>
<value></value>
<description>
a separate minimum replication factor for calculating safe block count.
This is an expert level setting.
Setting this lower than the dfs.namenode.replication.min
is not recommend and/or dangerous for production setups.
When it's not set it takes value from dfs.namenode.replication.min
</description>
</property>
<property>
<name>dfs.blocksize</name>
<value>134217728</value>
<description>
The default block size for new files, in bytes.
You can use the following suffix (case insensitive):
k(kilo), m(mega), g(giga), t(tera), p(peta), e(exa) to specify the size (such as 128k, 512m, 1g, etc.),
Or provide complete size in bytes (such as 134217728 for 128 MB).
</description>
</property>
<property>
<name>dfs.client.block.write.retries</name>
<value>3</value>
<description>The number of retries for writing blocks to the data nodes,
before we signal failure to the application.
</description>
</property>
<property>
<name>dfs.client.block.write.replace-datanode-on-failure.enable</name>
<value>true</value>
<description>
If there is a datanode/network failure in the write pipeline,
DFSClient will try to remove the failed datanode from the pipeline
and then continue writing with the remaining datanodes. As a result,
the number of datanodes in the pipeline is decreased. The feature is
to add new datanodes to the pipeline.
This is a site-wide property to enable/disable the feature.
When the cluster size is extremely small, e.g. 3 nodes or less, cluster
administrators may want to set the policy to NEVER in the default
configuration file or disable this feature. Otherwise, users may
experience an unusually high rate of pipeline failures since it is
impossible to find new datanodes for replacement.
See also dfs.client.block.write.replace-datanode-on-failure.policy
</description>
</property>
<property>
<name>dfs.client.block.write.replace-datanode-on-failure.policy</name>
<value>DEFAULT</value>
<description>
This property is used only if the value of
dfs.client.block.write.replace-datanode-on-failure.enable is true.
ALWAYS: always add a new datanode when an existing datanode is removed.
NEVER: never add a new datanode.
DEFAULT:
Let r be the replication number.
Let n be the number of existing datanodes.
Add a new datanode only if r is greater than or equal to 3 and either
(1) floor(r/2) is greater than or equal to n; or
(2) r is greater than n and the block is hflushed/appended.
</description>
</property>
<property>
<name>dfs.client.block.write.replace-datanode-on-failure.best-effort</name>
<value>false</value>
<description>
This property is used only if the value of
dfs.client.block.write.replace-datanode-on-failure.enable is true.
Best effort means that the client will try to replace a failed datanode
in write pipeline (provided that the policy is satisfied), however, it
continues the write operation in case that the datanode replacement also
fails.
Suppose the datanode replacement fails.
false: An exception should be thrown so that the write will fail.
true : The write should be resumed with the remaining datandoes.
Note that setting this property to true allows writing to a pipeline
with a smaller number of datanodes. As a result, it increases the
probability of data loss.
</description>
</property>
<property>
<name>dfs.blockreport.intervalMsec</name>
<value>21600000</value>
<description>Determines block reporting interval in milliseconds.</description>
</property>
<property>
<name>dfs.blockreport.initialDelay</name> <value>0</value>
<description>Delay for first block report in seconds.</description>
</property>
<property>
<name>dfs.blockreport.split.threshold</name>
<value>1000000</value>
<description>If the number of blocks on the DataNode is below this
threshold then it will send block reports for all Storage Directories
in a single message.
If the number of blocks exceeds this threshold then the DataNode will
send block reports for each Storage Directory in separate messages.
Set to zero to always split.
</description>
</property>
<property>
<name>dfs.namenode.max.full.block.report.leases</name>
<value>6</value>
<description>The maximum number of leases for full block reports that the
NameNode will issue at any given time. This prevents the NameNode from
being flooded with full block reports that use up all the RPC handler
threads. This number should never be more than the number of RPC handler
threads or less than 1.
</description>
</property>
<property>
<name>dfs.namenode.full.block.report.lease.length.ms</name>
<value>300000</value>
<description>
The number of milliseconds that the NameNode will wait before invalidating
a full block report lease. This prevents a crashed DataNode from
permanently using up a full block report lease.
</description>
</property>
<property>
<name>dfs.datanode.directoryscan.interval</name>
<value>21600</value>
<description>Interval in seconds for Datanode to scan data directories and
reconcile the difference between blocks in memory and on the disk.
</description>
</property>
<property>
<name>dfs.datanode.directoryscan.threads</name>
<value>1</value>
<description>How many threads should the threadpool used to compile reports
for volumes in parallel have.
</description>
</property>
<property>
<name>dfs.datanode.directoryscan.throttle.limit.ms.per.sec</name>
<value>1000</value>
<description>The report compilation threads are limited to only running for
a given number of milliseconds per second, as configured by the
property. The limit is taken per thread, not in aggregate, e.g. setting
a limit of 100ms for 4 compiler threads will result in each thread being
limited to 100ms, not 25ms.
Note that the throttle does not interrupt the report compiler threads, so the
actual running time of the threads per second will typically be somewhat
higher than the throttle limit, usually by no more than 20%.
Setting this limit to 1000 disables compiler thread throttling. Only
values between 1 and 1000 are valid. Setting an invalid value will result
in the throttle being disabled and an error message being logged. 1000 is
the default setting.
</description>
</property>
<property>
<name>dfs.heartbeat.interval</name>
<value>3</value>
<description>Determines datanode heartbeat interval in seconds.</description>
</property>
<property>
<name>dfs.datanode.lifeline.interval.seconds</name>
<value></value>
<description>
Sets the interval in seconds between sending DataNode Lifeline Protocol
messages from the DataNode to the NameNode. The value must be greater than
the value of dfs.heartbeat.interval. If this property is not defined, then
the default behavior is to calculate the interval as 3x the value of
dfs.heartbeat.interval. Note that normal heartbeat processing may cause the
DataNode to postpone sending lifeline messages if they are not required.
Under normal operations with speedy heartbeat processing, it is possible
that no lifeline messages will need to be sent at all. This property has no
effect if dfs.namenode.lifeline.rpc-address is not defined.
</description>
</property>
<property>
<name>dfs.namenode.handler.count</name>
<value>10</value>
<description>The number of Namenode RPC server threads that listen to
requests from clients.
If dfs.namenode.servicerpc-address is not configured then
Namenode RPC server threads listen to requests from all nodes.
</description>
</property>
<property>
<name>dfs.namenode.service.handler.count</name>
<value>10</value>
<description>The number of Namenode RPC server threads that listen to
requests from DataNodes and from all other non-client nodes.
dfs.namenode.service.handler.count will be valid only if
dfs.namenode.servicerpc-address is configured.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.handler.ratio</name>
<value>0.10</value>
<description>
A ratio applied to the value of dfs.namenode.handler.count, which then
provides the number of RPC server threads the NameNode runs for handling the
lifeline RPC server. For example, if dfs.namenode.handler.count is 100, and
dfs.namenode.lifeline.handler.factor is 0.10, then the NameNode starts
100 * 0.10 = 10 threads for handling the lifeline RPC server. It is common
to tune the value of dfs.namenode.handler.count as a function of the number
of DataNodes in a cluster. Using this property allows for the lifeline RPC
server handler threads to be tuned automatically without needing to touch a
separate property. Lifeline message processing is lightweight, so it is
expected to require many fewer threads than the main NameNode RPC server.
This property is not used if dfs.namenode.lifeline.handler.count is defined,
which sets an absolute thread count. This property has no effect if
dfs.namenode.lifeline.rpc-address is not defined.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.handler.count</name>
<value></value>
<description>
Sets an absolute number of RPC server threads the NameNode runs for handling
the DataNode Lifeline Protocol and HA health check requests from ZKFC. If
this property is defined, then it overrides the behavior of
dfs.namenode.lifeline.handler.ratio. By default, it is not defined. This
property has no effect if dfs.namenode.lifeline.rpc-address is not defined.
</description>
</property>
<property>
<name>dfs.namenode.safemode.threshold-pct</name>
<value>0.999f</value>
<description>
Specifies the percentage of blocks that should satisfy
the minimal replication requirement defined by dfs.namenode.replication.min.
Values less than or equal to 0 mean not to wait for any particular
percentage of blocks before exiting safemode.
Values greater than 1 will make safe mode permanent.
</description>
</property>
<property>
<name>dfs.namenode.safemode.min.datanodes</name>
<value>0</value>
<description>
Specifies the number of datanodes that must be considered alive
before the name node exits safemode.
Values less than or equal to 0 mean not to take the number of live
datanodes into account when deciding whether to remain in safe mode
during startup.
Values greater than the number of datanodes in the cluster
will make safe mode permanent.
</description>
</property>
<property>
<name>dfs.namenode.safemode.extension</name>
<value>30000</value>
<description>
Determines extension of safe mode in milliseconds after the threshold level
is reached. Support multiple time unit suffix (case insensitive), as
described in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.namenode.resource.check.interval</name>
<value>5000</value>
<description>
The interval in milliseconds at which the NameNode resource checker runs.
The checker calculates the number of the NameNode storage volumes whose
available spaces are more than dfs.namenode.resource.du.reserved, and
enters safemode if the number becomes lower than the minimum value
specified by dfs.namenode.resource.checked.volumes.minimum.
</description>
</property>
<property>
<name>dfs.namenode.resource.du.reserved</name>
<value>104857600</value>
<description>
The amount of space to reserve/require for a NameNode storage directory
in bytes. The default is 100MB.
</description>
</property>
<property>
<name>dfs.namenode.resource.checked.volumes</name>
<value></value>
<description>
A list of local directories for the NameNode resource checker to check in
addition to the local edits directories.
</description>
</property>
<property>
<name>dfs.namenode.resource.checked.volumes.minimum</name>
<value>1</value>
<description>
The minimum number of redundant NameNode storage volumes required.
</description>
</property>
<property>
<name>dfs.datanode.balance.bandwidthPerSec</name>
<value>10m</value>
<description>
Specifies the maximum amount of bandwidth that each datanode
can utilize for the balancing purpose in term of
the number of bytes per second. You can use the following
suffix (case insensitive):
k(kilo), m(mega), g(giga), t(tera), p(peta), e(exa)to specify the size
(such as 128k, 512m, 1g, etc.).
Or provide complete size in bytes (such as 134217728 for 128 MB).
</description>
</property>
<property>
<name>dfs.hosts</name>
<value></value>
<description>Names a file that contains a list of hosts that are
permitted to connect to the namenode. The full pathname of the file
must be specified. If the value is empty, all hosts are
permitted.</description>
</property>
<property>
<name>dfs.hosts.exclude</name>
<value></value>
<description>Names a file that contains a list of hosts that are
not permitted to connect to the namenode. The full pathname of the
file must be specified. If the value is empty, no hosts are
excluded.</description>
</property>
<property>
<name>dfs.namenode.max.objects</name>
<value>0</value>
<description>The maximum number of files, directories and blocks
dfs supports. A value of zero indicates no limit to the number
of objects that dfs supports.
</description>
</property>
<property>
<name>dfs.namenode.datanode.registration.ip-hostname-check</name>
<value>true</value>
<description>
If true (the default), then the namenode requires that a connecting
datanode's address must be resolved to a hostname. If necessary, a reverse
DNS lookup is performed. All attempts to register a datanode from an
unresolvable address are rejected.
It is recommended that this setting be left on to prevent accidental
registration of datanodes listed by hostname in the excludes file during a
DNS outage. Only set this to false in environments where there is no
infrastructure to support reverse DNS lookup.
</description>
</property>
<property>
<name>dfs.namenode.decommission.interval</name>
<value>30</value>
<description>Namenode periodicity in seconds to check if decommission is
complete.</description>
</property>
<property>
<name>dfs.namenode.decommission.blocks.per.interval</name>
<value>500000</value>
<description>The approximate number of blocks to process per
decommission interval, as defined in dfs.namenode.decommission.interval.
</description>
</property>
<property>
<name>dfs.namenode.decommission.max.concurrent.tracked.nodes</name>
<value>100</value>
<description>
The maximum number of decommission-in-progress datanodes nodes that will be
tracked at one time by the namenode. Tracking a decommission-in-progress
datanode consumes additional NN memory proportional to the number of blocks
on the datnode. Having a conservative limit reduces the potential impact
of decomissioning a large number of nodes at once.
A value of 0 means no limit will be enforced.
</description>
</property>
<property>
<name>dfs.namenode.replication.interval</name>
<value>3</value>
<description>The periodicity in seconds with which the namenode computes
replication work for datanodes. </description>
</property>
<property>
<name>dfs.namenode.accesstime.precision</name>
<value>3600000</value>
<description>The access time for HDFS file is precise upto this value.
The default value is 1 hour. Setting a value of 0 disables
access times for HDFS.
</description>
</property>
<property>
<name>dfs.datanode.plugins</name>
<value></value>
<description>Comma-separated list of datanode plug-ins to be activated.
</description>
</property>
<property>
<name>dfs.namenode.plugins</name>
<value></value>
<description>Comma-separated list of namenode plug-ins to be activated.
</description>
</property>
<property>
<name>dfs.namenode.block-placement-policy.default.prefer-local-node</name>
<value>true</value>
<description>Controls how the default block placement policy places
the first replica of a block. When true, it will prefer the node where
the client is running. When false, it will prefer a node in the same rack
as the client. Setting to false avoids situations where entire copies of
large files end up on a single node, thus creating hotspots.
</description>
</property>
<property>
<name>dfs.stream-buffer-size</name>
<value>4096</value>