API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Jul 15th, 2016
112
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 30.62 KB | None | 0 0
raw download clone embed print report
  1. <?xml version="1.0" encoding="UTF-8"?>
  2. <configuration>
  3. <property>
  4. <name>javax.jdo.option.ConnectionURL</name>
  5. <value>jdbc:mysql://127.0.0.1:3306/hive?createDatabaseIfNotExist=true</value>
  6. </property>
  7. <property>
  8. <name>javax.jdo.option.ConnectionDriverName</name>
  9. <value>com.mysql.jdbc.Driver</value>
  10. </property>
  11. <property>
  12. <name>javax.jdo.option.ConnectionUserName</name>
  13. <value>root</value>
  14. </property>
  15. <property>
  16. <name>javax.jdo.option.ConnectionPassword</name>
  17. <value>admin</value>
  18. </property>
  19. <property>
  20. <name>hive.metastore.warehouse.dir</name>
  21. <value>/user/hive/warehouse</value>
  22. </property>
  23. <property>
  24. <name>hive.execution.engine</name>
  25. <value>mr</value>
  26. </property>
  27. <property>
  28. <name>hive.exec.submitviachild</name>
  29. <value>false</value>
  30. </property>
  31. <property>
  32. <name>hive.exec.submit.local.task.via.child</name>
  33. <value>true</value>
  34. </property>
  35. <property>
  36. <name>hive.ignore.mapjoin.hint</name>
  37. <value>true</value>
  38. </property>
  39. <property>
  40. <name>hive.map.aggr</name>
  41. <value>true</value>
  42. <description>Whether to use map-side aggregation in Hive Group By queries</description>
  43. </property>
  44. <property>
  45. <name>hive.groupby.skewindata</name>
  46. <value>true</value>
  47. <description>Whether there is skew in data to optimize group by queries</description>
  48. </property>
  49. <property>
  50. <name>hive.join.emit.interval</name>
  51. <value>1000</value>
  52. <description>How many rows in the right-most join operand Hive should buffer before emitting the join result.</description>
  53. </property>
  54. <property>
  55. <name>hive.join.cache.size</name>
  56. <value>25000</value>
  57. <description>How many rows in the joining tables (except the streaming table) should be cached in memory.</description>
  58. </property>
  59. <property>
  60. <name>hive.cbo.enable</name>
  61. <value>true</value>
  62. <description>Flag to control enabling Cost Based Optimizations using Calcite framework.</description>
  63. </property>
  64. <property>
  65. <name>hive.mapjoin.bucket.cache.size</name>
  66. <value>100</value>
  67. <description />
  68. </property>
  69. <property>
  70. <name>hive.mapjoin.optimized.hashtable</name>
  71. <value>true</value>
  72. <description>Whether Hive should use memory-optimized hash table for MapJoin. Only works on Tez,
  73. because memory-optimized hashtable cannot be serialized.</description>
  74. </property>
  75. <property>
  76. <name>hive.mapjoin.optimized.hashtable.wbsize</name>
  77. <value>10485760</value>
  78. <description>Optimized hashtable (see hive.mapjoin.optimized.hashtable) uses a chain of buffers to
  79. store data. This is one buffer size. HT may be slightly faster if this is larger, but for small
  80. joins unnecessary memory will be allocated and then trimmed.</description>
  81. </property>
  82. <property>
  83. <name>hive.smbjoin.cache.rows</name>
  84. <value>10000</value>
  85. <description>How many rows with the same key value should be cached in memory per smb joined table.</description>
  86. </property>
  87. <property>
  88. <name>hive.groupby.mapaggr.checkinterval</name>
  89. <value>100000</value>
  90. <description>Number of rows after which size of the grouping keys/aggregation classes is performed</description>
  91. </property>
  92. <property>
  93. <name>hive.map.aggr.hash.percentmemory</name>
  94. <value>0.5</value>
  95. <description>Portion of total memory to be used by map-side group aggregation hash table</description>
  96. </property>
  97. <property>
  98. <name>hive.mapjoin.followby.map.aggr.hash.percentmemory</name>
  99. <value>0.3</value>
  100. <description>Portion of total memory to be used by map-side group aggregation hash table, when this group by is followed by map join</description>
  101. </property>
  102. <property>
  103. <name>hive.map.aggr.hash.force.flush.memory.threshold</name>
  104. <value>0.9</value>
  105. <description>The max memory to be used by map-side group aggregation hash table.
  106. If the memory usage is higher than this number, force to flush data</description>
  107. </property>
  108. <property>
  109. <name>hive.map.aggr.hash.min.reduction</name>
  110. <value>0.5</value>
  111. <description>Hash aggregation will be turned off if the ratio between hash table size and input rows is bigger than this number.
  112. Set to 1 to make sure hash aggregation is never turned off.</description>
  113. </property>
  114. <property>
  115. <name>hive.multigroupby.singlereducer</name>
  116. <value>true</value>
  117. <description>Whether to optimize multi group by query to generate single M/R job plan. If the multi group by query has
  118. common group by keys, it will be optimized to generate single M/R job.</description>
  119. </property>
  120. <property>
  121. <name>hive.map.groupby.sorted</name>
  122. <value>true</value>
  123. <description>If the bucketing/sorting properties of the table exactly match the grouping key, whether to perform
  124. the group by in the mapper by using BucketizedHiveInputFormat. The only downside to this
  125. is that it limits the number of mappers to the number of files.</description>
  126. </property>
  127. <property>
  128. <name>hive.map.groupby.sorted.testmode</name>
  129. <value>false</value>
  130. <description>If the bucketing/sorting properties of the table exactly match the grouping key, whether to perform
  131. the group by in the mapper by using BucketizedHiveInputFormat. If the test mode is set, the plan
  132. is not converted, but a query property is set to denote the same.</description>
  133. </property>
  134. <property>
  135. <name>hive.groupby.orderby.position.alias</name>
  136. <value>true</value>
  137. <description>Whether to enable using Column Position Alias in Group By or Order By</description>
  138. </property>
  139. <property>
  140. <name>hive.new.job.grouping.set.cardinality</name>
  141. <value>30</value>
  142. <description>Whether a new map-reduce job should be launched for grouping sets/rollups/cubes.
  143. For a query like: select a, b, c, count(1) from T group by a, b, c with rollup;
  144. 4 rows are created per row: (a, b, c), (a, b, null), (a, null, null), (null, null, null).
  145. This can lead to explosion across map-reduce boundary if the cardinality of T is very high,
  146. and map-side aggregation does not do a very good job.
  147.  
  148. This parameter decides if Hive should add an additional map-reduce job. If the grouping set
  149. cardinality (4 in the example above), is more than this value, a new MR job is added under the
  150. assumption that the original group by will reduce the data size.</description>
  151. </property>
  152. <property>
  153. <name>hive.exec.copyfile.maxsize</name>
  154. <value>33554432</value>
  155. <description>Maximum file size (in Mb) that Hive uses to do single HDFS copies between directories.Distributed copies (distcp) will be used instead for bigger files so that copies can be done faster.</description>
  156. </property>
  157. <property>
  158. <name>hive.default.fileformat</name>
  159. <value>TextFile</value>
  160. <description>Expects one of [textfile, sequencefile, rcfile, orc].
  161. Default file format for CREATE TABLE statement. Users can explicitly override it by CREATE TABLE ... STORED AS [FORMAT]</description>
  162. </property>
  163. <property>
  164. <name>hive.exec.orc.memory.pool</name>
  165. <value>0.5</value>
  166. <description>Maximum fraction of heap that can be used by ORC file writers</description>
  167. </property>
  168. <property>
  169. <name>hive.exec.orc.write.format</name>
  170. <value />
  171. <description>Define the version of the file to write. Possible values are 0.11 and 0.12.
  172. If this parameter is not defined, ORC will use the run length encoding (RLE)
  173. introduced in Hive 0.12. Any value other than 0.11 results in the 0.12 encoding.</description>
  174. </property>
  175. <property>
  176. <name>hive.exec.orc.default.stripe.size</name>
  177. <value>67108864</value>
  178. <description>Define the default ORC stripe size, in bytes.</description>
  179. </property>
  180. <property>
  181. <name>hive.exec.orc.default.block.size</name>
  182. <value>268435456</value>
  183. <description>Define the default file system block size for ORC files.</description>
  184. </property>
  185. <property>
  186. <name>hive.exec.orc.dictionary.key.size.threshold</name>
  187. <value>0.8</value>
  188. <description>If the number of keys in a dictionary is greater than this fraction of the total number of
  189. non-null rows, turn off dictionary encoding. Use 1 to always use dictionary encoding.</description>
  190. </property>
  191. <property>
  192. <name>hive.exec.orc.default.row.index.stride</name>
  193. <value>10000</value>
  194. <description>Define the default ORC index stride in number of rows. (Stride is the number of rows
  195. an index entry represents.)</description>
  196. </property>
  197. <property>
  198. <name>hive.orc.row.index.stride.dictionary.check</name>
  199. <value>true</value>
  200. <description>If enabled dictionary check will happen after first row index stride (default 10000 rows)
  201. else dictionary check will happen before writing first stripe. In both cases, the decision
  202. to use dictionary or not will be retained thereafter.</description>
  203. </property>
  204. <property>
  205. <name>hive.exec.orc.default.buffer.size</name>
  206. <value>262144</value>
  207. <description>Define the default ORC buffer size, in bytes.</description>
  208. </property>
  209. <property>
  210. <name>hive.exec.orc.default.block.padding</name>
  211. <value>true</value>
  212. <description>Define the default block padding, which pads stripes to the HDFS block boundaries.</description>
  213. </property>
  214. <property>
  215. <name>hive.exec.orc.block.padding.tolerance</name>
  216. <value>0.05</value>
  217. <description>Define the tolerance for block padding as a decimal fraction of stripe size (for
  218. example, the default value 0.05 is 5% of the stripe size). For the defaults of 64Mb
  219. ORC stripe and 256Mb HDFS blocks, the default block padding tolerance of 5% will
  220. reserve a maximum of 3.2Mb for padding within the 256Mb block. In that case, if the
  221. available size within the block is more than 3.2Mb, a new smaller stripe will be
  222. inserted to fit within that space. This will make sure that no stripe written will
  223. cross block boundaries and cause remote reads within a node local task.</description>
  224. </property>
  225. <property>
  226. <name>hive.exec.orc.default.compress</name>
  227. <value>ZLIB</value>
  228. <description>Define the default compression codec for ORC file</description>
  229. </property>
  230. <property>
  231. <name>hive.exec.orc.encoding.strategy</name>
  232. <value>SPEED</value>
  233. <description>Expects one of [speed, compression].
  234. Define the encoding strategy to use while writing data. Changing this will
  235. only affect the light weight encoding for integers. This flag will not
  236. change the compression level of higher level compression codec (like ZLIB).</description>
  237. </property>
  238. <property>
  239. <name>hive.exec.orc.compression.strategy</name>
  240. <value>SPEED</value>
  241. <description>Expects one of [speed, compression].
  242. Define the compression strategy to use while writing data.
  243. This changes the compression level of higher level compression codec (like ZLIB).</description>
  244. </property>
  245. <property>
  246. <name>hive.orc.splits.include.file.footer</name>
  247. <value>false</value>
  248. <description>If turned on splits generated by orc will include metadata about the stripes in the file. This
  249. data is read remotely (from the client or HS2 machine) and sent to all the tasks.</description>
  250. </property>
  251. <property>
  252. <name>hive.orc.cache.stripe.details.size</name>
  253. <value>10000</value>
  254. <description>Cache size for keeping meta info about orc splits cached in the client.</description>
  255. </property>
  256. <property>
  257. <name>hive.orc.compute.splits.num.threads</name>
  258. <value>10</value>
  259. <description>How many threads orc should use to create splits in parallel.</description>
  260. </property>
  261. <property>
  262. <name>hive.exec.orc.skip.corrupt.data</name>
  263. <value>false</value>
  264. <description>If ORC reader encounters corrupt data, this value will be used to determine
  265. whether to skip the corrupt data or throw exception. The default behavior is to throw exception.</description>
  266. </property>
  267. <property>
  268. <name>hive.exec.orc.zerocopy</name>
  269. <value>true</value>
  270. <description>Use zerocopy reads with ORC. (This requires Hadoop 2.3 or later.)</description>
  271. </property>
  272. <property>
  273. <name>hive.optimize.skewjoin</name>
  274. <value>true</value>
  275. <description>Whether to enable skew join optimization.
  276. The algorithm is as follows: At runtime, detect the keys with a large skew. Instead of
  277. processing those keys, store them temporarily in an HDFS directory. In a follow-up map-reduce
  278. job, process those skewed keys. The same key need not be skewed for all the tables, and so,
  279. the follow-up map-reduce job (for the skewed keys) would be much faster, since it would be a
  280. map-join.</description>
  281. </property>
  282. <property>
  283. <name>hive.auto.convert.join</name>
  284. <value>true</value>
  285. <description>Whether Hive enables the optimization about converting common join into mapjoin based on the input file size</description>
  286. </property>
  287. <property>
  288. <name>hive.auto.convert.join.noconditionaltask</name>
  289. <value>true</value>
  290. <description>Whether Hive enables the optimization about converting common join into mapjoin based on the input file size.
  291. If this parameter is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than the
  292. specified size, the join is directly converted to a mapjoin (there is no conditional task).</description>
  293. </property>
  294. <property>
  295. <name>hive.auto.convert.join.noconditionaltask.size</name>
  296. <value>536870912</value>
  297. <description>If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect.
  298. However, if it is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than this size,
  299. the join is directly converted to a mapjoin(there is no conditional task). The default is 10MB</description>
  300. </property>
  301. <property>
  302. <name>hive.auto.convert.join.use.nonstaged</name>
  303. <value>false</value>
  304. <description>For conditional joins, if input stream from a small alias can be directly applied to join operator without
  305. filtering or projection, the alias need not to be pre-staged in distributed cache via mapred local task.
  306. Currently, this is not working with vectorization or tez execution engine.</description>
  307. </property>
  308. <property>
  309. <name>hive.skewjoin.key</name>
  310. <value>100000</value>
  311. <description>Determine if we get a skew key in join. If we see more than the specified number of rows with the same key in join operator,
  312. we think the key as a skew join key.</description>
  313. </property>
  314. <property>
  315. <name>hive.skewjoin.mapjoin.map.tasks</name>
  316. <value>10000</value>
  317. <description>Determine the number of map task used in the follow up map join job for a skew join.
  318. It should be used together with hive.skewjoin.mapjoin.min.split to perform a fine grained control.</description>
  319. </property>
  320. <property>
  321. <name>hive.skewjoin.mapjoin.min.split</name>
  322. <value>33554432</value>
  323. <description>Determine the number of map task at most used in the follow up map join job for a skew join by specifying
  324. the minimum split size. It should be used together with hive.skewjoin.mapjoin.map.tasks to perform a fine grained control.</description>
  325. </property>
  326. <property>
  327. <name>hive.hashtable.key.count.adjustment</name>
  328. <value>1.0</value>
  329. <description>Adjustment to mapjoin hashtable size derived from table and column statistics; the estimate of the number of keys is divided by this value. If the value is 0, statistics are not usedand hive.hashtable.initialCapacity is used instead.</description>
  330. </property>
  331. <property>
  332. <name>hive.hashtable.initialCapacity</name>
  333. <value>100000</value>
  334. <description>Initial capacity of mapjoin hashtable if statistics are absent, or if hive.hashtable.stats.key.estimate.adjustment is set to 0</description>
  335. </property>
  336. <property>
  337. <name>hive.hashtable.loadfactor</name>
  338. <value>0.75</value>
  339. <description />
  340. </property>
  341. <property>
  342. <name>hive.mapjoin.followby.gby.localtask.max.memory.usage</name>
  343. <value>0.55</value>
  344. <description>This number means how much memory the local task can take to hold the key/value into an in-memory hash table
  345. when this map join is followed by a group by. If the local task's memory usage is more than this number,
  346. the local task will abort by itself. It means the data of the small table is too large to be held in memory.</description>
  347. </property>
  348. <property>
  349. <name>hive.mapjoin.localtask.max.memory.usage</name>
  350. <value>0.9</value>
  351. <description>This number means how much memory the local task can take to hold the key/value into an in-memory hash table.
  352. If the local task's memory usage is more than this number, the local task will abort by itself.
  353. It means the data of the small table is too large to be held in memory.</description>
  354. </property>
  355. <property>
  356. <name>hive.mapjoin.check.memory.rows</name>
  357. <value>100000</value>
  358. <description>The number means after how many rows processed it needs to check the memory usage</description>
  359. </property>
  360. <property>
  361. <name>hive.auto.convert.sortmerge.join</name>
  362. <value>true</value>
  363. <description>Will the join be automatically converted to a sort-merge join, if the joined tables pass the criteria for sort-merge join.</description>
  364. </property>
  365. <property>
  366. <name>hive.auto.convert.sortmerge.join.bigtable.selection.policy</name>
  367. <value>org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ</value>
  368. <description>The policy to choose the big table for automatic conversion to sort-merge join.
  369. By default, the table with the largest partitions is assigned the big table. All policies are:
  370. . based on position of the table - the leftmost table is selected
  371. org.apache.hadoop.hive.ql.optimizer.LeftmostBigTableSMJ.
  372. . based on total size (all the partitions selected in the query) of the table
  373. org.apache.hadoop.hive.ql.optimizer.TableSizeBasedBigTableSelectorForAutoSMJ.
  374. . based on average size (all the partitions selected in the query) of the table
  375. org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ.
  376. New policies can be added in future.</description>
  377. </property>
  378. <property>
  379. <name>hive.auto.convert.sortmerge.join.to.mapjoin</name>
  380. <value>true</value>
  381. <description>If hive.auto.convert.sortmerge.join is set to true, and a join was converted to a sort-merge join,
  382. this parameter decides whether each table should be tried as a big table, and effectively a map-join should be
  383. tried. That would create a conditional task with n+1 children for a n-way join (1 child for each table as the
  384. big table), and the backup task will be the sort-merge join. In some cases, a map-join would be faster than a
  385. sort-merge join, if there is no advantage of having the output bucketed and sorted. For example, if a very big sorted
  386. and bucketed table with few files (say 10 files) are being joined with a very small sorter and bucketed table
  387. with few files (10 files), the sort-merge join will only use 10 mappers, and a simple map-only join might be faster
  388. if the complete small table can fit in memory, and a map-join can be performed.</description>
  389. </property>
  390. <property>
  391. <name>hive.server2.thrift.min.worker.threads</name>
  392. <value>5</value>
  393. <description>Minimum number of Thrift worker threads</description>
  394. </property>
  395. <property>
  396. <name>hive.server2.thrift.max.worker.threads</name>
  397. <value>500</value>
  398. <description>Maximum number of Thrift worker threads</description>
  399. </property>
  400. <property>
  401. <name>hive.server2.thrift.exponential.backoff.slot.length</name>
  402. <value>100ms</value>
  403. <description>Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
  404. Binary exponential backoff slot time for Thrift clients during login to HiveServer2,
  405. for retries until hitting Thrift client timeout</description>
  406. </property>
  407. <property>
  408. <name>hive.server2.thrift.login.timeout</name>
  409. <value>20s</value>
  410. <description>Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
  411. Timeout for Thrift clients during login to HiveServer2</description>
  412. </property>
  413. <property>
  414. <name>hive.server2.thrift.worker.keepalive.time</name>
  415. <value>60s</value>
  416. <description>Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
  417. Keepalive time (in seconds) for an idle worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval.</description>
  418. </property>
  419. <property>
  420. <name>hive.server2.async.exec.threads</name>
  421. <value>100</value>
  422. <description>Number of threads in the async thread pool for HiveServer2</description>
  423. </property>
  424. <property>
  425. <name>hive.server2.async.exec.shutdown.timeout</name>
  426. <value>10s</value>
  427. <description>Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
  428. How long HiveServer2 shutdown will wait for async threads to terminate.</description>
  429. </property>
  430. <property>
  431. <name>hive.server2.async.exec.wait.queue.size</name>
  432. <value>100</value>
  433. <description>Size of the wait queue for async thread pool in HiveServer2.
  434. After hitting this limit, the async thread pool will reject new requests.</description>
  435. </property>
  436. <property>
  437. <name>hive.server2.async.exec.keepalive.time</name>
  438. <value>10s</value>
  439. <description>Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
  440. Time that an idle HiveServer2 async thread (from the thread pool) will wait for a new task
  441. to arrive before terminating</description>
  442. </property>
  443. <property>
  444. <name>hive.server2.long.polling.timeout</name>
  445. <value>5000ms</value>
  446. <description>Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
  447. Time that HiveServer2 will wait before responding to asynchronous calls that use long polling</description>
  448. </property>
  449. <property>
  450. <name>hive.server2.authentication</name>
  451. <value>NONE</value>
  452. <description>Expects one of [nosasl, none, ldap, kerberos, pam, custom].
  453. Client authentication types.
  454. NONE: no authentication check
  455. LDAP: LDAP/AD based authentication
  456. KERBEROS: Kerberos/GSSAPI authentication
  457. CUSTOM: Custom authentication provider
  458. (Use with property hive.server2.custom.authentication.class)
  459. PAM: Pluggable authentication module
  460. NOSASL: Raw transport</description>
  461. </property>
  462. <property>
  463. <name>hive.server2.allow.user.substitution</name>
  464. <value>true</value>
  465. <description>Allow alternate user to be specified as part of HiveServer2 open connection request.</description>
  466. </property>
  467. <property>
  468. <name>hive.vectorized.execution.enabled</name>
  469. <value>true</value>
  470. <description>This flag should be set to true to enable vectorized mode of query execution.
  471. The default value is false.</description>
  472. </property>
  473. <property>
  474. <name>hive.vectorized.execution.reduce.enabled</name>
  475. <value>true</value>
  476. <description>This flag should be set to true to enable vectorized mode of the reduce-side of query execution.
  477. The default value is true.</description>
  478. </property>
  479. <property>
  480. <name>hive.vectorized.execution.reduce.groupby.enabled</name>
  481. <value>true</value>
  482. <description>This flag should be set to true to enable vectorized mode of the reduce-side GROUP BY query execution.
  483. The default value is true.</description>
  484. </property>
  485. <property>
  486. <name>hive.vectorized.groupby.checkinterval</name>
  487. <value>100000</value>
  488. <description>Number of entries added to the group by aggregation hash before a recomputation of average entry size is performed.</description>
  489. </property>
  490. <property>
  491. <name>hive.vectorized.groupby.maxentries</name>
  492. <value>1000000</value>
  493. <description>Max number of entries in the vector group by aggregation hashtables.
  494. Exceeding this will trigger a flush irrelevant of memory pressure condition.</description>
  495. </property>
  496. <property>
  497. <name>hive.vectorized.groupby.flush.percent</name>
  498. <value>0.1</value>
  499. <description>Percent of entries in the group by aggregation hash flushed when the memory threshold is exceeded.</description>
  500. </property>
  501. <property>
  502. <name>hive.rpc.query.plan</name>
  503. <value>true</value>
  504. <description>Whether to send the query plan via local resource or RPC</description>
  505. </property>
  506. <property>
  507. <name>hive.compute.splits.in.am</name>
  508. <value>true</value>
  509. <description>Whether to generate the splits locally or in the AM (tez only)</description>
  510. </property>
  511. <property>
  512. <name>hive.prewarm.enabled</name>
  513. <value>false</value>
  514. <description>Enables container prewarm for Tez (Hadoop 2 only)</description>
  515. </property>
  516. <property>
  517. <name>hive.prewarm.numcontainers</name>
  518. <value>10</value>
  519. <description>Controls the number of containers to prewarm for Tez (Hadoop 2 only)</description>
  520. </property>
  521. <property>
  522. <name>hive.exec.parallel</name>
  523. <value>true</value>
  524. <description>Whether to execute jobs in parallel</description>
  525. </property>
  526. <property>
  527. <name>hive.exec.parallel.thread.number</name>
  528. <value>16</value>
  529. <description>How many jobs at most can be executed in parallel</description>
  530. </property>
  531. <property>
  532. <name>hive.mapred.reduce.tasks.speculative.execution</name>
  533. <value>true</value>
  534. <description>Whether speculative execution for reducers should be turned on.</description>
  535. </property>
  536. <property>
  537. <name>hive.exec.counters.pull.interval</name>
  538. <value>1000</value>
  539. <description>The interval with which to poll the JobTracker for the counters the running job.
  540. The smaller it is the more load there will be on the jobtracker, the higher it is the less granular the caught will be.</description>
  541. </property>
  542. <property>
  543. <name>hive.exec.dynamic.partition</name>
  544. <value>true</value>
  545. <description>Whether or not to allow dynamic partitions in DML/DDL.</description>
  546. </property>
  547. <property>
  548. <name>hive.exec.dynamic.partition.mode</name>
  549. <value>strict</value>
  550. <description>In strict mode, the user must specify at least one static partition
  551. in case the user accidentally overwrites all partitions.
  552. In nonstrict mode all partitions are allowed to be dynamic.</description>
  553. </property>
  554. <property>
  555. <name>hive.localize.resource.wait.interval</name>
  556. <value>5000ms</value>
  557. <description>Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
  558. Time to wait for another thread to localize the same resource for hive-tez.</description>
  559. </property>
  560. <property>
  561. <name>hive.localize.resource.num.wait.attempts</name>
  562. <value>5</value>
  563. <description>The number of attempts waiting for localizing a resource in hive-tez.</description>
  564. </property>
  565. <property>
  566. <name>hive.merge.tezfiles</name>
  567. <value>false</value>
  568. <description>Merge small files at the end of a Tez DAG</description>
  569. </property>
  570. <property>
  571. <name>hive.tez.input.format</name>
  572. <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value>
  573. <description>The default input format for tez. Tez groups splits in the AM.</description>
  574. </property>
  575. <property>
  576. <name>hive.tez.container.size</name>
  577. <value>4096</value>
  578. </property>
  579. <property>
  580. <name>hive.tez.cpu.vcores</name>
  581. <value>-1</value>
  582. </property>
  583. <property>
  584. <name>hive.tez.java.opts</name>
  585. <value>-Xmx1024m -XX:NewRatio=8 -XX:+UseNUMA -XX:+UseParallelGC</value>
  586. </property>
  587. <property>
  588. <name>hive.tez.log.level</name>
  589. <value>INFO</value>
  590. </property>
  591. <property>
  592. <name>hive.server2.tez.default.queues</name>
  593. <value />
  594. </property>
  595. <property>
  596. <name>hive.server2.tez.sessions.per.default.queue</name>
  597. <value>1</value>
  598. </property>
  599. <property>
  600. <name>hive.server2.tez.initialize.default.sessions</name>
  601. <value>false</value>
  602. </property>
  603. <property>
  604. <name>hive.convert.join.bucket.mapjoin.tez</name>
  605. <value>true</value>
  606. </property>
  607. <property>
  608. <name>hive.tez.auto.reducer.parallelism</name>
  609. <value>true</value>
  610. </property>
  611. <property>
  612. <name>hive.tez.max.partition.factor</name>
  613. <value>2.0</value>
  614. <description>When auto reducer parallelism is enabled this factor will be used to over-partition data in shuffle edges.</description>
  615. </property>
  616. <property>
  617. <name>hive.tez.min.partition.factor</name>
  618. <value>0.25</value>
  619. </property>
  620. <property>
  621. <name>hive.tez.dynamic.partition.pruning</name>
  622. <value>true</value>
  623. </property>
  624. <property>
  625. <name>hive.tez.dynamic.partition.pruning.max.event.size</name>
  626. <value>1048576</value>
  627. <description>Maximum size of events sent by processors in dynamic pruning. If this size is crossed no pruning will take place.</description>
  628. </property>
  629. <property>
  630. <name>hive.tez.dynamic.partition.pruning.max.data.size</name>
  631. <value>104857600</value>
  632. <description>Maximum total data size of events in dynamic pruning.</description>
  633. </property>
  634. <property>
  635. <name>hive.tez.smb.number.waves</name>
  636. <value>0.5</value>
  637. <description>The number of waves in which to run the SMB join. Account for cluster being occupied. Ideally should be 1 wave.</description>
  638. </property>
  639. <property>
  640. <name>hive.tez.exec.print.summary</name>
  641. <value>false</value>
  642. <description>Display breakdown of execution steps, for every query executed by the shell.</description>
  643. </property>
  644. <property>
  645. <name>hive.tez.exec.inplace.progress</name>
  646. <value>true</value>
  647. <description>Updates tez job execution progress in-place in the terminal.</description>
  648. </property>
  649. </configuration>
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!