PageRenderTime 60ms CodeModel.GetById 23ms RepoModel.GetById 0ms app.codeStats 0ms

/tags/release-0.2.0-rc0/hive/external/ql/src/test/results/clientpositive/bucketmapjoin4.q.out

#
text | 1013 lines | 989 code | 24 blank | 0 comment | 0 complexity | 570d96aceb6cb4a11e968199a42b5df6 MD5 | raw file
Possible License(s): Apache-2.0, BSD-3-Clause, JSON, CPL-1.0

Large files files are truncated, but you can click here to view the full file

    

  1. PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
    2. 

  2. PREHOOK: type: CREATETABLE
    3. 

  3. POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
    4. 

  4. POSTHOOK: type: CREATETABLE
    5. 

  5. POSTHOOK: Output: default@srcbucket_mapjoin
    6. 

  6. PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin
    7. 

  7. PREHOOK: type: LOAD
    8. 

  8. PREHOOK: Output: default@srcbucket_mapjoin
    9. 

  9. POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin
    10. 

  10. POSTHOOK: type: LOAD
    11. 

  11. POSTHOOK: Output: default@srcbucket_mapjoin
    12. 

  12. PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin
    13. 

  13. PREHOOK: type: LOAD
    14. 

  14. PREHOOK: Output: default@srcbucket_mapjoin
    15. 

  15. POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin
    16. 

  16. POSTHOOK: type: LOAD
    17. 

  17. POSTHOOK: Output: default@srcbucket_mapjoin
    18. 

  18. PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
    19. 

  19. PREHOOK: type: CREATETABLE
    20. 

  20. POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
    21. 

  21. POSTHOOK: type: CREATETABLE
    22. 

  22. POSTHOOK: Output: default@srcbucket_mapjoin_part
    23. 

  23. PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    24. 

  24. PREHOOK: type: LOAD
    25. 

  25. PREHOOK: Output: default@srcbucket_mapjoin_part
    26. 

  26. POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    27. 

  27. POSTHOOK: type: LOAD
    28. 

  28. POSTHOOK: Output: default@srcbucket_mapjoin_part
    29. 

  29. POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
    30. 

  30. PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    31. 

  31. PREHOOK: type: LOAD
    32. 

  32. PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
    33. 

  33. POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    34. 

  34. POSTHOOK: type: LOAD
    35. 

  35. POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
    36. 

  36. PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    37. 

  37. PREHOOK: type: LOAD
    38. 

  38. PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
    39. 

  39. POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    40. 

  40. POSTHOOK: type: LOAD
    41. 

  41. POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
    42. 

  42. PREHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    43. 

  43. PREHOOK: type: LOAD
    44. 

  44. PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
    45. 

  45. POSTHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
    46. 

  46. POSTHOOK: type: LOAD
    47. 

  47. POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
    48. 

  48. PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
    49. 

  49. PREHOOK: type: CREATETABLE
    50. 

  50. POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
    51. 

  51. POSTHOOK: type: CREATETABLE
    52. 

  52. POSTHOOK: Output: default@srcbucket_mapjoin_part_2
    53. 

  53. PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
    54. 

  54. PREHOOK: type: LOAD
    55. 

  55. PREHOOK: Output: default@srcbucket_mapjoin_part_2
    56. 

  56. POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
    57. 

  57. POSTHOOK: type: LOAD
    58. 

  58. POSTHOOK: Output: default@srcbucket_mapjoin_part_2
    59. 

  59. POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08
    60. 

  60. PREHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
    61. 

  61. PREHOOK: type: LOAD
    62. 

  62. PREHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08
    63. 

  63. POSTHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
    64. 

  64. POSTHOOK: type: LOAD
    65. 

  65. POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08
    66. 

  66. PREHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint)
    67. 

  67. PREHOOK: type: CREATETABLE
    68. 

  68. POSTHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint)
    69. 

  69. POSTHOOK: type: CREATETABLE
    70. 

  70. POSTHOOK: Output: default@bucketmapjoin_hash_result_1
    71. 

  71. PREHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint)
    72. 

  72. PREHOOK: type: CREATETABLE
    73. 

  73. POSTHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint)
    74. 

  74. POSTHOOK: type: CREATETABLE
    75. 

  75. POSTHOOK: Output: default@bucketmapjoin_hash_result_2
    76. 

  76. PREHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string)
    77. 

  77. PREHOOK: type: CREATETABLE
    78. 

  78. POSTHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string)
    79. 

  79. POSTHOOK: type: CREATETABLE
    80. 

  80. POSTHOOK: Output: default@bucketmapjoin_tmp_result
    81. 

  81. PREHOOK: query: explain extended
    82. 

  82. insert overwrite table bucketmapjoin_tmp_result
    83. 

  83. select /*+mapjoin(b)*/ a.key, a.value, b.value
    84. 

  84. from srcbucket_mapjoin a join srcbucket_mapjoin b
    85. 

  85. on a.key=b.key
    86. 

  86. PREHOOK: type: QUERY
    87. 

  87. POSTHOOK: query: explain extended
    88. 

  88. insert overwrite table bucketmapjoin_tmp_result
    89. 

  89. select /*+mapjoin(b)*/ a.key, a.value, b.value
    90. 

  90. from srcbucket_mapjoin a join srcbucket_mapjoin b
    91. 

  91. on a.key=b.key
    92. 

  92. POSTHOOK: type: QUERY
    93. 

  93. ABSTRACT SYNTAX TREE:
    94. 

  94.   (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST b))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value)))))
    95. 

  95. 

  96. STAGE DEPENDENCIES:
    97. 

  97.   Stage-7 is a root stage
    98. 

  98.   Stage-1 depends on stages: Stage-7
    99. 

  99.   Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3
    100. 

  100.   Stage-4
    101. 

  101.   Stage-0 depends on stages: Stage-4, Stage-3
    102. 

  102.   Stage-2 depends on stages: Stage-0
    103. 

  103.   Stage-3
    104. 

  104. 

  105. STAGE PLANS:
    106. 

  106.   Stage: Stage-7
    107. 

  107.     Map Reduce Local Work
    108. 

  108.       Alias -> Map Local Tables:
    109. 

  109.         b 
    110. 

  110.           Fetch Operator
    111. 

  111.             limit: -1
    112. 

  112.       Alias -> Map Local Operator Tree:
    113. 

  113.         b 
    114. 

  114.           TableScan
    115. 

  115.             alias: b
    116. 

  116.             GatherStats: false
    117. 

  117.             HashTable Sink Operator
    118. 

  118.               condition expressions:
    119. 

  119.                 0 {key} {value}
    120. 

  120.                 1 {value}
    121. 

  121.               handleSkewJoin: false
    122. 

  122.               keys:
    123. 

  123.                 0 [Column[key]]
    124. 

  124.                 1 [Column[key]]
    125. 

  125.               Position of Big Table: 0
    126. 

  126.       Bucket Mapjoin Context:
    127. 

  127.           Alias Bucket Base File Name Mapping:
    128. 

  128.             b {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt]}
    129. 

  129.           Alias Bucket File Name Mapping:
    130. 

  130.             b {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
    131. 

  131.           Alias Bucket Output File Name Mapping:
    132. 

  132.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
    133. 

  133.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
    134. 

  134. 

  135.   Stage: Stage-1
    136. 

  136.     Map Reduce
    137. 

  137.       Alias -> Map Operator Tree:
    138. 

  138.         a 
    139. 

  139.           TableScan
    140. 

  140.             alias: a
    141. 

  141.             GatherStats: false
    142. 

  142.             Map Join Operator
    143. 

  143.               condition map:
    144. 

  144.                    Inner Join 0 to 1
    145. 

  145.               condition expressions:
    146. 

  146.                 0 {key} {value}
    147. 

  147.                 1 {value}
    148. 

  148.               handleSkewJoin: false
    149. 

  149.               keys:
    150. 

  150.                 0 [Column[key]]
    151. 

  151.                 1 [Column[key]]
    152. 

  152.               outputColumnNames: _col0, _col1, _col5
    153. 

  153.               Position of Big Table: 0
    154. 

  154.               Select Operator
    155. 

  155.                 expressions:
    156. 

  156.                       expr: _col0
    157. 

  157.                       type: int
    158. 

  158.                       expr: _col1
    159. 

  159.                       type: string
    160. 

  160.                       expr: _col5
    161. 

  161.                       type: string
    162. 

  162.                 outputColumnNames: _col0, _col1, _col5
    163. 

  163.                 Select Operator
    164. 

  164.                   expressions:
    165. 

  165.                         expr: _col0
    166. 

  166.                         type: int
    167. 

  167.                         expr: _col1
    168. 

  168.                         type: string
    169. 

  169.                         expr: _col5
    170. 

  170.                         type: string
    171. 

  171.                   outputColumnNames: _col0, _col1, _col2
    172. 

  172.                   File Output Operator
    173. 

  173.                     compressed: false
    174. 

  174.                     GlobalTableId: 1
    175. 

  175.                     directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002
    176. 

  176.                     NumFilesPerFileSink: 1
    177. 

  177.                     Stats Publishing Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000/
    178. 

  178.                     table:
    179. 

  179.                         input format: org.apache.hadoop.mapred.TextInputFormat
    180. 

  180.                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    181. 

  181.                         properties:
    182. 

  182.                           bucket_count -1
    183. 

  183.                           columns key,value1,value2
    184. 

  184.                           columns.types string:string:string
    185. 

  185.                           file.inputformat org.apache.hadoop.mapred.TextInputFormat
    186. 

  186.                           file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    187. 

  187.                           location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    188. 

  188.                           name default.bucketmapjoin_tmp_result
    189. 

  189.                           serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    190. 

  190.                           serialization.format 1
    191. 

  191.                           serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    192. 

  192.                           transient_lastDdlTime 1306979244
    193. 

  193.                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    194. 

  194.                         name: default.bucketmapjoin_tmp_result
    195. 

  195.                     TotalFiles: 1
    196. 

  196.                     GatherStats: true
    197. 

  197.                     MultiFileSpray: false
    198. 

  198.       Local Work:
    199. 

  199.         Map Reduce Local Work
    200. 

  200.       Needs Tagging: false
    201. 

  201.       Path -> Alias:
    202. 

  202.         pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin [a]
    203. 

  203.       Path -> Partition:
    204. 

  204.         pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin 
    205. 

  205.           Partition
    206. 

  206.             base file name: srcbucket_mapjoin
    207. 

  207.             input format: org.apache.hadoop.mapred.TextInputFormat
    208. 

  208.             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    209. 

  209.             properties:
    210. 

  210.               bucket_count 2
    211. 

  211.               bucket_field_name key
    212. 

  212.               columns key,value
    213. 

  213.               columns.types int:string
    214. 

  214.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    215. 

  215.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    216. 

  216.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
    217. 

  217.               name default.srcbucket_mapjoin
    218. 

  218.               serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
    219. 

  219.               serialization.format 1
    220. 

  220.               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    221. 

  221.               transient_lastDdlTime 1306979239
    222. 

  222.             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    223. 

  223.           
    224. 

  224.               input format: org.apache.hadoop.mapred.TextInputFormat
    225. 

  225.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    226. 

  226.               properties:
    227. 

  227.                 bucket_count 2
    228. 

  228.                 bucket_field_name key
    229. 

  229.                 columns key,value
    230. 

  230.                 columns.types int:string
    231. 

  231.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    232. 

  232.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    233. 

  233.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
    234. 

  234.                 name default.srcbucket_mapjoin
    235. 

  235.                 serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
    236. 

  236.                 serialization.format 1
    237. 

  237.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    238. 

  238.                 transient_lastDdlTime 1306979239
    239. 

  239.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    240. 

  240.               name: default.srcbucket_mapjoin
    241. 

  241.             name: default.srcbucket_mapjoin
    242. 

  242. 

  243.   Stage: Stage-5
    244. 

  244.     Conditional Operator
    245. 

  245. 

  246.   Stage: Stage-4
    247. 

  247.     Move Operator
    248. 

  248.       files:
    249. 

  249.           hdfs directory: true
    250. 

  250.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002
    251. 

  251.           destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000
    252. 

  252. 

  253.   Stage: Stage-0
    254. 

  254.     Move Operator
    255. 

  255.       tables:
    256. 

  256.           replace: true
    257. 

  257.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000
    258. 

  258.           table:
    259. 

  259.               input format: org.apache.hadoop.mapred.TextInputFormat
    260. 

  260.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    261. 

  261.               properties:
    262. 

  262.                 bucket_count -1
    263. 

  263.                 columns key,value1,value2
    264. 

  264.                 columns.types string:string:string
    265. 

  265.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    266. 

  266.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    267. 

  267.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    268. 

  268.                 name default.bucketmapjoin_tmp_result
    269. 

  269.                 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    270. 

  270.                 serialization.format 1
    271. 

  271.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    272. 

  272.                 transient_lastDdlTime 1306979244
    273. 

  273.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    274. 

  274.               name: default.bucketmapjoin_tmp_result
    275. 

  275.           tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10001
    276. 

  276. 

  277.   Stage: Stage-2
    278. 

  278.     Stats-Aggr Operator
    279. 

  279.       Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000/
    280. 

  280. 

  281.   Stage: Stage-3
    282. 

  282.     Map Reduce
    283. 

  283.       Alias -> Map Operator Tree:
    284. 

  284.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002 
    285. 

  285.             File Output Operator
    286. 

  286.               compressed: false
    287. 

  287.               GlobalTableId: 0
    288. 

  288.               directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000
    289. 

  289.               NumFilesPerFileSink: 1
    290. 

  290.               table:
    291. 

  291.                   input format: org.apache.hadoop.mapred.TextInputFormat
    292. 

  292.                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    293. 

  293.                   properties:
    294. 

  294.                     bucket_count -1
    295. 

  295.                     columns key,value1,value2
    296. 

  296.                     columns.types string:string:string
    297. 

  297.                     file.inputformat org.apache.hadoop.mapred.TextInputFormat
    298. 

  298.                     file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    299. 

  299.                     location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    300. 

  300.                     name default.bucketmapjoin_tmp_result
    301. 

  301.                     serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    302. 

  302.                     serialization.format 1
    303. 

  303.                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    304. 

  304.                     transient_lastDdlTime 1306979244
    305. 

  305.                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    306. 

  306.                   name: default.bucketmapjoin_tmp_result
    307. 

  307.               TotalFiles: 1
    308. 

  308.               GatherStats: false
    309. 

  309.               MultiFileSpray: false
    310. 

  310.       Needs Tagging: false
    311. 

  311.       Path -> Alias:
    312. 

  312.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002]
    313. 

  313.       Path -> Partition:
    314. 

  314.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002 
    315. 

  315.           Partition
    316. 

  316.             base file name: -ext-10002
    317. 

  317.             input format: org.apache.hadoop.mapred.TextInputFormat
    318. 

  318.             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    319. 

  319.             properties:
    320. 

  320.               bucket_count -1
    321. 

  321.               columns key,value1,value2
    322. 

  322.               columns.types string:string:string
    323. 

  323.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    324. 

  324.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    325. 

  325.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    326. 

  326.               name default.bucketmapjoin_tmp_result
    327. 

  327.               serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    328. 

  328.               serialization.format 1
    329. 

  329.               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    330. 

  330.               transient_lastDdlTime 1306979244
    331. 

  331.             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    332. 

  332.           
    333. 

  333.               input format: org.apache.hadoop.mapred.TextInputFormat
    334. 

  334.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    335. 

  335.               properties:
    336. 

  336.                 bucket_count -1
    337. 

  337.                 columns key,value1,value2
    338. 

  338.                 columns.types string:string:string
    339. 

  339.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    340. 

  340.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    341. 

  341.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    342. 

  342.                 name default.bucketmapjoin_tmp_result
    343. 

  343.                 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    344. 

  344.                 serialization.format 1
    345. 

  345.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    346. 

  346.                 transient_lastDdlTime 1306979244
    347. 

  347.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    348. 

  348.               name: default.bucketmapjoin_tmp_result
    349. 

  349.             name: default.bucketmapjoin_tmp_result
    350. 

  350. 

  351. 

  352. PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result
    353. 

  353. select /*+mapjoin(b)*/ a.key, a.value, b.value
    354. 

  354. from srcbucket_mapjoin a join srcbucket_mapjoin b
    355. 

  355. on a.key=b.key
    356. 

  356. PREHOOK: type: QUERY
    357. 

  357. PREHOOK: Input: default@srcbucket_mapjoin
    358. 

  358. PREHOOK: Output: default@bucketmapjoin_tmp_result
    359. 

  359. POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result
    360. 

  360. select /*+mapjoin(b)*/ a.key, a.value, b.value
    361. 

  361. from srcbucket_mapjoin a join srcbucket_mapjoin b
    362. 

  362. on a.key=b.key
    363. 

  363. POSTHOOK: type: QUERY
    364. 

  364. POSTHOOK: Input: default@srcbucket_mapjoin
    365. 

  365. POSTHOOK: Output: default@bucketmapjoin_tmp_result
    366. 

  366. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    367. 

  367. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    368. 

  368. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    369. 

  369. PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
    370. 

  370. PREHOOK: type: QUERY
    371. 

  371. PREHOOK: Input: default@bucketmapjoin_tmp_result
    372. 

  372. PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-33_354_3111033757385788525/-mr-10000
    373. 

  373. POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
    374. 

  374. POSTHOOK: type: QUERY
    375. 

  375. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    376. 

  376. POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-33_354_3111033757385788525/-mr-10000
    377. 

  377. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    378. 

  378. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    379. 

  379. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    380. 

  380. 464
    381. 

  381. PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
    382. 

  382. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    383. 

  383. PREHOOK: type: QUERY
    384. 

  384. PREHOOK: Input: default@bucketmapjoin_tmp_result
    385. 

  385. PREHOOK: Output: default@bucketmapjoin_hash_result_1
    386. 

  386. POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
    387. 

  387. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    388. 

  388. POSTHOOK: type: QUERY
    389. 

  389. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    390. 

  390. POSTHOOK: Output: default@bucketmapjoin_hash_result_1
    391. 

  391. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    392. 

  392. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    393. 

  393. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    394. 

  394. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    395. 

  395. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    396. 

  396. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    397. 

  397. PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result
    398. 

  398. select /*+mapjoin(b)*/ a.key, a.value, b.value
    399. 

  399. from srcbucket_mapjoin a join srcbucket_mapjoin b
    400. 

  400. on a.key=b.key
    401. 

  401. PREHOOK: type: QUERY
    402. 

  402. PREHOOK: Input: default@srcbucket_mapjoin
    403. 

  403. PREHOOK: Output: default@bucketmapjoin_tmp_result
    404. 

  404. POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result
    405. 

  405. select /*+mapjoin(b)*/ a.key, a.value, b.value
    406. 

  406. from srcbucket_mapjoin a join srcbucket_mapjoin b
    407. 

  407. on a.key=b.key
    408. 

  408. POSTHOOK: type: QUERY
    409. 

  409. POSTHOOK: Input: default@srcbucket_mapjoin
    410. 

  410. POSTHOOK: Output: default@bucketmapjoin_tmp_result
    411. 

  411. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    412. 

  412. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    413. 

  413. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    414. 

  414. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    415. 

  415. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    416. 

  416. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    417. 

  417. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    418. 

  418. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    419. 

  419. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    420. 

  420. PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
    421. 

  421. PREHOOK: type: QUERY
    422. 

  422. PREHOOK: Input: default@bucketmapjoin_tmp_result
    423. 

  423. PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-49_331_2976822432880371649/-mr-10000
    424. 

  424. POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
    425. 

  425. POSTHOOK: type: QUERY
    426. 

  426. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    427. 

  427. POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-49_331_2976822432880371649/-mr-10000
    428. 

  428. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    429. 

  429. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    430. 

  430. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    431. 

  431. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    432. 

  432. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    433. 

  433. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    434. 

  434. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    435. 

  435. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    436. 

  436. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    437. 

  437. 464
    438. 

  438. PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
    439. 

  439. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    440. 

  440. PREHOOK: type: QUERY
    441. 

  441. PREHOOK: Input: default@bucketmapjoin_tmp_result
    442. 

  442. PREHOOK: Output: default@bucketmapjoin_hash_result_2
    443. 

  443. POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
    444. 

  444. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    445. 

  445. POSTHOOK: type: QUERY
    446. 

  446. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    447. 

  447. POSTHOOK: Output: default@bucketmapjoin_hash_result_2
    448. 

  448. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    449. 

  449. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    450. 

  450. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    451. 

  451. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    452. 

  452. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    453. 

  453. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    454. 

  454. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    455. 

  455. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    456. 

  456. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    457. 

  457. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    458. 

  458. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    459. 

  459. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    460. 

  460. PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
    461. 

  461. from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
    462. 

  462. on a.key = b.key
    463. 

  463. PREHOOK: type: QUERY
    464. 

  464. PREHOOK: Input: default@bucketmapjoin_hash_result_1
    465. 

  465. PREHOOK: Input: default@bucketmapjoin_hash_result_2
    466. 

  466. PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-56_317_7787039686001016086/-mr-10000
    467. 

  467. POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
    468. 

  468. from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
    469. 

  469. on a.key = b.key
    470. 

  470. POSTHOOK: type: QUERY
    471. 

  471. POSTHOOK: Input: default@bucketmapjoin_hash_result_1
    472. 

  472. POSTHOOK: Input: default@bucketmapjoin_hash_result_2
    473. 

  473. POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-56_317_7787039686001016086/-mr-10000
    474. 

  474. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    475. 

  475. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    476. 

  476. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    477. 

  477. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    478. 

  478. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    479. 

  479. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    480. 

  480. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    481. 

  481. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    482. 

  482. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    483. 

  483. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    484. 

  484. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    485. 

  485. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    486. 

  486. 0	0	0
    487. 

  487. PREHOOK: query: explain extended
    488. 

  488. insert overwrite table bucketmapjoin_tmp_result
    489. 

  489. select /*+mapjoin(a)*/ a.key, a.value, b.value
    490. 

  490. from srcbucket_mapjoin a join srcbucket_mapjoin b
    491. 

  491. on a.key=b.key
    492. 

  492. PREHOOK: type: QUERY
    493. 

  493. POSTHOOK: query: explain extended
    494. 

  494. insert overwrite table bucketmapjoin_tmp_result
    495. 

  495. select /*+mapjoin(a)*/ a.key, a.value, b.value
    496. 

  496. from srcbucket_mapjoin a join srcbucket_mapjoin b
    497. 

  497. on a.key=b.key
    498. 

  498. POSTHOOK: type: QUERY
    499. 

  499. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    500. 

  500. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    501. 

  501. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    502. 

  502. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    503. 

  503. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    504. 

  504. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    505. 

  505. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    506. 

  506. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
    507. 

  507. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    508. 

  508. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
    509. 

  509. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    510. 

  510. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
    511. 

  511. ABSTRACT SYNTAX TREE:
    512. 

  512.   (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value)))))
    513. 

  513. 

  514. STAGE DEPENDENCIES:
    515. 

  515.   Stage-7 is a root stage
    516. 

  516.   Stage-1 depends on stages: Stage-7
    517. 

  517.   Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3
    518. 

  518.   Stage-4
    519. 

  519.   Stage-0 depends on stages: Stage-4, Stage-3
    520. 

  520.   Stage-2 depends on stages: Stage-0
    521. 

  521.   Stage-3
    522. 

  522. 

  523. STAGE PLANS:
    524. 

  524.   Stage: Stage-7
    525. 

  525.     Map Reduce Local Work
    526. 

  526.       Alias -> Map Local Tables:
    527. 

  527.         a 
    528. 

  528.           Fetch Operator
    529. 

  529.             limit: -1
    530. 

  530.       Alias -> Map Local Operator Tree:
    531. 

  531.         a 
    532. 

  532.           TableScan
    533. 

  533.             alias: a
    534. 

  534.             GatherStats: false
    535. 

  535.             HashTable Sink Operator
    536. 

  536.               condition expressions:
    537. 

  537.                 0 {key} {value}
    538. 

  538.                 1 {value}
    539. 

  539.               handleSkewJoin: false
    540. 

  540.               keys:
    541. 

  541.                 0 [Column[key]]
    542. 

  542.                 1 [Column[key]]
    543. 

  543.               Position of Big Table: 1
    544. 

  544.       Bucket Mapjoin Context:
    545. 

  545.           Alias Bucket Base File Name Mapping:
    546. 

  546.             a {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt]}
    547. 

  547.           Alias Bucket File Name Mapping:
    548. 

  548.             a {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
    549. 

  549.           Alias Bucket Output File Name Mapping:
    550. 

  550.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
    551. 

  551.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
    552. 

  552. 

  553.   Stage: Stage-1
    554. 

  554.     Map Reduce
    555. 

  555.       Alias -> Map Operator Tree:
    556. 

  556.         b 
    557. 

  557.           TableScan
    558. 

  558.             alias: b
    559. 

  559.             GatherStats: false
    560. 

  560.             Map Join Operator
    561. 

  561.               condition map:
    562. 

  562.                    Inner Join 0 to 1
    563. 

  563.               condition expressions:
    564. 

  564.                 0 {key} {value}
    565. 

  565.                 1 {value}
    566. 

  566.               handleSkewJoin: false
    567. 

  567.               keys:
    568. 

  568.                 0 [Column[key]]
    569. 

  569.                 1 [Column[key]]
    570. 

  570.               outputColumnNames: _col0, _col1, _col5
    571. 

  571.               Position of Big Table: 1
    572. 

  572.               Select Operator
    573. 

  573.                 expressions:
    574. 

  574.                       expr: _col0
    575. 

  575.                       type: int
    576. 

  576.                       expr: _col1
    577. 

  577.                       type: string
    578. 

  578.                       expr: _col5
    579. 

  579.                       type: string
    580. 

  580.                 outputColumnNames: _col0, _col1, _col5
    581. 

  581.                 Select Operator
    582. 

  582.                   expressions:
    583. 

  583.                         expr: _col0
    584. 

  584.                         type: int
    585. 

  585.                         expr: _col1
    586. 

  586.                         type: string
    587. 

  587.                         expr: _col5
    588. 

  588.                         type: string
    589. 

  589.                   outputColumnNames: _col0, _col1, _col2
    590. 

  590.                   File Output Operator
    591. 

  591.                     compressed: false
    592. 

  592.                     GlobalTableId: 1
    593. 

  593.                     directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002
    594. 

  594.                     NumFilesPerFileSink: 1
    595. 

  595.                     Stats Publishing Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000/
    596. 

  596.                     table:
    597. 

  597.                         input format: org.apache.hadoop.mapred.TextInputFormat
    598. 

  598.                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    599. 

  599.                         properties:
    600. 

  600.                           bucket_count -1
    601. 

  601.                           columns key,value1,value2
    602. 

  602.                           columns.types string:string:string
    603. 

  603.                           file.inputformat org.apache.hadoop.mapred.TextInputFormat
    604. 

  604.                           file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    605. 

  605.                           location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    606. 

  606.                           name default.bucketmapjoin_tmp_result
    607. 

  607.                           numFiles 1
    608. 

  608.                           numPartitions 0
    609. 

  609.                           numRows 464
    610. 

  610.                           rawDataSize 8519
    611. 

  611.                           serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    612. 

  612.                           serialization.format 1
    613. 

  613.                           serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    614. 

  614.                           totalSize 8983
    615. 

  615.                           transient_lastDdlTime 1306979269
    616. 

  616.                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    617. 

  617.                         name: default.bucketmapjoin_tmp_result
    618. 

  618.                     TotalFiles: 1
    619. 

  619.                     GatherStats: true
    620. 

  620.                     MultiFileSpray: false
    621. 

  621.       Local Work:
    622. 

  622.         Map Reduce Local Work
    623. 

  623.       Needs Tagging: false
    624. 

  624.       Path -> Alias:
    625. 

  625.         pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin [b]
    626. 

  626.       Path -> Partition:
    627. 

  627.         pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin 
    628. 

  628.           Partition
    629. 

  629.             base file name: srcbucket_mapjoin
    630. 

  630.             input format: org.apache.hadoop.mapred.TextInputFormat
    631. 

  631.             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    632. 

  632.             properties:
    633. 

  633.               bucket_count 2
    634. 

  634.               bucket_field_name key
    635. 

  635.               columns key,value
    636. 

  636.               columns.types int:string
    637. 

  637.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    638. 

  638.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    639. 

  639.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
    640. 

  640.               name default.srcbucket_mapjoin
    641. 

  641.               serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
    642. 

  642.               serialization.format 1
    643. 

  643.               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    644. 

  644.               transient_lastDdlTime 1306979239
    645. 

  645.             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    646. 

  646.           
    647. 

  647.               input format: org.apache.hadoop.mapred.TextInputFormat
    648. 

  648.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    649. 

  649.               properties:
    650. 

  650.                 bucket_count 2
    651. 

  651.                 bucket_field_name key
    652. 

  652.                 columns key,value
    653. 

  653.                 columns.types int:string
    654. 

  654.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    655. 

  655.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    656. 

  656.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
    657. 

  657.                 name default.srcbucket_mapjoin
    658. 

  658.                 serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
    659. 

  659.                 serialization.format 1
    660. 

  660.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    661. 

  661.                 transient_lastDdlTime 1306979239
    662. 

  662.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    663. 

  663.               name: default.srcbucket_mapjoin
    664. 

  664.             name: default.srcbucket_mapjoin
    665. 

  665. 

  666.   Stage: Stage-5
    667. 

  667.     Conditional Operator
    668. 

  668. 

  669.   Stage: Stage-4
    670. 

  670.     Move Operator
    671. 

  671.       files:
    672. 

  672.           hdfs directory: true
    673. 

  673.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002
    674. 

  674.           destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000
    675. 

  675. 

  676.   Stage: Stage-0
    677. 

  677.     Move Operator
    678. 

  678.       tables:
    679. 

  679.           replace: true
    680. 

  680.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000
    681. 

  681.           table:
    682. 

  682.               input format: org.apache.hadoop.mapred.TextInputFormat
    683. 

  683.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    684. 

  684.               properties:
    685. 

  685.                 bucket_count -1
    686. 

  686.                 columns key,value1,value2
    687. 

  687.                 columns.types string:string:string
    688. 

  688.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    689. 

  689.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    690. 

  690.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    691. 

  691.                 name default.bucketmapjoin_tmp_result
    692. 

  692.                 numFiles 1
    693. 

  693.                 numPartitions 0
    694. 

  694.                 numRows 464
    695. 

  695.                 rawDataSize 8519
    696. 

  696.                 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    697. 

  697.                 serialization.format 1
    698. 

  698.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    699. 

  699.                 totalSize 8983
    700. 

  700.                 transient_lastDdlTime 1306979269
    701. 

  701.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    702. 

  702.               name: default.bucketmapjoin_tmp_result
    703. 

  703.           tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10001
    704. 

  704. 

  705.   Stage: Stage-2
    706. 

  706.     Stats-Aggr Operator
    707. 

  707.       Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000/
    708. 

  708. 

  709.   Stage: Stage-3
    710. 

  710.     Map Reduce
    711. 

  711.       Alias -> Map Operator Tree:
    712. 

  712.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002 
    713. 

  713.             File Output Operator
    714. 

  714.               compressed: false
    715. 

  715.               GlobalTableId: 0
    716. 

  716.               directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000
    717. 

  717.               NumFilesPerFileSink: 1
    718. 

  718.               table:
    719. 

  719.                   input format: org.apache.hadoop.mapred.TextInputFormat
    720. 

  720.                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    721. 

  721.                   properties:
    722. 

  722.                     bucket_count -1
    723. 

  723.                     columns key,value1,value2
    724. 

  724.                     columns.types string:string:string
    725. 

  725.                     file.inputformat org.apache.hadoop.mapred.TextInputFormat
    726. 

  726.                     file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    727. 

  727.                     location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    728. 

  728.                     name default.bucketmapjoin_tmp_result
    729. 

  729.                     numFiles 1
    730. 

  730.                     numPartitions 0
    731. 

  731.                     numRows 464
    732. 

  732.                     rawDataSize 8519
    733. 

  733.                     serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    734. 

  734.                     serialization.format 1
    735. 

  735.                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    736. 

  736.                     totalSize 8983
    737. 

  737.                     transient_lastDdlTime 1306979269
    738. 

  738.                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    739. 

  739.                   name: default.bucketmapjoin_tmp_result
    740. 

  740.               TotalFiles: 1
    741. 

  741.               GatherStats: false
    742. 

  742.               MultiFileSpray: false
    743. 

  743.       Needs Tagging: false
    744. 

  744.       Path -> Alias:
    745. 

  745.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002]
    746. 

  746.       Path -> Partition:
    747. 

  747.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002 
    748. 

  748.           Partition
    749. 

  749.             base file name: -ext-10002
    750. 

  750.             input format: org.apache.hadoop.mapred.TextInputFormat
    751. 

  751.             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    752. 

  752.             properties:
    753. 

  753.               bucket_count -1
    754. 

  754.               columns key,value1,value2
    755. 

  755.               columns.types string:string:string
    756. 

  756.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    757. 

  757.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    758. 

  758.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    759. 

  759.               name default.bucketmapjoin_tmp_result
    760. 

  760.               numFiles 1
    761. 

  761.               numPartitions 0
    762. 

  762.               numRows 464
    763. 

  763.               rawDataSize 8519
    764. 

  764.               serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    765. 

  765.               serialization.format 1
    766. 

  766.               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    767. 

  767.               totalSize 8983
    768. 

  768.               transient_lastDdlTime 1306979269
    769. 

  769.             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    770. 

  770.           
    771. 

  771.               input format: org.apache.hadoop.mapred.TextInputFormat
    772. 

  772.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    773. 

  773.               properties:
    774. 

  774.                 bucket_count -1
    775. 

  775.                 columns key,value1,value2
    776. 

  776.                 columns.types string:string:string
    777. 

  777.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    778. 

  778.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    779. 

  779.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    780. 

  780.                 name default.bucketmapjoin_tmp_result
    781. 

  781.                 numFiles 1
    782. 

  782.                 numPartitions 0
    783. 

  783.                 numRows 464
    784. 

  784.                 rawDataSize 8519
    785. 

  785.                 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    786. 

  786.                 serialization.format 1
    787. 

  787.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    788. 

  788.                 totalSize 8983
    789. 

  789.                 transient_lastDdlTime 1306979269
    790. 

  790.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    791. 

  791.               name: default.bucketmapjoin_tmp_result
    792. 

  792.             name: default.bucketmapjoin_tmp_result
    793. 

  793. 

  794. 

  795. PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result
    796. 

  796. select /*+mapjoin(a)*/ a.key, a.value, b.value
    797. 

  797. from srcbucket_mapjoin a join srcbucket_mapjoin b
    798. 

  798. on a.key=b.key
    799. 

  799. PREHOOK: type: QUERY
    800. 

  800. PREHOOK: Input: default@srcbucket_mapjoin
    801. 

  801. PREHOOK: Output: default@bucketmapjoin_tmp_result
    802. 

  802. POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result
    803. 

  803. select /*+mapjoin(a)*/ a.key, a.value, b.value
    804. 

  804. from srcbucket_mapjoin a join srcbucket_mapjoin b
    805. 

  805. on a.key=b.key
    806. 

  806. POSTHOOK: type: QUERY
    807. 

  807. POSTHOOK: Input: default@srcbucket_mapjoin
    808. 

  808. POSTHOOK: Output: default@bucketmapjoin_tmp_result
    809. 

  809. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    810. 

  810. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    811. 

  811. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    812. 

  812. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null…
    813.

Large files files are truncated, but you can click here to view the full file