PageRenderTime 57ms CodeModel.GetById 18ms RepoModel.GetById 1ms app.codeStats 0ms

/tags/release-0.2.0-rc0/hive/external/ql/src/test/results/clientpositive/bucketmapjoin3.q.out

#
text | 1031 lines | 1007 code | 24 blank | 0 comment | 0 complexity | f51fdcb56bf6cbad98bc2dd47d4c0869 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_part_2 a join srcbucket_mapjoin_part b 
    85. 

  85. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    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_part_2 a join srcbucket_mapjoin_part b 
    91. 

  91. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    92. 

  92. POSTHOOK: type: QUERY
    93. 

  93. ABSTRACT SYNTAX TREE:
    94. 

  94.   (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part_2) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part) b) (and (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL b) ds) "2008-04-08")) (= (. (TOK_TABLE_OR_COL a) ds) "2008-04-08")))) (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 {srcbucket22.txt=[srcbucket20.txt, srcbucket22.txt], srcbucket23.txt=[srcbucket21.txt, srcbucket23.txt]}
    129. 

  129.           Alias Bucket File Name Mapping:
    130. 

  130.             b {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt, pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt, pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt]}
    131. 

  131.           Alias Bucket Output File Name Mapping:
    132. 

  132.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt 0
    133. 

  133.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.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, _col6
    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: _col6
    161. 

  161.                       type: string
    162. 

  162.                 outputColumnNames: _col0, _col1, _col6
    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: _col6
    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:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-34-40_179_2078859592920140854/-ext-10002
    176. 

  176.                     NumFilesPerFileSink: 1
    177. 

  177.                     Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-34-40_179_2078859592920140854/-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:/home/amarsri/workspace/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 1310373280
    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_part_2/ds=2008-04-08 [a]
    203. 

  203.       Path -> Partition:
    204. 

  204.         pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 
    205. 

  205.           Partition
    206. 

  206.             base file name: ds=2008-04-08
    207. 

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

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

  209.             partition values:
    210. 

  210.               ds 2008-04-08
    211. 

  211.             properties:
    212. 

  212.               bucket_count 2
    213. 

  213.               bucket_field_name key
    214. 

  214.               columns key,value
    215. 

  215.               columns.types int:string
    216. 

  216.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    217. 

  217.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    218. 

  218.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08
    219. 

  219.               name default.srcbucket_mapjoin_part_2
    220. 

  220.               partition_columns ds
    221. 

  221.               serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
    222. 

  222.               serialization.format 1
    223. 

  223.               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    224. 

  224.               transient_lastDdlTime 1306979174
    225. 

  225.             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    226. 

  226.           
    227. 

  227.               input format: org.apache.hadoop.mapred.TextInputFormat
    228. 

  228.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    229. 

  229.               properties:
    230. 

  230.                 bucket_count 2
    231. 

  231.                 bucket_field_name key
    232. 

  232.                 columns key,value
    233. 

  233.                 columns.types int:string
    234. 

  234.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    235. 

  235.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    236. 

  236.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2
    237. 

  237.                 name default.srcbucket_mapjoin_part_2
    238. 

  238.                 partition_columns ds
    239. 

  239.                 serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
    240. 

  240.                 serialization.format 1
    241. 

  241.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    242. 

  242.                 transient_lastDdlTime 1306979173
    243. 

  243.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    244. 

  244.               name: default.srcbucket_mapjoin_part_2
    245. 

  245.             name: default.srcbucket_mapjoin_part_2
    246. 

  246. 

  247.   Stage: Stage-5
    248. 

  248.     Conditional Operator
    249. 

  249. 

  250.   Stage: Stage-4
    251. 

  251.     Move Operator
    252. 

  252.       files:
    253. 

  253.           hdfs directory: true
    254. 

  254.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002
    255. 

  255.           destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000
    256. 

  256. 

  257.   Stage: Stage-0
    258. 

  258.     Move Operator
    259. 

  259.       tables:
    260. 

  260.           replace: true
    261. 

  261.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000
    262. 

  262.           table:
    263. 

  263.               input format: org.apache.hadoop.mapred.TextInputFormat
    264. 

  264.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    265. 

  265.               properties:
    266. 

  266.                 bucket_count -1
    267. 

  267.                 columns key,value1,value2
    268. 

  268.                 columns.types string:string:string
    269. 

  269.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    270. 

  270.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    271. 

  271.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    272. 

  272.                 name default.bucketmapjoin_tmp_result
    273. 

  273.                 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    274. 

  274.                 serialization.format 1
    275. 

  275.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    276. 

  276.                 transient_lastDdlTime 1306979174
    277. 

  277.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    278. 

  278.               name: default.bucketmapjoin_tmp_result
    279. 

  279.           tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10001
    280. 

  280. 

  281.   Stage: Stage-2
    282. 

  282.     Stats-Aggr Operator
    283. 

  283.       Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000/
    284. 

  284. 

  285.   Stage: Stage-3
    286. 

  286.     Map Reduce
    287. 

  287.       Alias -> Map Operator Tree:
    288. 

  288.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002 
    289. 

  289.             File Output Operator
    290. 

  290.               compressed: false
    291. 

  291.               GlobalTableId: 0
    292. 

  292.               directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000
    293. 

  293.               NumFilesPerFileSink: 1
    294. 

  294.               table:
    295. 

  295.                   input format: org.apache.hadoop.mapred.TextInputFormat
    296. 

  296.                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    297. 

  297.                   properties:
    298. 

  298.                     bucket_count -1
    299. 

  299.                     columns key,value1,value2
    300. 

  300.                     columns.types string:string:string
    301. 

  301.                     file.inputformat org.apache.hadoop.mapred.TextInputFormat
    302. 

  302.                     file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    303. 

  303.                     location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    304. 

  304.                     name default.bucketmapjoin_tmp_result
    305. 

  305.                     serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    306. 

  306.                     serialization.format 1
    307. 

  307.                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    308. 

  308.                     transient_lastDdlTime 1306979174
    309. 

  309.                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    310. 

  310.                   name: default.bucketmapjoin_tmp_result
    311. 

  311.               TotalFiles: 1
    312. 

  312.               GatherStats: false
    313. 

  313.               MultiFileSpray: false
    314. 

  314.       Needs Tagging: false
    315. 

  315.       Path -> Alias:
    316. 

  316.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002]
    317. 

  317.       Path -> Partition:
    318. 

  318.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002 
    319. 

  319.           Partition
    320. 

  320.             base file name: -ext-10002
    321. 

  321.             input format: org.apache.hadoop.mapred.TextInputFormat
    322. 

  322.             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    323. 

  323.             properties:
    324. 

  324.               bucket_count -1
    325. 

  325.               columns key,value1,value2
    326. 

  326.               columns.types string:string:string
    327. 

  327.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    328. 

  328.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    329. 

  329.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    330. 

  330.               name default.bucketmapjoin_tmp_result
    331. 

  331.               serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    332. 

  332.               serialization.format 1
    333. 

  333.               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    334. 

  334.               transient_lastDdlTime 1306979174
    335. 

  335.             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    336. 

  336.           
    337. 

  337.               input format: org.apache.hadoop.mapred.TextInputFormat
    338. 

  338.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    339. 

  339.               properties:
    340. 

  340.                 bucket_count -1
    341. 

  341.                 columns key,value1,value2
    342. 

  342.                 columns.types string:string:string
    343. 

  343.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    344. 

  344.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    345. 

  345.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    346. 

  346.                 name default.bucketmapjoin_tmp_result
    347. 

  347.                 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    348. 

  348.                 serialization.format 1
    349. 

  349.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    350. 

  350.                 transient_lastDdlTime 1306979174
    351. 

  351.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    352. 

  352.               name: default.bucketmapjoin_tmp_result
    353. 

  353.             name: default.bucketmapjoin_tmp_result
    354. 

  354. 

  355. 

  356. PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result 
    357. 

  357. select /*+mapjoin(b)*/ a.key, a.value, b.value 
    358. 

  358. from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b 
    359. 

  359. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    360. 

  360. PREHOOK: type: QUERY
    361. 

  361. PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
    362. 

  362. PREHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08
    363. 

  363. PREHOOK: Output: default@bucketmapjoin_tmp_result
    364. 

  364. POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result 
    365. 

  365. select /*+mapjoin(b)*/ a.key, a.value, b.value 
    366. 

  366. from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b 
    367. 

  367. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    368. 

  368. POSTHOOK: type: QUERY
    369. 

  369. POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
    370. 

  370. POSTHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08
    371. 

  371. POSTHOOK: Output: default@bucketmapjoin_tmp_result
    372. 

  372. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    373. 

  373. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    374. 

  374. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    375. 

  375. PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
    376. 

  376. PREHOOK: type: QUERY
    377. 

  377. PREHOOK: Input: default@bucketmapjoin_tmp_result
    378. 

  378. PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-21_973_1112542633479425376/-mr-10000
    379. 

  379. POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
    380. 

  380. POSTHOOK: type: QUERY
    381. 

  381. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    382. 

  382. POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-21_973_1112542633479425376/-mr-10000
    383. 

  383. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    384. 

  384. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    385. 

  385. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    386. 

  386. 564
    387. 

  387. PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
    388. 

  388. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    389. 

  389. PREHOOK: type: QUERY
    390. 

  390. PREHOOK: Input: default@bucketmapjoin_tmp_result
    391. 

  391. PREHOOK: Output: default@bucketmapjoin_hash_result_1
    392. 

  392. POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
    393. 

  393. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    394. 

  394. POSTHOOK: type: QUERY
    395. 

  395. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    396. 

  396. POSTHOOK: Output: default@bucketmapjoin_hash_result_1
    397. 

  397. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    398. 

  398. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    399. 

  399. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    400. 

  400. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    401. 

  401. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    402. 

  402. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    403. 

  403. PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result 
    404. 

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

  405. from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b 
    406. 

  406. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    407. 

  407. PREHOOK: type: QUERY
    408. 

  408. PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
    409. 

  409. PREHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08
    410. 

  410. PREHOOK: Output: default@bucketmapjoin_tmp_result
    411. 

  411. POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result 
    412. 

  412. select /*+mapjoin(b)*/ a.key, a.value, b.value 
    413. 

  413. from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b 
    414. 

  414. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    415. 

  415. POSTHOOK: type: QUERY
    416. 

  416. POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
    417. 

  417. POSTHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08
    418. 

  418. POSTHOOK: Output: default@bucketmapjoin_tmp_result
    419. 

  419. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    420. 

  420. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    421. 

  421. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    422. 

  422. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    423. 

  423. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    424. 

  424. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    425. 

  425. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    426. 

  426. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    427. 

  427. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    428. 

  428. PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
    429. 

  429. PREHOOK: type: QUERY
    430. 

  430. PREHOOK: Input: default@bucketmapjoin_tmp_result
    431. 

  431. PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-35_394_5427265786129780250/-mr-10000
    432. 

  432. POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
    433. 

  433. POSTHOOK: type: QUERY
    434. 

  434. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    435. 

  435. POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-35_394_5427265786129780250/-mr-10000
    436. 

  436. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    437. 

  437. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    438. 

  438. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    439. 

  439. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    440. 

  440. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    441. 

  441. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    442. 

  442. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    443. 

  443. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    444. 

  444. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    445. 

  445. 564
    446. 

  446. PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
    447. 

  447. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    448. 

  448. PREHOOK: type: QUERY
    449. 

  449. PREHOOK: Input: default@bucketmapjoin_tmp_result
    450. 

  450. PREHOOK: Output: default@bucketmapjoin_hash_result_2
    451. 

  451. POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
    452. 

  452. select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
    453. 

  453. POSTHOOK: type: QUERY
    454. 

  454. POSTHOOK: Input: default@bucketmapjoin_tmp_result
    455. 

  455. POSTHOOK: Output: default@bucketmapjoin_hash_result_2
    456. 

  456. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    457. 

  457. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    458. 

  458. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    459. 

  459. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    460. 

  460. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    461. 

  461. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    462. 

  462. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    463. 

  463. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    464. 

  464. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    465. 

  465. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    466. 

  466. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    467. 

  467. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    468. 

  468. PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
    469. 

  469. from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
    470. 

  470. on a.key = b.key
    471. 

  471. PREHOOK: type: QUERY
    472. 

  472. PREHOOK: Input: default@bucketmapjoin_hash_result_1
    473. 

  473. PREHOOK: Input: default@bucketmapjoin_hash_result_2
    474. 

  474. PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-42_543_1855526648690468691/-mr-10000
    475. 

  475. POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
    476. 

  476. from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
    477. 

  477. on a.key = b.key
    478. 

  478. POSTHOOK: type: QUERY
    479. 

  479. POSTHOOK: Input: default@bucketmapjoin_hash_result_1
    480. 

  480. POSTHOOK: Input: default@bucketmapjoin_hash_result_2
    481. 

  481. POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-42_543_1855526648690468691/-mr-10000
    482. 

  482. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    483. 

  483. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    484. 

  484. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    485. 

  485. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    486. 

  486. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    487. 

  487. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    488. 

  488. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    489. 

  489. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    490. 

  490. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    491. 

  491. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    492. 

  492. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    493. 

  493. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    494. 

  494. 0	0	0
    495. 

  495. PREHOOK: query: explain extended 
    496. 

  496. insert overwrite table bucketmapjoin_tmp_result 
    497. 

  497. select /*+mapjoin(a)*/ a.key, a.value, b.value 
    498. 

  498. from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b 
    499. 

  499. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    500. 

  500. PREHOOK: type: QUERY
    501. 

  501. POSTHOOK: query: explain extended 
    502. 

  502. insert overwrite table bucketmapjoin_tmp_result 
    503. 

  503. select /*+mapjoin(a)*/ a.key, a.value, b.value 
    504. 

  504. from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b 
    505. 

  505. on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08"
    506. 

  506. POSTHOOK: type: QUERY
    507. 

  507. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    508. 

  508. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    509. 

  509. POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    510. 

  510. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
    511. 

  511. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
    512. 

  512. POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
    513. 

  513. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    514. 

  514. POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ]
    515. 

  515. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    516. 

  516. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ]
    517. 

  517. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    518. 

  518. POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ]
    519. 

  519. ABSTRACT SYNTAX TREE:
    520. 

  520.   (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part_2) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part) b) (and (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL b) ds) "2008-04-08")) (= (. (TOK_TABLE_OR_COL a) ds) "2008-04-08")))) (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)))))
    521. 

  521. 

  522. STAGE DEPENDENCIES:
    523. 

  523.   Stage-7 is a root stage
    524. 

  524.   Stage-1 depends on stages: Stage-7
    525. 

  525.   Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3
    526. 

  526.   Stage-4
    527. 

  527.   Stage-0 depends on stages: Stage-4, Stage-3
    528. 

  528.   Stage-2 depends on stages: Stage-0
    529. 

  529.   Stage-3
    530. 

  530. 

  531. STAGE PLANS:
    532. 

  532.   Stage: Stage-7
    533. 

  533.     Map Reduce Local Work
    534. 

  534.       Alias -> Map Local Tables:
    535. 

  535.         a 
    536. 

  536.           Fetch Operator
    537. 

  537.             limit: -1
    538. 

  538.       Alias -> Map Local Operator Tree:
    539. 

  539.         a 
    540. 

  540.           TableScan
    541. 

  541.             alias: a
    542. 

  542.             GatherStats: false
    543. 

  543.             HashTable Sink Operator
    544. 

  544.               condition expressions:
    545. 

  545.                 0 {key} {value}
    546. 

  546.                 1 {value}
    547. 

  547.               handleSkewJoin: false
    548. 

  548.               keys:
    549. 

  549.                 0 [Column[key]]
    550. 

  550.                 1 [Column[key]]
    551. 

  551.               Position of Big Table: 1
    552. 

  552.       Bucket Mapjoin Context:
    553. 

  553.           Alias Bucket Base File Name Mapping:
    554. 

  554.             a {srcbucket20.txt=[srcbucket22.txt], srcbucket21.txt=[srcbucket23.txt], srcbucket22.txt=[srcbucket22.txt], srcbucket23.txt=[srcbucket23.txt]}
    555. 

  555.           Alias Bucket File Name Mapping:
    556. 

  556.             a {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt]}
    557. 

  557.           Alias Bucket Output File Name Mapping:
    558. 

  558.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt 0
    559. 

  559.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt 1
    560. 

  560.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt 2
    561. 

  561.             pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt 3
    562. 

  562. 

  563.   Stage: Stage-1
    564. 

  564.     Map Reduce
    565. 

  565.       Alias -> Map Operator Tree:
    566. 

  566.         b 
    567. 

  567.           TableScan
    568. 

  568.             alias: b
    569. 

  569.             GatherStats: false
    570. 

  570.             Map Join Operator
    571. 

  571.               condition map:
    572. 

  572.                    Inner Join 0 to 1
    573. 

  573.               condition expressions:
    574. 

  574.                 0 {key} {value}
    575. 

  575.                 1 {value}
    576. 

  576.               handleSkewJoin: false
    577. 

  577.               keys:
    578. 

  578.                 0 [Column[key]]
    579. 

  579.                 1 [Column[key]]
    580. 

  580.               outputColumnNames: _col0, _col1, _col6
    581. 

  581.               Position of Big Table: 1
    582. 

  582.               Select Operator
    583. 

  583.                 expressions:
    584. 

  584.                       expr: _col0
    585. 

  585.                       type: int
    586. 

  586.                       expr: _col1
    587. 

  587.                       type: string
    588. 

  588.                       expr: _col6
    589. 

  589.                       type: string
    590. 

  590.                 outputColumnNames: _col0, _col1, _col6
    591. 

  591.                 Select Operator
    592. 

  592.                   expressions:
    593. 

  593.                         expr: _col0
    594. 

  594.                         type: int
    595. 

  595.                         expr: _col1
    596. 

  596.                         type: string
    597. 

  597.                         expr: _col6
    598. 

  598.                         type: string
    599. 

  599.                   outputColumnNames: _col0, _col1, _col2
    600. 

  600.                   File Output Operator
    601. 

  601.                     compressed: false
    602. 

  602.                     GlobalTableId: 1
    603. 

  603.                     directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-35-06_760_1506759328569853293/-ext-10002
    604. 

  604.                     NumFilesPerFileSink: 1
    605. 

  605.                     Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-35-06_760_1506759328569853293/-ext-10000/
    606. 

  606.                     table:
    607. 

  607.                         input format: org.apache.hadoop.mapred.TextInputFormat
    608. 

  608.                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    609. 

  609.                         properties:
    610. 

  610.                           bucket_count -1
    611. 

  611.                           columns key,value1,value2
    612. 

  612.                           columns.types string:string:string
    613. 

  613.                           file.inputformat org.apache.hadoop.mapred.TextInputFormat
    614. 

  614.                           file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    615. 

  615.                           location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    616. 

  616.                           name default.bucketmapjoin_tmp_result
    617. 

  617.                           numFiles 1
    618. 

  618.                           numPartitions 0
    619. 

  619.                           numRows 564
    620. 

  620.                           rawDataSize 10503
    621. 

  621.                           serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    622. 

  622.                           serialization.format 1
    623. 

  623.                           serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    624. 

  624.                           totalSize 11067
    625. 

  625.                           transient_lastDdlTime 1310373297
    626. 

  626.                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    627. 

  627.                         name: default.bucketmapjoin_tmp_result
    628. 

  628.                     TotalFiles: 1
    629. 

  629.                     GatherStats: true
    630. 

  630.                     MultiFileSpray: false
    631. 

  631.       Local Work:
    632. 

  632.         Map Reduce Local Work
    633. 

  633.       Needs Tagging: false
    634. 

  634.       Path -> Alias:
    635. 

  635.         pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 [b]
    636. 

  636.       Path -> Partition:
    637. 

  637.         pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 
    638. 

  638.           Partition
    639. 

  639.             base file name: ds=2008-04-08
    640. 

  640.             input format: org.apache.hadoop.mapred.TextInputFormat
    641. 

  641.             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    642. 

  642.             partition values:
    643. 

  643.               ds 2008-04-08
    644. 

  644.             properties:
    645. 

  645.               bucket_count 4
    646. 

  646.               bucket_field_name key
    647. 

  647.               columns key,value
    648. 

  648.               columns.types int:string
    649. 

  649.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    650. 

  650.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    651. 

  651.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08
    652. 

  652.               name default.srcbucket_mapjoin_part
    653. 

  653.               partition_columns ds
    654. 

  654.               serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
    655. 

  655.               serialization.format 1
    656. 

  656.               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    657. 

  657.               transient_lastDdlTime 1306979173
    658. 

  658.             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    659. 

  659.           
    660. 

  660.               input format: org.apache.hadoop.mapred.TextInputFormat
    661. 

  661.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    662. 

  662.               properties:
    663. 

  663.                 bucket_count 4
    664. 

  664.                 bucket_field_name key
    665. 

  665.                 columns key,value
    666. 

  666.                 columns.types int:string
    667. 

  667.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    668. 

  668.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    669. 

  669.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part
    670. 

  670.                 name default.srcbucket_mapjoin_part
    671. 

  671.                 partition_columns ds
    672. 

  672.                 serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
    673. 

  673.                 serialization.format 1
    674. 

  674.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    675. 

  675.                 transient_lastDdlTime 1306979170
    676. 

  676.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    677. 

  677.               name: default.srcbucket_mapjoin_part
    678. 

  678.             name: default.srcbucket_mapjoin_part
    679. 

  679. 

  680.   Stage: Stage-5
    681. 

  681.     Conditional Operator
    682. 

  682. 

  683.   Stage: Stage-4
    684. 

  684.     Move Operator
    685. 

  685.       files:
    686. 

  686.           hdfs directory: true
    687. 

  687.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002
    688. 

  688.           destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000
    689. 

  689. 

  690.   Stage: Stage-0
    691. 

  691.     Move Operator
    692. 

  692.       tables:
    693. 

  693.           replace: true
    694. 

  694.           source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000
    695. 

  695.           table:
    696. 

  696.               input format: org.apache.hadoop.mapred.TextInputFormat
    697. 

  697.               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    698. 

  698.               properties:
    699. 

  699.                 bucket_count -1
    700. 

  700.                 columns key,value1,value2
    701. 

  701.                 columns.types string:string:string
    702. 

  702.                 file.inputformat org.apache.hadoop.mapred.TextInputFormat
    703. 

  703.                 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    704. 

  704.                 location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    705. 

  705.                 name default.bucketmapjoin_tmp_result
    706. 

  706.                 numFiles 1
    707. 

  707.                 numPartitions 0
    708. 

  708.                 numRows 564
    709. 

  709.                 rawDataSize 10503
    710. 

  710.                 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    711. 

  711.                 serialization.format 1
    712. 

  712.                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    713. 

  713.                 totalSize 11067
    714. 

  714.                 transient_lastDdlTime 1306979195
    715. 

  715.               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    716. 

  716.               name: default.bucketmapjoin_tmp_result
    717. 

  717.           tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10001
    718. 

  718. 

  719.   Stage: Stage-2
    720. 

  720.     Stats-Aggr Operator
    721. 

  721.       Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000/
    722. 

  722. 

  723.   Stage: Stage-3
    724. 

  724.     Map Reduce
    725. 

  725.       Alias -> Map Operator Tree:
    726. 

  726.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002 
    727. 

  727.             File Output Operator
    728. 

  728.               compressed: false
    729. 

  729.               GlobalTableId: 0
    730. 

  730.               directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000
    731. 

  731.               NumFilesPerFileSink: 1
    732. 

  732.               table:
    733. 

  733.                   input format: org.apache.hadoop.mapred.TextInputFormat
    734. 

  734.                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    735. 

  735.                   properties:
    736. 

  736.                     bucket_count -1
    737. 

  737.                     columns key,value1,value2
    738. 

  738.                     columns.types string:string:string
    739. 

  739.                     file.inputformat org.apache.hadoop.mapred.TextInputFormat
    740. 

  740.                     file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    741. 

  741.                     location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
    742. 

  742.                     name default.bucketmapjoin_tmp_result
    743. 

  743.                     numFiles 1
    744. 

  744.                     numPartitions 0
    745. 

  745.                     numRows 564
    746. 

  746.                     rawDataSize 10503
    747. 

  747.                     serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
    748. 

  748.                     serialization.format 1
    749. 

  749.                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    750. 

  750.                     totalSize 11067
    751. 

  751.                     transient_lastDdlTime 1306979195
    752. 

  752.                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
    753. 

  753.                   name: default.bucketmapjoin_tmp_result
    754. 

  754.               TotalFiles: 1
    755. 

  755.               GatherStats: false
    756. 

  756.               MultiFileSpray: false
    757. 

  757.       Needs Tagging: false
    758. 

  758.       Path -> Alias:
    759. 

  759.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002]
    760. 

  760.       Path -> Partition:
    761. 

  761.         pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002 
    762. 

  762.           Partition
    763. 

  763.             base file name: -ext-10002
    764. 

  764.             input format: org.apache.hadoop.mapred.TextInputFormat
    765. 

  765.             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    766. 

  766.             properties:
    767. 

  767.               bucket_count -1
    768. 

  768.               columns key,value1,value2
    769. 

  769.               columns.types string:string:string
    770. 

  770.               file.inputformat org.apache.hadoop.mapred.TextInputFormat
    771. 

  771.               file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    772. 

  772.               location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_r…
    773.

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