You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2014/04/08 16:26:23 UTC
svn commit: r1585741 - in /hive/trunk: itests/qtest/pom.xml
ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezProcessor.java
ql/src/test/queries/clientpositive/tez_fsstat.q
ql/src/test/results/clientpositive/tez/tez_fsstat.q.out
Author: hashutosh
Date: Tue Apr 8 14:26:23 2014
New Revision: 1585741
URL: http://svn.apache.org/r1585741
Log:
HIVE-6860 : Issue with FS based stats collection on Tez (Ashutosh Chauhan via Vikram Dixit)
Added:
hive/trunk/ql/src/test/queries/clientpositive/tez_fsstat.q
hive/trunk/ql/src/test/results/clientpositive/tez/tez_fsstat.q.out
Modified:
hive/trunk/itests/qtest/pom.xml
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezProcessor.java
Modified: hive/trunk/itests/qtest/pom.xml
URL: http://svn.apache.org/viewvc/hive/trunk/itests/qtest/pom.xml?rev=1585741&r1=1585740&r2=1585741&view=diff
==============================================================================
--- hive/trunk/itests/qtest/pom.xml (original)
+++ hive/trunk/itests/qtest/pom.xml Tue Apr 8 14:26:23 2014
@@ -38,7 +38,7 @@
<execute.beeline.tests>false</execute.beeline.tests>
<minimr.query.files>stats_counter_partitioned.q,list_bucket_dml_10.q,input16_cc.q,scriptfile1.q,scriptfile1_win.q,bucket4.q,bucketmapjoin6.q,disable_merge_for_bucketing.q,reduce_deduplicate.q,smb_mapjoin_8.q,join1.q,groupby2.q,bucketizedhiveinputformat.q,bucketmapjoin7.q,optrstat_groupby.q,bucket_num_reducers.q,bucket5.q,load_fs2.q,bucket_num_reducers2.q,infer_bucket_sort_merge.q,infer_bucket_sort_reducers_power_two.q,infer_bucket_sort_dyn_part.q,infer_bucket_sort_bucketed_table.q,infer_bucket_sort_map_operators.q,infer_bucket_sort_num_buckets.q,leftsemijoin_mr.q,schemeAuthority.q,schemeAuthority2.q,truncate_column_buckets.q,remote_script.q,,load_hdfs_file_with_space_in_the_name.q,parallel_orderby.q,import_exported_table.q,stats_counter.q,auto_sortmerge_join_16.q,quotedid_smb.q,file_with_header_footer.q,external_table_with_space_in_location_path.q,root_dir_external_table.q,index_bitmap3.q,ql_rewrite_gbtoidx.q,index_bitmap_auto.q,udf_using.q</minimr.query.files>
<minimr.query.negative.files>cluster_tasklog_retrieval.q,minimr_broken_pipe.q,mapreduce_stack_trace.q,mapreduce_stack_trace_turnoff.q,mapreduce_stack_trace_hadoop20.q,mapreduce_stack_trace_turnoff_hadoop20.q,file_with_header_footer_negative.q,udf_local_resource.q</minimr.query.negative.files>
- <minitez.query.files>mapjoin_decimal.q,tez_join_tests.q,tez_joins_explain.q,mrr.q,tez_dml.q,tez_insert_overwrite_local_directory_1.q,tez_union.q,bucket_map_join_tez1.q,bucket_map_join_tez2.q</minitez.query.files>
+ <minitez.query.files>tez_fsstat.q,mapjoin_decimal.q,tez_join_tests.q,tez_joins_explain.q,mrr.q,tez_dml.q,tez_insert_overwrite_local_directory_1.q,tez_union.q,bucket_map_join_tez1.q,bucket_map_join_tez2.q</minitez.query.files>
<minitez.query.files.shared>cross_product_check_1.q,cross_product_check_2.q,dynpart_sort_opt_vectorization.q,dynpart_sort_optimization.q,orc_analyze.q,join0.q,join1.q,auto_join0.q,auto_join1.q,bucket2.q,bucket3.q,bucket4.q,count.q,create_merge_compressed.q,cross_join.q,ctas.q,custom_input_output_format.q,disable_merge_for_bucketing.q,enforce_order.q,filter_join_breaktask.q,filter_join_breaktask2.q,groupby1.q,groupby2.q,groupby3.q,having.q,insert1.q,insert_into1.q,insert_into2.q,leftsemijoin.q,limit_pushdown.q,load_dyn_part1.q,load_dyn_part2.q,load_dyn_part3.q,mapjoin_mapjoin.q,mapreduce1.q,mapreduce2.q,merge1.q,merge2.q,metadata_only_queries.q,sample1.q,subquery_in.q,subquery_exists.q,vectorization_15.q,ptf.q,stats_counter.q,stats_noscan_1.q,stats_counter_partitioned.q,union2.q,union3.q,union4.q,union5.q,union6.q,union7.q,union8.q,union9.q</minitez.query.files.shared>
<beeline.positive.exclude>add_part_exist.q,alter1.q,alter2.q,alter4.q,alter5.q,alter_rename_partition.q,alter_rename_partition_authorization.q,archive.q,archive_corrupt.q,archive_multi.q,archive_mr_1806.q,archive_multi_mr_1806.q,authorization_1.q,authorization_2.q,authorization_4.q,authorization_5.q,authorization_6.q,authorization_7.q,ba_table1.q,ba_table2.q,ba_table3.q,ba_table_udfs.q,binary_table_bincolserde.q,binary_table_colserde.q,cluster.q,columnarserde_create_shortcut.q,combine2.q,constant_prop.q,create_nested_type.q,create_or_replace_view.q,create_struct_table.q,create_union_table.q,database.q,database_location.q,database_properties.q,ddltime.q,describe_database_json.q,drop_database_removes_partition_dirs.q,escape1.q,escape2.q,exim_00_nonpart_empty.q,exim_01_nonpart.q,exim_02_00_part_empty.q,exim_02_part.q,exim_03_nonpart_over_compat.q,exim_04_all_part.q,exim_04_evolved_parts.q,exim_05_some_part.q,exim_06_one_part.q,exim_07_all_part_over_nonoverlap.q,exim_08_nonpart_rena
me.q,exim_09_part_spec_nonoverlap.q,exim_10_external_managed.q,exim_11_managed_external.q,exim_12_external_location.q,exim_13_managed_location.q,exim_14_managed_location_over_existing.q,exim_15_external_part.q,exim_16_part_external.q,exim_17_part_managed.q,exim_18_part_external.q,exim_19_00_part_external_location.q,exim_19_part_external_location.q,exim_20_part_managed_location.q,exim_21_export_authsuccess.q,exim_22_import_exist_authsuccess.q,exim_23_import_part_authsuccess.q,exim_24_import_nonexist_authsuccess.q,global_limit.q,groupby_complex_types.q,groupby_complex_types_multi_single_reducer.q,index_auth.q,index_auto.q,index_auto_empty.q,index_bitmap.q,index_bitmap1.q,index_bitmap2.q,index_bitmap3.q,index_bitmap_auto.q,index_bitmap_rc.q,index_compact.q,index_compact_1.q,index_compact_2.q,index_compact_3.q,index_stale_partitioned.q,init_file.q,input16.q,input16_cc.q,input46.q,input_columnarserde.q,input_dynamicserde.q,input_lazyserde.q,input_testxpath3.q,input_testxpath4.q,insert2_o
verwrite_partitions.q,insertexternal1.q,join_thrift.q,lateral_view.q,load_binary_data.q,load_exist_part_authsuccess.q,load_nonpart_authsuccess.q,load_part_authsuccess.q,loadpart_err.q,lock1.q,lock2.q,lock3.q,lock4.q,merge_dynamic_partition.q,multi_insert.q,multi_insert_move_tasks_share_dependencies.q,null_column.q,ppd_clusterby.q,query_with_semi.q,rename_column.q,sample6.q,sample_islocalmode_hook.q,set_processor_namespaces.q,show_tables.q,source.q,split_sample.q,str_to_map.q,transform1.q,udaf_collect_set.q,udaf_context_ngrams.q,udaf_histogram_numeric.q,udaf_ngrams.q,udaf_percentile_approx.q,udf_array.q,udf_bitmap_and.q,udf_bitmap_or.q,udf_explode.q,udf_format_number.q,udf_map.q,udf_map_keys.q,udf_map_values.q,udf_max.q,udf_min.q,udf_named_struct.q,udf_percentile.q,udf_printf.q,udf_sentences.q,udf_sort_array.q,udf_split.q,udf_struct.q,udf_substr.q,udf_translate.q,udf_union.q,udf_xpath.q,udtf_stack.q,view.q,virtual_column.q</beeline.positive.exclude>
</properties>
Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezProcessor.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezProcessor.java?rev=1585741&r1=1585740&r2=1585741&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezProcessor.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezProcessor.java Tue Apr 8 14:26:23 2014
@@ -118,6 +118,7 @@ public class TezProcessor implements Log
String taskAttemptIdStr = taskAttemptIdBuilder.toString();
this.jobConf.set("mapred.task.id", taskAttemptIdStr);
this.jobConf.set("mapreduce.task.attempt.id", taskAttemptIdStr);
+ this.jobConf.setInt("mapred.task.partition",processorContext.getTaskIndex());
}
@Override
Added: hive/trunk/ql/src/test/queries/clientpositive/tez_fsstat.q
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/tez_fsstat.q?rev=1585741&view=auto
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/tez_fsstat.q (added)
+++ hive/trunk/ql/src/test/queries/clientpositive/tez_fsstat.q Tue Apr 8 14:26:23 2014
@@ -0,0 +1,19 @@
+set hive.execution.engine=tez;
+CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE;
+CREATE TABLE t1 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE;
+
+load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE t1 partition(ds='2008-04-08');
+load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE t1 partition(ds='2008-04-08');
+load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE t1 partition(ds='2008-04-08');
+load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE t1 partition(ds='2008-04-08');
+
+set hive.enforce.bucketing=true;
+set hive.enforce.sorting = true;
+set hive.optimize.bucketingsorting=false;
+set hive.stats.dbclass=fs;
+
+insert overwrite table tab_part partition (ds='2008-04-08')
+select key,value from t1;
+describe formatted tab_part partition(ds='2008-04-08');
+
+set hive.stats.dbclass=jdbc:derby;
Added: hive/trunk/ql/src/test/results/clientpositive/tez/tez_fsstat.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/tez_fsstat.q.out?rev=1585741&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/tez/tez_fsstat.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/tez/tez_fsstat.q.out Tue Apr 8 14:26:23 2014
@@ -0,0 +1,104 @@
+PREHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+POSTHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tab_part
+PREHOOK: query: CREATE TABLE t1 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+POSTHOOK: query: CREATE TABLE t1 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@t1
+PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE t1 partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t1
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE t1 partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t1
+POSTHOOK: Output: default@t1@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE t1 partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t1@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE t1 partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t1@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE t1 partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t1@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE t1 partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t1@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE t1 partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t1@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE t1 partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t1@ds=2008-04-08
+PREHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08')
+select key,value from t1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t1@ds=2008-04-08
+PREHOOK: Output: default@tab_part@ds=2008-04-08
+POSTHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08')
+select key,value from t1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t1@ds=2008-04-08
+POSTHOOK: Output: default@tab_part@ds=2008-04-08
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(t1)t1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: describe formatted tab_part partition(ds='2008-04-08')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@tab_part
+POSTHOOK: query: describe formatted tab_part partition(ds='2008-04-08')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@tab_part
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(t1)t1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+# col_name data_type comment
+
+key int
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08]
+Database: default
+Table: tab_part
+#### A masked pattern was here ####
+Protect Mode: None
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE true
+ numFiles 4
+ numRows 500
+ rawDataSize 5312
+ totalSize 5812
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: 4
+Bucket Columns: [key]
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1