PREHOOK: query: -- EXCLUDE_HADOOP_MAJOR_VERSIONS( 0.20S) -- create file inputs create table sih_i_part (key int, value string) partitioned by (p string) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@sih_i_part POSTHOOK: query: -- EXCLUDE_HADOOP_MAJOR_VERSIONS( 0.20S) -- create file inputs create table sih_i_part (key int, value string) partitioned by (p string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@sih_i_part PREHOOK: query: insert overwrite table sih_i_part partition (p='1') select key, value from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@sih_i_part@p=1 POSTHOOK: query: insert overwrite table sih_i_part partition (p='1') select key, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@sih_i_part@p=1 POSTHOOK: Lineage: sih_i_part PARTITION(p=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: sih_i_part PARTITION(p=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: insert overwrite table sih_i_part partition (p='2') select key+10000, value from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@sih_i_part@p=2 POSTHOOK: query: insert overwrite table sih_i_part partition (p='2') select key+10000, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@sih_i_part@p=2 POSTHOOK: Lineage: sih_i_part PARTITION(p=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: sih_i_part PARTITION(p=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: insert overwrite table sih_i_part partition (p='3') select key+20000, value from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@sih_i_part@p=3 POSTHOOK: query: insert overwrite table sih_i_part partition (p='3') select key+20000, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@sih_i_part@p=3 POSTHOOK: Lineage: sih_i_part PARTITION(p=3).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: sih_i_part PARTITION(p=3).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: create table sih_src as select key, value from sih_i_part order by key, value PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@sih_i_part PREHOOK: Input: default@sih_i_part@p=1 PREHOOK: Input: default@sih_i_part@p=2 PREHOOK: Input: default@sih_i_part@p=3 PREHOOK: Output: database:default PREHOOK: Output: default@sih_src POSTHOOK: query: create table sih_src as select key, value from sih_i_part order by key, value POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@sih_i_part POSTHOOK: Input: default@sih_i_part@p=1 POSTHOOK: Input: default@sih_i_part@p=2 POSTHOOK: Input: default@sih_i_part@p=3 POSTHOOK: Output: database:default POSTHOOK: Output: default@sih_src PREHOOK: query: create table sih_src2 as select key, value from sih_src order by key, value PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@sih_src PREHOOK: Output: database:default PREHOOK: Output: default@sih_src2 POSTHOOK: query: create table sih_src2 as select key, value from sih_src order by key, value POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@sih_src POSTHOOK: Output: database:default POSTHOOK: Output: default@sih_src2 PREHOOK: query: -- Relaxing hive.exec.mode.local.auto.input.files.max=1. -- Hadoop20 will not generate more splits than there are files (one). -- Hadoop23 generate splits correctly (four), hence the max needs to be adjusted to ensure running in local mode. -- Default value is hive.exec.mode.local.auto.input.files.max=4 which produces expected behavior on Hadoop23. -- hive.sample.seednumber is required because Hadoop23 generates multiple splits and tablesample is non-repeatable without it. -- sample split, running locally limited by num tasks select count(1) from sih_src tablesample(1 percent) PREHOOK: type: QUERY PREHOOK: Input: default@sih_src #### A masked pattern was here #### 25 PREHOOK: query: -- sample two tables select count(1) from sih_src tablesample(1 percent) a join sih_src2 tablesample(1 percent) b on a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@sih_src PREHOOK: Input: default@sih_src2 #### A masked pattern was here #### 49 PREHOOK: query: -- sample split, running locally limited by max bytes select count(1) from sih_src tablesample(1 percent) PREHOOK: type: QUERY PREHOOK: Input: default@sih_src #### A masked pattern was here #### 25