blob: c40ef8d8402bf46fb09ffffcf73373f9bbf56d82 [file] [log] [blame]
PREHOOK: query: drop table part_hive
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table part_hive
POSTHOOK: type: DROPTABLE
PREHOOK: query: drop table partsupp_hive
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table partsupp_hive
POSTHOOK: type: DROPTABLE
PREHOOK: query: drop table supplier_hive
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table supplier_hive
POSTHOOK: type: DROPTABLE
PREHOOK: query: create table part_hive (P_PARTKEY INT, P_NAME STRING, P_MFGR STRING, P_BRAND STRING, P_TYPE STRING,
P_SIZE INT, P_CONTAINER STRING, P_RETAILPRICE DOUBLE, P_COMMENT STRING)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@part_hive
POSTHOOK: query: create table part_hive (P_PARTKEY INT, P_NAME STRING, P_MFGR STRING, P_BRAND STRING, P_TYPE STRING,
P_SIZE INT, P_CONTAINER STRING, P_RETAILPRICE DOUBLE, P_COMMENT STRING)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@part_hive
PREHOOK: query: create table partsupp_hive (PS_PARTKEY INT, PS_SUPPKEY INT, PS_AVAILQTY INT, PS_SUPPLYCOST DOUBLE,
PS_COMMENT STRING)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@partsupp_hive
POSTHOOK: query: create table partsupp_hive (PS_PARTKEY INT, PS_SUPPKEY INT, PS_AVAILQTY INT, PS_SUPPLYCOST DOUBLE,
PS_COMMENT STRING)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@partsupp_hive
PREHOOK: query: create table supplier_hive (S_SUPPKEY INT, S_NAME STRING, S_ADDRESS STRING, S_NATIONKEY INT,
S_PHONE STRING, S_ACCTBAL DOUBLE, S_COMMENT STRING)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@supplier_hive
POSTHOOK: query: create table supplier_hive (S_SUPPKEY INT, S_NAME STRING, S_ADDRESS STRING, S_NATIONKEY INT,
S_PHONE STRING, S_ACCTBAL DOUBLE, S_COMMENT STRING)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@supplier_hive
PREHOOK: query: analyze table part_hive compute statistics
PREHOOK: type: QUERY
PREHOOK: Input: default@part_hive
PREHOOK: Output: default@part_hive
POSTHOOK: query: analyze table part_hive compute statistics
POSTHOOK: type: QUERY
POSTHOOK: Input: default@part_hive
POSTHOOK: Output: default@part_hive
PREHOOK: query: analyze table part_hive compute statistics for columns
PREHOOK: type: ANALYZE_TABLE
PREHOOK: Input: default@part_hive
PREHOOK: Output: default@part_hive
#### A masked pattern was here ####
POSTHOOK: query: analyze table part_hive compute statistics for columns
POSTHOOK: type: ANALYZE_TABLE
POSTHOOK: Input: default@part_hive
POSTHOOK: Output: default@part_hive
#### A masked pattern was here ####
PREHOOK: query: analyze table partsupp_hive compute statistics
PREHOOK: type: QUERY
PREHOOK: Input: default@partsupp_hive
PREHOOK: Output: default@partsupp_hive
POSTHOOK: query: analyze table partsupp_hive compute statistics
POSTHOOK: type: QUERY
POSTHOOK: Input: default@partsupp_hive
POSTHOOK: Output: default@partsupp_hive
PREHOOK: query: analyze table partsupp_hive compute statistics for columns
PREHOOK: type: ANALYZE_TABLE
PREHOOK: Input: default@partsupp_hive
PREHOOK: Output: default@partsupp_hive
#### A masked pattern was here ####
POSTHOOK: query: analyze table partsupp_hive compute statistics for columns
POSTHOOK: type: ANALYZE_TABLE
POSTHOOK: Input: default@partsupp_hive
POSTHOOK: Output: default@partsupp_hive
#### A masked pattern was here ####
PREHOOK: query: analyze table supplier_hive compute statistics
PREHOOK: type: QUERY
PREHOOK: Input: default@supplier_hive
PREHOOK: Output: default@supplier_hive
POSTHOOK: query: analyze table supplier_hive compute statistics
POSTHOOK: type: QUERY
POSTHOOK: Input: default@supplier_hive
POSTHOOK: Output: default@supplier_hive
PREHOOK: query: analyze table supplier_hive compute statistics for columns
PREHOOK: type: ANALYZE_TABLE
PREHOOK: Input: default@supplier_hive
PREHOOK: Output: default@supplier_hive
#### A masked pattern was here ####
POSTHOOK: query: analyze table supplier_hive compute statistics for columns
POSTHOOK: type: ANALYZE_TABLE
POSTHOOK: Input: default@supplier_hive
POSTHOOK: Output: default@supplier_hive
#### A masked pattern was here ####
Warning: Shuffle Join MERGEJOIN[69][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select
p_brand,
p_type,
p_size,
count(distinct ps_suppkey) as supplier_cnt
from
partsupp_hive,
part_hive
where
p_partkey = ps_partkey
and p_brand <> 'Brand#34'
and p_type not like 'ECONOMY BRUSHED%'
and p_size in (22, 14, 27, 49, 21, 33, 35, 28)
and partsupp_hive.ps_suppkey not in (
select
s_suppkey
from
supplier_hive
where
s_comment like '%Customer%Complaints%'
)
group by
p_brand,
p_type,
p_size
order by
supplier_cnt desc,
p_brand,
p_type,
p_size
PREHOOK: type: QUERY
PREHOOK: Input: default@part_hive
PREHOOK: Input: default@partsupp_hive
PREHOOK: Input: default@supplier_hive
#### A masked pattern was here ####
POSTHOOK: query: explain select
p_brand,
p_type,
p_size,
count(distinct ps_suppkey) as supplier_cnt
from
partsupp_hive,
part_hive
where
p_partkey = ps_partkey
and p_brand <> 'Brand#34'
and p_type not like 'ECONOMY BRUSHED%'
and p_size in (22, 14, 27, 49, 21, 33, 35, 28)
and partsupp_hive.ps_suppkey not in (
select
s_suppkey
from
supplier_hive
where
s_comment like '%Customer%Complaints%'
)
group by
p_brand,
p_type,
p_size
order by
supplier_cnt desc,
p_brand,
p_type,
p_size
POSTHOOK: type: QUERY
POSTHOOK: Input: default@part_hive
POSTHOOK: Input: default@partsupp_hive
POSTHOOK: Input: default@supplier_hive
#### A masked pattern was here ####
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (XPROD_EDGE), Reducer 7 (XPROD_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
Reducer 8 <- Map 6 (SIMPLE_EDGE)
Reducer 9 <- Map 10 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: part_hive
filterExpr: ((p_size) IN (22, 14, 27, 49, 21, 33, 35, 28) and (p_brand <> 'Brand#34') and p_partkey is not null and (not (p_type like 'ECONOMY BRUSHED%'))) (type: boolean)
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((p_size) IN (22, 14, 27, 49, 21, 33, 35, 28) and (p_brand <> 'Brand#34') and p_partkey is not null and (not (p_type like 'ECONOMY BRUSHED%'))) (type: boolean)
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 10
Map Operator Tree:
TableScan
alias: partsupp_hive
filterExpr: ps_partkey is not null (type: boolean)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ps_partkey is not null (type: boolean)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ps_partkey (type: int), ps_suppkey (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
null sort order: z
sort order: +
Map-reduce partition columns: _col1 (type: int)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 6
Map Operator Tree:
TableScan
alias: supplier_hive
filterExpr: ((s_comment like '%Customer%Complaints%') or ((s_comment like '%Customer%Complaints%') and s_suppkey is not null)) (type: boolean)
Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (s_comment like '%Customer%Complaints%') (type: boolean)
Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: s_suppkey (type: int)
outputColumnNames: s_suppkey
Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(s_suppkey)
minReductionHashAggr: 0.0
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: bigint)
Filter Operator
predicate: ((s_comment like '%Customer%Complaints%') and s_suppkey is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: s_suppkey (type: int)
outputColumnNames: s_suppkey
Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: s_suppkey (type: int)
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
0
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: bigint), _col5 (type: bigint)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7, _col9
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col7 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: bigint), _col5 (type: bigint), _col9 (type: boolean)
outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col9
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((_col6 = 0L) or (_col9 is null and (_col7 >= _col6) and _col1 is not null)) (type: boolean)
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int)
outputColumnNames: _col1, _col3, _col4, _col5
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col3 (type: string), _col4 (type: string), _col5 (type: int), _col1 (type: int)
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int)
null sort order: zzzz
sort order: ++++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 4
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col3 (type: int), _col0 (type: string), _col1 (type: string), _col2 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(_col0)
keys: _col1 (type: string), _col2 (type: string), _col3 (type: int)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col3 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: int)
null sort order: azzz
sort order: -+++
Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: vectorized, llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 7
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0), count(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: bigint)
Reducer 8
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean)
Reducer 9
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col1 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int), _col3 (type: boolean)
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink