Krisztian Kasa created HIVE-22735:
-------------------------------------
Summary: TopNKey operator deduplication
Key: HIVE-22735
URL: https://issues.apache.org/jira/browse/HIVE-22735
Project: Hive
Issue Type: Improvement
Components: Physical Optimizer
Reporter: Krisztian Kasa
Assignee: Krisztian Kasa
Fix For: 4.0.0
In some cases more than one TNK operator has the same expressions in the same
operator tree or the difference is only a constant column. Most of this cases
only one TNK op. should remain.
{code}
+----------------------------------------------------+
| Explain |
+----------------------------------------------------+
| Plan not optimized by CBO. |
| |
| Vertex dependency in root stage |
| Map 1 <- Reducer 8 (BROADCAST_EDGE) |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE), Map 6
(BROADCAST_EDGE), Map 7 (BROADCAST_EDGE), Map 9 (BROADCAST_EDGE) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| Reducer 4 <- Reducer 3 (SIMPLE_EDGE) |
| Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) |
| |
| Stage-0 |
| Fetch Operator |
| limit:50 |
| Stage-1 |
| Reducer 4 vectorized |
| File Output Operator [FS_127] |
| Limit [LIM_126] (rows=50 width=538) |
| Number of rows:50 |
| Select Operator [SEL_125] (rows=190 width=538) |
| Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] |
| <-Reducer 3 [SIMPLE_EDGE] |
| SHUFFLE [RS_30] |
| Select Operator [SEL_29] (rows=190 width=538) |
|
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] |
| Group By Operator [GBY_28] (rows=190 width=538) |
|
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["avg(VALUE._col0)","avg(VALUE._col1)","avg(VALUE._col2)","avg(VALUE._col3)"],keys:KEY._col0,
KEY._col1, KEY._col2 |
| <-Reducer 2 [SIMPLE_EDGE] |
| SHUFFLE [RS_27] |
| PartitionCols:_col0, _col1, _col2 |
| Group By Operator [GBY_26] (rows=190 width=1134) |
|
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["avg(_col9)","avg(_col11)","avg(_col18)","avg(_col12)"],keys:_col102,
_col93, 0L |
| Top N Key Operator [TNK_60] (rows=127 width=234) |
| keys:_col102, _col93, 0L,top n:50 |
| Select Operator [SEL_25] (rows=127 width=234) |
|
Output:["_col9","_col11","_col12","_col18","_col93","_col102"] |
| Top N Key Operator [TNK_58] (rows=127 width=234) |
| keys:_col102, _col93,top n:50 |
| Filter Operator [FIL_49] (rows=127 width=234) |
| predicate:((_col22 = _col38) and (_col1 =
_col101) and (_col6 = _col69) and (_col3 = _col26)) |
| Map Join Operator [MAPJOIN_102] (rows=2044
width=232) |
|
Conds:MAPJOIN_101._col1=RS_123.i_item_sk(Inner),Output:["_col1","_col3","_col6","_col9","_col11","_col12","_col18","_col22","_col26","_col38","_col69","_col93","_col101","_col102"]
|
| <-Map 9 [BROADCAST_EDGE] vectorized |
| BROADCAST [RS_123] |
| PartitionCols:i_item_sk |
| Filter Operator [FIL_122] (rows=204000
width=108) |
| predicate:i_item_sk is not null |
| TableScan [TS_4] (rows=204000 width=108) |
|
tpcds_bin_partitioned_orc_100@item,item, ACID
table,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] |
| <-Map Join Operator [MAPJOIN_101] (rows=2010
width=118) |
|
Conds:MAPJOIN_100._col6=RS_107.s_store_sk(Inner),Output:["_col1","_col3","_col6","_col9","_col11","_col12","_col18","_col22","_col26","_col38","_col69","_col93"]
|
| <-Map 7 [BROADCAST_EDGE] vectorized |
| PARTITION_ONLY_SHUFFLE [RS_107] |
| PartitionCols:s_store_sk |
| Filter Operator [FIL_106] (rows=402
width=94) |
| predicate:s_store_sk is not null |
| TableScan [TS_3] (rows=402 width=94) |
|
tpcds_bin_partitioned_orc_100@store,store, ACID
table,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] |
| <-Map Join Operator [MAPJOIN_100]
(rows=9604000 width=24) |
|
Conds:MERGEJOIN_99._col22=RS_118.d_date_sk(Inner),Output:["_col1","_col3","_col6","_col9","_col11","_col12","_col18","_col22","_col26","_col38"]
|
| <-Map 6 [BROADCAST_EDGE] vectorized |
| BROADCAST [RS_118] |
| PartitionCols:d_date_sk |
| Filter Operator [FIL_117] (rows=73049
width=8) |
| predicate:d_date_sk is not null |
| TableScan [TS_2] (rows=73049 width=8)
|
|
tpcds_bin_partitioned_orc_100@date_dim,date_dim, ACID
table,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk"] |
| Dynamic Partitioning Event Operator
[EVENT_121] (rows=1 width=8) |
| Group By Operator [GBY_120] (rows=1
width=8) |
| Output:["_col0"],keys:_col0 |
| Select Operator [SEL_119] (rows=73049
width=8) |
| Output:["_col0"] |
| Please refer to the previous
Filter Operator [FIL_117] |
| <-Merge Join Operator [MERGEJOIN_99]
(rows=9604000 width=16) |
|
Conds:RS_114.ss_cdemo_sk=RS_116.cd_demo_sk(Inner),Output:["_col1","_col3","_col6","_col9","_col11","_col12","_col18","_col22","_col26"]
|
| <-Map 1 [SIMPLE_EDGE] vectorized |
| SHUFFLE [RS_114] |
| PartitionCols:ss_cdemo_sk |
| Filter Operator [FIL_113]
(rows=235814137 width=353) |
| predicate:(ss_cdemo_sk is not null
and ss_store_sk is not null and ss_item_sk is not null and ss_store_sk BETWEEN
DynamicValue(RS_17_store_s_store_sk_min) AND
DynamicValue(RS_17_store_s_store_sk_max) and in_bloom_filter(ss_store_sk,
DynamicValue(RS_17_store_s_store_sk_bloom_filter))) |
| TableScan [TS_0] (rows=275041999
width=723) |
|
tpcds_bin_partitioned_orc_100@store_sales,store_sales, ACID
table,Tbl:COMPLETE,Col:PARTIAL,Output:["ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"]
|
| <-Reducer 8 [BROADCAST_EDGE]
vectorized |
| BROADCAST [RS_112] |
| Group By Operator [GBY_111]
(rows=1 width=24) |
|
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2,
expectedEntries=1000000)"] |
| <-Map 5 [SIMPLE_EDGE] vectorized |
| SHUFFLE [RS_116] |
| PartitionCols:cd_demo_sk |
| Filter Operator [FIL_115]
(rows=1920800 width=8) |
| predicate:cd_demo_sk is not null |
| TableScan [TS_1] (rows=1920800
width=8) |
|
tpcds_bin_partitioned_orc_100@customer_demographics,customer_demographics, ACID
table,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] |
| |
+----------------------------------------------------+
{code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
