blob: f17df16d1e9272354716cb10f7b491731bdf34c4 [file]
# Avro scan.
select * from tpch_avro.orders
---- HIVE_MAJOR_VERSION
# Hive 3 creates different number of files for this table than Hive 2.
2
---- PLAN
Max Per-Host Resource Reservation: Memory=12.00MB Threads=2
Per-Host Resource Estimates: Memory=74MB
WARNING: The following tables are missing relevant table and/or column statistics.
tpch_avro.orders
Analyzed query: SELECT * FROM tpch_avro.orders
F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Host Resources: mem-estimate=74.00MB mem-reservation=12.00MB thread-reservation=2
PLAN-ROOT SINK
| output exprs: tpch_avro.orders.o_orderkey, tpch_avro.orders.o_custkey, tpch_avro.orders.o_orderstatus, tpch_avro.orders.o_totalprice, tpch_avro.orders.o_orderdate, tpch_avro.orders.o_orderpriority, tpch_avro.orders.o_clerk, tpch_avro.orders.o_shippriority, tpch_avro.orders.o_comment
| mem-estimate=10.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
00:SCAN HDFS [tpch_avro.orders]
HDFS partitions=1/1 files=2 size=156.92MB
stored statistics:
table: rows=unavailable size=156.92MB
columns: unavailable
extrapolated-rows=disabled max-scan-range-rows=unavailable
mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
tuple-ids=0 row-size=88B cardinality=unavailable
in pipelines: 00(GETNEXT)
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=12.00MB Threads=3
Per-Host Resource Estimates: Memory=75MB
WARNING: The following tables are missing relevant table and/or column statistics.
tpch_avro.orders
Analyzed query: SELECT * FROM tpch_avro.orders
F01:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Host Resources: mem-estimate=10.27MB mem-reservation=4.00MB thread-reservation=1
PLAN-ROOT SINK
| output exprs: tpch_avro.orders.o_orderkey, tpch_avro.orders.o_custkey, tpch_avro.orders.o_orderstatus, tpch_avro.orders.o_totalprice, tpch_avro.orders.o_orderdate, tpch_avro.orders.o_orderpriority, tpch_avro.orders.o_clerk, tpch_avro.orders.o_shippriority, tpch_avro.orders.o_comment
| mem-estimate=10.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
01:EXCHANGE [UNPARTITIONED]
| mem-estimate=183.96KB mem-reservation=0B thread-reservation=0
| tuple-ids=0 row-size=88B cardinality=unavailable
| in pipelines: 00(GETNEXT)
|
F00:PLAN FRAGMENT [RANDOM] hosts=2 instances=2
Per-Host Resources: mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=2
00:SCAN HDFS [tpch_avro.orders, RANDOM]
HDFS partitions=1/1 files=2 size=156.92MB
stored statistics:
table: rows=unavailable size=156.92MB
columns: unavailable
extrapolated-rows=disabled max-scan-range-rows=unavailable
mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
tuple-ids=0 row-size=88B cardinality=unavailable
in pipelines: 00(GETNEXT)
---- PARALLELPLANS
Max Per-Host Resource Reservation: Memory=12.00MB Threads=2
Per-Host Resource Estimates: Memory=74MB
WARNING: The following tables are missing relevant table and/or column statistics.
tpch_avro.orders
Analyzed query: SELECT * FROM tpch_avro.orders
F01:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Host Resources: mem-estimate=10.27MB mem-reservation=4.00MB thread-reservation=1
PLAN-ROOT SINK
| output exprs: tpch_avro.orders.o_orderkey, tpch_avro.orders.o_custkey, tpch_avro.orders.o_orderstatus, tpch_avro.orders.o_totalprice, tpch_avro.orders.o_orderdate, tpch_avro.orders.o_orderpriority, tpch_avro.orders.o_clerk, tpch_avro.orders.o_shippriority, tpch_avro.orders.o_comment
| mem-estimate=10.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
01:EXCHANGE [UNPARTITIONED]
| mem-estimate=183.96KB mem-reservation=0B thread-reservation=0
| tuple-ids=0 row-size=88B cardinality=unavailable
| in pipelines: 00(GETNEXT)
|
F00:PLAN FRAGMENT [RANDOM] hosts=2 instances=2
Per-Instance Resources: mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
00:SCAN HDFS [tpch_avro.orders, RANDOM]
HDFS partitions=1/1 files=2 size=156.92MB
stored statistics:
table: rows=unavailable size=156.92MB
columns: unavailable
extrapolated-rows=disabled max-scan-range-rows=unavailable
mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=0
tuple-ids=0 row-size=88B cardinality=unavailable
in pipelines: 00(GETNEXT)
====
select * from tpch_avro.orders
---- HIVE_MAJOR_VERSION
# Hive 3 creates different number of files for this table than Hive 2.
3
---- PLAN
Max Per-Host Resource Reservation: Memory=12.00MB Threads=2
Per-Host Resource Estimates: Memory=74MB
WARNING: The following tables are missing relevant table and/or column statistics.
tpch_avro.orders
Analyzed query: SELECT * FROM tpch_avro.orders
F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Host Resources: mem-estimate=74.00MB mem-reservation=12.00MB thread-reservation=2
PLAN-ROOT SINK
| output exprs: tpch_avro.orders.o_orderkey, tpch_avro.orders.o_custkey, tpch_avro.orders.o_orderstatus, tpch_avro.orders.o_totalprice, tpch_avro.orders.o_orderdate, tpch_avro.orders.o_orderpriority, tpch_avro.orders.o_clerk, tpch_avro.orders.o_shippriority, tpch_avro.orders.o_comment
| mem-estimate=10.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
00:SCAN HDFS [tpch_avro.orders]
HDFS partitions=1/1 files=3 size=156.92MB
stored statistics:
table: rows=unavailable size=156.92MB
columns: unavailable
extrapolated-rows=disabled max-scan-range-rows=unavailable
mem-estimate=64.00MB mem-reservation=8.00MB thread-reservation=1
tuple-ids=0 row-size=88B cardinality=unavailable
in pipelines: 00(GETNEXT)
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=12.00MB Threads=3
Per-Host Resource Estimates: Memory=85MB
WARNING: The following tables are missing relevant table and/or column statistics.
tpch_avro.orders
Analyzed query: SELECT * FROM tpch_avro.orders
F01:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Host Resources: mem-estimate=20.27MB mem-reservation=4.00MB thread-reservation=1
PLAN-ROOT SINK
| output exprs: tpch_avro.orders.o_orderkey, tpch_avro.orders.o_custkey, tpch_avro.orders.o_orderstatus, tpch_avro.orders.o_totalprice, tpch_avro.orders.o_orderdate, tpch_avro.orders.o_orderpriority, tpch_avro.orders.o_clerk, tpch_avro.orders.o_shippriority, tpch_avro.orders.o_comment
| mem-estimate=10.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
01:EXCHANGE [UNPARTITIONED]
| mem-estimate=10.27MB mem-reservation=0B thread-reservation=0
| tuple-ids=0 row-size=88B cardinality=unavailable
| in pipelines: 00(GETNEXT)
|
F00:PLAN FRAGMENT [RANDOM] hosts=3 instances=3
Per-Host Resources: mem-estimate=64.36MB mem-reservation=8.00MB thread-reservation=2
00:SCAN HDFS [tpch_avro.orders, RANDOM]
HDFS partitions=1/1 files=3 size=156.92MB
stored statistics:
table: rows=unavailable size=156.92MB
columns: unavailable
extrapolated-rows=disabled max-scan-range-rows=unavailable
mem-estimate=64.00MB mem-reservation=8.00MB thread-reservation=1
tuple-ids=0 row-size=88B cardinality=unavailable
in pipelines: 00(GETNEXT)
====
# IMPALA-13622: TPC-H Q18 with tpch.customer replaced with tpch_avro.customer
# that does not have stats. This meant to test that none of cardinality estimation code
# for AggregationNode return cardinality or numGroups less than -1.
# All preconditions in AggregationNode.java should pass.
select
c_name,
c_custkey,
o_orderkey,
o_orderdate,
o_totalprice,
sum(l_quantity)
from
tpch_avro.customer,
tpch.orders,
tpch.lineitem
where
o_orderkey in (
select
l_orderkey
from
tpch.lineitem
group by
l_orderkey
having
sum(l_quantity) > 300
)
and c_custkey = o_custkey
and o_orderkey = l_orderkey
group by
c_name,
c_custkey,
o_orderkey,
o_orderdate,
o_totalprice
order by
o_totalprice desc,
o_orderdate
limit 100
---- PLAN
Max Per-Host Resource Reservation: Memory=138.50MB Threads=5
Per-Host Resource Estimates: Memory=2.46GB
WARNING: The following tables are missing relevant table and/or column statistics.
tpch_avro.customer
Analyzed query: SELECT c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice,
sum(l_quantity) FROM tpch_avro.customer, tpch.orders, tpch.lineitem LEFT SEMI
JOIN (SELECT l_orderkey FROM tpch.lineitem GROUP BY l_orderkey HAVING
sum(l_quantity) > CAST(300 AS DECIMAL(5,0))) `$a$1` (`$c$1`) ON o_orderkey =
`$a$1`.`$c$1` WHERE TRUE AND c_custkey = o_custkey AND o_orderkey = l_orderkey
GROUP BY c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice ORDER BY
o_totalprice DESC, o_orderdate ASC LIMIT CAST(100 AS TINYINT)
F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Host Resources: mem-estimate=2.46GB mem-reservation=138.50MB thread-reservation=5 runtime-filters-memory=4.00MB
PLAN-ROOT SINK
| output exprs: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice, sum(l_quantity)
| mem-estimate=4.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
09:TOP-N [LIMIT=100]
| order by: o_totalprice DESC, o_orderdate ASC
| mem-estimate=7.23KB mem-reservation=0B thread-reservation=0
| tuple-ids=7 row-size=74B cardinality=100
| in pipelines: 09(GETNEXT), 08(OPEN)
|
08:AGGREGATE [FINALIZE]
| output: sum(l_quantity)
| group by: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice
| mem-estimate=128.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=6 row-size=74B cardinality=600.12K
| in pipelines: 08(GETNEXT), 02(OPEN)
|
07:HASH JOIN [LEFT SEMI JOIN]
| hash predicates: o_orderkey = l_orderkey
| runtime filters: RF000[bloom] <- l_orderkey
| mem-estimate=8.50MB mem-reservation=8.50MB spill-buffer=512.00KB thread-reservation=0
| tuple-ids=2,1,0 row-size=82B cardinality=600.12K
| in pipelines: 02(GETNEXT), 04(OPEN)
|
|--04:AGGREGATE [FINALIZE]
| | output: sum(l_quantity)
| | group by: l_orderkey
| | having: sum(l_quantity) > CAST(300 AS DECIMAL(5,0))
| | mem-estimate=53.68MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| | tuple-ids=4 row-size=24B cardinality=156.34K
| | in pipelines: 04(GETNEXT), 03(OPEN)
| |
| 03:SCAN HDFS [tpch.lineitem]
| HDFS partitions=1/1 files=1 size=718.94MB
| stored statistics:
| table: rows=6.00M size=718.94MB
| columns: all
| extrapolated-rows=disabled max-scan-range-rows=1.07M
| mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
| tuple-ids=3 row-size=16B cardinality=6.00M
| in pipelines: 03(GETNEXT)
|
06:HASH JOIN [INNER JOIN]
| hash predicates: o_custkey = c_custkey
| fk/pk conjuncts: assumed fk/pk
| runtime filters: RF002[bloom] <- c_custkey
| mem-estimate=2.00GB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=2,1,0 row-size=82B cardinality=5.76M
| in pipelines: 02(GETNEXT), 00(OPEN)
|
|--00:SCAN HDFS [tpch_avro.customer]
| HDFS partitions=1/1 files=1 size=23.05MB
| stored statistics:
| table: rows=unavailable size=23.05MB
| columns: unavailable
| extrapolated-rows=disabled max-scan-range-rows=unavailable
| mem-estimate=32.00MB mem-reservation=8.00MB thread-reservation=1
| tuple-ids=0 row-size=20B cardinality=unavailable
| in pipelines: 00(GETNEXT)
|
05:HASH JOIN [INNER JOIN]
| hash predicates: l_orderkey = o_orderkey
| fk/pk conjuncts: l_orderkey = o_orderkey
| runtime filters: RF004[bloom] <- o_orderkey
| mem-estimate=113.80MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=2,1 row-size=62B cardinality=5.76M
| in pipelines: 02(GETNEXT), 01(OPEN)
|
|--01:SCAN HDFS [tpch.orders]
| HDFS partitions=1/1 files=1 size=162.56MB
| runtime filters: RF000[bloom] -> o_orderkey, RF002[bloom] -> o_custkey
| stored statistics:
| table: rows=1.50M size=162.56MB
| columns: all
| extrapolated-rows=disabled max-scan-range-rows=1.18M
| mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
| tuple-ids=1 row-size=46B cardinality=1.50M
| in pipelines: 01(GETNEXT)
|
02:SCAN HDFS [tpch.lineitem]
HDFS partitions=1/1 files=1 size=718.94MB
runtime filters: RF000[bloom] -> tpch.lineitem.l_orderkey, RF004[bloom] -> l_orderkey
stored statistics:
table: rows=6.00M size=718.94MB
columns: all
extrapolated-rows=disabled max-scan-range-rows=1.07M
mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
tuple-ids=2 row-size=16B cardinality=6.00M
in pipelines: 02(GETNEXT)
---- DISTRIBUTEDPLAN
Max Per-Host Resource Reservation: Memory=253.75MB Threads=11
Per-Host Resource Estimates: Memory=2.73GB
WARNING: The following tables are missing relevant table and/or column statistics.
tpch_avro.customer
Analyzed query: SELECT c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice,
sum(l_quantity) FROM tpch_avro.customer, tpch.orders, tpch.lineitem LEFT SEMI
JOIN (SELECT l_orderkey FROM tpch.lineitem GROUP BY l_orderkey HAVING
sum(l_quantity) > CAST(300 AS DECIMAL(5,0))) `$a$1` (`$c$1`) ON o_orderkey =
`$a$1`.`$c$1` WHERE TRUE AND c_custkey = o_custkey AND o_orderkey = l_orderkey
GROUP BY c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice ORDER BY
o_totalprice DESC, o_orderdate ASC LIMIT CAST(100 AS TINYINT)
F07:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Host Resources: mem-estimate=4.02MB mem-reservation=4.00MB thread-reservation=1
PLAN-ROOT SINK
| output exprs: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice, sum(l_quantity)
| mem-estimate=4.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
17:MERGING-EXCHANGE [UNPARTITIONED]
| order by: o_totalprice DESC, o_orderdate ASC
| limit: 100
| mem-estimate=25.26KB mem-reservation=0B thread-reservation=0
| tuple-ids=7 row-size=74B cardinality=100
| in pipelines: 09(GETNEXT)
|
F06:PLAN FRAGMENT [HASH(c_name,c_custkey,o_orderkey,o_orderdate,o_totalprice)] hosts=3 instances=3
Per-Host Resources: mem-estimate=138.23MB mem-reservation=34.00MB thread-reservation=1
09:TOP-N [LIMIT=100]
| order by: o_totalprice DESC, o_orderdate ASC
| mem-estimate=7.23KB mem-reservation=0B thread-reservation=0
| tuple-ids=7 row-size=74B cardinality=100
| in pipelines: 09(GETNEXT), 16(OPEN)
|
16:AGGREGATE [FINALIZE]
| output: sum:merge(l_quantity)
| group by: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice
| mem-estimate=128.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=6 row-size=74B cardinality=600.12K
| in pipelines: 16(GETNEXT), 02(OPEN)
|
15:EXCHANGE [HASH(c_name,c_custkey,o_orderkey,o_orderdate,o_totalprice)]
| mem-estimate=10.23MB mem-reservation=0B thread-reservation=0
| tuple-ids=6 row-size=74B cardinality=600.12K
| in pipelines: 02(GETNEXT)
|
F02:PLAN FRAGMENT [HASH(l_orderkey)] hosts=3 instances=3
Per-Host Resources: mem-estimate=2.24GB mem-reservation=144.75MB thread-reservation=1 runtime-filters-memory=4.00MB
08:AGGREGATE [STREAMING]
| output: sum(l_quantity)
| group by: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice
| mem-estimate=128.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=6 row-size=74B cardinality=600.12K
| in pipelines: 02(GETNEXT)
|
07:HASH JOIN [LEFT SEMI JOIN, PARTITIONED]
| hash predicates: o_orderkey = l_orderkey
| runtime filters: RF000[bloom] <- l_orderkey
| mem-estimate=4.75MB mem-reservation=4.75MB spill-buffer=256.00KB thread-reservation=0
| tuple-ids=2,1,0 row-size=82B cardinality=600.12K
| in pipelines: 02(GETNEXT), 14(OPEN)
|
|--14:AGGREGATE [FINALIZE]
| | output: sum:merge(l_quantity)
| | group by: l_orderkey
| | having: sum(l_quantity) > CAST(300 AS DECIMAL(5,0))
| | mem-estimate=38.74MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| | tuple-ids=4 row-size=24B cardinality=156.34K
| | in pipelines: 14(GETNEXT), 03(OPEN)
| |
| 13:EXCHANGE [HASH(l_orderkey)]
| | mem-estimate=10.08MB mem-reservation=0B thread-reservation=0
| | tuple-ids=4 row-size=24B cardinality=3.39M
| | in pipelines: 03(GETNEXT)
| |
| F04:PLAN FRAGMENT [RANDOM] hosts=3 instances=3
| Per-Host Resources: mem-estimate=139.84MB mem-reservation=42.00MB thread-reservation=2
| 04:AGGREGATE [STREAMING]
| | output: sum(l_quantity)
| | group by: l_orderkey
| | mem-estimate=51.51MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| | tuple-ids=4 row-size=24B cardinality=3.39M
| | in pipelines: 03(GETNEXT)
| |
| 03:SCAN HDFS [tpch.lineitem, RANDOM]
| HDFS partitions=1/1 files=1 size=718.94MB
| stored statistics:
| table: rows=6.00M size=718.94MB
| columns: all
| extrapolated-rows=disabled max-scan-range-rows=1.07M
| mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
| tuple-ids=3 row-size=16B cardinality=6.00M
| in pipelines: 03(GETNEXT)
|
06:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: o_custkey = c_custkey
| fk/pk conjuncts: assumed fk/pk
| runtime filters: RF002[bloom] <- c_custkey
| mem-estimate=2.00GB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=2,1,0 row-size=82B cardinality=5.76M
| in pipelines: 02(GETNEXT), 00(OPEN)
|
|--12:EXCHANGE [BROADCAST]
| | mem-estimate=10.02MB mem-reservation=0B thread-reservation=0
| | tuple-ids=0 row-size=20B cardinality=unavailable
| | in pipelines: 00(GETNEXT)
| |
| F03:PLAN FRAGMENT [RANDOM] hosts=1 instances=1
| Per-Host Resources: mem-estimate=32.09MB mem-reservation=8.00MB thread-reservation=2
| 00:SCAN HDFS [tpch_avro.customer, RANDOM]
| HDFS partitions=1/1 files=1 size=23.05MB
| stored statistics:
| table: rows=unavailable size=23.05MB
| columns: unavailable
| extrapolated-rows=disabled max-scan-range-rows=unavailable
| mem-estimate=32.00MB mem-reservation=8.00MB thread-reservation=1
| tuple-ids=0 row-size=20B cardinality=unavailable
| in pipelines: 00(GETNEXT)
|
05:HASH JOIN [INNER JOIN, PARTITIONED]
| hash predicates: l_orderkey = o_orderkey
| fk/pk conjuncts: l_orderkey = o_orderkey
| runtime filters: RF004[bloom] <- o_orderkey
| mem-estimate=37.93MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=2,1 row-size=62B cardinality=5.76M
| in pipelines: 02(GETNEXT), 01(OPEN)
|
|--11:EXCHANGE [HASH(o_orderkey)]
| | mem-estimate=10.10MB mem-reservation=0B thread-reservation=0
| | tuple-ids=1 row-size=46B cardinality=1.50M
| | in pipelines: 01(GETNEXT)
| |
| F01:PLAN FRAGMENT [RANDOM] hosts=2 instances=2
| Per-Host Resources: mem-estimate=90.59MB mem-reservation=10.00MB thread-reservation=2 runtime-filters-memory=2.00MB
| 01:SCAN HDFS [tpch.orders, RANDOM]
| HDFS partitions=1/1 files=1 size=162.56MB
| runtime filters: RF000[bloom] -> o_orderkey, RF002[bloom] -> o_custkey
| stored statistics:
| table: rows=1.50M size=162.56MB
| columns: all
| extrapolated-rows=disabled max-scan-range-rows=1.18M
| mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
| tuple-ids=1 row-size=46B cardinality=1.50M
| in pipelines: 01(GETNEXT)
|
10:EXCHANGE [HASH(l_orderkey)]
| mem-estimate=10.06MB mem-reservation=0B thread-reservation=0
| tuple-ids=2 row-size=16B cardinality=6.00M
| in pipelines: 02(GETNEXT)
|
F00:PLAN FRAGMENT [RANDOM] hosts=3 instances=3
Per-Host Resources: mem-estimate=91.23MB mem-reservation=11.00MB thread-reservation=2 runtime-filters-memory=3.00MB
02:SCAN HDFS [tpch.lineitem, RANDOM]
HDFS partitions=1/1 files=1 size=718.94MB
runtime filters: RF000[bloom] -> tpch.lineitem.l_orderkey, RF004[bloom] -> l_orderkey
stored statistics:
table: rows=6.00M size=718.94MB
columns: all
extrapolated-rows=disabled max-scan-range-rows=1.07M
mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=1
tuple-ids=2 row-size=16B cardinality=6.00M
in pipelines: 02(GETNEXT)
---- PARALLELPLANS
Max Per-Host Resource Reservation: Memory=477.75MB Threads=16
Per-Host Resource Estimates: Memory=3.27GB
Analyzed query: SELECT c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice,
sum(l_quantity) FROM tpch_avro.customer, tpch.orders, tpch.lineitem LEFT SEMI
JOIN (SELECT l_orderkey FROM tpch.lineitem GROUP BY l_orderkey HAVING
sum(l_quantity) > CAST(300 AS DECIMAL(5,0))) `$a$1` (`$c$1`) ON o_orderkey =
`$a$1`.`$c$1` WHERE TRUE AND c_custkey = o_custkey AND o_orderkey = l_orderkey
GROUP BY c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice ORDER BY
o_totalprice DESC, o_orderdate ASC LIMIT CAST(100 AS TINYINT)
F07:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1
| Per-Instance Resources: mem-estimate=4.05MB mem-reservation=4.00MB thread-reservation=1
PLAN-ROOT SINK
| output exprs: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice, sum(l_quantity)
| mem-estimate=4.00MB mem-reservation=4.00MB spill-buffer=2.00MB thread-reservation=0
|
17:MERGING-EXCHANGE [UNPARTITIONED]
| order by: o_totalprice DESC, o_orderdate ASC
| limit: 100
| mem-estimate=48.11KB mem-reservation=0B thread-reservation=0
| tuple-ids=7 row-size=74B cardinality=100
| in pipelines: 09(GETNEXT)
|
F06:PLAN FRAGMENT [HASH(c_name,c_custkey,o_orderkey,o_orderdate,o_totalprice)] hosts=3 instances=6
Per-Instance Resources: mem-estimate=138.46MB mem-reservation=34.00MB thread-reservation=1
09:TOP-N [LIMIT=100]
| order by: o_totalprice DESC, o_orderdate ASC
| mem-estimate=7.23KB mem-reservation=0B thread-reservation=0
| tuple-ids=7 row-size=74B cardinality=100
| in pipelines: 09(GETNEXT), 16(OPEN)
|
16:AGGREGATE [FINALIZE]
| output: sum:merge(l_quantity)
| group by: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice
| mem-estimate=128.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=6 row-size=74B cardinality=600.12K
| in pipelines: 16(GETNEXT), 02(OPEN)
|
15:EXCHANGE [HASH(c_name,c_custkey,o_orderkey,o_orderdate,o_totalprice)]
| mem-estimate=10.46MB mem-reservation=0B thread-reservation=0
| tuple-ids=6 row-size=74B cardinality=600.12K
| in pipelines: 02(GETNEXT)
|
F02:PLAN FRAGMENT [HASH(l_orderkey)] hosts=3 instances=6
Per-Instance Resources: mem-estimate=139.95MB mem-reservation=34.00MB thread-reservation=1
08:AGGREGATE [STREAMING]
| output: sum(l_quantity)
| group by: c_name, c_custkey, o_orderkey, o_orderdate, o_totalprice
| mem-estimate=128.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| tuple-ids=6 row-size=74B cardinality=600.12K
| in pipelines: 02(GETNEXT)
|
07:HASH JOIN [LEFT SEMI JOIN, PARTITIONED]
| hash-table-id=00
| hash predicates: o_orderkey = l_orderkey
| mem-estimate=0B mem-reservation=0B spill-buffer=128.00KB thread-reservation=0
| tuple-ids=2,1,0 row-size=82B cardinality=600.12K
| in pipelines: 02(GETNEXT), 14(OPEN)
|
|--F08:PLAN FRAGMENT [HASH(l_orderkey)] hosts=3 instances=6
| | Per-Instance Resources: mem-estimate=45.16MB mem-reservation=37.88MB thread-reservation=1 runtime-filters-memory=1.00MB
| JOIN BUILD
| | join-table-id=00 plan-id=01 cohort-id=01
| | build expressions: l_orderkey
| | runtime filters: RF000[bloom] <- l_orderkey
| | mem-estimate=2.88MB mem-reservation=2.88MB spill-buffer=128.00KB thread-reservation=0
| |
| 14:AGGREGATE [FINALIZE]
| | output: sum:merge(l_quantity)
| | group by: l_orderkey
| | having: sum(l_quantity) > CAST(300 AS DECIMAL(5,0))
| | mem-estimate=34.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| | tuple-ids=4 row-size=24B cardinality=156.34K
| | in pipelines: 14(GETNEXT), 03(OPEN)
| |
| 13:EXCHANGE [HASH(l_orderkey)]
| | mem-estimate=10.16MB mem-reservation=0B thread-reservation=0
| | tuple-ids=4 row-size=24B cardinality=4.43M
| | in pipelines: 03(GETNEXT)
| |
| F04:PLAN FRAGMENT [RANDOM] hosts=3 instances=6
| Per-Instance Resources: mem-estimate=122.66MB mem-reservation=42.00MB thread-reservation=1
| 04:AGGREGATE [STREAMING]
| | output: sum(l_quantity)
| | group by: l_orderkey
| | mem-estimate=34.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| | tuple-ids=4 row-size=24B cardinality=4.43M
| | in pipelines: 03(GETNEXT)
| |
| 03:SCAN HDFS [tpch.lineitem, RANDOM]
| HDFS partitions=1/1 files=1 size=718.94MB
| stored statistics:
| table: rows=6.00M size=718.94MB
| columns: all
| extrapolated-rows=disabled max-scan-range-rows=1.07M
| mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=0
| tuple-ids=3 row-size=16B cardinality=6.00M
| in pipelines: 03(GETNEXT)
|
06:HASH JOIN [INNER JOIN, BROADCAST]
| hash-table-id=01
| hash predicates: o_custkey = c_custkey
| fk/pk conjuncts: assumed fk/pk
| mem-estimate=0B mem-reservation=0B spill-buffer=2.00MB thread-reservation=0
| tuple-ids=2,1,0 row-size=82B cardinality=5.76M
| in pipelines: 02(GETNEXT), 00(OPEN)
|
|--F09:PLAN FRAGMENT [HASH(l_orderkey)] hosts=3 instances=3
| | Per-Instance Resources: mem-estimate=2.01GB mem-reservation=69.00MB thread-reservation=1 runtime-filters-memory=1.00MB
| JOIN BUILD
| | join-table-id=01 plan-id=02 cohort-id=01
| | build expressions: c_custkey
| | runtime filters: RF002[bloom] <- c_custkey
| | mem-estimate=2.00GB mem-reservation=68.00MB spill-buffer=2.00MB thread-reservation=0
| |
| 12:EXCHANGE [BROADCAST]
| | mem-estimate=10.02MB mem-reservation=0B thread-reservation=0
| | tuple-ids=0 row-size=20B cardinality=unavailable
| | in pipelines: 00(GETNEXT)
| |
| F03:PLAN FRAGMENT [RANDOM] hosts=1 instances=1
| Per-Instance Resources: mem-estimate=32.09MB mem-reservation=8.00MB thread-reservation=1
| 00:SCAN HDFS [tpch_avro.customer, RANDOM]
| HDFS partitions=1/1 files=1 size=23.05MB
| stored statistics:
| table: rows=unavailable size=23.05MB
| columns: unavailable
| extrapolated-rows=disabled max-scan-range-rows=unavailable
| mem-estimate=32.00MB mem-reservation=8.00MB thread-reservation=0
| tuple-ids=0 row-size=20B cardinality=unavailable
| in pipelines: 00(GETNEXT)
|
05:HASH JOIN [INNER JOIN, PARTITIONED]
| hash-table-id=02
| hash predicates: l_orderkey = o_orderkey
| fk/pk conjuncts: l_orderkey = o_orderkey
| mem-estimate=0B mem-reservation=0B spill-buffer=2.00MB thread-reservation=0
| tuple-ids=2,1 row-size=62B cardinality=5.76M
| in pipelines: 02(GETNEXT), 01(OPEN)
|
|--F10:PLAN FRAGMENT [HASH(l_orderkey)] hosts=3 instances=6
| | Per-Instance Resources: mem-estimate=46.10MB mem-reservation=36.00MB thread-reservation=1 runtime-filters-memory=2.00MB
| JOIN BUILD
| | join-table-id=02 plan-id=03 cohort-id=01
| | build expressions: o_orderkey
| | runtime filters: RF004[bloom] <- o_orderkey
| | mem-estimate=34.00MB mem-reservation=34.00MB spill-buffer=2.00MB thread-reservation=0
| |
| 11:EXCHANGE [HASH(o_orderkey)]
| | mem-estimate=10.10MB mem-reservation=0B thread-reservation=0
| | tuple-ids=1 row-size=46B cardinality=1.50M
| | in pipelines: 01(GETNEXT)
| |
| F01:PLAN FRAGMENT [RANDOM] hosts=2 instances=2
| Per-Host Shared Resources: mem-estimate=2.00MB mem-reservation=2.00MB thread-reservation=0 runtime-filters-memory=2.00MB
| Per-Instance Resources: mem-estimate=89.17MB mem-reservation=8.00MB thread-reservation=1
| 01:SCAN HDFS [tpch.orders, RANDOM]
| HDFS partitions=1/1 files=1 size=162.56MB
| runtime filters: RF000[bloom] -> o_orderkey, RF002[bloom] -> o_custkey
| stored statistics:
| table: rows=1.50M size=162.56MB
| columns: all
| extrapolated-rows=disabled max-scan-range-rows=1.18M
| mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=0
| tuple-ids=1 row-size=46B cardinality=1.50M
| in pipelines: 01(GETNEXT)
|
10:EXCHANGE [HASH(l_orderkey)]
| mem-estimate=10.12MB mem-reservation=0B thread-reservation=0
| tuple-ids=2 row-size=16B cardinality=6.00M
| in pipelines: 02(GETNEXT)
|
F00:PLAN FRAGMENT [RANDOM] hosts=3 instances=6
Per-Host Shared Resources: mem-estimate=3.00MB mem-reservation=3.00MB thread-reservation=0 runtime-filters-memory=3.00MB
Per-Instance Resources: mem-estimate=88.47MB mem-reservation=8.00MB thread-reservation=1
02:SCAN HDFS [tpch.lineitem, RANDOM]
HDFS partitions=1/1 files=1 size=718.94MB
runtime filters: RF000[bloom] -> tpch.lineitem.l_orderkey, RF004[bloom] -> l_orderkey
stored statistics:
table: rows=6.00M size=718.94MB
columns: all
extrapolated-rows=disabled max-scan-range-rows=1.07M
mem-estimate=88.00MB mem-reservation=8.00MB thread-reservation=0
tuple-ids=2 row-size=16B cardinality=6.00M
in pipelines: 02(GETNEXT)
====