jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2026-01-31 18:00:17 -05:00
Code Issues Projects Releases Wiki Activity
Files
616eb2fccecef6ff17b4e3fd48e1908aaae7726e
impala/testdata/workloads/functional-planner/queries/PlannerTest/tpch-nested.test
Thomas Tauber-Marshall 8c2bf9769a IMPALA-2805: Order conjuncts based on selectivity and cost 
Added costs to all Exprs, which estimate the relative cost of evaluating
an expression and all of its children. Costs are calculated during
analysis. For now, these costs are intended as a simple way to order
expressions from cheap to expensive, not necessarily to be a precise
reflection of running times.

In general, expressions that deal with variable length types like strings
will have higher cost than those dealing with fixed length types
like numbers and booleans. Additionally, expressions with complicated
subexpressions will have higher cost than simpler expressions.

Also added PlanNode.orderConjunctsByCost, which takes a list of Exprs and
returns a new list sorted according to an estimate of the cheapest order to
evaulate the conjuncts in, based on their cost and selectivity.

The conjuncts are sorted by repeatedly iterating over them and choosing the
conjunct that would result in the least total estimated work were it to be
applied before the remaining conjuncts. Selectivities are exponentially
backed off, and Exprs without selectivity estimates are given a reasonable
default.

Change-Id: I02279a26fbc6308ac5eb819d78345fc010469034
Reviewed-on: http://gerrit.cloudera.org:8080/2598
Reviewed-by: Thomas Tauber-Marshall <tmarshall@cloudera.com>
Tested-by: Internal Jenkins
2016-05-12 14:17:53 -07:00

2507 lines
64 KiB
Plaintext
Raw Blame History

# TPCH-Q1
# Q1 - Pricing Summary Report Query
select
l_returnflag,
l_linestatus,
sum(l_quantity) as sum_qty,
sum(l_extendedprice) as sum_base_price,
sum(l_extendedprice * (1 - l_discount)) as sum_disc_price,
sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) as sum_charge,
avg(l_quantity) as avg_qty,
avg(l_extendedprice) as avg_price,
avg(l_discount) as avg_disc,
count(*) as count_order
from
customer.c_orders.o_lineitems
where
l_shipdate <= '1998-09-02'
group by
l_returnflag,
l_linestatus
order by
l_returnflag,
l_linestatus
---- PLAN
02:SORT
| order by: l_returnflag ASC, l_linestatus ASC
|
01:AGGREGATE [FINALIZE]
| output: sum(l_quantity), sum(l_extendedprice), sum(l_extendedprice * (1 - l_discount)), sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)), avg(l_quantity), avg(l_extendedprice), avg(l_discount), count(*)
| group by: l_returnflag, l_linestatus
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate <= '1998-09-02'
---- DISTRIBUTEDPLAN
05:MERGING-EXCHANGE [UNPARTITIONED]
| order by: l_returnflag ASC, l_linestatus ASC
|
02:SORT
| order by: l_returnflag ASC, l_linestatus ASC
|
04:AGGREGATE [FINALIZE]
| output: sum:merge(l_quantity), sum:merge(l_extendedprice), sum:merge(l_extendedprice * (1 - l_discount)), sum:merge(l_extendedprice * (1 - l_discount) * (1 + l_tax)), avg:merge(l_quantity), avg:merge(l_extendedprice), avg:merge(l_discount), count:merge(*)
| group by: l_returnflag, l_linestatus
|
03:EXCHANGE [HASH(l_returnflag,l_linestatus)]
|
01:AGGREGATE [STREAMING]
| output: sum(l_quantity), sum(l_extendedprice), sum(l_extendedprice * (1 - l_discount)), sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)), avg(l_quantity), avg(l_extendedprice), avg(l_discount), count(*)
| group by: l_returnflag, l_linestatus
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate <= '1998-09-02'
====
# TPCH-Q2
# Q2 - Minimum Cost Supplier Query
select
s_acctbal,
s_name,
n_name,
p_partkey,
p_mfgr,
s_address,
s_phone,
s_comment
from
supplier s,
s.s_partsupps ps,
part p,
region r,
r.r_nations n
where
p_partkey = ps_partkey
and p_size = 15
and p_type like '%BRASS'
and s_nationkey = n_nationkey
and r_name = 'EUROPE'
and ps_supplycost = (
select
min(ps_supplycost)
from
supplier s,
s.s_partsupps ps,
region r,
r.r_nations n
where
p_partkey = ps_partkey
and s_nationkey = n_nationkey
and r_name = 'EUROPE'
)
order by
s_acctbal desc,
n_name,
s_name,
p_partkey
limit 100
---- PLAN
26:TOP-N [LIMIT=100]
| order by: s_acctbal DESC, n_name ASC, s_name ASC, p_partkey ASC
|
25:HASH JOIN [LEFT SEMI JOIN]
| hash predicates: ps_supplycost = min(ps_supplycost), p_partkey = ps_partkey
| runtime filters: RF001 <- ps_partkey
|
|--22:AGGREGATE [FINALIZE]
| | output: min(ps_supplycost)
| | group by: ps_partkey
| |
| 21:HASH JOIN [INNER JOIN]
| | hash predicates: s_nationkey = n_nationkey
| | runtime filters: RF004 <- n_nationkey
| |
| |--17:SUBPLAN
| | |
| | |--20:NESTED LOOP JOIN [CROSS JOIN]
| | | |
| | | |--18:SINGULAR ROW SRC
| | | |
| | | 19:UNNEST [r.r_nations n]
| | |
| | 16:SCAN HDFS [tpch_nested_parquet.region r]
| | partitions=1/1 files=1 size=4.18KB
| | predicates: r_name = 'EUROPE', !empty(r.r_nations)
| |
| 12:SUBPLAN
| |
| |--15:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--13:SINGULAR ROW SRC
| | |
| | 14:UNNEST [s.s_partsupps ps]
| |
| 11:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF004 -> s_nationkey
|
24:HASH JOIN [INNER JOIN]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF002 <- n_nationkey
|
|--07:SUBPLAN
| |
| |--10:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--08:SINGULAR ROW SRC
| | |
| | 09:UNNEST [r.r_nations n]
| |
| 06:SCAN HDFS [tpch_nested_parquet.region r]
| partitions=1/1 files=1 size=4.18KB
| predicates: r_name = 'EUROPE', !empty(r.r_nations)
|
23:HASH JOIN [INNER JOIN]
| hash predicates: ps_partkey = p_partkey
|
|--05:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_size = 15, p_type LIKE '%BRASS'
| runtime filters: RF001 -> p_partkey
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [s.s_partsupps ps]
|
00:SCAN HDFS [tpch_nested_parquet.supplier s]
partitions=1/1 files=1 size=111.08MB
predicates: !empty(s.s_partsupps)
runtime filters: RF002 -> s_nationkey
---- DISTRIBUTEDPLAN
33:MERGING-EXCHANGE [UNPARTITIONED]
| order by: s_acctbal DESC, n_name ASC, s_name ASC, p_partkey ASC
| limit: 100
|
26:TOP-N [LIMIT=100]
| order by: s_acctbal DESC, n_name ASC, s_name ASC, p_partkey ASC
|
25:HASH JOIN [LEFT SEMI JOIN, BROADCAST]
| hash predicates: ps_supplycost = min(ps_supplycost), p_partkey = ps_partkey
| runtime filters: RF001 <- ps_partkey
|
|--32:EXCHANGE [BROADCAST]
| |
| 31:AGGREGATE [FINALIZE]
| | output: min:merge(ps_supplycost)
| | group by: ps_partkey
| |
| 30:EXCHANGE [HASH(ps_partkey)]
| |
| 22:AGGREGATE [STREAMING]
| | output: min(ps_supplycost)
| | group by: ps_partkey
| |
| 21:HASH JOIN [INNER JOIN, BROADCAST]
| | hash predicates: s_nationkey = n_nationkey
| | runtime filters: RF004 <- n_nationkey
| |
| |--29:EXCHANGE [BROADCAST]
| | |
| | 17:SUBPLAN
| | |
| | |--20:NESTED LOOP JOIN [CROSS JOIN]
| | | |
| | | |--18:SINGULAR ROW SRC
| | | |
| | | 19:UNNEST [r.r_nations n]
| | |
| | 16:SCAN HDFS [tpch_nested_parquet.region r]
| | partitions=1/1 files=1 size=4.18KB
| | predicates: r_name = 'EUROPE', !empty(r.r_nations)
| |
| 12:SUBPLAN
| |
| |--15:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--13:SINGULAR ROW SRC
| | |
| | 14:UNNEST [s.s_partsupps ps]
| |
| 11:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF004 -> s_nationkey
|
24:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF002 <- n_nationkey
|
|--28:EXCHANGE [BROADCAST]
| |
| 07:SUBPLAN
| |
| |--10:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--08:SINGULAR ROW SRC
| | |
| | 09:UNNEST [r.r_nations n]
| |
| 06:SCAN HDFS [tpch_nested_parquet.region r]
| partitions=1/1 files=1 size=4.18KB
| predicates: r_name = 'EUROPE', !empty(r.r_nations)
|
23:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: ps_partkey = p_partkey
|
|--27:EXCHANGE [BROADCAST]
| |
| 05:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_size = 15, p_type LIKE '%BRASS'
| runtime filters: RF001 -> p_partkey
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [s.s_partsupps ps]
|
00:SCAN HDFS [tpch_nested_parquet.supplier s]
partitions=1/1 files=1 size=111.08MB
predicates: !empty(s.s_partsupps)
runtime filters: RF002 -> s_nationkey
====
# TPCH-Q3
# Q3 - Shipping Priority Query
select
o_orderkey,
sum(l_extendedprice * (1 - l_discount)) as revenue,
o_orderdate,
o_shippriority
from
customer c,
c.c_orders o,
o.o_lineitems l
where
c_mktsegment = 'BUILDING'
and o_orderdate < '1995-03-15'
and l_shipdate > '1995-03-15'
group by
o_orderkey,
o_orderdate,
o_shippriority
order by
revenue desc,
o_orderdate
limit 10
---- PLAN
10:TOP-N [LIMIT=10]
| order by: sum(l_extendedprice * (1 - l_discount)) DESC, o_orderdate ASC
|
09:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: o_orderkey, o_orderdate, o_shippriority
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: c_mktsegment = 'BUILDING', !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate < '1995-03-15'
predicates on l: l_shipdate > '1995-03-15'
---- DISTRIBUTEDPLAN
13:MERGING-EXCHANGE [UNPARTITIONED]
| order by: sum(l_extendedprice * (1 - l_discount)) DESC, o_orderdate ASC
| limit: 10
|
10:TOP-N [LIMIT=10]
| order by: sum(l_extendedprice * (1 - l_discount)) DESC, o_orderdate ASC
|
12:AGGREGATE [FINALIZE]
| output: sum:merge(l_extendedprice * (1 - l_discount))
| group by: o_orderkey, o_orderdate, o_shippriority
|
11:EXCHANGE [HASH(o_orderkey,o_orderdate,o_shippriority)]
|
09:AGGREGATE [STREAMING]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: o_orderkey, o_orderdate, o_shippriority
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: c_mktsegment = 'BUILDING', !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate < '1995-03-15'
predicates on l: l_shipdate > '1995-03-15'
====
# TPCH-Q4
# Q4 - Order Priority Checking Query
select
o_orderpriority,
count(*) as order_count
from
customer c,
c.c_orders o
where
o_orderdate >= '1993-07-01'
and o_orderdate < '1993-10-01'
and exists (
select
*
from
o.o_lineitems
where
l_commitdate < l_receiptdate
)
group by
o_orderpriority
order by
o_orderpriority
---- PLAN
10:SORT
| order by: o_orderpriority ASC
|
09:AGGREGATE [FINALIZE]
| output: count(*)
| group by: o_orderpriority
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [RIGHT SEMI JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: o_orderdate >= '1993-07-01', o_orderdate < '1993-10-01'
predicates on o_lineitems: l_commitdate < l_receiptdate
---- DISTRIBUTEDPLAN
13:MERGING-EXCHANGE [UNPARTITIONED]
| order by: o_orderpriority ASC
|
10:SORT
| order by: o_orderpriority ASC
|
12:AGGREGATE [FINALIZE]
| output: count:merge(*)
| group by: o_orderpriority
|
11:EXCHANGE [HASH(o_orderpriority)]
|
09:AGGREGATE [STREAMING]
| output: count(*)
| group by: o_orderpriority
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [RIGHT SEMI JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: o_orderdate >= '1993-07-01', o_orderdate < '1993-10-01'
predicates on o_lineitems: l_commitdate < l_receiptdate
====
# TPCH-Q5
# Q5 - Local Supplier Volume Query
select
n_name,
sum(l_extendedprice * (1 - l_discount)) as revenue
from
customer c,
c.c_orders o,
o.o_lineitems l,
supplier s,
region r,
r.r_nations n
where
l_suppkey = s_suppkey
and c_nationkey = s_nationkey
and s_nationkey = n_nationkey
and r_name = 'ASIA'
and o_orderdate >= '1994-01-01'
and o_orderdate < '1995-01-01'
group by
n_name
order by
revenue desc
---- PLAN
18:SORT
| order by: sum(l_extendedprice * (1 - l_discount)) DESC
|
17:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: n_name
|
16:HASH JOIN [INNER JOIN]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--11:SUBPLAN
| |
| |--14:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--12:SINGULAR ROW SRC
| | |
| | 13:UNNEST [r.r_nations n]
| |
| 10:SCAN HDFS [tpch_nested_parquet.region r]
| partitions=1/1 files=1 size=4.18KB
| predicates: r_name = 'ASIA', !empty(r.r_nations)
|
15:HASH JOIN [INNER JOIN]
| hash predicates: l_suppkey = s_suppkey, c_nationkey = s_nationkey
| runtime filters: RF002 <- s_nationkey
|
|--09:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate >= '1994-01-01', o_orderdate < '1995-01-01'
runtime filters: RF000 -> c.c_nationkey, RF002 -> c_nationkey
---- DISTRIBUTEDPLAN
23:MERGING-EXCHANGE [UNPARTITIONED]
| order by: sum(l_extendedprice * (1 - l_discount)) DESC
|
18:SORT
| order by: sum(l_extendedprice * (1 - l_discount)) DESC
|
22:AGGREGATE [FINALIZE]
| output: sum:merge(l_extendedprice * (1 - l_discount))
| group by: n_name
|
21:EXCHANGE [HASH(n_name)]
|
17:AGGREGATE [STREAMING]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: n_name
|
16:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--20:EXCHANGE [BROADCAST]
| |
| 11:SUBPLAN
| |
| |--14:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--12:SINGULAR ROW SRC
| | |
| | 13:UNNEST [r.r_nations n]
| |
| 10:SCAN HDFS [tpch_nested_parquet.region r]
| partitions=1/1 files=1 size=4.18KB
| predicates: r_name = 'ASIA', !empty(r.r_nations)
|
15:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_suppkey = s_suppkey, c_nationkey = s_nationkey
| runtime filters: RF002 <- s_nationkey
|
|--19:EXCHANGE [BROADCAST]
| |
| 09:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate >= '1994-01-01', o_orderdate < '1995-01-01'
runtime filters: RF000 -> c.c_nationkey, RF002 -> c_nationkey
====
# TPCH-Q6
# Q6 - Forecasting Revenue Change Query
select
sum(l_extendedprice * l_discount) as revenue
from
customer.c_orders.o_lineitems
where
l_shipdate >= '1994-01-01'
and l_shipdate < '1995-01-01'
and l_discount between 0.05 and 0.07
and l_quantity < 24
---- PLAN
01:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * l_discount)
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems]
partitions=1/1 files=4 size=554.13MB
predicates: l_discount >= 0.05, l_discount <= 0.07, l_quantity < 24, l_shipdate >= '1994-01-01', l_shipdate < '1995-01-01'
---- DISTRIBUTEDPLAN
03:AGGREGATE [FINALIZE]
| output: sum:merge(l_extendedprice * l_discount)
|
02:EXCHANGE [UNPARTITIONED]
|
01:AGGREGATE
| output: sum(l_extendedprice * l_discount)
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems]
partitions=1/1 files=4 size=554.13MB
predicates: l_discount >= 0.05, l_discount <= 0.07, l_quantity < 24, l_shipdate >= '1994-01-01', l_shipdate < '1995-01-01'
====
# TPCH-Q7
# Q7 - Volume Shipping Query
select
supp_nation,
cust_nation,
l_year,
sum(volume) as revenue
from (
select
n1.n_name as supp_nation,
n2.n_name as cust_nation,
year(l_shipdate) as l_year,
l_extendedprice * (1 - l_discount) as volume
from
customer c,
c.c_orders o,
o.o_lineitems l,
supplier s,
region.r_nations n1,
region.r_nations n2
where
s_suppkey = l_suppkey
and s_nationkey = n1.n_nationkey
and c_nationkey = n2.n_nationkey
and (
(n1.n_name = 'FRANCE' and n2.n_name = 'GERMANY')
or (n1.n_name = 'GERMANY' and n2.n_name = 'FRANCE')
)
and l_shipdate between '1995-01-01' and '1996-12-31'
) as shipping
group by
supp_nation,
cust_nation,
l_year
order by
supp_nation,
cust_nation,
l_year
---- PLAN
16:SORT
| order by: supp_nation ASC, cust_nation ASC, l_year ASC
|
15:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: n1.n_name, n2.n_name, year(l_shipdate)
|
14:HASH JOIN [INNER JOIN]
| hash predicates: c_nationkey = n2.n_nationkey
| other predicates: ((n1.n_name = 'FRANCE' AND n2.n_name = 'GERMANY') OR (n1.n_name = 'GERMANY' AND n2.n_name = 'FRANCE'))
| runtime filters: RF000 <- n2.n_nationkey
|
|--11:SCAN HDFS [tpch_nested_parquet.region.r_nations n2]
| partitions=1/1 files=1 size=4.18KB
|
13:HASH JOIN [INNER JOIN]
| hash predicates: s_nationkey = n1.n_nationkey
| runtime filters: RF001 <- n1.n_nationkey
|
|--10:SCAN HDFS [tpch_nested_parquet.region.r_nations n1]
| partitions=1/1 files=1 size=4.18KB
|
12:HASH JOIN [INNER JOIN]
| hash predicates: l_suppkey = s_suppkey
|
|--09:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| runtime filters: RF001 -> s_nationkey
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems)
predicates on l: l_shipdate >= '1995-01-01', l_shipdate <= '1996-12-31'
runtime filters: RF000 -> c_nationkey
---- DISTRIBUTEDPLAN
22:MERGING-EXCHANGE [UNPARTITIONED]
| order by: supp_nation ASC, cust_nation ASC, l_year ASC
|
16:SORT
| order by: supp_nation ASC, cust_nation ASC, l_year ASC
|
21:AGGREGATE [FINALIZE]
| output: sum:merge(volume)
| group by: supp_nation, cust_nation, l_year
|
20:EXCHANGE [HASH(supp_nation,cust_nation,l_year)]
|
15:AGGREGATE [STREAMING]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: n1.n_name, n2.n_name, year(l_shipdate)
|
14:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: c_nationkey = n2.n_nationkey
| other predicates: ((n1.n_name = 'FRANCE' AND n2.n_name = 'GERMANY') OR (n1.n_name = 'GERMANY' AND n2.n_name = 'FRANCE'))
| runtime filters: RF000 <- n2.n_nationkey
|
|--19:EXCHANGE [BROADCAST]
| |
| 11:SCAN HDFS [tpch_nested_parquet.region.r_nations n2]
| partitions=1/1 files=1 size=4.18KB
|
13:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: s_nationkey = n1.n_nationkey
| runtime filters: RF001 <- n1.n_nationkey
|
|--18:EXCHANGE [BROADCAST]
| |
| 10:SCAN HDFS [tpch_nested_parquet.region.r_nations n1]
| partitions=1/1 files=1 size=4.18KB
|
12:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_suppkey = s_suppkey
|
|--17:EXCHANGE [BROADCAST]
| |
| 09:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| runtime filters: RF001 -> s_nationkey
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems)
predicates on l: l_shipdate >= '1995-01-01', l_shipdate <= '1996-12-31'
runtime filters: RF000 -> c_nationkey
====
# TPCH-Q8
# Q8 - National Market Share Query
select
o_year,
sum(case
when nation = 'BRAZIL'
then volume
else 0
end) / sum(volume) as mkt_share
from (
select
year(o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) as volume,
n2.n_name as nation
from
customer c,
c.c_orders o,
o.o_lineitems l,
supplier s,
part p,
region r,
r.r_nations n1,
region.r_nations n2
where
p_partkey = l_partkey
and s_suppkey = l_suppkey
and c_nationkey = n1.n_nationkey
and r_name = 'AMERICA'
and s_nationkey = n2.n_nationkey
and o_orderdate between '1995-01-01' and '1996-12-31'
and p_type = 'ECONOMY ANODIZED STEEL'
) as all_nations
group by
o_year
order by
o_year
---- PLAN
22:SORT
| order by: o_year ASC
|
21:AGGREGATE [FINALIZE]
| output: sum(CASE WHEN n2.n_name = 'BRAZIL' THEN l_extendedprice * (1 - l_discount) ELSE 0 END), sum(l_extendedprice * (1 - l_discount))
| group by: year(o_orderdate)
|
20:HASH JOIN [INNER JOIN]
| hash predicates: s_nationkey = n2.n_nationkey
| runtime filters: RF000 <- n2.n_nationkey
|
|--16:SCAN HDFS [tpch_nested_parquet.region.r_nations n2]
| partitions=1/1 files=1 size=4.18KB
|
19:HASH JOIN [INNER JOIN]
| hash predicates: c_nationkey = n1.n_nationkey
| runtime filters: RF001 <- n1.n_nationkey
|
|--12:SUBPLAN
| |
| |--15:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--13:SINGULAR ROW SRC
| | |
| | 14:UNNEST [r.r_nations n1]
| |
| 11:SCAN HDFS [tpch_nested_parquet.region r]
| partitions=1/1 files=1 size=4.18KB
| predicates: r_name = 'AMERICA', !empty(r.r_nations)
|
18:HASH JOIN [INNER JOIN]
| hash predicates: l_partkey = p_partkey
|
|--10:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_type = 'ECONOMY ANODIZED STEEL'
|
17:HASH JOIN [INNER JOIN]
| hash predicates: l_suppkey = s_suppkey
|
|--09:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| runtime filters: RF000 -> s_nationkey
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate >= '1995-01-01', o_orderdate <= '1996-12-31'
runtime filters: RF001 -> c_nationkey
---- DISTRIBUTEDPLAN
29:MERGING-EXCHANGE [UNPARTITIONED]
| order by: o_year ASC
|
22:SORT
| order by: o_year ASC
|
28:AGGREGATE [FINALIZE]
| output: sum:merge(CASE WHEN nation = 'BRAZIL' THEN volume ELSE 0 END), sum:merge(volume)
| group by: o_year
|
27:EXCHANGE [HASH(o_year)]
|
21:AGGREGATE [STREAMING]
| output: sum(CASE WHEN n2.n_name = 'BRAZIL' THEN l_extendedprice * (1 - l_discount) ELSE 0 END), sum(l_extendedprice * (1 - l_discount))
| group by: year(o_orderdate)
|
20:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: s_nationkey = n2.n_nationkey
| runtime filters: RF000 <- n2.n_nationkey
|
|--26:EXCHANGE [BROADCAST]
| |
| 16:SCAN HDFS [tpch_nested_parquet.region.r_nations n2]
| partitions=1/1 files=1 size=4.18KB
|
19:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: c_nationkey = n1.n_nationkey
| runtime filters: RF001 <- n1.n_nationkey
|
|--25:EXCHANGE [BROADCAST]
| |
| 12:SUBPLAN
| |
| |--15:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--13:SINGULAR ROW SRC
| | |
| | 14:UNNEST [r.r_nations n1]
| |
| 11:SCAN HDFS [tpch_nested_parquet.region r]
| partitions=1/1 files=1 size=4.18KB
| predicates: r_name = 'AMERICA', !empty(r.r_nations)
|
18:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_partkey = p_partkey
|
|--24:EXCHANGE [BROADCAST]
| |
| 10:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_type = 'ECONOMY ANODIZED STEEL'
|
17:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_suppkey = s_suppkey
|
|--23:EXCHANGE [BROADCAST]
| |
| 09:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| runtime filters: RF000 -> s_nationkey
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate >= '1995-01-01', o_orderdate <= '1996-12-31'
runtime filters: RF001 -> c_nationkey
====
# TPCH-Q9
# Q9 - Product Type Measure Query
select
nation,
o_year,
sum(amount) as sum_profit
from(
select
n_name as nation,
year(o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) - ps_supplycost * l_quantity as amount
from
customer.c_orders o,
o.o_lineitems l,
supplier s,
s.s_partsupps ps,
part p,
region.r_nations n
where
s_suppkey = l_suppkey
and ps_partkey = l_partkey
and p_partkey = l_partkey
and s_nationkey = n_nationkey
and p_name like '%green%'
) as profit
group by
nation,
o_year
order by
nation,
o_year desc
---- PLAN
16:SORT
| order by: nation ASC, o_year DESC
|
15:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * (1 - l_discount) - ps_supplycost * l_quantity)
| group by: n_name, year(o_orderdate)
|
14:HASH JOIN [INNER JOIN]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--11:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
|
13:HASH JOIN [INNER JOIN]
| hash predicates: l_partkey = p_partkey
|
|--10:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_name LIKE '%green%'
|
12:HASH JOIN [INNER JOIN]
| hash predicates: l_partkey = ps_partkey, l_suppkey = s_suppkey
|
|--06:SUBPLAN
| |
| |--09:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--07:SINGULAR ROW SRC
| | |
| | 08:UNNEST [s.s_partsupps ps]
| |
| 05:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF000 -> s_nationkey
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [o.o_lineitems l]
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders o]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(o.o_lineitems)
---- DISTRIBUTEDPLAN
22:MERGING-EXCHANGE [UNPARTITIONED]
| order by: nation ASC, o_year DESC
|
16:SORT
| order by: nation ASC, o_year DESC
|
21:AGGREGATE [FINALIZE]
| output: sum:merge(amount)
| group by: nation, o_year
|
20:EXCHANGE [HASH(nation,o_year)]
|
15:AGGREGATE [STREAMING]
| output: sum(l_extendedprice * (1 - l_discount) - ps_supplycost * l_quantity)
| group by: n_name, year(o_orderdate)
|
14:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--19:EXCHANGE [BROADCAST]
| |
| 11:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
|
13:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_partkey = p_partkey
|
|--18:EXCHANGE [BROADCAST]
| |
| 10:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_name LIKE '%green%'
|
12:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_partkey = ps_partkey, l_suppkey = s_suppkey
|
|--17:EXCHANGE [BROADCAST]
| |
| 06:SUBPLAN
| |
| |--09:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--07:SINGULAR ROW SRC
| | |
| | 08:UNNEST [s.s_partsupps ps]
| |
| 05:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF000 -> s_nationkey
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [o.o_lineitems l]
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders o]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(o.o_lineitems)
====
# TPCH-Q10
# Q10 - Returned Item Reporting Query
# Converted select from multiple tables to joins
select
c_custkey,
c_name,
sum(l_extendedprice * (1 - l_discount)) as revenue,
c_acctbal,
n_name,
c_address,
c_phone,
c_comment
from
customer c,
c.c_orders o,
o.o_lineitems l,
region.r_nations n
where
o_orderdate >= '1993-10-01'
and o_orderdate < '1994-01-01'
and l_returnflag = 'R'
and c_nationkey = n_nationkey
group by
c_custkey,
c_name,
c_acctbal,
c_phone,
n_name,
c_address,
c_comment
order by
revenue desc
limit 20
---- PLAN
12:TOP-N [LIMIT=20]
| order by: sum(l_extendedprice * (1 - l_discount)) DESC
|
11:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: c_custkey, c_name, c_acctbal, c_phone, n_name, c_address, c_comment
|
10:HASH JOIN [INNER JOIN]
| hash predicates: c_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--09:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate >= '1993-10-01', o_orderdate < '1994-01-01'
predicates on l: l_returnflag = 'R'
runtime filters: RF000 -> c_nationkey
---- DISTRIBUTEDPLAN
16:MERGING-EXCHANGE [UNPARTITIONED]
| order by: sum(l_extendedprice * (1 - l_discount)) DESC
| limit: 20
|
12:TOP-N [LIMIT=20]
| order by: sum(l_extendedprice * (1 - l_discount)) DESC
|
15:AGGREGATE [FINALIZE]
| output: sum:merge(l_extendedprice * (1 - l_discount))
| group by: c_custkey, c_name, c_acctbal, c_phone, n_name, c_address, c_comment
|
14:EXCHANGE [HASH(c_custkey,c_name,c_acctbal,c_phone,n_name,c_address,c_comment)]
|
11:AGGREGATE [STREAMING]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: c_custkey, c_name, c_acctbal, c_phone, n_name, c_address, c_comment
|
10:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: c_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--13:EXCHANGE [BROADCAST]
| |
| 09:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
|
01:SUBPLAN
|
|--08:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--07:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 06:UNNEST [o.o_lineitems l]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: !empty(o.o_lineitems), o_orderdate >= '1993-10-01', o_orderdate < '1994-01-01'
predicates on l: l_returnflag = 'R'
runtime filters: RF000 -> c_nationkey
====
# TPCH-Q11
# Q11 - Important Stock Identification
# Modifications: query was rewritten to not have a subquery in the having clause
select
*
from (
select
ps_partkey,
sum(ps_supplycost * ps_availqty) as value
from
supplier s,
s.s_partsupps ps,
region.r_nations n
where
s_nationkey = n_nationkey
and n_name = 'GERMANY'
group by
ps_partkey
) as inner_query
where
value > (
select
sum(ps_supplycost * ps_availqty) * 0.0001
from
supplier s,
s.s_partsupps ps,
region.r_nations n
where
s_nationkey = n_nationkey
and n_name = 'GERMANY'
)
order by
value desc
---- PLAN
17:SORT
| order by: value DESC
|
16:NESTED LOOP JOIN [INNER JOIN]
| predicates: sum(ps_supplycost * ps_availqty) > sum(ps_supplycost * ps_availqty) * 0.0001
|
|--15:AGGREGATE [FINALIZE]
| | output: sum(ps_supplycost * ps_availqty)
| |
| 14:HASH JOIN [INNER JOIN]
| | hash predicates: s_nationkey = n_nationkey
| | runtime filters: RF001 <- n_nationkey
| |
| |--13:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| | partitions=1/1 files=1 size=4.18KB
| | predicates: n_name = 'GERMANY'
| |
| 09:SUBPLAN
| |
| |--12:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--10:SINGULAR ROW SRC
| | |
| | 11:UNNEST [s.s_partsupps ps]
| |
| 08:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF001 -> s_nationkey
|
07:AGGREGATE [FINALIZE]
| output: sum(ps_supplycost * ps_availqty)
| group by: ps_partkey
|
06:HASH JOIN [INNER JOIN]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--05:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
| predicates: n_name = 'GERMANY'
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [s.s_partsupps ps]
|
00:SCAN HDFS [tpch_nested_parquet.supplier s]
partitions=1/1 files=1 size=111.08MB
predicates: !empty(s.s_partsupps)
runtime filters: RF000 -> s_nationkey
---- DISTRIBUTEDPLAN
25:MERGING-EXCHANGE [UNPARTITIONED]
| order by: value DESC
|
17:SORT
| order by: value DESC
|
16:NESTED LOOP JOIN [INNER JOIN, BROADCAST]
| predicates: sum(ps_supplycost * ps_availqty) > sum(ps_supplycost * ps_availqty) * 0.0001
|
|--24:EXCHANGE [BROADCAST]
| |
| 23:AGGREGATE [FINALIZE]
| | output: sum:merge(ps_supplycost * ps_availqty)
| |
| 22:EXCHANGE [UNPARTITIONED]
| |
| 15:AGGREGATE
| | output: sum(ps_supplycost * ps_availqty)
| |
| 14:HASH JOIN [INNER JOIN, BROADCAST]
| | hash predicates: s_nationkey = n_nationkey
| | runtime filters: RF001 <- n_nationkey
| |
| |--21:EXCHANGE [BROADCAST]
| | |
| | 13:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| | partitions=1/1 files=1 size=4.18KB
| | predicates: n_name = 'GERMANY'
| |
| 09:SUBPLAN
| |
| |--12:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--10:SINGULAR ROW SRC
| | |
| | 11:UNNEST [s.s_partsupps ps]
| |
| 08:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF001 -> s_nationkey
|
20:AGGREGATE [FINALIZE]
| output: sum:merge(ps_supplycost * ps_availqty)
| group by: ps_partkey
|
19:EXCHANGE [HASH(ps_partkey)]
|
07:AGGREGATE [STREAMING]
| output: sum(ps_supplycost * ps_availqty)
| group by: ps_partkey
|
06:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--18:EXCHANGE [BROADCAST]
| |
| 05:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
| predicates: n_name = 'GERMANY'
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [s.s_partsupps ps]
|
00:SCAN HDFS [tpch_nested_parquet.supplier s]
partitions=1/1 files=1 size=111.08MB
predicates: !empty(s.s_partsupps)
runtime filters: RF000 -> s_nationkey
====
# TPCH-Q12
# Q12 - Shipping Mode and Order Priority Query
select
l_shipmode,
sum(case
when o_orderpriority = '1-URGENT'
or o_orderpriority = '2-HIGH'
then 1
else 0
end) as high_line_count,
sum(case
when o_orderpriority <> '1-URGENT'
and o_orderpriority <> '2-HIGH'
then 1
else 0
end) as low_line_count
from
customer.c_orders o,
o.o_lineitems l
where
l_shipmode in ('MAIL', 'SHIP')
and l_commitdate < l_receiptdate
and l_shipdate < l_commitdate
and l_receiptdate >= '1994-01-01'
and l_receiptdate < '1995-01-01'
group by
l_shipmode
order by
l_shipmode
---- PLAN
06:SORT
| order by: l_shipmode ASC
|
05:AGGREGATE [FINALIZE]
| output: sum(CASE WHEN o_orderpriority = '1-URGENT' OR o_orderpriority = '2-HIGH' THEN 1 ELSE 0 END), sum(CASE WHEN o_orderpriority != '1-URGENT' AND o_orderpriority != '2-HIGH' THEN 1 ELSE 0 END)
| group by: l_shipmode
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [o.o_lineitems l]
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders o]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(o.o_lineitems)
predicates on l: l_shipmode IN ('MAIL', 'SHIP'), l_commitdate < l_receiptdate, l_shipdate < l_commitdate, l_receiptdate >= '1994-01-01', l_receiptdate < '1995-01-01'
---- DISTRIBUTEDPLAN
09:MERGING-EXCHANGE [UNPARTITIONED]
| order by: l_shipmode ASC
|
06:SORT
| order by: l_shipmode ASC
|
08:AGGREGATE [FINALIZE]
| output: sum:merge(CASE WHEN o_orderpriority = '1-URGENT' OR o_orderpriority = '2-HIGH' THEN 1 ELSE 0 END), sum:merge(CASE WHEN o_orderpriority != '1-URGENT' AND o_orderpriority != '2-HIGH' THEN 1 ELSE 0 END)
| group by: l_shipmode
|
07:EXCHANGE [HASH(l_shipmode)]
|
05:AGGREGATE [STREAMING]
| output: sum(CASE WHEN o_orderpriority = '1-URGENT' OR o_orderpriority = '2-HIGH' THEN 1 ELSE 0 END), sum(CASE WHEN o_orderpriority != '1-URGENT' AND o_orderpriority != '2-HIGH' THEN 1 ELSE 0 END)
| group by: l_shipmode
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [o.o_lineitems l]
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders o]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(o.o_lineitems)
predicates on l: l_shipmode IN ('MAIL', 'SHIP'), l_commitdate < l_receiptdate, l_shipdate < l_commitdate, l_receiptdate >= '1994-01-01', l_receiptdate < '1995-01-01'
====
# TPCH-Q13
# Q13 - Customer Distribution Query
select
c_count,
count(*) as custdist
from (
select
c_custkey,
count(o_orderkey) as c_count
from
customer c left outer join c.c_orders on (
o_comment not like '%special%requests%'
)
group by
c_custkey
) as c_orders
group by
c_count
order by
custdist desc,
c_count desc
---- PLAN
07:SORT
| order by: count(*) DESC, c_count DESC
|
06:AGGREGATE [FINALIZE]
| output: count(*)
| group by: count(o_orderkey)
|
05:AGGREGATE [FINALIZE]
| output: count(o_orderkey)
| group by: c_custkey
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [RIGHT OUTER JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [c.c_orders]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates on c_orders: (NOT o_comment LIKE '%special%requests%')
---- DISTRIBUTEDPLAN
12:MERGING-EXCHANGE [UNPARTITIONED]
| order by: count(*) DESC, c_count DESC
|
07:SORT
| order by: count(*) DESC, c_count DESC
|
11:AGGREGATE [FINALIZE]
| output: count:merge(*)
| group by: c_count
|
10:EXCHANGE [HASH(c_count)]
|
06:AGGREGATE [STREAMING]
| output: count(*)
| group by: count(o_orderkey)
|
09:AGGREGATE [FINALIZE]
| output: count:merge(o_orderkey)
| group by: c_custkey
|
08:EXCHANGE [HASH(c_custkey)]
|
05:AGGREGATE [STREAMING]
| output: count(o_orderkey)
| group by: c_custkey
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [RIGHT OUTER JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [c.c_orders]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates on c_orders: (NOT o_comment LIKE '%special%requests%')
====
# TPCH-Q14
# Q14 - Promotion Effect
select
100.00 * sum(case
when p_type like 'PROMO%'
then l_extendedprice * (1 - l_discount)
else 0.0
end) / sum(l_extendedprice * (1 - l_discount)) as promo_revenue
from
customer.c_orders.o_lineitems l,
part p
where
l_partkey = p_partkey
and l_shipdate >= '1995-09-01'
and l_shipdate < '1995-10-01'
---- PLAN
03:AGGREGATE [FINALIZE]
| output: sum(CASE WHEN p_type LIKE 'PROMO%' THEN l_extendedprice * (1 - l_discount) ELSE 0.0 END), sum(l_extendedprice * (1 - l_discount))
|
02:HASH JOIN [INNER JOIN]
| hash predicates: l_partkey = p_partkey
| runtime filters: RF000 <- p_partkey
|
|--01:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate >= '1995-09-01', l_shipdate < '1995-10-01'
runtime filters: RF000 -> l_partkey
---- DISTRIBUTEDPLAN
06:AGGREGATE [FINALIZE]
| output: sum:merge(CASE WHEN p_type LIKE 'PROMO%' THEN l_extendedprice * (1 - l_discount) ELSE 0.0 END), sum:merge(l_extendedprice * (1 - l_discount))
|
05:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE
| output: sum(CASE WHEN p_type LIKE 'PROMO%' THEN l_extendedprice * (1 - l_discount) ELSE 0.0 END), sum(l_extendedprice * (1 - l_discount))
|
02:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_partkey = p_partkey
| runtime filters: RF000 <- p_partkey
|
|--04:EXCHANGE [BROADCAST]
| |
| 01:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate >= '1995-09-01', l_shipdate < '1995-10-01'
runtime filters: RF000 -> l_partkey
====
# TPCH-Q15
# Q15 - Top Supplier Query
with revenue_view as (
select
l_suppkey as supplier_no,
sum(l_extendedprice * (1 - l_discount)) as total_revenue
from
customer.c_orders.o_lineitems l
where
l_shipdate >= '1996-01-01'
and l_shipdate < '1996-04-01'
group by
l_suppkey)
select
s_suppkey,
s_name,
s_address,
s_phone,
total_revenue
from
supplier,
revenue_view
where
s_suppkey = supplier_no
and total_revenue = (
select
max(total_revenue)
from
revenue_view
)
order by
s_suppkey
---- PLAN
08:SORT
| order by: s_suppkey ASC
|
07:HASH JOIN [LEFT SEMI JOIN]
| hash predicates: sum(l_extendedprice * (1 - l_discount)) = max(total_revenue)
|
|--05:AGGREGATE [FINALIZE]
| | output: max(sum(l_extendedprice * (1 - l_discount)))
| |
| 04:AGGREGATE [FINALIZE]
| | output: sum(l_extendedprice * (1 - l_discount))
| | group by: l_suppkey
| |
| 03:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
| partitions=1/1 files=4 size=554.13MB
| predicates: l_shipdate >= '1996-01-01', l_shipdate < '1996-04-01'
|
06:HASH JOIN [INNER JOIN]
| hash predicates: l_suppkey = s_suppkey
| runtime filters: RF000 <- s_suppkey
|
|--00:SCAN HDFS [tpch_nested_parquet.supplier]
| partitions=1/1 files=1 size=111.08MB
|
02:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: l_suppkey
|
01:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate >= '1996-01-01', l_shipdate < '1996-04-01'
runtime filters: RF000 -> l.l_suppkey
---- DISTRIBUTEDPLAN
17:MERGING-EXCHANGE [UNPARTITIONED]
| order by: s_suppkey ASC
|
08:SORT
| order by: s_suppkey ASC
|
07:HASH JOIN [LEFT SEMI JOIN, BROADCAST]
| hash predicates: sum(l_extendedprice * (1 - l_discount)) = max(total_revenue)
|
|--16:EXCHANGE [BROADCAST]
| |
| 15:AGGREGATE [FINALIZE]
| | output: max:merge(total_revenue)
| |
| 14:EXCHANGE [UNPARTITIONED]
| |
| 05:AGGREGATE
| | output: max(sum(l_extendedprice * (1 - l_discount)))
| |
| 13:AGGREGATE [FINALIZE]
| | output: sum:merge(l_extendedprice * (1 - l_discount))
| | group by: l_suppkey
| |
| 12:EXCHANGE [HASH(l_suppkey)]
| |
| 04:AGGREGATE [STREAMING]
| | output: sum(l_extendedprice * (1 - l_discount))
| | group by: l_suppkey
| |
| 03:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
| partitions=1/1 files=4 size=554.13MB
| predicates: l_shipdate >= '1996-01-01', l_shipdate < '1996-04-01'
|
06:HASH JOIN [INNER JOIN, PARTITIONED]
| hash predicates: l_suppkey = s_suppkey
| runtime filters: RF000 <- s_suppkey
|
|--11:EXCHANGE [HASH(s_suppkey)]
| |
| 00:SCAN HDFS [tpch_nested_parquet.supplier]
| partitions=1/1 files=1 size=111.08MB
|
10:AGGREGATE [FINALIZE]
| output: sum:merge(l_extendedprice * (1 - l_discount))
| group by: l_suppkey
|
09:EXCHANGE [HASH(l_suppkey)]
|
02:AGGREGATE [STREAMING]
| output: sum(l_extendedprice * (1 - l_discount))
| group by: l_suppkey
|
01:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate >= '1996-01-01', l_shipdate < '1996-04-01'
runtime filters: RF000 -> l.l_suppkey
====
# TPCH-Q16
# Q16 - Parts/Supplier Relation Query
select
p_brand,
p_type,
p_size,
count(distinct s_suppkey) as supplier_cnt
from
supplier s,
s.s_partsupps ps,
part p
where
p_partkey = ps_partkey
and p_brand <> 'Brand#45'
and p_type not like 'MEDIUM POLISHED%'
and p_size in (49, 14, 23, 45, 19, 3, 36, 9)
and s_comment not like '%Customer%Complaints%'
group by
p_brand,
p_type,
p_size
order by
supplier_cnt desc,
p_brand,
p_type,
p_size
---- PLAN
09:SORT
| order by: count(s_suppkey) DESC, p_brand ASC, p_type ASC, p_size ASC
|
08:AGGREGATE [FINALIZE]
| output: count(s_suppkey)
| group by: p_brand, p_type, p_size
|
07:AGGREGATE
| group by: p_brand, p_type, p_size, s_suppkey
|
06:HASH JOIN [INNER JOIN]
| hash predicates: ps_partkey = p_partkey
|
|--05:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_size IN (49, 14, 23, 45, 19, 3, 36, 9), p_brand != 'Brand#45', NOT p_type LIKE 'MEDIUM POLISHED%'
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [s.s_partsupps ps]
|
00:SCAN HDFS [tpch_nested_parquet.supplier s]
partitions=1/1 files=1 size=111.08MB
predicates: NOT s_comment LIKE '%Customer%Complaints%', !empty(s.s_partsupps)
---- DISTRIBUTEDPLAN
13:MERGING-EXCHANGE [UNPARTITIONED]
| order by: count(s_suppkey) DESC, p_brand ASC, p_type ASC, p_size ASC
|
09:SORT
| order by: count(s_suppkey) DESC, p_brand ASC, p_type ASC, p_size ASC
|
08:AGGREGATE [FINALIZE]
| output: count(s_suppkey)
| group by: p_brand, p_type, p_size
|
12:AGGREGATE
| group by: p_brand, p_type, p_size, s_suppkey
|
11:EXCHANGE [HASH(p_brand,p_type,p_size)]
|
07:AGGREGATE [STREAMING]
| group by: p_brand, p_type, p_size, s_suppkey
|
06:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: ps_partkey = p_partkey
|
|--10:EXCHANGE [BROADCAST]
| |
| 05:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_size IN (49, 14, 23, 45, 19, 3, 36, 9), p_brand != 'Brand#45', NOT p_type LIKE 'MEDIUM POLISHED%'
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [s.s_partsupps ps]
|
00:SCAN HDFS [tpch_nested_parquet.supplier s]
partitions=1/1 files=1 size=111.08MB
predicates: NOT s_comment LIKE '%Customer%Complaints%', !empty(s.s_partsupps)
====
# TPCH-Q17
# Q17 - Small-Quantity-Order Revenue Query
select
sum(l_extendedprice) / 7.0 as avg_yearly
from
customer.c_orders.o_lineitems l,
part p
where
p_partkey = l_partkey
and p_brand = 'Brand#23'
and p_container = 'MED BOX'
and l_quantity < (
select
0.2 * avg(l_quantity)
from
customer.c_orders.o_lineitems l
where
l_partkey = p_partkey
)
---- PLAN
06:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice)
|
05:HASH JOIN [LEFT SEMI JOIN]
| hash predicates: p_partkey = l_partkey
| other join predicates: l_quantity < 0.2 * avg(l_quantity)
| runtime filters: RF000 <- l_partkey
|
|--03:AGGREGATE [FINALIZE]
| | output: avg(l_quantity)
| | group by: l_partkey
| |
| 02:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
| partitions=1/1 files=4 size=554.13MB
|
04:HASH JOIN [INNER JOIN]
| hash predicates: l_partkey = p_partkey
| runtime filters: RF001 <- p_partkey
|
|--01:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_container = 'MED BOX', p_brand = 'Brand#23'
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
runtime filters: RF000 -> l.l_partkey, RF001 -> l_partkey
---- DISTRIBUTEDPLAN
12:AGGREGATE [FINALIZE]
| output: sum:merge(l_extendedprice)
|
11:EXCHANGE [UNPARTITIONED]
|
06:AGGREGATE
| output: sum(l_extendedprice)
|
05:HASH JOIN [LEFT SEMI JOIN, BROADCAST]
| hash predicates: p_partkey = l_partkey
| other join predicates: l_quantity < 0.2 * avg(l_quantity)
| runtime filters: RF000 <- l_partkey
|
|--10:EXCHANGE [BROADCAST]
| |
| 09:AGGREGATE [FINALIZE]
| | output: avg:merge(l_quantity)
| | group by: l_partkey
| |
| 08:EXCHANGE [HASH(l_partkey)]
| |
| 03:AGGREGATE [STREAMING]
| | output: avg(l_quantity)
| | group by: l_partkey
| |
| 02:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
| partitions=1/1 files=4 size=554.13MB
|
04:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_partkey = p_partkey
| runtime filters: RF001 <- p_partkey
|
|--07:EXCHANGE [BROADCAST]
| |
| 01:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
| predicates: p_container = 'MED BOX', p_brand = 'Brand#23'
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
runtime filters: RF000 -> l.l_partkey, RF001 -> l_partkey
====
# TPCH-Q18
# Q18 - Large Value Customer Query
select
c_name,
c_custkey,
o_orderkey,
o_orderdate,
o_totalprice,
sum_quantity
from
customer c,
c.c_orders o,
(select sum(l_quantity) sum_quantity from o.o_lineitems) l
where
sum_quantity > 300
order by
o_totalprice desc,
o_orderdate
limit 100
---- PLAN
10:TOP-N [LIMIT=100]
| order by: o_totalprice DESC, o_orderdate ASC
|
01:SUBPLAN
|
|--09:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--08:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 07:AGGREGATE [FINALIZE]
| | | output: sum(l_quantity)
| | | having: sum(l_quantity) > 300
| | |
| | 06:UNNEST [o.o_lineitems]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
---- DISTRIBUTEDPLAN
11:MERGING-EXCHANGE [UNPARTITIONED]
| order by: o_totalprice DESC, o_orderdate ASC
| limit: 100
|
10:TOP-N [LIMIT=100]
| order by: o_totalprice DESC, o_orderdate ASC
|
01:SUBPLAN
|
|--09:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 04:SUBPLAN
| |
| |--08:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--05:SINGULAR ROW SRC
| | |
| | 07:AGGREGATE [FINALIZE]
| | | output: sum(l_quantity)
| | | having: sum(l_quantity) > 300
| | |
| | 06:UNNEST [o.o_lineitems]
| |
| 03:UNNEST [c.c_orders o]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
====
# TPCH-Q19
# Q19 - Discounted Revenue Query
select
sum(l_extendedprice * (1 - l_discount)) as revenue
from
customer.c_orders.o_lineitems l,
part p
where
p_partkey = l_partkey
and (
(
p_brand = 'Brand#12'
and p_container in ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG')
and l_quantity >= 1 and l_quantity <= 11
and p_size between 1 and 5
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
)
or
(
p_brand = 'Brand#23'
and p_container in ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK')
and l_quantity >= 10 and l_quantity <= 20
and p_size between 1 and 10
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
)
or
(
p_brand = 'Brand#34'
and p_container in ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG')
and l_quantity >= 20 and l_quantity <= 30
and p_size between 1 and 15
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
)
)
---- PLAN
03:AGGREGATE [FINALIZE]
| output: sum(l_extendedprice * (1 - l_discount))
|
02:HASH JOIN [INNER JOIN]
| hash predicates: l_partkey = p_partkey
| other predicates: ((p_brand = 'Brand#12' AND p_container IN ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG') AND l_quantity >= 1 AND l_quantity <= 11 AND p_size BETWEEN 1 AND 5 AND l_shipmode IN ('AIR', 'AIR REG') AND l_shipinstruct = 'DELIVER IN PERSON') OR (p_brand = 'Brand#23' AND p_container IN ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK') AND l_quantity >= 10 AND l_quantity <= 20 AND p_size BETWEEN 1 AND 10 AND l_shipmode IN ('AIR', 'AIR REG') AND l_shipinstruct = 'DELIVER IN PERSON') OR (p_brand = 'Brand#34' AND p_container IN ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG') AND l_quantity >= 20 AND l_quantity <= 30 AND p_size BETWEEN 1 AND 15 AND l_shipmode IN ('AIR', 'AIR REG') AND l_shipinstruct = 'DELIVER IN PERSON'))
| runtime filters: RF000 <- p_partkey
|
|--01:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
runtime filters: RF000 -> l_partkey
---- DISTRIBUTEDPLAN
06:AGGREGATE [FINALIZE]
| output: sum:merge(l_extendedprice * (1 - l_discount))
|
05:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE
| output: sum(l_extendedprice * (1 - l_discount))
|
02:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l_partkey = p_partkey
| other predicates: ((p_brand = 'Brand#12' AND p_container IN ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG') AND l_quantity >= 1 AND l_quantity <= 11 AND p_size BETWEEN 1 AND 5 AND l_shipmode IN ('AIR', 'AIR REG') AND l_shipinstruct = 'DELIVER IN PERSON') OR (p_brand = 'Brand#23' AND p_container IN ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK') AND l_quantity >= 10 AND l_quantity <= 20 AND p_size BETWEEN 1 AND 10 AND l_shipmode IN ('AIR', 'AIR REG') AND l_shipinstruct = 'DELIVER IN PERSON') OR (p_brand = 'Brand#34' AND p_container IN ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG') AND l_quantity >= 20 AND l_quantity <= 30 AND p_size BETWEEN 1 AND 15 AND l_shipmode IN ('AIR', 'AIR REG') AND l_shipinstruct = 'DELIVER IN PERSON'))
| runtime filters: RF000 <- p_partkey
|
|--04:EXCHANGE [BROADCAST]
| |
| 01:SCAN HDFS [tpch_nested_parquet.part p]
| partitions=1/1 files=1 size=6.30MB
|
00:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
runtime filters: RF000 -> l_partkey
====
# TPCH-Q20
# Note: Tricky rewrite from the original to avoid mixing
# correlated and uncorrelated table refs in a subquery.
select distinct
s_name,
s_address
from
supplier s,
s.s_partsupps ps,
region.r_nations n
where
ps_partkey in (
select
p_partkey
from
part p
where
p_name like 'forest%'
)
and ps_availqty > (
select
0.5 * sum(l_quantity)
from
customer.c_orders.o_lineitems l
where
l_partkey = ps_partkey
and l_suppkey = s_suppkey
and l_shipdate >= '1994-01-01'
and l_shipdate < '1995-01-01'
)
and s_nationkey = n_nationkey
and n_name = 'CANADA'
order by
s_name
---- PLAN
13:SORT
| order by: s_name ASC
|
12:AGGREGATE [FINALIZE]
| group by: s_name, s_address
|
11:HASH JOIN [RIGHT SEMI JOIN]
| hash predicates: l_suppkey = s_suppkey, l_partkey = ps_partkey
| other join predicates: ps_availqty > 0.5 * sum(l_quantity)
| runtime filters: RF000 <- s_suppkey, RF001 <- ps_partkey
|
|--10:HASH JOIN [LEFT SEMI JOIN]
| | hash predicates: ps_partkey = p_partkey
| |
| |--06:SCAN HDFS [tpch_nested_parquet.part p]
| | partitions=1/1 files=1 size=6.30MB
| | predicates: p_name LIKE 'forest%'
| |
| 09:HASH JOIN [INNER JOIN]
| | hash predicates: s_nationkey = n_nationkey
| | runtime filters: RF003 <- n_nationkey
| |
| |--05:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| | partitions=1/1 files=1 size=4.18KB
| | predicates: n_name = 'CANADA'
| |
| 01:SUBPLAN
| |
| |--04:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--02:SINGULAR ROW SRC
| | |
| | 03:UNNEST [s.s_partsupps ps]
| |
| 00:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF003 -> s_nationkey
|
08:AGGREGATE [FINALIZE]
| output: sum(l_quantity)
| group by: l_partkey, l_suppkey
|
07:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate >= '1994-01-01', l_shipdate < '1995-01-01'
runtime filters: RF000 -> l.l_suppkey, RF001 -> l.l_partkey
---- DISTRIBUTEDPLAN
21:MERGING-EXCHANGE [UNPARTITIONED]
| order by: s_name ASC
|
13:SORT
| order by: s_name ASC
|
20:AGGREGATE [FINALIZE]
| group by: s_name, s_address
|
19:EXCHANGE [HASH(s_name,s_address)]
|
12:AGGREGATE [STREAMING]
| group by: s_name, s_address
|
11:HASH JOIN [RIGHT SEMI JOIN, PARTITIONED]
| hash predicates: l_suppkey = s_suppkey, l_partkey = ps_partkey
| other join predicates: ps_availqty > 0.5 * sum(l_quantity)
| runtime filters: RF000 <- s_suppkey, RF001 <- ps_partkey
|
|--18:EXCHANGE [HASH(ps_partkey,s_suppkey)]
| |
| 10:HASH JOIN [LEFT SEMI JOIN, BROADCAST]
| | hash predicates: ps_partkey = p_partkey
| |
| |--17:EXCHANGE [BROADCAST]
| | |
| | 06:SCAN HDFS [tpch_nested_parquet.part p]
| | partitions=1/1 files=1 size=6.30MB
| | predicates: p_name LIKE 'forest%'
| |
| 09:HASH JOIN [INNER JOIN, BROADCAST]
| | hash predicates: s_nationkey = n_nationkey
| | runtime filters: RF003 <- n_nationkey
| |
| |--16:EXCHANGE [BROADCAST]
| | |
| | 05:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| | partitions=1/1 files=1 size=4.18KB
| | predicates: n_name = 'CANADA'
| |
| 01:SUBPLAN
| |
| |--04:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--02:SINGULAR ROW SRC
| | |
| | 03:UNNEST [s.s_partsupps ps]
| |
| 00:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| predicates: !empty(s.s_partsupps)
| runtime filters: RF003 -> s_nationkey
|
15:AGGREGATE [FINALIZE]
| output: sum:merge(l_quantity)
| group by: l_partkey, l_suppkey
|
14:EXCHANGE [HASH(l_partkey,l_suppkey)]
|
08:AGGREGATE [STREAMING]
| output: sum(l_quantity)
| group by: l_partkey, l_suppkey
|
07:SCAN HDFS [tpch_nested_parquet.customer.c_orders.o_lineitems l]
partitions=1/1 files=4 size=554.13MB
predicates: l_shipdate >= '1994-01-01', l_shipdate < '1995-01-01'
runtime filters: RF000 -> l.l_suppkey, RF001 -> l.l_partkey
====
# TPCH-Q21
# Q21 - Suppliers Who Kept Orders Waiting Query
select
s_name,
count(*) as numwait
from
supplier s,
customer c,
c.c_orders o,
o.o_lineitems l1,
region.r_nations n
where
s_suppkey = l1.l_suppkey
and o_orderstatus = 'F'
and l1.l_receiptdate > l1.l_commitdate
and exists (
select
*
from
o.o_lineitems l2
where
l2.l_suppkey <> l1.l_suppkey
)
and not exists (
select
*
from
o.o_lineitems l3
where
l3.l_suppkey <> l1.l_suppkey
and l3.l_receiptdate > l3.l_commitdate
)
and s_nationkey = n_nationkey
and n_name = 'SAUDI ARABIA'
group by
s_name
order by
numwait desc,
s_name
limit 100
---- PLAN
20:TOP-N [LIMIT=100]
| order by: count(*) DESC, s_name ASC
|
19:AGGREGATE [FINALIZE]
| output: count(*)
| group by: s_name
|
18:SUBPLAN
|
|--16:NESTED LOOP JOIN [RIGHT ANTI JOIN]
| | join predicates: l3.l_suppkey != l1.l_suppkey
| |
| |--14:SINGULAR ROW SRC
| |
| 15:UNNEST [o.o_lineitems l3]
|
17:HASH JOIN [INNER JOIN]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--12:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
| predicates: n_name = 'SAUDI ARABIA'
|
13:HASH JOIN [INNER JOIN]
| hash predicates: l1.l_suppkey = s_suppkey
|
|--00:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| runtime filters: RF000 -> s_nationkey
|
02:SUBPLAN
|
|--11:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--03:SINGULAR ROW SRC
| |
| 05:SUBPLAN
| |
| |--10:NESTED LOOP JOIN [LEFT SEMI JOIN]
| | | join predicates: l2.l_suppkey != l1.l_suppkey
| | |
| | |--08:UNNEST [o.o_lineitems l2]
| | |
| | 09:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--06:SINGULAR ROW SRC
| | |
| | 07:UNNEST [o.o_lineitems l1]
| |
| 04:UNNEST [c.c_orders o]
|
01:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: o_orderstatus = 'F', !empty(o.o_lineitems)
predicates on l1: l1.l_receiptdate > l1.l_commitdate
predicates on l3: l3.l_receiptdate > l3.l_commitdate
---- DISTRIBUTEDPLAN
25:MERGING-EXCHANGE [UNPARTITIONED]
| order by: count(*) DESC, s_name ASC
| limit: 100
|
20:TOP-N [LIMIT=100]
| order by: count(*) DESC, s_name ASC
|
24:AGGREGATE [FINALIZE]
| output: count:merge(*)
| group by: s_name
|
23:EXCHANGE [HASH(s_name)]
|
19:AGGREGATE [STREAMING]
| output: count(*)
| group by: s_name
|
18:SUBPLAN
|
|--16:NESTED LOOP JOIN [RIGHT ANTI JOIN]
| | join predicates: l3.l_suppkey != l1.l_suppkey
| |
| |--14:SINGULAR ROW SRC
| |
| 15:UNNEST [o.o_lineitems l3]
|
17:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: s_nationkey = n_nationkey
| runtime filters: RF000 <- n_nationkey
|
|--22:EXCHANGE [BROADCAST]
| |
| 12:SCAN HDFS [tpch_nested_parquet.region.r_nations n]
| partitions=1/1 files=1 size=4.18KB
| predicates: n_name = 'SAUDI ARABIA'
|
13:HASH JOIN [INNER JOIN, BROADCAST]
| hash predicates: l1.l_suppkey = s_suppkey
|
|--21:EXCHANGE [BROADCAST]
| |
| 00:SCAN HDFS [tpch_nested_parquet.supplier s]
| partitions=1/1 files=1 size=111.08MB
| runtime filters: RF000 -> s_nationkey
|
02:SUBPLAN
|
|--11:NESTED LOOP JOIN [CROSS JOIN]
| |
| |--03:SINGULAR ROW SRC
| |
| 05:SUBPLAN
| |
| |--10:NESTED LOOP JOIN [LEFT SEMI JOIN]
| | | join predicates: l2.l_suppkey != l1.l_suppkey
| | |
| | |--08:UNNEST [o.o_lineitems l2]
| | |
| | 09:NESTED LOOP JOIN [CROSS JOIN]
| | |
| | |--06:SINGULAR ROW SRC
| | |
| | 07:UNNEST [o.o_lineitems l1]
| |
| 04:UNNEST [c.c_orders o]
|
01:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: !empty(c.c_orders)
predicates on o: o_orderstatus = 'F', !empty(o.o_lineitems)
predicates on l1: l1.l_receiptdate > l1.l_commitdate
predicates on l3: l3.l_receiptdate > l3.l_commitdate
====
# TPCH-Q22
# Q22 - Global Sales Opportunity Query
select
cntrycode,
count(*) as numcust,
sum(c_acctbal) as totacctbal
from (
select
substr(c_phone, 1, 2) as cntrycode,
c_acctbal
from
customer c
where
substr(c_phone, 1, 2) in ('13', '31', '23', '29', '30', '18', '17')
and c_acctbal > (
select
avg(c_acctbal)
from
customer c
where
c_acctbal > 0.00
and substr(c_phone, 1, 2) in ('13', '31', '23', '29', '30', '18', '17')
)
and not exists (
select
o_orderkey
from
c.c_orders
)
) as custsale
group by
cntrycode
order by
cntrycode
---- PLAN
09:SORT
| order by: cntrycode ASC
|
08:AGGREGATE [FINALIZE]
| output: count(*), sum(c_acctbal)
| group by: substr(c_phone, 1, 2)
|
07:NESTED LOOP JOIN [INNER JOIN]
| predicates: c_acctbal > avg(c_acctbal)
|
|--06:AGGREGATE [FINALIZE]
| | output: avg(c_acctbal)
| |
| 05:SCAN HDFS [tpch_nested_parquet.customer c]
| partitions=1/1 files=4 size=554.13MB
| predicates: c_acctbal > 0.00, substr(c_phone, 1, 2) IN ('13', '31', '23', '29', '30', '18', '17')
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [RIGHT ANTI JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [c.c_orders]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: substr(c_phone, 1, 2) IN ('13', '31', '23', '29', '30', '18', '17')
---- DISTRIBUTEDPLAN
15:MERGING-EXCHANGE [UNPARTITIONED]
| order by: cntrycode ASC
|
09:SORT
| order by: cntrycode ASC
|
14:AGGREGATE [FINALIZE]
| output: count:merge(*), sum:merge(c_acctbal)
| group by: cntrycode
|
13:EXCHANGE [HASH(cntrycode)]
|
08:AGGREGATE [STREAMING]
| output: count(*), sum(c_acctbal)
| group by: substr(c_phone, 1, 2)
|
07:NESTED LOOP JOIN [INNER JOIN, BROADCAST]
| predicates: c_acctbal > avg(c_acctbal)
|
|--12:EXCHANGE [BROADCAST]
| |
| 11:AGGREGATE [FINALIZE]
| | output: avg:merge(c_acctbal)
| |
| 10:EXCHANGE [UNPARTITIONED]
| |
| 06:AGGREGATE
| | output: avg(c_acctbal)
| |
| 05:SCAN HDFS [tpch_nested_parquet.customer c]
| partitions=1/1 files=4 size=554.13MB
| predicates: c_acctbal > 0.00, substr(c_phone, 1, 2) IN ('13', '31', '23', '29', '30', '18', '17')
|
01:SUBPLAN
|
|--04:NESTED LOOP JOIN [RIGHT ANTI JOIN]
| |
| |--02:SINGULAR ROW SRC
| |
| 03:UNNEST [c.c_orders]
|
00:SCAN HDFS [tpch_nested_parquet.customer c]
partitions=1/1 files=4 size=554.13MB
predicates: substr(c_phone, 1, 2) IN ('13', '31', '23', '29', '30', '18', '17')
====
Reference in New Issue View Git Blame Copy Permalink