mirror of https://github.com/citusdata/citus.git
178 lines
7.7 KiB
Plaintext
178 lines
7.7 KiB
Plaintext
--
|
|
-- MULTI_JOIN_ORDER_ADDITIONAL
|
|
--
|
|
SET citus.next_shard_id TO 650000;
|
|
-- Set configuration to print table join order and pruned shards
|
|
SET citus.explain_distributed_queries TO off;
|
|
SET citus.log_multi_join_order TO TRUE;
|
|
SET citus.task_executor_type = 'task-tracker'; -- can't explain all queries otherwise
|
|
SET citus.shard_count to 2;
|
|
SET citus.shard_replication_factor to 1;
|
|
RESET client_min_messages;
|
|
-- Create new table definitions for use in testing in distributed planning and
|
|
-- execution functionality. Also create indexes to boost performance.
|
|
CREATE TABLE lineitem_hash (
|
|
l_orderkey bigint not null,
|
|
l_partkey integer not null,
|
|
l_suppkey integer not null,
|
|
l_linenumber integer not null,
|
|
l_quantity decimal(15, 2) not null,
|
|
l_extendedprice decimal(15, 2) not null,
|
|
l_discount decimal(15, 2) not null,
|
|
l_tax decimal(15, 2) not null,
|
|
l_returnflag char(1) not null,
|
|
l_linestatus char(1) not null,
|
|
l_shipdate date not null,
|
|
l_commitdate date not null,
|
|
l_receiptdate date not null,
|
|
l_shipinstruct char(25) not null,
|
|
l_shipmode char(10) not null,
|
|
l_comment varchar(44) not null,
|
|
PRIMARY KEY(l_orderkey, l_linenumber) );
|
|
SELECT create_distributed_table('lineitem_hash', 'l_orderkey');
|
|
create_distributed_table
|
|
--------------------------
|
|
|
|
(1 row)
|
|
|
|
CREATE INDEX lineitem_hash_time_index ON lineitem_hash (l_shipdate);
|
|
CREATE TABLE orders_hash (
|
|
o_orderkey bigint not null,
|
|
o_custkey integer not null,
|
|
o_orderstatus char(1) not null,
|
|
o_totalprice decimal(15,2) not null,
|
|
o_orderdate date not null,
|
|
o_orderpriority char(15) not null,
|
|
o_clerk char(15) not null,
|
|
o_shippriority integer not null,
|
|
o_comment varchar(79) not null,
|
|
PRIMARY KEY(o_orderkey) );
|
|
SELECT create_distributed_table('orders_hash', 'o_orderkey');
|
|
create_distributed_table
|
|
--------------------------
|
|
|
|
(1 row)
|
|
|
|
CREATE TABLE customer_hash (
|
|
c_custkey integer not null,
|
|
c_name varchar(25) not null,
|
|
c_address varchar(40) not null,
|
|
c_nationkey integer not null,
|
|
c_phone char(15) not null,
|
|
c_acctbal decimal(15,2) not null,
|
|
c_mktsegment char(10) not null,
|
|
c_comment varchar(117) not null);
|
|
SELECT create_distributed_table('customer_hash', 'c_custkey');
|
|
create_distributed_table
|
|
--------------------------
|
|
|
|
(1 row)
|
|
|
|
SET client_min_messages TO DEBUG2;
|
|
-- The following query checks that we can correctly handle self-joins
|
|
EXPLAIN SELECT l1.l_quantity FROM lineitem l1, lineitem l2
|
|
WHERE l1.l_orderkey = l2.l_orderkey AND l1.l_quantity > 5;
|
|
DEBUG: Router planner does not support append-partitioned tables.
|
|
LOG: join order: [ "lineitem" ][ local partition join "lineitem" ]
|
|
DEBUG: join prunable for intervals [1,5986] and [8997,14947]
|
|
DEBUG: join prunable for intervals [8997,14947] and [1,5986]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------
|
|
Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(2 rows)
|
|
|
|
SET client_min_messages TO LOG;
|
|
-- The following queries check that we correctly handle joins and OR clauses. In
|
|
-- particular, these queries check that we factorize out OR clauses if possible,
|
|
-- and that we default to a cartesian product otherwise.
|
|
EXPLAIN SELECT count(*) FROM lineitem, orders
|
|
WHERE (l_orderkey = o_orderkey AND l_quantity > 5)
|
|
OR (l_orderkey = o_orderkey AND l_quantity < 10);
|
|
LOG: join order: [ "lineitem" ][ local partition join "orders" ]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------------
|
|
Aggregate (cost=0.00..0.00 rows=0 width=0)
|
|
-> Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(3 rows)
|
|
|
|
EXPLAIN SELECT l_quantity FROM lineitem, orders
|
|
WHERE (l_orderkey = o_orderkey OR l_quantity > 5);
|
|
LOG: join order: [ "lineitem" ][ cartesian product "orders" ]
|
|
ERROR: cannot perform distributed planning on this query
|
|
DETAIL: Cartesian products are currently unsupported
|
|
EXPLAIN SELECT count(*) FROM orders, lineitem_hash
|
|
WHERE o_orderkey = l_orderkey;
|
|
LOG: join order: [ "orders" ][ single range partition join "lineitem_hash" ]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------------
|
|
Aggregate (cost=0.00..0.00 rows=0 width=0)
|
|
-> Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(3 rows)
|
|
|
|
-- Verify we handle local joins between two hash-partitioned tables.
|
|
EXPLAIN SELECT count(*) FROM orders_hash, lineitem_hash
|
|
WHERE o_orderkey = l_orderkey;
|
|
LOG: join order: [ "orders_hash" ][ local partition join "lineitem_hash" ]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------------
|
|
Aggregate (cost=0.00..0.00 rows=0 width=0)
|
|
-> Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(3 rows)
|
|
|
|
-- Validate that we can handle broadcast joins with hash-partitioned tables.
|
|
EXPLAIN SELECT count(*) FROM customer_hash, nation
|
|
WHERE c_nationkey = n_nationkey;
|
|
LOG: join order: [ "customer_hash" ][ reference join "nation" ]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------------
|
|
Aggregate (cost=0.00..0.00 rows=0 width=0)
|
|
-> Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(3 rows)
|
|
|
|
-- Validate that we don't use a single-partition join method for a hash
|
|
-- re-partitioned table, thus preventing a partition of just the customer table.
|
|
EXPLAIN SELECT count(*) FROM orders, lineitem, customer_append
|
|
WHERE o_custkey = l_partkey AND o_custkey = c_nationkey;
|
|
LOG: join order: [ "orders" ][ dual partition join "lineitem" ][ dual partition join "customer_append" ]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------------
|
|
Aggregate (cost=0.00..0.00 rows=0 width=0)
|
|
-> Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(3 rows)
|
|
|
|
-- Validate that we don't chose a single-partition join method with a
|
|
-- hash-partitioned base table
|
|
EXPLAIN SELECT count(*) FROM orders, customer_hash
|
|
WHERE c_custkey = o_custkey;
|
|
LOG: join order: [ "orders" ][ dual partition join "customer_hash" ]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------------
|
|
Aggregate (cost=0.00..0.00 rows=0 width=0)
|
|
-> Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(3 rows)
|
|
|
|
-- Validate that we can re-partition a hash partitioned table to join with a
|
|
-- range partitioned one.
|
|
EXPLAIN SELECT count(*) FROM orders_hash, customer_append
|
|
WHERE c_custkey = o_custkey;
|
|
LOG: join order: [ "orders_hash" ][ single range partition join "customer_append" ]
|
|
QUERY PLAN
|
|
--------------------------------------------------------------------------
|
|
Aggregate (cost=0.00..0.00 rows=0 width=0)
|
|
-> Custom Scan (Citus Task-Tracker) (cost=0.00..0.00 rows=0 width=0)
|
|
explain statements for distributed queries are not enabled
|
|
(3 rows)
|
|
|
|
-- Reset client logging level to its previous value
|
|
SET client_min_messages TO NOTICE;
|
|
DROP TABLE lineitem_hash;
|
|
DROP TABLE orders_hash;
|
|
DROP TABLE customer_hash;
|