testdata/workloads/functional-query/queries/QueryTest/bloom_filters.test

====
---- QUERY
####################################################
# Test case 1: bloom filters with high expected FP rate get disabled.
# To trigger this path, we limit the size of the filter to a much lower value than
# required to achieve the desired FP rate.
#
# IMPALA-10112: This test is removed because high FP rate check has been removed
####################################################
#
####################################################
# Test case 2: Filter sizes change according to their NDV
####################################################
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MIN_SIZE=64KB;
with l as (select * from tpch.lineitem UNION ALL select * from tpch.lineitem)
select STRAIGHT_JOIN count(*) from (select * from tpch.lineitem a LIMIT 1) a
    join (select * from l LIMIT 125000) b on a.l_orderkey = -b.l_orderkey;
---- RESULTS
0
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(64.00 KB\).*
====
---- QUERY
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MIN_SIZE=64KB;
with l as (select * from tpch.lineitem UNION ALL select * from tpch.lineitem)
select STRAIGHT_JOIN count(*) from (select * from tpch.lineitem a LIMIT 1) a
    join (select * from l LIMIT 500000) b on a.l_orderkey = -b.l_orderkey;
---- RESULTS
0
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(256.00 KB\).*
====
---- QUERY
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MIN_SIZE=64KB;
with l as (select * from tpch.lineitem UNION ALL select * from tpch.lineitem)
select STRAIGHT_JOIN count(*) from (select * from tpch.lineitem a LIMIT 1) a
    join (select * from l LIMIT 1000000) b on a.l_orderkey = -b.l_orderkey;
---- RESULTS
0
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(512.00 KB\).*
====
---- QUERY
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MIN_SIZE=64KB;
with l as (select * from tpch.lineitem UNION ALL select * from tpch.lineitem)
select STRAIGHT_JOIN count(*) from (select * from tpch.lineitem a LIMIT 1) a
    join (select * from l LIMIT 2000000) b on a.l_orderkey = -b.l_orderkey;
---- RESULTS
0
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(1.00 MB\).*
====



---- QUERY
####################################################
# Test case 3: Filter sizes respect query options
####################################################
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MIN_SIZE=128KB;
SET RUNTIME_FILTER_MAX_SIZE=128KB;
# This query would produce a 64KB filter without setting the minimum size.
select STRAIGHT_JOIN count(*) from alltypes a join [SHUFFLE] alltypes b on a.id = b.id;
---- RESULTS
7300
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(128.00 KB\).*
====
---- QUERY
# Check that filter sizes are rounded up to power-of-two
SET RUNTIME_FILTER_MIN_SIZE=80000B;
SET RUNTIME_FILTER_MAX_SIZE=80000B;
select STRAIGHT_JOIN count(*) from alltypes a join [SHUFFLE] alltypes b on a.id = b.id;
---- RESULTS
7300
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(128.00 KB\).*
====
---- QUERY
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MAX_SIZE=64KB;
# Query would produce a 512KB filter without setting the max
with l as (select * from tpch.lineitem UNION ALL select * from tpch.lineitem)
select STRAIGHT_JOIN count(*) from (select * from tpch.lineitem a LIMIT 1) a
    join (select * from l LIMIT 1000000) b on a.l_orderkey = -b.l_orderkey;
---- RUNTIME_PROFILE
row_regex: .*Filter 0 \(64.00 KB\).*
====



---- QUERY
####################################################
# Test case 4: Filter size is >= the min buffer size that can be allocated by the
# buffer pool
####################################################
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MIN_SIZE=4KB;
SET RUNTIME_BLOOM_FILTER_SIZE=4KB;
SET DISABLE_HDFS_NUM_ROWS_ESTIMATE=1;
# The min buffer size is set to 8KB for end to end tests. This query would
# produce a 4KB filter if the min buffer size limit bound is not enforced.
select STRAIGHT_JOIN count(*) from alltypes a join [SHUFFLE] alltypes b on a.id = b.id;
---- RESULTS
7300
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(8.00 KB\).*
====
---- QUERY
####################################################
# Test case 5: RUNTIME_FILTER_ERROR_RATE affects filter size.
# This uses the first query from test case 2 and modifies the fpp to
# result in a different filter size.
####################################################
SET RUNTIME_FILTER_MODE=GLOBAL;
SET RUNTIME_FILTER_WAIT_TIME_MS=30000;
SET RUNTIME_FILTER_MIN_SIZE=64KB;
SET RUNTIME_FILTER_ERROR_RATE=0.01;
with l as (select * from tpch.lineitem UNION ALL select * from tpch.lineitem)
select STRAIGHT_JOIN count(*) from (select * from tpch.lineitem a LIMIT 1) a
    join (select * from l LIMIT 125000) b on a.l_orderkey = -b.l_orderkey;
---- RESULTS
0
---- RUNTIME_PROFILE
row_regex: .*1 of 1 Runtime Filter Published.*
row_regex: .*Filter 0 \(256.00 KB\).*
====