Files
impala/testdata/workloads/functional-query/queries/QueryTest/explain-level2.test
poojanilangekar 2a4835cfba IMPALA-7367: Pack StringValue and CollectionValue slots
This change packs StringValue and CollectionValue slots to ensure
they now occupy 12 bytes instead of 16 bytes. This reduces the
memory requirements and improves the performance. Since Kudu
tuples are populated using a memcopy, 4 bytes of padding was
added to StringSlots in Kudu tables.

Testing:
Ran core tests.
Added static asserts to ensure the value sizes are as expected.
Performance tests on TPCH-40  produced 3.96% improvement.

Change-Id: I32f3b06622c087e4aa288e8db1bf4581b10d386a
Reviewed-on: http://gerrit.cloudera.org:8080/11599
Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
Reviewed-by: Tim Armstrong <tarmstrong@cloudera.com>
2018-11-19 17:27:13 +00:00

73 lines
3.3 KiB
Plaintext

====
---- QUERY
# Explain a simple hash join query.
explain
select *
from tpch.lineitem join tpch.orders on l_orderkey = o_orderkey;
---- RESULTS: VERIFY_IS_EQUAL
row_regex:.*Max Per-Host Resource Reservation: Memory=[0-9.]*MB Threads=[0-9]*.*
row_regex:.*Per-Host Resource Estimates: Memory=[0-9.]*MB.*
'Analyzed query: SELECT * FROM tpch.lineitem INNER JOIN tpch.orders ON l_orderkey'
'= o_orderkey'
''
'F02:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
row_regex:.*| Per-Host Resources: mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=1
'PLAN-ROOT SINK'
row_regex:.*| mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=0
'|'
'04:EXCHANGE [UNPARTITIONED]'
row_regex:.*| mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=0
'| tuple-ids=0,1 row-size=402B cardinality=5757710'
'| in pipelines: 00(GETNEXT)'
'|'
'F00:PLAN FRAGMENT [RANDOM] hosts=3 instances=3'
row_regex:.*Per-Host Resources: mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=.*
'02:HASH JOIN [INNER JOIN, BROADCAST]'
'| hash predicates: l_orderkey = o_orderkey'
'| fk/pk conjuncts: l_orderkey = o_orderkey'
'| runtime filters: RF000[bloom] <- o_orderkey'
row_regex:.*| mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B spill-buffer=[0-9.]*MB thread-reservation=0.*
'| tuple-ids=0,1 row-size=402B cardinality=5757710'
'| in pipelines: 00(GETNEXT), 01(OPEN)'
'|'
'|--03:EXCHANGE [BROADCAST]'
row_regex:.*| | mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=0
'| | tuple-ids=1 row-size=171B cardinality=1500000'
'| | in pipelines: 01(GETNEXT)'
'| |'
'| F01:PLAN FRAGMENT [RANDOM] hosts=2 instances=2'
row_regex:.*| Per-Host Resources: mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=.*
'| 01:SCAN HDFS [tpch.orders, RANDOM]'
row_regex:.*partitions=1/1 files=1 size=.*
'| stored statistics:'
row_regex:.*table: rows=1500000 size=.*
'| columns: all'
row_regex:.*| extrapolated-rows=disabled max-scan-range-rows=[0-9]*.*
row_regex:.*| mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=1.*
'| tuple-ids=1 row-size=171B cardinality=1500000'
'| in pipelines: 01(GETNEXT)'
'|'
'00:SCAN HDFS [tpch.lineitem, RANDOM]'
row_regex:.*partitions=1/1 files=1 size=.*
' runtime filters: RF000[bloom] -> l_orderkey'
' stored statistics:'
row_regex:.*table: rows=6001215 size=.*
' columns: all'
row_regex:.* extrapolated-rows=disabled max-scan-range-rows=[0-9]*.*
row_regex:.* mem-estimate=[0-9.]*[A-Z]*B mem-reservation=[0-9.]*[A-Z]*B thread-reservation=1.*
' tuple-ids=0 row-size=231B cardinality=6001215'
' in pipelines: 00(GETNEXT)'
====
---- QUERY
# Tests the warning about missing table stats in the explain header.
explain select count(t1.int_col), avg(t2.float_col), sum(t3.bigint_col)
from functional_avro.alltypes t1
inner join functional_parquet.alltypessmall t2 on (t1.id = t2.id)
left outer join functional_avro.alltypes t3 on (t2.id = t3.id)
where t1.month = 1 and t2.year = 2009 and t3.bool_col = false
---- RESULTS: VERIFY_IS_SUBSET
'Per-Host Resource Estimates: Memory=4.07GB'
'WARNING: The following tables are missing relevant table and/or column statistics.'
'functional_avro.alltypes, functional_parquet.alltypessmall'
====