mirror of
https://github.com/apache/impala.git
synced 2026-01-23 12:00:26 -05:00
b7d509d761
This adds some informational output to explain plans and sends the information to the backend. The idea is that this will make it easier to explain how Impala's pipelined execution works and also enable future work on profile analysis that can more intelligently group plan nodes. Tests: * Updated planner tests to include new output. Change-Id: I1d10eb14d997242f445e5c5fc5362d5410370721 Reviewed-on: http://gerrit.cloudera.org:8080/10848 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
74 lines
3.2 KiB
Plaintext
74 lines
3.2 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.*
|
|
''
|
|
'F02:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
|
|
'Per-Host Resources: mem-estimate=0B mem-reservation=0B thread-reservation=1'
|
|
' PLAN-ROOT SINK'
|
|
' | mem-estimate=0B mem-reservation=0B thread-reservation=0'
|
|
' |'
|
|
' 04:EXCHANGE [UNPARTITIONED]'
|
|
' mem-estimate=0B mem-reservation=0B thread-reservation=0'
|
|
' tuple-ids=0,1 row-size=454B cardinality=5757710'
|
|
' in pipelines: 00(GETNEXT)'
|
|
''
|
|
'F00:PLAN FRAGMENT [RANDOM] hosts=3 instances=3'
|
|
row_regex:.*Per-Host Resources: mem-estimate=[0-9.]*MB mem-reservation=[0-9.]*MB thread-reservation=.*
|
|
' DATASTREAM SINK [FRAGMENT=F02, EXCHANGE=04, UNPARTITIONED]'
|
|
' | mem-estimate=0B mem-reservation=0B thread-reservation=0'
|
|
' 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.]*MB mem-reservation=[0-9.]*MB spill-buffer=[0-9.]*MB thread-reservation=.*
|
|
' | tuple-ids=0,1 row-size=454B cardinality=5757710'
|
|
' | in pipelines: 00(GETNEXT), 01(OPEN)'
|
|
' |'
|
|
' |--03:EXCHANGE [BROADCAST]'
|
|
' | mem-estimate=0B mem-reservation=0B thread-reservation=0'
|
|
' | tuple-ids=1 row-size=191B 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.]*MB mem-reservation=[0-9.]*MB thread-reservation=1.*
|
|
' tuple-ids=0 row-size=263B cardinality=6001215'
|
|
' in pipelines: 00(GETNEXT)'
|
|
''
|
|
'F01:PLAN FRAGMENT [RANDOM] hosts=2 instances=2'
|
|
row_regex:.*Per-Host Resources: mem-estimate=[0-9.]*MB mem-reservation=[0-9.]*MB thread-reservation=.*
|
|
' DATASTREAM SINK [FRAGMENT=F00, EXCHANGE=03, BROADCAST]'
|
|
' | mem-estimate=0B mem-reservation=0B thread-reservation=0'
|
|
' 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.]*MB mem-reservation=[0-9.]*MB thread-reservation=.*
|
|
' tuple-ids=1 row-size=191B cardinality=1500000'
|
|
' in pipelines: 01(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
|
|
'WARNING: The following tables are missing relevant table and/or column statistics.'
|
|
'functional_avro.alltypes, functional_parquet.alltypessmall'
|
|
====
|