mirror of
https://github.com/apache/impala.git
synced 2026-01-05 12:01:11 -05:00
a98b90bd38
Always create global BufferPool at startup using 80% of memory and limit reservations to 80% of query memory (same as BufferedBlockMgr). The query's initial reservation is computed in the planner, claimed centrally (managed by the InitialReservations class) and distributed to query operators from there. min_spillable_buffer_size and default_spillable_buffer_size query options control the buffer size that the planner selects for spilling operators. Port ExecNodes to use BufferPool: * Each ExecNode has to claim its reservation during Open() * Port Sorter to use BufferPool. * Switch from BufferedTupleStream to BufferedTupleStreamV2 * Port HashTable to use BufferPool via a Suballocator. This also makes PAGG memory consumption more efficient (avoid wasting buffers) and improve the spilling algorithm: * Allow preaggs to execute with 0 reservation - if streams and hash tables cannot be allocated, it will pass through rows. * Halve the buffer requirement for spilling aggs - avoid allocating buffers for aggregated and unaggregated streams simultaneously. * Rebuild spilled partitions instead of repartitioning (IMPALA-2708) TODO in follow-up patches: * Rename BufferedTupleStreamV2 to BufferedTupleStream * Implement max_row_size query option. Testing: * Updated tests to reflect new memory requirements Change-Id: I7fc7fe1c04e9dfb1a0c749fb56a5e0f2bf9c6c3e Reviewed-on: http://gerrit.cloudera.org:8080/5801 Reviewed-by: Tim Armstrong <tarmstrong@cloudera.com> Tested-by: Impala Public Jenkins
64 lines
2.4 KiB
Plaintext
64 lines
2.4 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
|
|
'Per-Host Resource Reservation: Memory=34.00MB'
|
|
'Per-Host Resource Estimates: Memory=476.41MB'
|
|
''
|
|
'F02:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
|
|
'| Per-Host Resources: mem-estimate=0B mem-reservation=0B'
|
|
'PLAN-ROOT SINK'
|
|
'| mem-estimate=0B mem-reservation=0B'
|
|
'|'
|
|
'04:EXCHANGE [UNPARTITIONED]'
|
|
'| mem-estimate=0B mem-reservation=0B'
|
|
'| tuple-ids=0,1 row-size=454B cardinality=5757710'
|
|
'|'
|
|
'F00:PLAN FRAGMENT [RANDOM] hosts=3 instances=3'
|
|
'Per-Host Resources: mem-estimate=388.41MB mem-reservation=34.00MB'
|
|
'02:HASH JOIN [INNER JOIN, BROADCAST]'
|
|
'| hash predicates: l_orderkey = o_orderkey'
|
|
'| fk/pk conjuncts: l_orderkey = o_orderkey'
|
|
'| runtime filters: RF000 <- o_orderkey'
|
|
'| mem-estimate=300.41MB mem-reservation=34.00MB spill-buffer=2.00MB'
|
|
'| tuple-ids=0,1 row-size=454B cardinality=5757710'
|
|
'|'
|
|
'|--03:EXCHANGE [BROADCAST]'
|
|
'| | mem-estimate=0B mem-reservation=0B'
|
|
'| | tuple-ids=1 row-size=191B cardinality=1500000'
|
|
'| |'
|
|
'| F01:PLAN FRAGMENT [RANDOM] hosts=2 instances=2'
|
|
'| Per-Host Resources: mem-estimate=88.00MB mem-reservation=0B'
|
|
'| 01:SCAN HDFS [tpch.orders, RANDOM]'
|
|
row_regex:.*partitions=1/1 files=1 size=.*
|
|
'| stats-rows=1500000 extrapolated-rows=disabled'
|
|
'| table stats: rows=1500000 size=162.56MB'
|
|
'| column stats: all'
|
|
'| mem-estimate=88.00MB mem-reservation=0B'
|
|
'| tuple-ids=1 row-size=191B cardinality=1500000'
|
|
'|'
|
|
'00:SCAN HDFS [tpch.lineitem, RANDOM]'
|
|
row_regex:.*partitions=1/1 files=1 size=.*
|
|
' runtime filters: RF000 -> l_orderkey'
|
|
' stats-rows=6001215 extrapolated-rows=disabled'
|
|
' table stats: rows=6001215 size=718.94MB'
|
|
' column stats: all'
|
|
' mem-estimate=88.00MB mem-reservation=0B'
|
|
' tuple-ids=0 row-size=263B cardinality=6001215'
|
|
====
|
|
---- 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'
|
|
====
|