mirror of
https://github.com/apache/impala.git
synced 2026-01-01 18:00:30 -05:00
b3d8a507cb
Adds the TABLESAMPLE clause for COMPUTE STATS.
Syntax:
COMPUTE STATS <table> TABLESAMPLE SYSTEM(<number>) [REPEATABLE(<number>)]
Computes and replaces the table-level row count and total file size,
as well as all table-level column statistics. Existing partition-level
row counts are not modified.
The TABLESAMPLE clause can be used to limit the scanned data volume to
a desired percentage. When sampling, the unmodified results of the
COMPUTE STATS queries are sent to the CatalogServer. There, the stats
are extrapolated before storing them into the HMS so as not to confuse
other engines like Hive/SparkSQL which may rely on the shared HMS
fields being accurate.
Limitations
- Only works for HDFS tables
- TABLESAMPLE is not supported for COMPUTE INCREMENTAL STATS
- TABLESAMPLE requires --enable_stats_extrapolation=true
Changes to EXPLAIN
The stored statistics from the HMS are more clearly displayed under
a 'stored statistics' section. Example:
00:SCAN HDFS [functional.alltypes, RANDOM]
partitions=24/24 files=24 size=478.45KB
stored statistics:
table: rows=7300 size=478.45KB
partitions: 24/24 rows=7300
columns: all
Testing:
- added new functional tests
- core/hdfs run passed
Change-Id: I7f3e72471ac563adada4a4156033a85852b7c8b7
Reviewed-on: http://gerrit.cloudera.org:8080/8136
Reviewed-by: Alex Behm <alex.behm@cloudera.com>
Tested-by: Impala Public Jenkins
66 lines
2.5 KiB
Plaintext
66 lines
2.5 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
|
|
'Max 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[bloom] <- 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=.*
|
|
'| stored statistics:'
|
|
row_regex:.*table: rows=1500000 size=.*
|
|
'| columns: all'
|
|
'| extrapolated-rows=disabled'
|
|
'| 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[bloom] -> l_orderkey'
|
|
' stored statistics:'
|
|
row_regex:.*table: rows=6001215 size=.*
|
|
' columns: all'
|
|
' extrapolated-rows=disabled'
|
|
' 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'
|
|
====
|