mirror of
https://github.com/apache/impala.git
synced 2026-01-02 03:00:32 -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
134 lines
3.8 KiB
Plaintext
134 lines
3.8 KiB
Plaintext
====
|
|
---- QUERY
|
|
# test computing stats on an HBase table
|
|
create table alltypessmall_hbase like functional_hbase.alltypessmall
|
|
====
|
|
---- QUERY
|
|
compute stats alltypessmall_hbase
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 13 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
show table stats alltypessmall_hbase
|
|
---- LABELS
|
|
REGION LOCATION, START ROWKEY, EST. #ROWS, SIZE
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
regex:.+,'',regex:.+,regex:.+B
|
|
regex:.+,'1',regex:.+,regex:.+B
|
|
regex:.+,'3',regex:.+,regex:.+B
|
|
regex:.+,'5',regex:.+,regex:.+B
|
|
regex:.+,'7',regex:.+,regex:.+B
|
|
regex:.+,'9',regex:.+,regex:.+B
|
|
'Total','',regex:.+,regex:.+B
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats alltypessmall_hbase
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE
|
|
---- RESULTS
|
|
'id','INT',99,-1,4,4
|
|
'bigint_col','BIGINT',10,-1,8,8
|
|
'bool_col','BOOLEAN',2,-1,1,1
|
|
'date_string_col','STRING',12,-1,8,8
|
|
'double_col','DOUBLE',10,-1,8,8
|
|
'float_col','FLOAT',10,-1,4,4
|
|
'int_col','INT',10,-1,4,4
|
|
'month','INT',4,-1,4,4
|
|
'smallint_col','SMALLINT',10,-1,2,2
|
|
'string_col','STRING',10,-1,1,1
|
|
'timestamp_col','TIMESTAMP',100,-1,16,16
|
|
'tinyint_col','TINYINT',10,-1,1,1
|
|
'year','INT',1,-1,4,4
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE
|
|
====
|
|
---- QUERY
|
|
# test computing stats on an binary HBase table
|
|
create table alltypessmall_hbase_bin like functional_hbase.alltypessmallbinary
|
|
====
|
|
---- QUERY
|
|
compute stats alltypessmall_hbase_bin
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 13 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY: VERIFY_IS_EQUAL
|
|
show table stats alltypessmall_hbase_bin
|
|
---- LABELS
|
|
REGION LOCATION, START ROWKEY, EST. #ROWS, SIZE
|
|
---- RESULTS
|
|
regex:.+,'',regex:.+,regex:.+
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats alltypessmall_hbase_bin
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE
|
|
---- RESULTS
|
|
'id','INT',99,-1,4,4
|
|
'bigint_col','BIGINT',10,-1,8,8
|
|
'bool_col','BOOLEAN',2,-1,1,1
|
|
'date_string_col','STRING',12,-1,8,8
|
|
'double_col','DOUBLE',10,-1,8,8
|
|
'float_col','FLOAT',10,-1,4,4
|
|
'int_col','INT',10,-1,4,4
|
|
'month','INT',4,-1,4,4
|
|
'smallint_col','SMALLINT',10,-1,2,2
|
|
'string_col','STRING',10,-1,1,1
|
|
'timestamp_col','TIMESTAMP',100,-1,16,16
|
|
'tinyint_col','TINYINT',10,-1,1,1
|
|
'year','INT',1,-1,4,4
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE
|
|
====
|
|
---- QUERY
|
|
# IMP-1227: Test computing stats on an HBase table that has a
|
|
# complex-typed column that Impala does not yet support.
|
|
create table allcomplextypes_hbase like functional_hbase.allcomplextypes
|
|
====
|
|
---- QUERY
|
|
compute stats allcomplextypes_hbase
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 3 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY: VERIFY_IS_EQUAL
|
|
show table stats allcomplextypes_hbase
|
|
---- LABELS
|
|
REGION LOCATION, START ROWKEY, EST. #ROWS, SIZE
|
|
---- RESULTS
|
|
regex:.+,'',regex:.+,regex:.+
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats allcomplextypes_hbase
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE
|
|
---- RESULTS
|
|
'id','INT',0,-1,4,4
|
|
'array_array_col','ARRAY<ARRAY<INT>>',-1,-1,-1,-1
|
|
'array_map_col','MAP<STRING,ARRAY<INT>>',-1,-1,-1,-1
|
|
'complex_nested_struct_col','STRUCT<f1:INT,f2:ARRAY<STRUCT<f11:BIGINT,f12:MAP<STRING,STRUCT<f21:BIGINT>>>>>',-1,-1,-1,-1
|
|
'complex_struct_col','STRUCT<f1:INT,f2:ARRAY<INT>,f3:MAP<STRING,INT>>',-1,-1,-1,-1
|
|
'int_array_col','ARRAY<INT>',-1,-1,-1,-1
|
|
'int_map_col','MAP<STRING,INT>',-1,-1,-1,-1
|
|
'int_struct_col','STRUCT<f1:INT,f2:INT>',-1,-1,-1,-1
|
|
'map_array_col','ARRAY<MAP<STRING,INT>>',-1,-1,-1,-1
|
|
'map_map_col','MAP<STRING,MAP<STRING,INT>>',-1,-1,-1,-1
|
|
'month','INT',0,-1,4,4
|
|
'nested_struct_col','STRUCT<f1:INT,f2:STRUCT<f11:BIGINT,f12:STRUCT<f21:BIGINT>>>',-1,-1,-1,-1
|
|
'struct_array_col','ARRAY<STRUCT<f1:BIGINT,f2:STRING>>',-1,-1,-1,-1
|
|
'struct_map_col','MAP<STRING,STRUCT<f1:BIGINT,f2:STRING>>',-1,-1,-1,-1
|
|
'year','INT',0,-1,4,4
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE
|
|
====
|