mirror of
https://github.com/apache/impala.git
synced 2026-01-08 12:02:54 -05:00
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
174 lines
13 KiB
Plaintext
174 lines
13 KiB
Plaintext
====
|
|
---- QUERY
|
|
# Stats on a partitioned Hdfs table stored as text
|
|
show table stats alltypes
|
|
---- LABELS
|
|
YEAR, MONTH, #ROWS, #FILES, SIZE, BYTES CACHED, CACHE REPLICATION, FORMAT, INCREMENTAL STATS, LOCATION
|
|
---- RESULTS
|
|
'2009','1',310,1,'19.95KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=1'
|
|
'2009','2',280,1,'18.12KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=2'
|
|
'2009','3',310,1,'20.06KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=3'
|
|
'2009','4',300,1,'19.61KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=4'
|
|
'2009','5',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=5'
|
|
'2009','6',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=6'
|
|
'2009','7',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=7'
|
|
'2009','8',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=8'
|
|
'2009','9',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=9'
|
|
'2009','10',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=10'
|
|
'2009','11',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=11'
|
|
'2009','12',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=12'
|
|
'2010','1',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=1'
|
|
'2010','2',280,1,'18.39KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=2'
|
|
'2010','3',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=3'
|
|
'2010','4',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=4'
|
|
'2010','5',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=5'
|
|
'2010','6',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=6'
|
|
'2010','7',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=7'
|
|
'2010','8',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=8'
|
|
'2010','9',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=9'
|
|
'2010','10',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=10'
|
|
'2010','11',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=11'
|
|
'2010','12',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=12'
|
|
'Total','',7300,24,'478.45KB','0B','','','',''
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, STRING, STRING, STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# SHOW PARTITIONS returns the same results as SHOW TABLE STATS.
|
|
show partitions alltypes
|
|
---- LABELS
|
|
YEAR, MONTH, #ROWS, #FILES, SIZE, BYTES CACHED, CACHE REPLICATION, FORMAT, INCREMENTAL STATS, LOCATION
|
|
---- RESULTS
|
|
'2009','1',310,1,'19.95KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=1'
|
|
'2009','2',280,1,'18.12KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=2'
|
|
'2009','3',310,1,'20.06KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=3'
|
|
'2009','4',300,1,'19.61KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=4'
|
|
'2009','5',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=5'
|
|
'2009','6',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=6'
|
|
'2009','7',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=7'
|
|
'2009','8',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=8'
|
|
'2009','9',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=9'
|
|
'2009','10',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=10'
|
|
'2009','11',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=11'
|
|
'2009','12',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2009/month=12'
|
|
'2010','1',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=1'
|
|
'2010','2',280,1,'18.39KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=2'
|
|
'2010','3',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=3'
|
|
'2010','4',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=4'
|
|
'2010','5',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=5'
|
|
'2010','6',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=6'
|
|
'2010','7',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=7'
|
|
'2010','8',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=8'
|
|
'2010','9',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=9'
|
|
'2010','10',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=10'
|
|
'2010','11',300,1,'19.71KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=11'
|
|
'2010','12',310,1,'20.36KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypes/year=2010/month=12'
|
|
'Total','',7300,24,'478.45KB','0B','','','',''
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, STRING, STRING, STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# Stats on an unpartitioned Hdfs table stored as text
|
|
show table stats alltypesaggmultifilesnopart
|
|
---- LABELS
|
|
#ROWS, #FILES, SIZE, BYTES CACHED, CACHE REPLICATION, FORMAT, INCREMENTAL STATS, LOCATION
|
|
---- RESULTS
|
|
11000,4,'805.23KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypesaggmultifilesnopart'
|
|
---- TYPES
|
|
BIGINT, BIGINT, STRING, STRING, STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# Stats on an Hdfs with mixed partition formats
|
|
show table stats alltypesmixedformat
|
|
---- LABELS
|
|
YEAR, MONTH, #ROWS, #FILES, SIZE, BYTES CACHED, CACHE REPLICATION, FORMAT, INCREMENTAL STATS, LOCATION
|
|
---- RESULTS
|
|
'2009','1',-1,1,'19.59KB','NOT CACHED','NOT CACHED','TEXT','false','$NAMENODE/test-warehouse/alltypesmixedformat/year=2009/month=1'
|
|
'2009','2',-1,1,'21.35KB','NOT CACHED','NOT CACHED','SEQUENCE_FILE','false','$NAMENODE/test-warehouse/alltypesmixedformat/year=2009/month=2'
|
|
'2009','3',-1,1,'17.42KB','NOT CACHED','NOT CACHED','RC_FILE','false','$NAMENODE/test-warehouse/alltypesmixedformat/year=2009/month=3'
|
|
'Total','',-1,3,'58.36KB','0B','','','',''
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, STRING, STRING, STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# Stats on a table that has no statistics
|
|
show table stats functional_parquet.alltypes
|
|
---- LABELS
|
|
YEAR, MONTH, #ROWS, #FILES, SIZE, BYTES CACHED, CACHE REPLICATION, FORMAT, INCREMENTAL STATS, LOCATION
|
|
---- RESULTS
|
|
'2009','1',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=1'
|
|
'2009','2',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=2'
|
|
'2009','3',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=3'
|
|
'2009','4',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=4'
|
|
'2009','5',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=5'
|
|
'2009','6',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=6'
|
|
'2009','7',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=7'
|
|
'2009','8',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=8'
|
|
'2009','9',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=9'
|
|
'2009','10',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=10'
|
|
'2009','11',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=11'
|
|
'2009','12',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2009/month=12'
|
|
'2010','1',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=1'
|
|
'2010','2',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=2'
|
|
'2010','3',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=3'
|
|
'2010','4',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=4'
|
|
'2010','5',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=5'
|
|
'2010','6',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=6'
|
|
'2010','7',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=7'
|
|
'2010','8',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=8'
|
|
'2010','9',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=9'
|
|
'2010','10',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=10'
|
|
'2010','11',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=11'
|
|
'2010','12',-1,1,regex:.+KB,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/alltypes_parquet/year=2010/month=12'
|
|
'Total','',-1,24,regex:.+KB,'0B','','','',''
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, STRING, STRING, STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# Column stats on an HdfsTable
|
|
show column stats alltypes
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE
|
|
---- RESULTS
|
|
'id','INT',7300,-1,4,4
|
|
'bool_col','BOOLEAN',2,-1,1,1
|
|
'tinyint_col','TINYINT',10,-1,1,1
|
|
'smallint_col','SMALLINT',10,-1,2,2
|
|
'int_col','INT',10,-1,4,4
|
|
'bigint_col','BIGINT',10,-1,8,8
|
|
'float_col','FLOAT',10,-1,4,4
|
|
'double_col','DOUBLE',10,-1,8,8
|
|
'date_string_col','STRING',736,-1,8,8
|
|
'string_col','STRING',10,-1,1,1
|
|
'timestamp_col','TIMESTAMP',7300,-1,16,16
|
|
'year','INT',2,0,4,4
|
|
'month','INT',12,0,4,4
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE
|
|
====
|
|
---- QUERY
|
|
# Column column stats for a table with complex types.
|
|
show column stats functional.allcomplextypes
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE
|
|
---- RESULTS
|
|
---- RESULTS
|
|
'id','INT',-1,-1,4,4
|
|
'int_array_col','ARRAY<INT>',-1,-1,-1,-1
|
|
'array_array_col','ARRAY<ARRAY<INT>>',-1,-1,-1,-1
|
|
'map_array_col','ARRAY<MAP<STRING,INT>>',-1,-1,-1,-1
|
|
'struct_array_col','ARRAY<STRUCT<f1:BIGINT,f2:STRING>>',-1,-1,-1,-1
|
|
'int_map_col','MAP<STRING,INT>',-1,-1,-1,-1
|
|
'array_map_col','MAP<STRING,ARRAY<INT>>',-1,-1,-1,-1
|
|
'map_map_col','MAP<STRING,MAP<STRING,INT>>',-1,-1,-1,-1
|
|
'struct_map_col','MAP<STRING,STRUCT<f1:BIGINT,f2:STRING>>',-1,-1,-1,-1
|
|
'int_struct_col','STRUCT<f1:INT,f2:INT>',-1,-1,-1,-1
|
|
'complex_struct_col','STRUCT<f1:INT,f2:ARRAY<INT>,f3:MAP<STRING,INT>>',-1,-1,-1,-1
|
|
'nested_struct_col','STRUCT<f1:INT,f2:STRUCT<f11:BIGINT,f12:STRUCT<f21:BIGINT>>>',-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
|
|
'year','INT',0,0,4,4
|
|
'month','INT',0,0,4,4
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE
|
|
====
|