mirror of
https://github.com/apache/impala.git
synced 2026-01-01 09:00:42 -05:00
a2cbd2820e
The Impala CatalogService manages the caching and dissemination of cluster-wide metadata. The CatalogService combines the metadata from the Hive Metastore, the NameNode, and potentially additional sources in the future. The CatalogService uses the StateStore to broadcast metadata updates across the cluster. The CatalogService also directly handles executing metadata updates request from impalad servers (DDL requests). It exposes a Thrift interface to allow impalads to directly connect execute their DDL operations. The CatalogService has two main components - a C++ server that implements StateStore integration, Thrift service implementiation, and exporting of the debug webpage/metrics. The other main component is the Java Catalog that manages caching and updating of of all the metadata. For each StateStore heartbeat, a delta of all metadata updates is broadcast to the rest of the cluster. Some Notes On the Changes --- * The metadata is all sent as thrift structs. To do this all catalog objects (Tables/Views, Databases, UDFs) have thrift struct to represent them. These are sent with each statestore delta update. * The existing Catalog class has been seperated into two seperate sub-classes. An ImpladCatalog and a CatalogServiceCatalog. See the comments on those classes for more details. What is working: * New CatalogService created * Working with statestore delta updates and latest UDF changes * DDL performed on Node 1 is now visible on all other nodes without a "refresh". * Each DDL operation against the Catalog Service will return the catalog version that contains the change. An impalad will wait for the statestore heartbeat that contains this version before returning from the DDL comment. * All table types (Hbase, Hdfs, Views) getting their metadata propagated properly * Block location information included in CS updates and used by Impalads * Column and table stats included in CS updates and used by Impalads * Query tests are all passing Still TODO: * Directly return catalog object metadata from DDL requests * Poll the Hive Metastore to detect new/dropped/modified tables * Reorganize the FE code for the Catalog Service. I don't think we want everything in the same JAR. Change-Id: I8c61296dac28fb98bcfdc17361f4f141d3977eda Reviewed-on: http://gerrit.ent.cloudera.com:8080/601 Reviewed-by: Lenni Kuff <lskuff@cloudera.com> Tested-by: Lenni Kuff <lskuff@cloudera.com>
171 lines
4.6 KiB
Plaintext
171 lines
4.6 KiB
Plaintext
====
|
|
---- QUERY
|
|
# Test that we properly write null values to text tables.
|
|
insert overwrite table nullinsert
|
|
select NULL, "", "NULL", "\\N", NULL from alltypes limit 1
|
|
---- SETUP
|
|
RESET nullinsert
|
|
---- RESULTS
|
|
: 1
|
|
====
|
|
---- QUERY
|
|
select * from nullinsert
|
|
---- TYPES
|
|
string, string, string, string, int
|
|
---- RESULTS
|
|
'NULL','','NULL','\N',NULL
|
|
====
|
|
---- QUERY
|
|
select * from nullinsert_alt
|
|
---- TYPES
|
|
string
|
|
---- SETUP
|
|
RESET nullinsert_alt
|
|
---- RESULTS
|
|
'\N,,NULL,\\N,\N'
|
|
====
|
|
---- QUERY
|
|
# Test NULL partition keys using static partition insert. Both partitions keys are NULL.
|
|
insert overwrite table alltypesinsert
|
|
partition(year=NULL, month=NULL)
|
|
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
|
|
float_col, double_col, date_string_col, string_col, timestamp_col
|
|
from alltypessmall
|
|
where year=2009 and month=4
|
|
---- SETUP
|
|
DROP PARTITIONS alltypesinsert
|
|
---- RESULTS
|
|
year=__HIVE_DEFAULT_PARTITION__/month=__HIVE_DEFAULT_PARTITION__/: 25
|
|
====
|
|
---- QUERY
|
|
# Verify contents of alltypesinsert.
|
|
select count(*) from alltypesinsert where year is null and month is null
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
25
|
|
====
|
|
---- QUERY
|
|
# Verify that dropping NULL partitions works in the SETUP section.
|
|
select * from alltypesinsert
|
|
---- SETUP
|
|
DROP PARTITIONS alltypesinsert
|
|
---- TYPES
|
|
int, int, int, boolean, tinyint, smallint, int, bigint, float, double, string, string, timestamp
|
|
---- RESULTS
|
|
====
|
|
---- QUERY
|
|
# Test NULL partition keys using static partition insert. Year partition key is NULL.
|
|
insert overwrite table alltypesinsert
|
|
partition(year=NULL, month=10)
|
|
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
|
|
float_col, double_col, date_string_col, string_col, timestamp_col
|
|
from alltypessmall
|
|
where year=2009 and month=4
|
|
---- SETUP
|
|
DROP PARTITIONS alltypesinsert
|
|
---- RESULTS
|
|
year=__HIVE_DEFAULT_PARTITION__/month=10/: 25
|
|
====
|
|
---- QUERY
|
|
# Verify contents of alltypesinsert.
|
|
select count(*) from alltypesinsert where year is null and month=10
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
25
|
|
====
|
|
---- QUERY
|
|
# Test NULL partition keys using dynamic partition insert. Month partition key is NULL.
|
|
insert overwrite table alltypesinsert
|
|
partition(year=2008, month=NULL)
|
|
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
|
|
float_col, double_col, date_string_col, string_col, timestamp_col
|
|
from alltypessmall
|
|
where year=2009 and month=4
|
|
---- SETUP
|
|
DROP PARTITIONS alltypesinsert
|
|
---- RESULTS
|
|
year=2008/month=__HIVE_DEFAULT_PARTITION__/: 25
|
|
====
|
|
---- QUERY
|
|
# Verify contents of alltypesinsert.
|
|
select count(*) from alltypesinsert where year=2008 and month is null
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
25
|
|
====
|
|
---- QUERY
|
|
# Test NULL partition keys using dynamic partition insert.
|
|
insert overwrite table alltypesinsert
|
|
partition(year, month)
|
|
select id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
|
|
float_col, double_col, date_string_col, string_col, timestamp_col,
|
|
cast(if(bool_col, NULL, 2007) as int) as year, cast(if(tinyint_col % 3 = 0, NULL, 6) as int) as month
|
|
from alltypessmall
|
|
where year=2009 and month=4
|
|
---- RESULTS: VERIFY_IS_EQUAL_SORTED
|
|
year=2007/month=6/: 8
|
|
year=2007/month=__HIVE_DEFAULT_PARTITION__/: 5
|
|
year=__HIVE_DEFAULT_PARTITION__/month=6/: 7
|
|
year=__HIVE_DEFAULT_PARTITION__/month=__HIVE_DEFAULT_PARTITION__/: 5
|
|
====
|
|
---- QUERY
|
|
# Verify contents of each new partition in alltypesinsert.
|
|
select count(*) from alltypesinsert where year=2007 and month=6
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
8
|
|
====
|
|
---- QUERY
|
|
# Verify contents of each new partition in alltypesinsert.
|
|
select count(*) from alltypesinsert where year=2007 and month is null
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
5
|
|
====
|
|
---- QUERY
|
|
# Verify contents of each new partition in alltypesinsert.
|
|
select count(*) from alltypesinsert where year is null and month=6
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
7
|
|
====
|
|
---- QUERY
|
|
# Verify contents of each new partition in alltypesinsert.
|
|
select count(*) from alltypesinsert where year is null and month is null
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
5
|
|
====
|
|
---- QUERY
|
|
# Insert nulls and non-null values into table with
|
|
# custom table property serialization.null.format='xyz'
|
|
insert overwrite nullformat_custom
|
|
select 1, NULL, NULL, NULL, NULL union all
|
|
select 2, true, "", 1, 1 union all
|
|
select 3, false, "NULL", 2, 2 union all
|
|
select 4, false, "xyz", 3, 3 union all
|
|
select 5, false, "xyzbar", 4, 4
|
|
---- RESULTS
|
|
: 5
|
|
====
|
|
---- QUERY
|
|
# Test correct interpretation of NULLs with custom
|
|
# table property serialization.null.format='xyz'
|
|
select id, a, b, b is null, c, d from nullformat_custom order by id limit 10
|
|
---- TYPES
|
|
int, boolean, string, boolean, int, double
|
|
---- RESULTS
|
|
1,NULL,'NULL',true,NULL,NULL
|
|
2,true,'',false,1,1
|
|
3,false,'NULL',false,2,2
|
|
4,false,'NULL',true,3,3
|
|
5,false,'xyzbar',false,4,4
|
|
====
|