mirror of
https://github.com/apache/impala.git
synced 2026-01-20 21:01:42 -05:00
0163a10332
Hive 3 changed the typical storage model for tables to split them between two directories: - hive.metastore.warehouse.dir stores managed tables (which is now defined to be only transactional tables) - hive.metastore.warehouse.external.dir stores external tables (everything that is not a transactional table) In more recent commits of Hive, there is now validation that the external tables cannot be stored in the managed directory. In order to adopt these newer versions of Hive, we need to use separate directories for external vs managed warehouses. Most of our test tables are not transactional, so they would reside in the external directory. To keep the test changes small, this uses /test-warehouse for the external directory and /test-warehouse/managed for the managed directory. Having the managed directory be a subdirectory of /test-warehouse means that the data snapshot code should not need to change. The Hive 2 configuration doesn't change as it does not have this concept. Since this changes the dataload layout, this also sets the CDH_MAJOR_VERSION to 7 for USE_CDP_HIVE=true. This means that dataload will uses a separate location for data as compared to USE_CDP_HIVE=false. That should reduce conflicts between the two configurations. Testing: - Ran exhaustive tests with USE_CDP_HIVE=false - Ran exhaustive tests with USE_CDP_HIVE=true (with current Hive version) - Verified that dataload succeeds and tests are able to run with a newer Hive version. Change-Id: I3db69f1b8ca07ae98670429954f5f7a1a359eaec Reviewed-on: http://gerrit.cloudera.org:8080/15026 Reviewed-by: Joe McDonnell <joemcdonnell@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
133 lines
3.3 KiB
Plaintext
133 lines
3.3 KiB
Plaintext
====
|
|
---- QUERY
|
|
create database $DATABASE_2 comment "For testing"
|
|
---- RESULTS
|
|
'Database has been created.'
|
|
====
|
|
---- QUERY
|
|
show databases like "$DATABASE_2"
|
|
---- RESULTS
|
|
'$DATABASE_2','For testing'
|
|
---- TYPES
|
|
STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# Test that DESCRIBE shows the proper database location
|
|
# for a newly created database (regression test for IMPALA-7439)
|
|
describe database $DATABASE_2
|
|
---- RESULTS
|
|
'$DATABASE_2','$NAMENODE/$MANAGED_WAREHOUSE_DIR/$DATABASE_2.db','For testing'
|
|
---- TYPES
|
|
string, string, string
|
|
====
|
|
---- QUERY
|
|
# Test that DESCRIBE EXTENDED also has all of the necessary info.
|
|
describe database extended $DATABASE_2
|
|
---- RESULTS
|
|
'$DATABASE_2','$NAMENODE/$MANAGED_WAREHOUSE_DIR/$DATABASE_2.db','For testing'
|
|
'Owner: ','',''
|
|
'','$USER','USER'
|
|
---- TYPES
|
|
string, string, string
|
|
====
|
|
---- QUERY
|
|
# Make sure creating a database with the same name doesn't throw an error when
|
|
# IF NOT EXISTS is specified.
|
|
create database if not exists $DATABASE_2
|
|
---- RESULTS
|
|
'Database already exists.'
|
|
====
|
|
---- QUERY
|
|
# Test dropping the database.
|
|
drop database $DATABASE_2
|
|
---- RESULTS
|
|
'Database has been dropped.'
|
|
====
|
|
---- QUERY
|
|
show databases like "$DATABASE_2"
|
|
---- RESULTS
|
|
---- TYPES
|
|
STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# Dropping a non-existent databases is ok with IF EXISTS
|
|
drop database if exists $DATABASE_2
|
|
---- RESULTS
|
|
'Database does not exist.'
|
|
====
|
|
---- QUERY
|
|
# Test DROP DATABASE ... CASCADE
|
|
create database if not exists $DATABASE_cascade
|
|
====
|
|
---- QUERY
|
|
create table if not exists $DATABASE_cascade.t1 (i int);
|
|
create table if not exists $DATABASE_cascade.t2 (i int)
|
|
partitioned by (year smallint, month smallint);
|
|
insert into $DATABASE_cascade.t2 partition (year=2015, month=8) values(1);
|
|
create external table if not exists $DATABASE_cascade.t3 like functional.alltypes
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/alltypes_external';
|
|
create view if not exists $DATABASE_cascade.v1 as
|
|
select int_col from functional.alltypes;
|
|
create function if not exists $DATABASE_cascade.f1() returns string
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/libTestUdfs.so' symbol='NoArgs';
|
|
create aggregate function if not exists $DATABASE_cascade.f2(int, string) RETURNS int
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/libTestUdas.so' UPDATE_FN='TwoArgUpdate'
|
|
---- RESULTS
|
|
'Function has been created.'
|
|
====
|
|
---- QUERY
|
|
show tables in $DATABASE_cascade
|
|
---- RESULTS
|
|
't1'
|
|
't2'
|
|
't3'
|
|
'v1'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
show functions in $DATABASE_cascade
|
|
---- RESULTS
|
|
'STRING','f1()','NATIVE','true'
|
|
---- TYPES
|
|
STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
show aggregate functions in $DATABASE_cascade
|
|
---- RESULTS
|
|
'INT','f2(INT, STRING)','NATIVE','true'
|
|
---- TYPES
|
|
STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# Should drop all tables, functions, and aggregate functions, as well
|
|
# as the database itself.
|
|
drop database $DATABASE_cascade cascade
|
|
---- RESULTS
|
|
'Database has been dropped.'
|
|
====
|
|
---- QUERY
|
|
show databases like '$DATABASE_cascade'
|
|
---- RESULTS
|
|
====
|
|
---- QUERY
|
|
# Test that DROP DATABASE ... RESTRICT executes ok.
|
|
create database if not exists $DATABASE_restrict
|
|
====
|
|
---- QUERY
|
|
show databases like '$DATABASE_restrict'
|
|
---- RESULTS
|
|
'$DATABASE_restrict',''
|
|
---- TYPES
|
|
STRING,STRING
|
|
====
|
|
---- QUERY
|
|
drop database $DATABASE_restrict restrict
|
|
---- RESULTS
|
|
'Database has been dropped.'
|
|
====
|
|
---- QUERY
|
|
show databases like '$DATABASE_restrict'
|
|
---- RESULTS
|
|
====
|