mirror of
https://github.com/apache/impala.git
synced 2026-01-05 21:00:54 -05:00
387bde0639
When converting TQueryOptions to a map<string,string>, we now convert
unset options to the empty string. Within TQueryOptions we have optional
options (like mt_dop or compression_codec) with no default specified. In
this case, the user was seeing 0 for numeric types and the first enum
option for enumeration types (e.g., "NONE" in the compression case).
This was confusing as the implementation handles this "null" case
differently (e.g., using SNAPPY as the default codec in the case
reported in the JIRA).
When running "set" in impala-shell, the difference is as
follows:
- BUFFER_POOL_LIMIT: [0]
+ BUFFER_POOL_LIMIT: []
- COMPRESSION_CODEC: [NONE]
+ COMPRESSION_CODEC: []
- MT_DOP: [0]
+ MT_DOP: []
- RESERVATION_REQUEST_TIMEOUT: [0]
+ RESERVATION_REQUEST_TIMEOUT: []
- SEQ_COMPRESSION_MODE: [0]
+ SEQ_COMPRESSION_MODE: []
- V_CPU_CORES: [0]
+ V_CPU_CORES: []
Obviously, the empty string is a valid value for a string-typed option, where
it will be impossible to tell the difference between "unset" and "set to empty
string." Today, there are two string-typed options: debug_string defaults to ""
and request_pool has no default. An alternative would have been to use
a special token like "_unset" or to introduce a new field in the beeswax
Thrift ConfigVariable struct. I think the empty string approach
is clearest.
The other users of this state, which I believe are HiveServer2's OpenSession()
call and HiveServer2's response to a "SET" query are affected. They
benefit from the same fix, and a new test has been added to test_hs2.py.
I did a mild refactoring in the HS2 tests to write a helper method
for the very common pattern of excecuting a query.
Testing:
* Manual testing with impala-shell
* Modified impala-shell tests to check this explicitly for one case.
* Modified HS2 test to check this as well as the SET k=v statement,
which looked otherwise untested.
Change-Id: I86bc06a58d67b099da911293202dae9e844c439b
Reviewed-on: http://gerrit.cloudera.org:8080/7886
Reviewed-by: Matthew Jacobs <mj@cloudera.com>
Tested-by: Impala Public Jenkins
294 lines
6.6 KiB
Plaintext
294 lines
6.6 KiB
Plaintext
====
|
|
---- QUERY
|
|
set
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'ABORT_ON_DEFAULT_LIMIT_EXCEEDED','0'
|
|
'ABORT_ON_ERROR','0'
|
|
'ALLOW_UNSUPPORTED_FORMATS','0'
|
|
'BATCH_SIZE','0'
|
|
'DEBUG_ACTION',''
|
|
'DEFAULT_ORDER_BY_LIMIT','-1'
|
|
'DISABLE_CACHED_READS','0'
|
|
'DISABLE_CODEGEN','0'
|
|
'DISABLE_OUTERMOST_TOPN','0'
|
|
'EXPLAIN_LEVEL','1'
|
|
'HBASE_CACHE_BLOCKS','0'
|
|
'HBASE_CACHING','0'
|
|
'MAX_ERRORS','100'
|
|
'MAX_IO_BUFFERS','0'
|
|
'MAX_SCAN_RANGE_LENGTH','0'
|
|
'MEM_LIMIT','0'
|
|
'NUM_NODES','0'
|
|
'NUM_SCANNER_THREADS','0'
|
|
'COMPRESSION_CODEC',''
|
|
'PARQUET_FILE_SIZE','0'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT',''
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES',''
|
|
---- TYPES
|
|
STRING, STRING
|
|
====
|
|
---- QUERY
|
|
set explain_level=3;
|
|
set;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'ABORT_ON_DEFAULT_LIMIT_EXCEEDED','0'
|
|
'ABORT_ON_ERROR','0'
|
|
'ALLOW_UNSUPPORTED_FORMATS','0'
|
|
'BATCH_SIZE','0'
|
|
'DEBUG_ACTION',''
|
|
'DEFAULT_ORDER_BY_LIMIT','-1'
|
|
'DISABLE_CACHED_READS','0'
|
|
'DISABLE_CODEGEN','0'
|
|
'DISABLE_OUTERMOST_TOPN','0'
|
|
'EXPLAIN_LEVEL','3'
|
|
'HBASE_CACHE_BLOCKS','0'
|
|
'HBASE_CACHING','0'
|
|
'MAX_ERRORS','100'
|
|
'MAX_IO_BUFFERS','0'
|
|
'MAX_SCAN_RANGE_LENGTH','0'
|
|
'MEM_LIMIT','0'
|
|
'NUM_NODES','0'
|
|
'NUM_SCANNER_THREADS','0'
|
|
'COMPRESSION_CODEC',''
|
|
'PARQUET_FILE_SIZE','0'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT',''
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES',''
|
|
---- TYPES
|
|
STRING, STRING
|
|
====
|
|
---- QUERY
|
|
set explain_level='0';
|
|
set;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'ABORT_ON_DEFAULT_LIMIT_EXCEEDED','0'
|
|
'ABORT_ON_ERROR','0'
|
|
'ALLOW_UNSUPPORTED_FORMATS','0'
|
|
'BATCH_SIZE','0'
|
|
'DEBUG_ACTION',''
|
|
'DEFAULT_ORDER_BY_LIMIT','-1'
|
|
'DISABLE_CACHED_READS','0'
|
|
'DISABLE_CODEGEN','0'
|
|
'DISABLE_OUTERMOST_TOPN','0'
|
|
'EXPLAIN_LEVEL','0'
|
|
'HBASE_CACHE_BLOCKS','0'
|
|
'HBASE_CACHING','0'
|
|
'MAX_ERRORS','100'
|
|
'MAX_IO_BUFFERS','0'
|
|
'MAX_SCAN_RANGE_LENGTH','0'
|
|
'MEM_LIMIT','0'
|
|
'NUM_NODES','0'
|
|
'NUM_SCANNER_THREADS','0'
|
|
'COMPRESSION_CODEC',''
|
|
'PARQUET_FILE_SIZE','0'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT',''
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES',''
|
|
---- TYPES
|
|
STRING, STRING
|
|
====
|
|
---- QUERY
|
|
# IMPALA-1906: Test that SET changes PARQUET_FILE_SIZE only if it's less than 2GB.
|
|
set parquet_file_size='1.5g';
|
|
set;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'ABORT_ON_DEFAULT_LIMIT_EXCEEDED','0'
|
|
'ABORT_ON_ERROR','0'
|
|
'ALLOW_UNSUPPORTED_FORMATS','0'
|
|
'BATCH_SIZE','0'
|
|
'DEBUG_ACTION',''
|
|
'DEFAULT_ORDER_BY_LIMIT','-1'
|
|
'DISABLE_CACHED_READS','0'
|
|
'DISABLE_CODEGEN','0'
|
|
'DISABLE_OUTERMOST_TOPN','0'
|
|
'EXPLAIN_LEVEL','1'
|
|
'HBASE_CACHE_BLOCKS','0'
|
|
'HBASE_CACHING','0'
|
|
'MAX_ERRORS','100'
|
|
'MAX_IO_BUFFERS','0'
|
|
'MAX_SCAN_RANGE_LENGTH','0'
|
|
'MEM_LIMIT','0'
|
|
'NUM_NODES','0'
|
|
'NUM_SCANNER_THREADS','0'
|
|
'COMPRESSION_CODEC',''
|
|
'PARQUET_FILE_SIZE','1610612736'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT',''
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES',''
|
|
---- TYPES
|
|
STRING, STRING
|
|
====
|
|
---- QUERY
|
|
set parquet_file_size='2g'
|
|
---- CATCH
|
|
The PARQUET_FILE_SIZE query option must be less than 2GB.
|
|
====
|
|
---- QUERY
|
|
set foo=bar
|
|
---- CATCH
|
|
Invalid query option: foo
|
|
====
|
|
---- QUERY
|
|
set parquet_compression_codec=bar
|
|
---- CATCH
|
|
Invalid compression codec: bar
|
|
====
|
|
---- QUERY
|
|
# Test that SET actually does change the mem_limit.
|
|
# First, show mem_limit is not hit.
|
|
select 1
|
|
---- RESULTS
|
|
1
|
|
====
|
|
---- QUERY
|
|
# Set mem_limit really small so that queries will fail.
|
|
set mem_limit=1;
|
|
select count(string_col) from functional.alltypestiny
|
|
---- CATCH
|
|
Memory limit exceeded
|
|
====
|
|
---- QUERY
|
|
# Set mem_limit back to unlimited and query should succeed again.
|
|
set mem_limit=0;
|
|
select count(string_col) from functional.alltypestiny
|
|
---- RESULTS
|
|
8
|
|
---- TYPES
|
|
BIGINT
|
|
====
|
|
---- QUERY
|
|
# IMPALA-3334: 'optimize_partition_key_scans' is a boolean query option
|
|
set explain_level=0;
|
|
set optimize_partition_key_scans=true;
|
|
explain select min(month), max(year), ndv(day) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'01:AGGREGATE [FINALIZE]'
|
|
'00:UNION'
|
|
' constant-operands=11'
|
|
====
|
|
---- QUERY
|
|
set explain_level=0;
|
|
set optimize_partition_key_scans=1;
|
|
explain select min(month), max(year), ndv(day) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'01:AGGREGATE [FINALIZE]'
|
|
'00:UNION'
|
|
' constant-operands=11'
|
|
====
|
|
---- QUERY
|
|
set explain_level=0;
|
|
set optimize_partition_key_scans=false;
|
|
explain select min(month), max(year), ndv(day) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'03:AGGREGATE [FINALIZE]'
|
|
'02:EXCHANGE [UNPARTITIONED]'
|
|
'01:AGGREGATE'
|
|
'00:SCAN HDFS [functional.alltypesagg]'
|
|
====
|
|
---- QUERY
|
|
set explain_level=0;
|
|
set optimize_partition_key_scans=0;
|
|
explain select min(month), max(year), ndv(day) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'03:AGGREGATE [FINALIZE]'
|
|
'02:EXCHANGE [UNPARTITIONED]'
|
|
'01:AGGREGATE'
|
|
'00:SCAN HDFS [functional.alltypesagg]'
|
|
====
|
|
---- QUERY
|
|
set explain_level=0;
|
|
set disable_streaming_preaggregations=false;
|
|
explain select count(distinct double_col) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'06:AGGREGATE [FINALIZE]'
|
|
'05:EXCHANGE [UNPARTITIONED]'
|
|
'02:AGGREGATE'
|
|
'04:AGGREGATE'
|
|
'03:EXCHANGE [HASH(double_col)]'
|
|
'01:AGGREGATE [STREAMING]'
|
|
'00:SCAN HDFS [functional.alltypesagg]'
|
|
====
|
|
---- QUERY
|
|
set explain_level=0;
|
|
set disable_streaming_preaggregations=0;
|
|
explain select count(distinct double_col) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'06:AGGREGATE [FINALIZE]'
|
|
'05:EXCHANGE [UNPARTITIONED]'
|
|
'02:AGGREGATE'
|
|
'04:AGGREGATE'
|
|
'03:EXCHANGE [HASH(double_col)]'
|
|
'01:AGGREGATE [STREAMING]'
|
|
'00:SCAN HDFS [functional.alltypesagg]'
|
|
====
|
|
---- QUERY
|
|
set explain_level=0;
|
|
set disable_streaming_preaggregations=true;
|
|
explain select count(distinct double_col) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'06:AGGREGATE [FINALIZE]'
|
|
'05:EXCHANGE [UNPARTITIONED]'
|
|
'02:AGGREGATE'
|
|
'04:AGGREGATE'
|
|
'03:EXCHANGE [HASH(double_col)]'
|
|
'01:AGGREGATE'
|
|
'00:SCAN HDFS [functional.alltypesagg]'
|
|
====
|
|
---- QUERY
|
|
set explain_level=0;
|
|
set disable_streaming_preaggregations=1;
|
|
explain select count(distinct double_col) from functional.alltypesagg;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'06:AGGREGATE [FINALIZE]'
|
|
'05:EXCHANGE [UNPARTITIONED]'
|
|
'02:AGGREGATE'
|
|
'04:AGGREGATE'
|
|
'03:EXCHANGE [HASH(double_col)]'
|
|
'01:AGGREGATE'
|
|
'00:SCAN HDFS [functional.alltypesagg]'
|
|
====
|
|
---- QUERY
|
|
# IMPALA-5591: This shouldn't throw an error.
|
|
set scratch_limit=-1;
|
|
====
|
|
---- QUERY
|
|
# Power of two max_row_size.
|
|
set max_row_size=8m;
|
|
set;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'MAX_ROW_SIZE','8388608'
|
|
---- TYPES
|
|
STRING,STRING
|
|
====
|
|
---- QUERY
|
|
# Non power of two max_row_size.
|
|
set max_row_size=12345;
|
|
set;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
'MAX_ROW_SIZE','12345'
|
|
---- TYPES
|
|
STRING,STRING
|
|
====
|
|
---- QUERY
|
|
set max_row_size=8m;
|
|
====
|
|
---- QUERY
|
|
set max_row_size=-1;
|
|
---- CATCH
|
|
Max row size must be a positive number of bytes: -1
|
|
====
|
|
---- QUERY
|
|
set max_row_size=0;
|
|
---- CATCH
|
|
Max row size must be a positive number of bytes: 0
|
|
====
|