mirror of
https://github.com/apache/impala.git
synced 2026-01-01 00:00:20 -05:00
95ed4434f2
Refactor BufferedBlockMgr/TmpFileMgr to push more I/O logic into TmpFileMgr, in anticipation of it being shared with BufferPool. TmpFileMgr now handles: * Scratch space allocation and recycling * Read and write I/O The interface is also greatly changed so that it is built around Write() and Read() calls, abstracting away the details of temporary file allocation from clients. This means the TmpFileMgr::File class can be hidden from clients. Write error recovery: Also implement write error recovery in TmpFileMgr. If an error occurs while writing to scratch and we have multiple scratch directories, we will try one of the other directories before cancelling the query. File-level blacklisting is used to prevent excessive repeated attempts to resize a scratch file during a single query. Device-level blacklisting is not implemented because it is problematic to permanently take a scratch directory out of use. To reduce the number of error paths, all I/O errors are now handled asynchronously. Previously errors creating or extending the file were returned synchronously from WriteUnpinnedBlock(). This required modifying DiskIoMgr to create the file if not present when opened. Also set the default max_errors value in the thrift definition file, so that it is in effect for backend tests. Future Work: * Support for recycling variable-length scratch file ranges. I omitted this to avoid making the patch even large. Testing: Updated BufferedBlockMgr unit test to reflect changes in behaviour: * Scratch space is no longer permanently associated with a block, and is remapped every time a new block is written to disk . * Files are now blacklisted - updated existing tests and enable the disable blacklisting test. Added some basic testing of recycling of scratch file ranges in the TmpFileMgr unit test. I also manually tested the code in two ways. First by removing permissions for /tmp/impala-scratch and ensuring that a spilling query fails cleanly. Second, by creating a tiny ramdisk (16M) and running with two scratch directories: one on /tmp and one on the tiny ramdisk. When spilling, an out of space error is encountered for the tiny ramdisk and impala spills the remaining data (72M) to /tmp. Change-Id: I8c9c587df006d2f09d72dd636adafbd295fcdc17 Reviewed-on: http://gerrit.cloudera.org:8080/5141 Reviewed-by: Tim Armstrong <tarmstrong@cloudera.com> Tested-by: Impala Public Jenkins
259 lines
6.0 KiB
Plaintext
259 lines
6.0 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','NONE'
|
|
'PARQUET_FILE_SIZE','0'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT','0'
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES','0'
|
|
---- 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','NONE'
|
|
'PARQUET_FILE_SIZE','0'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT','0'
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES','0'
|
|
---- 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','NONE'
|
|
'PARQUET_FILE_SIZE','0'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT','0'
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES','0'
|
|
---- 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','NONE'
|
|
'PARQUET_FILE_SIZE','1610612736'
|
|
'REQUEST_POOL',''
|
|
'RESERVATION_REQUEST_TIMEOUT','0'
|
|
'RM_INITIAL_MEM','0'
|
|
'SYNC_DDL','0'
|
|
'V_CPU_CORES','0'
|
|
---- 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]'
|
|
====
|