mirror of
https://github.com/apache/impala.git
synced 2026-01-28 00:04:45 -05:00
49ac55fb69
Result spooling has been relatively stable since it was introduced, and it has several benefits described in IMPALA-8656. This patch enable result spooling (SPOOL_QUERY_RESULTS) query options by default. Furthermore, some tests need to be adjusted to account for result spooling by default. The following are the adjustment categories and list of tests that fall under such category. Change in assertions: PlannerTest#testAcidTableScans PlannerTest#testBloomFilterAssignment PlannerTest#testConstantFolding PlannerTest#testFkPkJoinDetection PlannerTest#testFkPkJoinDetectionWithHDFSNumRowsEstDisabled PlannerTest#testKuduSelectivity PlannerTest#testMaxRowSize PlannerTest#testMinMaxRuntimeFilters PlannerTest#testMinMaxRuntimeFiltersWithHDFSNumRowsEstDisabled PlannerTest#testMtDopValidation PlannerTest#testParquetFiltering PlannerTest#testParquetFilteringDisabled PlannerTest#testPartitionPruning PlannerTest#testPreaggBytesLimit PlannerTest#testResourceRequirements PlannerTest#testRuntimeFilterQueryOptions PlannerTest#testSortExprMaterialization PlannerTest#testSpillableBufferSizing PlannerTest#testTableSample PlannerTest#testTpch PlannerTest#testKuduTpch PlannerTest#testTpchNested PlannerTest#testUnion TpcdsPlannerTest custom_cluster/test_admission_controller.py::TestAdmissionController::test_dedicated_coordinator_planner_estimates custom_cluster/test_admission_controller.py::TestAdmissionController::test_memory_rejection custom_cluster/test_admission_controller.py::TestAdmissionController::test_pool_mem_limit_configs metadata/test_explain.py::TestExplain::test_explain_level2 metadata/test_explain.py::TestExplain::test_explain_level3 metadata/test_stats_extrapolation.py::TestStatsExtrapolation::test_stats_extrapolation Increase BUFFER_POOL_LIMIT: query_test/test_queries.py::TestQueries::test_analytic_fns query_test/test_runtime_filters.py::TestRuntimeRowFilters::test_row_filter_reservation query_test/test_sort.py::TestQueryFullSort::test_multiple_mem_limits_full_output query_test/test_spilling.py::TestSpillingBroadcastJoins::test_spilling_broadcast_joins query_test/test_spilling.py::TestSpillingDebugActionDimensions::test_spilling_aggs query_test/test_spilling.py::TestSpillingDebugActionDimensions::test_spilling_regression_exhaustive query_test/test_udfs.py::TestUdfExecution::test_mem_limits Increase MEM_LIMIT: query_test/test_mem_usage_scaling.py::TestExchangeMemUsage::test_exchange_mem_usage_scaling query_test/test_mem_usage_scaling.py::TestScanMemLimit::test_hdfs_scanner_thread_mem_scaling Increase MAX_ROW_SIZE: custom_cluster/test_parquet_max_page_header.py::TestParquetMaxPageHeader::test_large_page_header_config query_test/test_insert.py::TestInsertQueries::test_insert_large_string query_test/test_query_mem_limit.py::TestQueryMemLimit::test_mem_limit query_test/test_scanners.py::TestTextSplitDelimiters::test_text_split_across_buffers_delimiter query_test/test_scanners.py::TestWideRow::test_wide_row Disable result spooling to maintain assertion: custom_cluster/test_admission_controller.py::TestAdmissionController::test_set_request_pool custom_cluster/test_admission_controller.py::TestAdmissionController::test_timeout_reason_host_memory custom_cluster/test_admission_controller.py::TestAdmissionController::test_timeout_reason_pool_memory custom_cluster/test_admission_controller.py::TestAdmissionController::test_queue_reasons_memory custom_cluster/test_admission_controller.py::TestAdmissionController::test_pool_config_change_while_queued custom_cluster/test_query_retries.py::TestQueryRetries::test_retry_fetched_rows custom_cluster/test_query_retries.py::TestQueryRetries::test_retry_finished_query custom_cluster/test_scratch_disk.py::TestScratchDir::test_no_dirs custom_cluster/test_scratch_disk.py::TestScratchDir::test_non_existing_dirs custom_cluster/test_scratch_disk.py::TestScratchDir::test_non_writable_dirs query_test/test_insert.py::TestInsertQueries::test_insert_large_string (the last query only) query_test/test_kudu.py::TestKuduMemLimits::test_low_mem_limit_low_selectivity_scan query_test/test_mem_usage_scaling.py::TestScanMemLimit::test_kudu_scan_mem_usage query_test/test_queries.py::TestQueriesParquetTables::test_very_large_strings query_test/test_query_mem_limit.py::TestCodegenMemLimit::test_codegen_mem_limit shell/test_shell_client.py::TestShellClient::test_fetch_size Testing: - Pass exhaustive tests. Change-Id: I9e360c1428676d8f3fab5d95efee18aca085eba4 Reviewed-on: http://gerrit.cloudera.org:8080/16755 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
245 lines
9.4 KiB
Plaintext
245 lines
9.4 KiB
Plaintext
====
|
|
---- QUERY
|
|
# This test relies on a deterministic row order so we use "sort by (id)".
|
|
create table alltypes sort by (id) like functional_parquet.alltypes;
|
|
alter table alltypes set tblproperties("impala.enable.stats.extrapolation"="true");
|
|
insert into alltypes partition(year, month)
|
|
select * from functional_parquet.alltypes where year = 2009;
|
|
====
|
|
---- QUERY
|
|
explain select id from alltypes;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
' stored statistics:'
|
|
' table: rows=unavailable size=unavailable'
|
|
' partitions: 0/12 rows=5.97K'
|
|
' columns: unavailable'
|
|
row_regex:.* extrapolated-rows=unavailable.*
|
|
' tuple-ids=0 row-size=4B cardinality=5.97K'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Disable the estimation of cardinality for an hdfs table withot stats.
|
|
SET DISABLE_HDFS_NUM_ROWS_ESTIMATE=1;
|
|
explain select id from alltypes;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
' stored statistics:'
|
|
' table: rows=unavailable size=unavailable'
|
|
' partitions: 0/12 rows=unavailable'
|
|
' columns: unavailable'
|
|
row_regex:.* extrapolated-rows=unavailable.*
|
|
' tuple-ids=0 row-size=4B cardinality=unavailable'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
compute stats alltypes
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 11 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Only the table-level row count is stored. The partition row counts are extrapolated.
|
|
show table stats alltypes
|
|
---- LABELS
|
|
YEAR, MONTH, #ROWS, EXTRAP #ROWS, #FILES, SIZE, BYTES CACHED, CACHE REPLICATION, FORMAT, INCREMENTAL STATS, LOCATION
|
|
---- RESULTS
|
|
'2009','1',-1,307,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=1'
|
|
'2009','10',-1,307,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=10'
|
|
'2009','11',-1,302,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=11'
|
|
'2009','12',-1,307,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=12'
|
|
'2009','2',-1,290,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=2'
|
|
'2009','3',-1,307,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=3'
|
|
'2009','4',-1,302,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=4'
|
|
'2009','5',-1,307,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=5'
|
|
'2009','6',-1,302,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=6'
|
|
'2009','7',-1,307,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=7'
|
|
'2009','8',-1,307,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=8'
|
|
'2009','9',-1,302,1,regex:.*B,'NOT CACHED','NOT CACHED','PARQUET','false','$NAMENODE/test-warehouse/$DATABASE.db/alltypes/year=2009/month=9'
|
|
'Total','',3650,3650,12,regex:.*B,'0B','','','',''
|
|
---- TYPES
|
|
STRING,STRING,BIGINT,BIGINT,BIGINT,STRING,STRING,STRING,STRING,STRING,STRING
|
|
====
|
|
---- QUERY
|
|
# Stats are available now.
|
|
explain select id from alltypes;
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
row_regex:.*Max Per-Host Resource Reservation: Memory=.*
|
|
row_regex:.*Per-Host Resource Estimates: Memory=.*
|
|
'Codegen disabled by planner'
|
|
row_regex:.*Analyzed query: SELECT id FROM test_stats_extrapolation_.*.alltypes.*
|
|
''
|
|
'F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
|
|
row_regex:.*Per-Host Resources: mem-estimate=.* mem-reservation=.*
|
|
'PLAN-ROOT SINK'
|
|
'| output exprs: id'
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
'|'
|
|
'00:SCAN $FILESYSTEM_NAME [$DATABASE.alltypes]'
|
|
row_regex:.*partitions=12/12 files=12 size=.*
|
|
' stored statistics:'
|
|
row_regex:.*table: rows=3.65K size=.*
|
|
' partitions: 0/12 rows=unavailable'
|
|
' columns: all'
|
|
row_regex:.* extrapolated-rows=3.65K .*
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
' tuple-ids=0 row-size=4B cardinality=3.65K'
|
|
' in pipelines: 00(GETNEXT)'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Select a subset of partitions.
|
|
explain select id from alltypes where month in (1, 2, 3);
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
row_regex:.*Max Per-Host Resource Reservation: Memory=.*
|
|
row_regex:.*Per-Host Resource Estimates: Memory=.*
|
|
'Codegen disabled by planner'
|
|
row_regex:.*Analyzed query: SELECT id FROM test_stats_extrapolation_.*.alltypes WHERE.*
|
|
'`month` IN (CAST(1 AS INT), CAST(2 AS INT), CAST(3 AS INT))'
|
|
''
|
|
'F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
'PLAN-ROOT SINK'
|
|
'| output exprs: id'
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
'|'
|
|
'00:SCAN $FILESYSTEM_NAME [$DATABASE.alltypes]'
|
|
' partition predicates: `month` IN (CAST(1 AS INT), CAST(2 AS INT), CAST(3 AS INT))'
|
|
row_regex:.*partitions=3/12 files=3 size=.*
|
|
' stored statistics:'
|
|
row_regex:.*table: rows=3.65K size=.*
|
|
' partitions: 0/3 rows=unavailable'
|
|
' columns: all'
|
|
row_regex:.* extrapolated-rows=904.*
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
' tuple-ids=0 row-size=4B cardinality=904'
|
|
' in pipelines: 00(GETNEXT)'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Double the data in existing partitions.
|
|
insert into alltypes partition(year, month)
|
|
select * from functional_parquet.alltypes where year = 2009;
|
|
explain select id from alltypes;
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
row_regex:.*Max Per-Host Resource Reservation: Memory=.*
|
|
row_regex:.*Per-Host Resource Estimates: Memory=.*
|
|
row_regex:.*Analyzed query: SELECT id FROM test_stats_extrapolation_.*.alltypes.*
|
|
''
|
|
'F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
|
|
row_regex:.*Per-Host Resources: mem-estimate=.* mem-reservation=.*
|
|
'PLAN-ROOT SINK'
|
|
'| output exprs: id'
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
'|'
|
|
'00:SCAN $FILESYSTEM_NAME [$DATABASE.alltypes]'
|
|
row_regex:.*partitions=12/12 files=24 size=.*
|
|
' stored statistics:'
|
|
row_regex:.*table: rows=3.65K size=.*
|
|
' partitions: 0/12 rows=unavailable'
|
|
' columns: all'
|
|
row_regex:.* extrapolated-rows=7.30K .*
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
' tuple-ids=0 row-size=4B cardinality=7.30K'
|
|
' in pipelines: 00(GETNEXT)'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Create new partitions and extrapolate their row count.
|
|
insert into alltypes partition(year, month)
|
|
select * from functional_parquet.alltypes where year = 2010;
|
|
explain select id from alltypes where year = 2010;
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
row_regex:.*Max Per-Host Resource Reservation: Memory=.*
|
|
row_regex:.*Per-Host Resource Estimates: Memory=20MB.*
|
|
'Codegen disabled by planner'
|
|
row_regex:.*Analyzed query: SELECT id FROM test_stats_extrapolation_.*.alltypes WHERE.*
|
|
'`year` = CAST(2010 AS INT)'
|
|
''
|
|
'F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
|
|
row_regex:.*Per-Host Resources: mem-estimate=.* mem-reservation=.*
|
|
'PLAN-ROOT SINK'
|
|
'| output exprs: id'
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
'|'
|
|
'00:SCAN $FILESYSTEM_NAME [$DATABASE.alltypes]'
|
|
' partition predicates: `year` = CAST(2010 AS INT)'
|
|
row_regex:.*partitions=12/24 files=12 size=.*
|
|
' stored statistics:'
|
|
row_regex:.*table: rows=3.65K size=.*
|
|
' partitions: 0/12 rows=unavailable'
|
|
' columns: all'
|
|
row_regex:.* extrapolated-rows=3.65K .*
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
' tuple-ids=0 row-size=4B cardinality=3.65K'
|
|
' in pipelines: 00(GETNEXT)'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Compute stats and run the same query again.
|
|
compute stats alltypes;
|
|
explain select id from alltypes where year = 2010;
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
row_regex:.*Max Per-Host Resource Reservation: Memory=.*
|
|
row_regex:.*Per-Host Resource Estimates: Memory=20MB.*
|
|
'Codegen disabled by planner'
|
|
row_regex:.*Analyzed query: SELECT id FROM test_stats_extrapolation_.*.alltypes WHERE.*
|
|
'`year` = CAST(2010 AS INT)'
|
|
''
|
|
'F00:PLAN FRAGMENT [UNPARTITIONED] hosts=1 instances=1'
|
|
row_regex:.*Per-Host Resources: mem-estimate=.* mem-reservation=.*
|
|
'PLAN-ROOT SINK'
|
|
'| output exprs: id'
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
'|'
|
|
'00:SCAN $FILESYSTEM_NAME [$DATABASE.alltypes]'
|
|
' partition predicates: `year` = CAST(2010 AS INT)'
|
|
row_regex:.*partitions=12/24 files=12 size=.*
|
|
' stored statistics:'
|
|
row_regex:.*table: rows=10.95K size=.*
|
|
' partitions: 0/12 rows=unavailable'
|
|
' columns: all'
|
|
row_regex:.* extrapolated-rows=3.65K .*
|
|
row_regex:.*mem-estimate=.* mem-reservation=.*
|
|
' tuple-ids=0 row-size=4B cardinality=3.65K'
|
|
' in pipelines: 00(GETNEXT)'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Test that dropping stats resets everything.
|
|
drop stats alltypes;
|
|
explain select id from alltypes;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
' stored statistics:'
|
|
' table: rows=unavailable size=unavailable'
|
|
' partitions: 0/24 rows=17.91K'
|
|
' columns: unavailable'
|
|
row_regex:.* extrapolated-rows=unavailable.*
|
|
row_regex:.* tuple-ids=0 row-size=4B cardinality=17\.9.*K
|
|
' in pipelines: 00(GETNEXT)'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
# Test that dropping stats resets everything.
|
|
SET DISABLE_HDFS_NUM_ROWS_ESTIMATE=1;
|
|
drop stats alltypes;
|
|
explain select id from alltypes;
|
|
---- RESULTS: VERIFY_IS_SUBSET
|
|
' stored statistics:'
|
|
' table: rows=unavailable size=unavailable'
|
|
' partitions: 0/24 rows=unavailable'
|
|
' columns: unavailable'
|
|
row_regex:.* extrapolated-rows=unavailable.*
|
|
' tuple-ids=0 row-size=4B cardinality=unavailable'
|
|
' in pipelines: 00(GETNEXT)'
|
|
---- TYPES
|
|
STRING
|
|
====
|