Riza Suminto has uploaded a new patch set (#23) to the change originally created by David Rorke. ( http://gerrit.cloudera.org:8080/21279 )
Change subject: IMPALA-12657: Improve ProcessingCost of ScanNode and NonGroupingAggregator ...................................................................... IMPALA-12657: Improve ProcessingCost of ScanNode and NonGroupingAggregator This patch improves the accuracy of the CPU ProcessingCost estimates for several of the CPU intensive operators by basing the costs on benchmark data. The general approach for a given operator was to run a set of queries that exercised the operator under various conditions (e.g. large vs small row sizes and row counts, varying NDV, different file formats, etc) and capture the CPU time spent per unit of work (the unit of work might be measured as some number of rows, some number of bytes, some number of predicates evaluated, or some combination of these). The data was then analyzed in an attempt to fit a simple model that would allow us to predict CPU consumption of a given operator based on information available at planning time. For example, the CPU ProcessingCost for a Parquet scan is estimated as: TotalCost = (0.0144 * BytesMaterialized) + (0.0281 * Rows * Predicate Count) The coefficients (0.0144 and 0.0281) are derived from benchmarking scans under a variety of conditions. Similar cost functions and coefficients were derived for all of the benchmarked operators. The coefficients for all the operators are normalized such that a single unit of cost equates to roughly 100 nanoseconds of CPU time on a r5d.4xlarge instance. So we would predict an operator with a cost of 10,000,000 would complete in roughly one second on a single core. Limitations: * Costing only addresses CPU time spent and doesn't account for any IO or other wait time. * Benchmarking scenarios didn't provide comprehensive coverage of the full range of data types, distributions, etc. More thorough benchmarking could improve the costing estimates further. * This initial patch only covers a subset of the operators, focusing on those that are most common and most CPU intensive. Specifically the following operators are covered by this patch. All others continue to use the previous ProcessingCost code: AggregationNode DataStreamSink (exchange sender) ExchangeNode HashJoinNode HdfsScanNode HdfsTableSink NestedLoopJoinNode SortNode UnionNode Benchmark-based costing of the remaining operators will be covered by a future patch. Future patches will automate the collection and analysis of the benchmark data and the computation of the cost coefficients to simplify maintenance of the costing as performance changes over time. Change-Id: Icf1edd48d4ae255b7b3b7f5b228800d7bac7d2ca --- M fe/src/main/java/org/apache/impala/analysis/AggregateInfo.java M fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java M fe/src/main/java/org/apache/impala/planner/AggregationNode.java M fe/src/main/java/org/apache/impala/planner/BaseProcessingCost.java M fe/src/main/java/org/apache/impala/planner/CostingSegment.java M fe/src/main/java/org/apache/impala/planner/DataStreamSink.java M fe/src/main/java/org/apache/impala/planner/EmptySetNode.java M fe/src/main/java/org/apache/impala/planner/ExchangeNode.java M fe/src/main/java/org/apache/impala/planner/HashJoinNode.java M fe/src/main/java/org/apache/impala/planner/HdfsScanNode.java M fe/src/main/java/org/apache/impala/planner/HdfsTableSink.java M fe/src/main/java/org/apache/impala/planner/NestedLoopJoinNode.java M fe/src/main/java/org/apache/impala/planner/PlanFragment.java M fe/src/main/java/org/apache/impala/planner/PlanNode.java M fe/src/main/java/org/apache/impala/planner/Planner.java M fe/src/main/java/org/apache/impala/planner/ProcessingCost.java M fe/src/main/java/org/apache/impala/planner/ScanNode.java M fe/src/main/java/org/apache/impala/planner/SortNode.java M fe/src/main/java/org/apache/impala/planner/UnionNode.java M testdata/workloads/functional-planner/queries/PlannerTest/processing-cost-plan-admission-slots.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds-processing-cost.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q01.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q02.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q03.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q04.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q05.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q06.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q07.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q08.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q09.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q10a.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q11.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q12.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q13.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q14a.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q14b.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q15.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q16.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q17.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q18.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q19.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q20.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q21.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q22.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q23a.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q23b.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q24a.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q24b.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q25.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q26.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q27.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q28.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q29.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q30.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q31.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q32.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q33.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q34.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q35a.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q36.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q37.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q38.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q39a.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q39b.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q40.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q41.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q42.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q43.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q44.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q45.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q46.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q47.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q48.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q49.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q50.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q51.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q52.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q53.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q54.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q55.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q56.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q57.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q58.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q59.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q60.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q61.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q62.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q63.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q64.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q65.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q66.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q67.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q68.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q69.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q70.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q71.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q72.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q73.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q74.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q75.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q76.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q77.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q78.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q79.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q80.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q81.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q82.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q83.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q84.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q85.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q86.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q87.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q88.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q89.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q90.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q91.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q92.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q93.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q94.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q95.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q96.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q97.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q98.test M testdata/workloads/functional-planner/queries/PlannerTest/tpcds_cpu_cost/tpcds-q99.test M tests/custom_cluster/test_executor_groups.py M tests/query_test/test_insert.py 126 files changed, 18,585 insertions(+), 18,198 deletions(-) git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/79/21279/23 -- To view, visit http://gerrit.cloudera.org:8080/21279 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-MessageType: newpatchset Gerrit-Change-Id: Icf1edd48d4ae255b7b3b7f5b228800d7bac7d2ca Gerrit-Change-Number: 21279 Gerrit-PatchSet: 23 Gerrit-Owner: David Rorke <dro...@cloudera.com> Gerrit-Reviewer: Abhishek Rawat <ara...@cloudera.com> Gerrit-Reviewer: David Rorke <dro...@cloudera.com> Gerrit-Reviewer: Impala Public Jenkins <impala-public-jenk...@cloudera.com> Gerrit-Reviewer: Kurt Deschler <kdesc...@cloudera.com> Gerrit-Reviewer: Michael Smith <michael.sm...@cloudera.com> Gerrit-Reviewer: Riza Suminto <riza.sumi...@cloudera.com> Gerrit-Reviewer: Wenzhe Zhou <wz...@cloudera.com>
