On Workload Characterization of Relational Database Environments
IEEE Transactions on Software Engineering
The COMFORT automatic tuning project
Information Systems
Dynamic resource brokering for multi-user query execution
SIGMOD '95 Proceedings of the 1995 ACM SIGMOD international conference on Management of data
Performance characterization of a Quad Pentium Pro SMP using OLTP workloads
Proceedings of the 25th annual international symposium on Computer architecture
An analysis of database workload performance on simultaneous multithreaded processors
Proceedings of the 25th annual international symposium on Computer architecture
Characterizing Web user sessions
ACM SIGMETRICS Performance Evaluation Review
Learning table access cardinalities with LEO
Proceedings of the 2002 ACM SIGMOD international conference on Management of data
Automatically classifying database workloads
Proceedings of the eleventh international conference on Information and knowledge management
LEO - DB2's LEarning Optimizer
Proceedings of the 27th International Conference on Very Large Data Bases
Dynamic Memory Allocation for Multiple-Query Workloads
VLDB '93 Proceedings of the 19th International Conference on Very Large Data Bases
Kernel independent component analysis
The Journal of Machine Learning Research
Toward a progress indicator for database queries
SIGMOD '04 Proceedings of the 2004 ACM SIGMOD international conference on Management of data
Estimating progress of execution for SQL queries
SIGMOD '04 Proceedings of the 2004 ACM SIGMOD international conference on Management of data
Increasing the Accuracy and Coverage of SQL Progress Indicators
ICDE '05 Proceedings of the 21st International Conference on Data Engineering
When can we trust progress estimators for SQL queries?
Proceedings of the 2005 ACM SIGMOD international conference on Management of data
Statistical learning techniques for costing XML queries
VLDB '05 Proceedings of the 31st international conference on Very large data bases
Achieving Class-Based QoS for Transactional Workloads
ICDE '06 Proceedings of the 22nd International Conference on Data Engineering
Dynamic workload management for very large data warehouses: juggling feathers and bowling balls
VLDB '07 Proceedings of the 33rd international conference on Very large data bases
PQR: Predicting Query Execution Times for Autonomous Workload Management
ICAC '08 Proceedings of the 2008 International Conference on Autonomic Computing
Predicting Multiple Metrics for Queries: Better Decisions Enabled by Machine Learning
ICDE '09 Proceedings of the 2009 IEEE International Conference on Data Engineering
Quality of service enabled database applications
ICSOC'06 Proceedings of the 4th international conference on Service-Oriented Computing
Multi-query SQL progress indicators
EDBT'06 Proceedings of the 10th international conference on Advances in Database Technology
Predicting completion times of batch query workloads using interaction-aware models and simulation
Proceedings of the 14th International Conference on Extending Database Technology
A mixed transaction processing and operational reporting benchmark
Information Systems Frontiers
Aggregation strategies for columnar in-memory databases in a mixed workload
Proceedings of the 4th workshop on Workshop for Ph.D. students in information & knowledge management
Managing dynamic mixed workloads for operational business intelligence
DNIS'10 Proceedings of the 6th international conference on Databases in Networked Information Systems
Hi-index | 0.00 |
We explore how to manage database workloads that contain a mixture of OLTP-like queries that run for milliseconds as well as business intelligence queries and maintenance tasks that last for hours. As data warehouses grow in size to petabytes and complex analytic queries play a greater role in day-to-day business operations, factors such as inaccurate cardinality estimates, data skew, and resource contention all make it notoriously difficult to predict how such queries will behave before they start executing. However, traditional workload management assumes that accurate expectations for the resource requirements and performance characteristics of a workload are available at compile-time, and relies on such information in order to make critical workload management decisions. In this paper, we describe our approach to dealing with inaccurate predictions. First, we evaluate the ability of workload management algorithms to handle workloads that include unexpectedly long-running queries. Second, we describe a new and more accurate method for predicting the resource usage of queries before runtime. We have carried out an extensive set of experiments, and report on a few of our results.