Michał Świtakowski
Abstract
In analytical applications, database systems often need to sustain workloads with multiple concurrent scans hitting the same table. The Cooperative Scans (CScans) framework, which introduces an Active Buffer Manager (ABM) component into the database architecture, has been the most effective and elaborate response to this problem, and was initially developed in the X100 research prototype. We now report on the the experiences of integrating Cooperative Scans into its industrial-strength successor, the Vectorwise database product. During this implementation we invented a simpler optimization of concurrent scan buffer management, called Predictive Buffer Management (PBM). PBM is based on the observation that in a workload with long-running scans, the buffer manager has quite a bit of information on the workload in the immediate future, such that an approximation of the ideal OPT algorithm becomes feasible. In the evaluation on both synthetic benchmarks as well as a TPC-H throughput run we compare the benefits of naive buffer management (LRU) versus CScans, PBM and OPT; showing that PBM achieves benefits close to Cooperative Scans, while incurring much lower architectural impact.
- L. A. Belady. A study of replacement algorithms for a virtual-storage computer. IBM Sys. Journal, 5(2):78--101, 1966. Google Scholar
- H. Berenson, P. Bernstein, J. Gray, J. Melton, E. O'Neil, and P. O'Neil. A critique of ansi sql isolation levels. SIGMOD Record, 24(2):1--10, 1995. Google Scholar
- C.-M. Chen and N. Roussopoulos. Adaptive database buffer allocation using query feedback. In VLDB, pages 342--353, 1993. Google Scholar
- H.-T. Chou and D. J. DeWitt. An evaluation of buffer management strategies for relational database systems. In VLDB, pages 127--141, 1985. Google Scholar
- C. Cook. Database Architecture: The Storage Engine, 2001. http://msdn.microsoft.com/library.Google Scholar
- C. Faloutsos, R. T. Ng, and T. K. Sellis. Predictive load control for flexible buffer allocation. In VLDB, pages 265--274, 1991. Google Scholar
- P. M. Fernandez. Red brick warehouse: a read-mostly rdbms for open smp platforms. SIGMOD Record, 23(2):492, 1994. Google Scholar
- G. Giannikis, P. Unterbrunner, J. Meyer, G. Alonso, D. Fauser, and D. Kossmann. Crescando. In SIGMOD, pages 1227--1230, 2010. Google Scholar
- G. Graefe. Encapsulation of parallelism in the volcano query processing system. In SIGMOD, pages 102--111, 1990. Google Scholar
- S. Harizopoulos, V. Shkapenyuk, and A. Ailamaki. Qpipe: a simultaneously pipelined relational query engine. In SIGMOD, pages 383--394, 2005. Google Scholar
- S. Héman, M. Zukowski, N. J. Nes, L. Sidirourgos, and P. Boncz. Positional update handling in column stores. In SIGMOD, pages 543--554, 2010. Google Scholar
- D. Inkster, P. Boncz, and M. Zukowski. Integration of VectorWise with Ingres. SIGMOD Record, 40(3):45--53, 2011. Google Scholar
- C. A. Lang, B. Bhattacharjee, T. Malkemus, S. Padmanabhan, and K. Wong. Increasing buffer-locality for multiple relational table scans through grouping and throttling. In ICDE, pages 1136--1145, 2007.Google Scholar
- C. A. Lang, B. Bhattacharjee, T. Malkemus, and K. Wong. Increasing buffer-locality for multiple index based scans through intelligent placement and index scan speed control. In VLDB, pages 1298--1309, 2007. Google Scholar
- B. V. Roy. A short proof of optimality for the min cache replacement algorithm. Technical report, Stanford University, 2010.Google Scholar
- T. J. Teorey and T. B. Pinkerton. A comparative analysis of disk scheduling policies. In SOSP, pages 78--87, 1971. Google Scholar
- P. Unterbrunner, G. Giannikis, G. Alonso, D. Fauser, and D. Kossmann. Predictable performance for unpredictable workloads. PVLDB, 2(1):706--717, 2009. Google Scholar
- Vectorwise. http://www.actian.com/vectorwise.Google Scholar
- M. Zukowski and P. Boncz. Vectorwise: Beyond Column Stores. IEEE DEBULL, 35(1):21--27, 2012.Google Scholar
- M. Zukowski, P. A. Boncz, N. J. Nes, and S. Heman. Monetdb/X100 - A DBMS In The CPU Cache. IEEE DEBULL, 28(2):17--22, 2005.Google Scholar
- M. Zukowski, S. Héman, N. Nes, and P. Boncz. Cooperative scans: dynamic bandwidth sharing in a dbms. In VLDB, pages 723--734, 2007. Google Scholar
Index Terms
- From cooperative scans to predictive buffer management
Recommendations
Second-Level Buffer Cache Management
Abstract--Buffer caches are commonly used in servers to reduce the number of slow disk accesses or network messages. These buffer caches form a multilevel buffer cache hierarchy. In such a hierarchy, second-level buffer caches have different access ...
Buffer Overflow Management in QoS Switches
We consider two types of buffering policies that are used in network switches supporting Quality of Service (QoS). In the FIFO type, packets must be transmitted in the order in which they arrive; the constraint in this case is the limited buffer ...
Comments