Analysis of Service-Oriented DBMS Organization

Cloud database management systems (DBMSs) often decouple database instances from physical storage to provide reliability and high availability to users. This design can robustly handle a single point of failure, but needs substantial effort to attain good performance. In this paper, we analyze the decoupled architecture and present important optimization issues that we faced in implementing the design. For implementing the prototyped system, we decouple MariaDB into a database instance and storage managing log and data pages. We evaluate the prototyped system using standard database benchmarks, and experimental results show that adopting the decoupled architecture for cloud DBMSs needs to address numerous optimization issues for achieving better performance.

[1]  Michael Stonebraker,et al.  The VoltDB Main Memory DBMS , 2013, IEEE Data Eng. Bull..

[2]  Florian Irmert,et al.  A new approach to modular database systems , 2008, SETMDM '08.

[3]  David Campbell Service Oriented Database Architecture: APP server-lite? , 2005, SIGMOD '05.

[4]  Michael Stonebraker,et al.  SciDB DBMS Research at M.I.T , 2013, IEEE Data Eng. Bull..

[5]  Goetz Graefe,et al.  Instant Recovery with Write-Ahead Logging: Page Repair, System Restart, and Media Restore , 2014, Synthesis Lectures on Data Management.

[6]  Klaus R. Dittrich,et al.  Towards Service-Based Database Management Systems , 2007, BTW Workshops.

[7]  Craig Freedman,et al.  Hekaton: SQL server's memory-optimized OLTP engine , 2013, SIGMOD '13.

[8]  Philip A. Bernstein,et al.  Optimistic concurrency control by melding trees , 2011, Proc. VLDB Endow..

[9]  Hamid Pirahesh,et al.  ARIES: a transaction recovery method supporting fine-granularity locking and partial rollbacks using write-ahead logging , 1998 .

[10]  Michael Stonebraker,et al.  Rethinking main memory OLTP recovery , 2014, 2014 IEEE 30th International Conference on Data Engineering.

[11]  Wee Hyong DBNet: A Service-Oriented Database Architecture , 2006 .

[12]  Wolfgang Lehner,et al.  Towards Integrated Data Analytics: Time Series Forecasting in DBMS , 2012, Datenbank-Spektrum.

[13]  Klaus R. Dittrich,et al.  Towards Service-Based Data Management Systems , 2007 .

[14]  Rajesh Gupta,et al.  From ARIES to MARS: transaction support for next-generation, solid-state drives , 2013, SOSP.

[15]  T. Härder Dbms Architecture – the Layer Model and Its Evolution 1 Motivation Dbms Architecture – the Layer Model and Its Evolution , 2005 .