eXtremeDB Financial Edition DBMS Sweeps Records in Big Data Benchmark
June 27, 2016 — McObject®, developer of the eXtremeDB® Financial Edition database management system (DBMS), announced a sweep of records by McObject’s DBMS running on an IBM POWER8 S824L Linux server in the Kanaga suite of STAC-M3™, key financial industry benchmarks of tick analytics on Big Data. The test results, audited and published by the Securities Technology Analysis Center (STAC®), position eXtremeDB Financial Edition as the most predictably fast and scalable tick data management solution for trading systems contending with high data volumes and increasingly complex queries in today’s capital markets.
The STAC-M3 benchmark consists of trading queries that were designed by firms on the STAC Benchmark Council to reflect real-world capital markets computing demands. Within STAC-M3, the Antuco test suite uses a limited data set to ease implementation, while the Kanaga test suite’s much larger data set simulates actual data volumes encountered by capital markets systems and shows the scalability of eXtremeDB Financial Edition, which managed 31 TB of tick data in its Kanaga implementation, with as many as 100 concurrent queries.
McObject previously completed four STAC-M3 Antuco implementations and holds records in 11 of the suite’s 17 benchmark tests. The recent STAC-M3 Kanaga is the first with eXtremeDB Financial Edition; its highlights include:
- Fastest mean response times and most consistent response times (lowest standard deviation) ever reported, for all combinations of query type, data volume, and concurrent users.
- Each mean response time was 5.5x to 212x the previous best result, including:
- 21x to 212x the performance of the previous best published result for the market snap benchmarks (10T.YR[n]-MKTSNAP.TIME)
- 21x the performance of the previous best published result for year high bid in the smallest year of the dataset (1T.OLDYRHIBID.TIME)
- 8x to 10x the performance of the previous best published result for the 100-user volume-weighted average bid benchmarks (100T.YR[n]VWAB-12D-HO.TIME)
- 5x to 8x the performance of the previous best published result for the N-year high-bid benchmarks (1T.[n]YRHIBID.TIME)
Queries were programmed in Python and SQL, which provide an ease-of-use advantage and much larger developer labor pool compared to the low-level languages and proprietary database APIs used in all other vendors’ Antuco and Kanaga implementations.
Tests utilized the DBMS’s columnar data storage and vector-based statistical function library. They also leveraged eXtremeDB Financial Edition’s distributed query processing (the database was partitioned horizontally across 72 shards running on 24 processor cores) and the ability to pipeline the vector-based functions from within SQL.
“Increasingly complex real-time analysis of high data volumes is transforming capital markets IT, in areas ranging from trading model simulation to fraud detection, predictive analytics and more,” said Chris Mureen, McObject chief operating officer. “The STAC-M3 Kanaga benchmarks, administered by a neutral third-party organization that rigorously audits results, is widely recognized as the most accurate yardstick for the scalability of tick analytics on Big Data. eXtremeDB Financial Edition’s outstanding performance on the benchmarks should place it on the short list for any project requiring this capability.”
Data management wherever you need it.
Hybrid Data Storage Unlike other IMDS, eXtremeDB databases can be all-in-memory, all-persistent, or have a mix of in-memory tables and persistent tables.
Row & Columnar Flexibility for Time Series Data eXtremeDB supports database designs that combine row-based and column-based layouts, in order to best leverage the CPU cache speed.
Embedded and Client/Server Fast, flexible eXtremeDB is data management wherever you need it, and can be deployed as an embedded database system, and/or as a client/server database system.
Platform Independent eXtremeDB is designed and implemented to be a highly portable.