STAC Report: eXtremeDB & IBM at scale under STAC-M3
9 May 2016 – New York
STAC recently used both the baseline and scalability suites of STAC-M3 to test a stack involving McObject’s eXtremeDB Financial Edition 7.0 on an IBM Power System S824L server connected to a 12 x 5.7TB IBM FlashSystem 900 storage system. The solution ncluded two 12-core IBM POWER8 CPUs and a new revision of the eXtremeDB STAC Pack with enhanced parallelism.
STAC Reports for both test suites are available at www.STACresearch.com/XTR160413.
Highlights from the scale benchmarks (Kanaga suite):
- 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) *
- 8-10x the performance of the previous best published result for the 100-user volume-weighted average bid benchmarks (100T.YR[n]VWAB-12D-HO.TIME) **
- 5-8x the performance of the previous best published result for the N-year high-bid benchmarks (1T.[n]YRHIBID.TIME) *
And in the baseline benchmarks (Antuco suite):
- Faster mean response times and more consistent response times (lower standard deviation) than the previous best results for 4 of the 17 operations.
- Compared to all publicly reported 2-socket systems, this system set records in 4 of the 17 benchmarks. 12 of the remaining records are still held by previous eXtremeDB/Power8 systems (SUT IDs XTR141023, XTR151016).
- 1.93x the performance of the previously published best result for 10T.THEOPL.TIME (SUT ID: KDB130603).
- 1.30x the performance of the previously published best result for 1T.STATS-UI.TIME (SUT ID: KDB1505283).
The report is available here. At this link, qualified members of the STAC Benchmark Council can also access the configuration details for the stack that was tested.
Originally posted here.