Weka Claims 6 Records on STAC-M3 WEKAFS File Systems on EC2

Print Friendly, PDF & Email

CAMPBELL, Calif. – June 8, 2021 – WekaIO (Weka), the data platform for artificial intelligence/machine learning (AI/ML), life sciences research, and high-performance computing (HPC), today announced record-breaking performance of its Weka File System (WekaFS) on Amazon Elastic Compute Cloud (Amazon EC2) according to the STAC-M3 Benchmark. An independent audit, conducted by Securities Technology Analysis Center (STAC), showed that the Weka solution broke 6 STAC-M3 records, confirming that the WekaFS POSIX-compliant file system on Amazon Web Services (AWS) is a capable and performant option for enterprises looking to enjoy the elasticity and agility of tick analytics in the cloud. Financial services use cases such as algorithmic trading, quantitative analytics, and back testing can benefit from these results for hybrid and cloud native workflows.

The STAC-M3 benchmark suite is the industry standard for testing solutions that enable high-speed analytics on time-series data, such as tick-by-tick market data (aka “tick analytics” stacks). STAC-M3 specifications were developed by the STAC Benchmark Council, which consists of over 400 financial institutions and 50 vendor organizations. User firms include the largest global banks, brokerage houses, exchanges, hedge funds, proprietary trading shops, and other market participants.

This testing was performed on Amazon EC2 Non-Volatile Memory Express (NVMe) instances using a kdb+ 4.0 database by KX Systems. Testing included the baseline STAC-M3 suite (Antuco) and the scaling suite (Kanaga).

Key result highlights for this solution, with 15 database server nodes and 40 storage nodes, include:

  • Outperformed all publicly disclosed results in 3 of the 5 throughput benchmarks in the STAC-M3 Kanaga suite (STAC-M3.β1.1T.{3,4,5}YRHIBID.BPS)
  • Outperformed all publicly disclosed results in 3 of 24 mean-response-time benchmarks in the STAC-M3 Kanaga suite
  • Versus a kdb+ 4.0 solution running on a 10-node cluster with 60TB of persistent memory (KDB200603), was faster in 16 of 24 Kanaga and 9 of 17 Antuco benchmarks
  • Versus a kdb+ 3.6 solution on a parallel file system with 15 database servers accessing all-flash storage appliances (KDB200915), was faster in 20 of 24 Kanaga benchmarks and 4 of 17 Antuco benchmarks
  • Versus a kdb+ 3.6 solution involving 9 database servers accessing networked flash storage (KDB200914), was faster in 15 of 17 Antuco benchmarks

To see the full STAC report, visit https://www.STACresearch.com/KDB210507.

Financial organizations with their “Cloud-First” strategy want to increasingly leverage public cloud for its elasticity, scalability, and ease of use for quantitative analytics, back testing, and algorithmic trading. However, these workloads are very latency-sensitive and require consistent high performance to reliably execute. WekaFS, with its record-breaking performance on AWS, has proven that a latency-sensitive mixed workload can effectively be run on AWS, while providing the elasticity and scalability on Amazon EC2 instances. With this capability, Quants and FSI professionals can more frequently run more complex models, perform back testing, and do algorithmic trading to derive actionable insight and match machine trading requirements.