SingleStore Makes Real-Time Performance on Hadoop a Reality
Cisco and SingleStore Demonstrate Dynamic Performance Optimization Using ACI-Ready Clusters at Strata + Hadoop World Conference
SAN FRANCISCO, October 16, 2014 - SingleStore, the leader in real-time and historical Big Data analysis, today announced that worldwide networking leader Cisco is using SingleStore technology to deliver real-time performance on Hadoop. The companies are demonstrating the recent collaboration at Strata + Hadoop World Conference this Thursday and Friday in New York City.
The collaboration between the two tech leaders enables Cisco to demonstrate exceptional throughput on concurrent SingleStore and Hadoop 2.0 workloads with new Application Centric Infrastructure including APIC and Nexus switch technology. The solution automatically prioritizes smaller packet streams generated by real-time workloads over larger packet streams generated by typical Hadoop workloads.
The result is that both workloads complete nearly as fast as if they were running by themselves on a dedicated cluster. At the conference, Cisco is demonstrating 2.4 million reads per second from SingleStore's in-memory database on an 80-node cluster without additional network traffic. It then compares this "best" case to a mixed workload with and without packet-prioritization enabled.
Without packet-prioritization, the database's performance drops to under 600 thousand reads per second when a simulated Hadoop workload is added to saturate the cluster's network. With packet-prioritization, the performance recovers to 1.4 million reads per second, essentially doubling the throughput. This advance provides the ability to collocate a distributed database such as SingleStore for real-time, mission critical data ingest and analysis with Hadoop workloads that are less time-sensitive and executed as large batch jobs on historical data.
"Analyzing real-time data has always been a challenge with Hadoop," said SingleStore CEO Eric Frenkiel. "By teaming up with Cisco, we're making it possible to ingest and query real-time and historical data simultaneously at webscale."
Cisco is using SingleStore Ops, a tool that provides real-time insight for performance monitoring, capacity planning and problem diagnosis of a cluster. The out-of-box dashboards highlight the critical key metrics while allowing DBAs to easily modify for their needs.
"We are excited to work with SingleStore to showcase dynamic performance optimization using ACI-ready clusters," said Thomas Scheibe, director of product management, INSBU, Cisco. "Cisco's Application Centric Infrastructure is a new operational model enabling Fast IT. ACI provides a common policy-based programming approach across the entire ACI-ready infrastructure, beginning with the network and extending to all its connected end points."
The live demonstration can be viewed this week at Strata + Hadoop Conference in New York.
SingleStore is the leader in real-time and historical Big Data analytics based on a distributed in-memory database. SingleStore is purpose built for instant access to real-time and historical data through a familiar SQL interface and uses a horizontally scalable distributed architecture that runs on commodity hardware. Innovative enterprises use SingleStore to accelerate time-to-value by extracting previously untapped value in their data that results in new revenue. SingleStore is proven in production environments across hundreds of nodes in high velocity Big Data environments. Based in San Francisco, SingleStore is a Y Combinator company funded by prominent venture capitalists and angel investors including Accel Partners, Khosla Ventures, First Round Capital and Data Collective.
Cisco is the worldwide leader in IT that helps companies seize the opportunities of tomorrow by proving that amazing things can happen when you connect the previously unconnected.