Clustrix Outscales both Amazon Aurora and Google Cloud SQL

Third-party benchmarks highlight true “scale-out SQL” for high-transaction scenarios

San Francisco, Calif. - Nov 10, 2016 - Clustrix (www.clustrix.com), provider of the first scale-out database designed for the elastic scaling requirements of high-transaction, high-value workloads of today’s web applications, demonstrated that its flagship relational database management system (RDBMS) ClustrixDB outperformed both Amazon Aurora and Google Cloud SQL in high-transaction scenarios. An Infoworld Test Center benchmark conducted earlier this year showed that Clustrix outscaled Amazon Aurora by great margins, while recent tests conducted by the same organization illustrate that Aurora outscales Google CloudSQL, leading to a single conclusion: Clustrix outperforms both of these MySQL alternatives.

Addressing MySQL’s shortcomings
As observed by Martin Heller in his recent review MySQL face-off: Amazon outscales Google, both Amazon Aurora and Google CloudSQL were developed in order to bridge limitations imposed by MySQL. Despite being the world’s most widely used open source RDBMS, “MySQL does not scale all that well and, in particular, cannot handle a lot of simultaneous clients compared to commercial databases.” Heller goes on to benchmark these two MySQL replacements against each other, concluding that “Google Cloud SQL performance may beat Amazon Aurora at low thread counts, but Aurora owns the high end.”

ClustrixDB was also developed to address MySQL limitations, but with an important difference—it is architected to “scale out” by adding server nodes, which enables it to scale linearly to the point where there are almost no limits to the number of simultaneous transactions it can handle with little perceptible latency to the end user—a distinction that is not true of Google Cloud SQL and Amazon Aurora. Heller highlighted this in “ClustrixDB scales out, way out—Clustered relational database outperforms Amazon Aurora for low-latency, high-transaction-rate scenarios.”

Clustrix “scales out” to outperform Aurora and CloudSQL

Heller concludes that “ClustrixDB is a more-scalable alternative to Amazon Aurora for people who need extremely high transactional performance,” pointing to several benefits of the database:

  • A shared-nothing architecture that eliminates the potential scaling bottlenecks caused by shared-disk or even shared-cache architectures
  • A rebalancer that ensures optimal data distribution across all nodes
  • A query optimizer that achieves maximum parallelism on individual queries and maximum concurrency on simultaneous queries
  • Ability to be scaled out “hot” without downtime

“A common misconception is that cloud databases like Google Cloud SQL and Amazon Aurora can scale just by adding cloud instances. However, the truth is that even they have limits,” said Mike Azevedo, CEO, Clustrix. “Customers that foresee rapid growth or anticipate large spikes in seasonal demand will need a scale-out solution like ClustrixDB that’s built for high-volume scenarios handling millions of concurrent transactions. They might be shocked to find that Google and Aurora’s options are lower-performing solutions, but the most unpleasant surprise might come when they find themselves pouring tremendous money and engineering time into trying to rig them to scale beyond what they were designed for.”