Versus Aurora: Performance

versus aurora performance

Clustrix Delivers Up to 10x Aurora Performance

More performance is better and the right kind of performance is always best. ClustrixDB can deliver 2x, 5x, even 10x Aurora performance, at much lower latencies—without complicated read slaves or sharding. This means that ClustrixDB can process more e-commerce check-outs, or ingest more real-time data, or serve more ads, or do more of anything faster than you can do with MySQL or Aurora.

To back up this claim, we ran a Sysbench test with a typical workload that is representative of the kinds of workloads our customers see in the course of their business (e-commerce, gaming, adtech, social, etc.)

For high-performance and high-value workloads, ClustrixDB is superior to Aurora performance in transactions per second and response time. And once Aurora is running on Amazon’s largest node, their ability to scale writes ends without resorting to database gymnastics like master/slave or sharding. But ClustrixDB offers scale-out performance of both reads and writes. So we ran the benchmark with 64, 128, 256 and 512 cores.

Only ClustrixDB offers users the ability to instantly add more nodes to the cluster in order to increase throughput and keep latency low — all without modifying your enterprise applications or sharding your database.

ClustrixDB matches Aurora's transactions per second throughput and latency on 32 cores and continues to deliver linear scalability as you add cores.

Write performance is often the biggest bottleneck of database solutions today. Ingesting large amounts of data, instantly updating thousands of records, or converting thousands of shopping cart items into checkout transactions are all write-heavy database functions that can bring MySQL and Aurora to their knees (and site owners to tears).

Aurora, MySQL, and other traditional SQL database products talk about scaling, but they only scale a portion of the workload—they only scale database reads.

ClustrixDB is the only MySQL drop-in replacement that scales both reads and writes. It is a “shared-nothing architecture” solution that permits ClustrixDB performance to scale the database in a near-linear fashion from 3 nodes to 50 or more, posing as a single database to the application. Each additional node in a cluster adds more capacity and performance.

Sharding, read slaves, or any of the other complicated SQL workarounds is never required. ClustrixDB can deliver this performance because each node handles writes and reads.

ClustrixDB is the only drop-in replacement for MySQL that can scale out both reads and writes by increasing the number of nodes in the cluster. With ClustrixDB you can get 10x the maximum performance of Aurora (or MySQL) without read slaves, sharding, or modifying your enterprise applications.

Ready to get started?