MongoDB ahead of Cassandra and Couchbase for scalability – report

MongoDB has raced ahead of its NoSQL database competitors Cassandra and Couchbase for scalability, according to tests using the Yahoo Cloud Serving Benchmark (YCSB).

The research, carried out by benchmarking and performance-testing firm United Software Associates (USA Inc), involved evaluating three different configurations: durability, throughput and a balanced configuration that provides strong performance and strong durability.

Further reading

In one of its tests, USA Inc used an equal mix of reads and updates in its workload and found that MongoDB provided over 1.8 times greater throughput than Cassandra and nearly 13 times greater throughput than Couchbase. In another workload, which consisted of 95 per cent reads and five per cent updates, MongoDB again came out on top, with more throughput than Cassandra and Couchbase.

USA Inc used the latest versions of each product – Couchbase 3.0.2., Cassandra 2.12 and MongoDB 3.0.1 with WiredTiger for the research and said that in all of its tests, best practices for each product were followed and multiple rounds of tests were run to determine the optimal number of threads and best performance for each product.

“While performance is important, it must be considered along with many different criteria when evaluating database technology,” warned Sam Bhat, CEO of USA Inc.

“The goal of this report is to take a closer look at scalability, another critical factor used to determine the right database technology for a project. MongoDB proved to have the best and most predictable scalability [of the three NoSQL products].

“With these tests we can confidently say MongoDB is well suited for the widest range of applications, and is also at the forefront of databases in terms of performance and scalability,” he added.

MongoDB has been working on improving its scalability, with some users reporting performance problems as deployments scale up, especially under such write-intensive workloads.

In an interview with Computing in February, Kelly Stirman, MongoDB VP of strategy and product marketing acknowledged that this had been a chink in the database’s armour.

“There has been a reputation that MongoDB is hard to scale. It’s incredibly easy to get started building applications on a laptop but when you want to use a 100 computers then it’s been more complicated than we would like,” he said, inferring that the 3.0 release would rectify the issue.

“This release is all about scalability and performance at scale. The performance for writes will be as good as any other solution out there,” Stirman said at the time, claiming that for typical applications users were going to be able to look forward to a five- to seven-times increase in throughput rates.

Dev Ittycheria, CEO of MongoDB, told delegates today at MongoDB World in New York that he was pleased about the independent research. He said it “illustrated that MongoDB delivers the best performance in multimode environment for a variety of workloads”.

Source :


  • Ask Question