Apache_Tutorial_728x90

Apache Cassandra NoSQL Performance Benchmarks

Apache Cassandra is a leading NoSQL database platform for online applications.  By offering benefits of continuous availability, high scalability & performance, strong security, and operational simplicity —  while lowering overall cost of ownership — Cassandra has become a proven choice for both technical and business stakeholders.

When compared to other database platforms such as HBase, MongoDB, Redis, MySQL and many others, Cassandra delivers higher performance under heavy workloads.

The following  benchmark tests provide a graphical, ‘at a glance’ view of how these platforms compare under different scenarios.


End Point Benchmark Configuration and and Results

University of Toronto NoSQL Database Performance

Netflix Benchmarking Cassandra Scalability on AWS

 

End Point Benchmark Configuration and Results Summary

End Point, a database and open source consulting company, benchmarked the top NoSQL databases — Apache Cassandra, Apache HBase, and MongoDB — using a variety of different workloads on Amazon Web Services EC2 instances. This is an industry-standard platform for hosting horizontally scalable services such as the three NoSQL databases that were tested. In order to minimize the effect of AWS CPU and I/O variability, End Point performed each test 3 times on 3 different days. New EC2 instances were used for each test run to further reduce the impact of any “lame instance” or “noisy neighbor” effect on any one test.

A summary of the workload analysis is available below. For a review of the entire testing process with testing environment configuration details, the benchmarking NoSQL databases white paper by End Point is available.

 

Tested Workloads

The following workloads were included in the benchmark:

  1. Read-mostly workload, based on YCSB’s provided workload B: 95% read to 5% update ratio
  2. Read/write combination, based on YCSB’s workload A: 50% read to 50% update ratio
  3. Write-mostly workload: 99% update to 1% read
  4. Read/scan combination: 47% read, 47% scan, 6% update
  5. Read/write combination with scans: 25% read, 25% scan, 25% update, 25% insert
  6. Read latest workload, based on YCSB workload D: 95% read to 5% insert
  7. Read-modify-write, based on YCSB workload F: 50% read to 50% read-modify-write

Throughput Results

End Point NoSQL Benchmark Testing Load Process 1Endpoint-1.2 

For the load process, MongoDB was not able to scale effectively to 32 nodes and produced errors until the thread count was reduced to 20.

End Point NoSQL Benchmark Testing Load Process 2Endpoint-2.2
End Point NoSQL Benchmark Testing Read/Write Mix WorkloadEndpoint-3.2
End Point NoSQL Benchmark Testing Write-mostly Workload
End Point NoSQL Benchmark Testing Read/Scan Mix Workload
End Point NoSQL Benchmark Testing Write/Scan Mix Workload
End Point NoSQL Benchmark Testing Read-latest Workload
End Point NoSQL Benchmark Testing Read-Modify-Write Workload

 

University of Toronto NoSQL Database Performance

Engineers at the University of Toronto, in 2012, conducted a thorough benchmarking analysis of various NoSQL platforms including:  Apache Cassandra, HBase, MySQL, Redis and Voldemort. The testing was extremely thorough and included a view into performance under varying  workloads.

For a look at the details behind this analysis as well as a complete write up of the benchmark configurations used, the white paper Solving Big Data Challenges for Enterprise Application Performance Management provides all of the insight from this test. Overall their results identified Apache Cassandra the “clear winner throughout our experiments”.

A summary of throughput and latency results are available here.

Throughput for workload Read/Write
Throughput for workload read/write
Throughput for workload Read/Scan/Write
Throughput for workload Read/Scan/Write
Read latency for workload Read/Write
Read latency for workload Read/Write
Write latency for workload Read/Write
Write latency for workload Read/Write

If this benchmarking data from University of Toronto is interesting, take a 1o minute Cassandra walkthrough and learn more.


Netflix

Netflix decided to run a test designed to validate their tooling and automation scalability as well as the performance characteristics of Cassandra. The results of their testing are provided below. For a more thorough write up of the Netflix testing process including configuration settings and commentary, visit their tech blog post titled Benchmarking Cassandra Scalability on AWS – Over a million writes per second.

Netflix performance testing: scale-up linearity
Netflix performance testing: per node activity
Netflix performance testing: time and money savings


Apache_Tutorial_728x90