Yahoo! Cloud Serving Benchmark (YCSB)

News

YCSB 0.7.0 (release note) is now available for download. Give it a try!

https://github.com/brianfrankcooper/YCSB/releases/download/0.7.0/ycsb-0.7.0.tar.gz

Links

[email protected]
http://groups.yahoo.com/group/ycsb-users

Papers and Presentations

Source code:

http://github.com/brianfrankcooper/YCSB/

---

Welcome Michi Mutsuzaki (m1ch1) as a new maintainer ofYCSB!  

Overview

There are many new serving databases available, including:

• HBase
• Hypertable
• Cassandra
• Couchbase
• Voldemort
• MongoDB
• OrientDB
• Infinispan
• Redis
• GemFire
• DynamoDB
• Tarantool
• Memcached
  …and many others

It is difficult to decide which system is right for your application, partially because the features differ between systems, and partially because there is not an easy way to compare the performance of one system versus another.

The goal of the YCSB project is to develop a framework and common set of workloads for evaluating the performance of different “key-value” and “cloud” serving stores. The project comprises(包含) two things:

• The YCSB Client, an extensible workload generator    //负载生成器
• The Core workloads, a set of workload scenarios to be executed by the generator  //测试方案生成器

Although the core workloads provide a well rounded picture of a system’s performance, the Client is extensible so that you can define new and different workloads to examine system aspects, or application scenarios, not adequately covered by the core workload. Similarly, the Client is extensible to support benchmarking different databases. Although we include sample code for benchmarking HBase, Cassandra, Infinispan and MongoDB, it is straightforward to write a new interface layer to benchmark your favorite database.

A common use of the tool is to benchmark multiple systems and compare them. For example, you can install multiple systems on the same hardware configuration, and run the same workloads against each system. Then you can plot the performance of each system (for example, as latency versus throughput curves) to see when one system does better than another.

A paper describing the benchmark and some results ishere.

Next

1. Getting Started
2. Running a Workload
3. Adding a Database

Note: YCSB is newly released into open source as of 4/23/2010. We believe this documentation is fairly complete, but if you find bugs or inconsistencies, please [email protected] or file an issue.

Other links

• Related Projects
• Redis benchmark by Robert Lehmann – http://robertlehmann.de/img/redis.pdf