OpenTSDB was originally written to address a common need: store and index metrics collected from computer systems (network gear, operating systems, applications) at a large scale, and make this data easily accessible and graphable.
Most existing open-source monitoring systems are not scalable or flexible enough. With OpenTSDB, and thanks to HBase’s scalability, it’s possible to collect many thousands of metrics from thousands of hosts and applications, at a high rate (every few seconds). OpenTSDB will never delete or downsample data and can easily store billions of data points.
Imagine having the ability to quickly generate a graph of the average number of IOPS your databases do, per database schema, over a period of a week, and on the same graph, plot the number of queries per second your servers are handling to see how much of a correlation there is. OpenTSDB makes this type of operation trivial, while manipulating millions of data point for very fine grained, real-time monitoring.
Sounds good. ☞ GitHub repo already set, but nothing in there yet.
Original title and link: OpenTSDB: A Distributed, Scalable Monitoring System on Top of HBase (NoSQL databases © myNoSQL)