StumbleUpon: All content tagged as StumbleUpon in NoSQL databases and polyglot persistence
Friday, 6 January 2012
NoSQL Applications Panel Video
Hey, it looks like the NoSQL applications panel I’ve moderated at QCon SF 2011 went live minutes ago on InfoQ. Featuring Andy Gross (Basho), Frank Weigel (Couchbase), Matt Pfeil (DataStax), Michael Stack (StumbleUpon), Jared Rosoff (10gen), and yours truly.
Drop everything and start watching it now! I promise you’ll love every second of it[1].
-
It misses my opening jokes though ↩
Original title and link: NoSQL Applications Panel Video (©myNoSQL)
Thursday, 4 November 2010
HBase and Hadoop: How StumbleUpon Built an Advertising Platform
Jean-Daniel Cryans presentation from Hadoop World on mixing real-time needs and batch processing for building an advertising platform using HBase and Hadoop:
Original title and link: HBase and Hadoop: How StumbleUpon Built an Advertising Platform (NoSQL databases © myNoSQL)
Thursday, 14 October 2010
OpenTSDB: A Distributed, Scalable Monitoring System on Top of HBase
Tracking this based on Hadoop world in tweets. StumbleUpon plans to open source ☞ OpenTSDB: a scalable time series database built on top of HBase. The project page explains what isOpenTSDB:
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)