I worked on a columnar database engine deployed on commodity Linux clusters in 2001, initial release 2002. This was at Sensage. We built a very fast DB engine that could store log data with 40x compression over traditional RDBMSs and ran log queries much more quickly than commercial DBs could at the time. I think we were too early.<p>Current Sensage company blurb about the event-data warehouse: <a href="http://sensage.com/content/clustered-columnar-database" rel="nofollow">http://sensage.com/content/clustered-columnar-database</a> and <a href="http://sensage.com/content/why-columnar%E2%80%A6not-row-based" rel="nofollow">http://sensage.com/content/why-columnar%E2%80%A6not-row-base...</a><p>Patent work: <a href="http://www.patentgenius.com/patent/7024414.html" rel="nofollow">http://www.patentgenius.com/patent/7024414.html</a><p>The core engineering team was CTO + 3 engineers. Best engineering experience of my life. I wasn't involved at the lowest DB storage level, the guys who did that did a great job.<p>Michael Stonebraker, technical advisor to Sensage, learned from the Sensage mistakes and built Vertica.
When I hear columnar storage, I can't help but remember all the stories my friends have told me about kx systems (I'd love to share them but my memory is so fuzzy that I wouldn't be doing them justice. Hopefully some of the HNers here can share some of theirs though!) [1][2].<p>[1] <a href="http://kx.com/" rel="nofollow">http://kx.com/</a><p>[2] <a href="http://en.wikipedia.org/wiki/K_(programming_language)" rel="nofollow">http://en.wikipedia.org/wiki/K_(programming_language)</a>
Everything old is new again. I remember considering using Sybase IQ Multiplex (columnar engine) back in 2000 in my startup. Just like "nosql" was all the rage a few years ago, bringing memory of the Pick databases of yore.
Google's Dremel[0] also belong in this category.<p>[0] <a href="http://research.google.com/pubs/pub36632.html" rel="nofollow">http://research.google.com/pubs/pub36632.html</a>