I’ve been catching up on some old RSS feed links recently and came across this gem: http://www.gridgain.com/blog/gridgains-open-source-in-memory-computing-strategy-sets-stage-for-unprecedented-advances/. I’m not too familiar with GridGain but I’m happy to see it being open sourced and joining the wave of other solutions like Spark.
I’m a little curious if anyone has hands-on performance data comparing GridGain and Spark. I dug up a link to a thesis that compared Spark to another technology and found some limitations in Spark when the data set size started to exceed the RAM in the cluster. But a quick search doesn’t yield anything similar for GridGain and Spark.