Aaron is Principal Support Engineer at MapR. Aaron is an expert on Big Data systems, distributed storage/computing/applications, Hadoop & Map/Reduce, HBase, and management, monitoring and administration of large computing clusters. Prior to MapR, Aaron was an Escalation Engineer for both Riverbed Technology and EMC, working directly with engineering to resolve complex issues.
Posted on December 16, 2013 by Aaron Eng
There is much more to memory calculations than just the “used” and “free” states. Here’s a quick primer on understanding memory utilization as reported by the MapR framework.
Posted on December 20, 2013 by Aaron Eng
Improving performance by letting MapR-FS do the right thing
Posted on December 30, 2013 by Aaron Eng
For various reasons, data may need to be re-replicated between nodes in a MapR cluster. For example, if a disk goes bad, the content it stored will need to be re-replicated to ensure that the data is fully protected. Decommissioning a node is another instance where re-replication is needed. When a node is moved into a topology which does not have any volumes associated with it, it forces re-replication of the data that it stores onto nodes that are in other topologies.
Blog Sign Up
Sign up and get the top posts from each week delivered to your inbox every Friday!