Apache HBase is a robust random-access distributed datastore built upon Apache Hadoop’s HDFS and Apache ZooKeeper. Over the past year at Cloudera, we’ve seen our customers’ use cases expand in size and scope leading to more multi-application, multi-tenant, and multi-datacenter deployments. One major trend in our production support has been more emphasis on tuning to deal with performance inconsistencies. The community has grown considerably as well; the proliferation of new frameworks and systems that integrate with HBase provide new functionality, opportunity, and demands.
This talk will describe three themes emerging based upon these trends and from recent features slated for the upcoming post-0.96 release. First, we’ll discuss improvements for multi-application, multi-tenant and multi-datacenter deployments such as namespaces and smarter balancers. Next, we’ll describe community activity focusing on mechanisms for faster mean-time-to-recovery (MTTR), and techniques for more predictable 99.9%tile latencies on reads and writes including smarter compactions, multiple write ahead logs, and proposals for read-replicas. Finally we’ll talk about the proliferation of new integrations that extend HBase to include new security/auditing capabilities and new database-like functionality including SQL querying and indexing support.
Software Engineer @ Cloudera. Apache HBase Commiter, Apache Flume Founder.
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
For exhibition and sponsorship opportunities, contact Susan Stewart at firstname.lastname@example.org
For information on trade opportunities with O'Reilly conferences email mediapartners
For media-related inquiries, contact Maureen Jennings at email@example.com
View a complete list of Strata + Hadoop World 2013 contacts