News for hackers. Stuff that matters.
Re:Big Data Debate: HBase by monstrado on Tuesday August 06, 2013 @09:43PM (#6170323)
Which version of HBase are you running? If we have a node or two go down in our cluster, HBase is completely unaffected. Recoveries can take up to a few minutes, in the old ages it took hours.

I know that MTTR (mean time to recovery) is being worked on together by several large companies to get down to seconds.

Re:Big Data Debate: HBase by jeremiahjordan on Tuesday August 06, 2013 @10:26PM (#6170454)
"Minutes" is not "unaffected" if your site is now down.
Re:Big Data Debate: HBase by monstrado on Tuesday August 06, 2013 @10:28PM (#6170462)
Sorry, I should have clarified. When a node goes down, there isn't any sort of "minute" interruption...When there's a full scale outage and you need to perform an actual recovery, that can take minutes.
Re:Big Data Debate: HBase by samspenc on Tuesday August 06, 2013 @11:45PM (#6170690)
Also, if you use the Thrift service as an interface to HBase (we do), you can have it running on several machines on the cluster and be able to set them up using a failover architecture - as long as the cluster itself is healthy, Thrift should work from any machine you have it running on.