Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Plain View
Kafka >> mail # user >> Cluster design distribution and JBOD vs RAID


+
Bert Corderman 2014-04-16, 17:58
+
Bert Corderman 2014-04-17, 13:21
+
Andrew Otto 2014-04-18, 14:36
+
Jay Kreps 2014-04-18, 17:06
+
Maxime Brugidou 2014-04-18, 22:24
Copy link to this message
-
Re: Cluster design distribution and JBOD vs RAID
I think we are saying the same thing. If any drive fails the broker is
down. But when the drive is repaired only the data on the destroyed drive
will need to be restored from replicas.

-Jay
On Fri, Apr 18, 2014 at 3:24 PM, Maxime Brugidou
<[EMAIL PROTECTED]>wrote:
 
+
Andrew Otto 2014-04-21, 14:00
+
Bert Corderman 2014-04-23, 14:46