ZK should have a separate disk IF you have tight latency or high throughput requirements.
If ZK committing the log after other disk writes is OK and if you are doing dozens of transactions per second rather than , then you are fine sharing a disk. In terms of latency, with a shared and busy disk you may find occasional times of 200-300 ms. ZK only requires as much RAM as you have data. For coordination work as with Hbase, the amount of data in ZK should be relatively small. You can ask ZK for information like this. The four letter commands are your friend: http://hadoop.apache.org/zookeeper/docs/r3.1.1/zookeeperAdmin.html#sc_zkCommands On Wed, Dec 8, 2010 at 10:07 AM, Hari Sreekumar <[email protected]> wrote: > Hi > > why is it generally said that zk should have a separate disk of it's > own? Currently in my small 5 node cluster, one of the regionservers > itself is also the zk. How beneficial is it to move it to a separate > machine? And in that case, what should be the machine config > like?should it be ram intensive or CPU intensive or io intensive? It > would be great if you could also explain the reason briefly. > > Thanks, > Hari >
