hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Patrick Hunt <ph...@apache.org>
Subject Re: Failures after a few hours of heavy load
Date Mon, 22 Feb 2010 17:24:57 GMT

Jean-Daniel Cryans wrote:
> On Sat, Feb 20, 2010 at 2:27 PM, Rod Cope <rod.cope@openlogic.com> wrote:
>>> 3. No need to run 9 ZK quorum members, 3 is fine or even 1 fwiw in your case.
>> Thanks for the suggestion - I'll go with 3.  I was planning to run 5, but
>> hadn't gotten around to running a separate ZK quorum (they're managed by
>> HBase right now).  Would having 9 cause problems?  It doesn't seem to be
>> making trouble at this point.
> 
> With 9 some write operations might take longer (search "Patrick Hunt"
> on this list and you will find links to graphs showing ops latency vs
> number of nodes). At StumbleUpon we run with quorums of 5, only 1 per
> datacenter.

As long as network latency between ZK servers in the ensemble is low it 
won't matter much (if at all) for the use case HBase is currently using. 
You only really need to think about reliability and 5 is fine for that: 
http://bit.ly/ak1Irk

On the other hand, you are using resources that could be applied to 
other parts of the system, so from that perspective it's bad/wasteful. 
Turn down the ZK servers and apply that memory/cpu to something more 
important - like the HBase server memory.

Patrick

Mime
View raw message