hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Andrew Purtell <apurt...@apache.org>
Subject Re: HBase-0.20.0 multi read
Date Tue, 25 Aug 2009 10:20:55 GMT
Zookeeper is deployed as an ensemble of quorum peers in order to be highly available. Ensembles
should be odd so one of a set of conflicting votes (should they occur) is always a majority.
Typical deployments are of 3, 5, and 7 dedicated servers. 

   - Andy




________________________________
From: "y_823910@tsmc.com" <y_823910@tsmc.com>
To: hbase-user@hadoop.apache.org
Sent: Tuesday, August 25, 2009 4:26:17 AM
Subject: Re: HBase-0.20.0 multi read

Hi,

By increasing two zookeeper servers, I've solved my multi read problem.
Thank you very much.

By the way, does anyone where to fine the machine spec or suggestion of
production deployment?
I want to know the percentage of each component will be better.
Maybe like zookeeper server 50% of region servers
           region server    10% of hadoop data nodes
Thank you

ps. sorry I don't understand -> a dedicated 2N+1 Zookeeper ensemble (N ~=
1...3)


      
Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message