Hi,

My name is Harry and I work for LinkedIn. Here in LinkedIn we have a use
case where in some service (Ambry is an example), a Helix client needs to
access aggregated information of Helix clusters from different data center
regions for management and coordination purpose. However, having each
client talking directly to ZooKeeper in different data centers introduces
heavy cross-dc traffic.

To solve problem like this, and to make the solution more generic, I would
like to propose a design for aggregated cluster view service in the Helix
ecosystem. Please checkout the PR of the design doc at
https://github.com/apache/helix/pull/266

--
Best,
Harry

Reply via email to