ignite-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Evgenii Zhuravlev <e.zhuravlev...@gmail.com>
Subject Re: 1 processing node, n partition nodes
Date Tue, 29 Aug 2017 13:38:47 GMT

What do you mean by 1 node that processing data? If you want to store data
on several nodes and run some compute jobs that use data from these caches
only on one node, then I could say that it a bad idea - it will lead to a
lot of data moving between nodes. It's better to use affinityCall to invoke
jobs on the nodes that hosts data needed in computing.


2017-08-29 15:54 GMT+03:00 matt <goodieboy@gmail.com>:

> Hi,
> Can someone recommend what CacheConfiguration settings would be ideal for a
> cluster that has 1 primary node processing data, while other nodes are
> there
> to host partitions for the purpose of reducing the primary node memory
> requirements? How can I control the size of the local cache per node,
> regardless of whether it's the node doing the processing or not?
> Thanks,
> - Matt
> --
> View this message in context: http://apache-ignite-users.
> 70518.x6.nabble.com/1-processing-node-n-partition-nodes-tp16485.html
> Sent from the Apache Ignite Users mailing list archive at Nabble.com.

View raw message