Yes in general the fetch can be improved using standalone clients. I am NOT saying that data nodes are a bottleneck as of now.Indexing is not impacting the search.
The point I am raising is data locality. Data is spread over few shards across few machines.Need to perform processing on this data without explicit fetch outside ES. I want to return sample of grouped entries after going over all matched entries within an index. Thanks, Ram On Saturday, December 13, 2014 9:24:11 PM UTC+5:30, Arie wrote: > > Hi,, > > Consider a non-data master node, this can improve data handling and search > speed a lot as I understand. > > -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/elasticsearch/4af3e662-f9a7-4200-84bf-4cc6af5e4d7d%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
