ignite-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Andrey Kornev <andrewkor...@hotmail.com>
Subject RE: Computation on NodeEntries
Date Tue, 15 Dec 2015 15:40:22 GMT
So now we are back to square one. I'm all ears to suggestions about how does one implement
the following use case in a reliable way:
- given a partitioned cache
- process cache entries on all nodes in parallel
- only the cache entries matching a query should be processed
- cluster topology changes must not cause inconsistent results

This is a fundamental use case, a particular variation of the so-called "collocation of compute
and data" and at the moment I don't see how I can reliably implement it on top Ignite.


Date: Tue, 15 Dec 2015 11:40:48 +0300
Subject: Re: Computation on NodeEntries
From: yzhdanov@apache.org
To: user@ignite.apache.org

SQL query guarantees that the entire data set will be processed. Of course, this should be
a single query, but not a sequence of broadcasted local queries.--Yakov 		 	   		  
View raw message