> > > > > I know there is IgniteDataStreamer for writing cache, but how about > > reading cache as stream for iterate all elements with scan performane > 1-3M > > tuple/sec? > > > > We already have Scan queries which allow for paginated iteration with > filters. Are you suggesting something beyond this?
I like the idea of DataStreamer approach for scanning a cache. I think it would be nice to have a way to iterate over cache partitions in parallel, similar to forEachPartition() method in Spark RDD. Benefits compared to current Scan query: * Parallel execution for different partitions * Bringing computation to data, not data to client. Of course, this can already be implemented by a user with local scan query + compute task, but having an utility method on an API will cut a lot of boilerplate code for users.
