Hi, I want to incorporate some intelligence while choosing the resources for rdd replication. I thought, if we replicate rdd on specially chosen nodes based on the capabilities, the next application that requires this rdd can be executed more efficiently. But, I found that an rdd creatd by an appplication is owned by only that application and nobody else can access it.
Can someone tell me what kind of operations can be done on a replicated rdd. Or to put it other way, what are the benefits of a replicated rdd or what operations can be performed on a replicated rdd. I just want to know how effective is my work going to be. I'll be happy if some other ideas in the similar line of thought are suggested. Thank you!! Karthik
