If I understand correctly, JVM GC takes care of the on-heap memory. My question is, who is going to take care of the off-heap memory?
I guess the answer is Ignite :-) But something I'm not so sure is, can I just make all caches off-heap, and my JVM GC will work with minimal memory, so that my application latency and throughput would be maximised. Is this true? Will the reclamation of off-heap memory cause any latency to the application, or lower the application throughput as Ignite threads run concurrently. Is there a way to monitor the off-heap activities, which is similar to Visual GC in JVisualVM? Could you help give some insight please? Also any best practice here? Thank you. -- View this message in context: http://apache-ignite-users.70518.x6.nabble.com/Who-is-going-to-take-care-of-the-off-heap-memory-tp7138.html Sent from the Apache Ignite Users mailing list archive at Nabble.com.
