Hi Jason, I will not be able to tell you all the details, but this was a IoT use case which doesn't require a lot of memory and doesn't store a lot of data in memory, but has strict SLAs on throughput and latency under load. Each incoming event triggered 2-3 atomic cache operations (get/put/invoke). Updates were persisted to Cassandra using write-through. In the benchmark we were running, the whole system was able to process million events per seconds. I don't remember the numbers for latency, but they were within production SLAs.
As for the large clusters, I recommend to try it and see how it behaves in production environment. You can also refer to this page for some tuning tips: https://apacheignite.readme.io/docs/preparing-for-production -Val -- View this message in context: http://apache-ignite-users.70518.x6.nabble.com/Is-Ignite-worth-using-in-its-current-state-in-production-Is-it-mature-enough-tp6748p6898.html Sent from the Apache Ignite Users mailing list archive at Nabble.com.
