Thanks Val for your sharing. >> The same goes for data size and latency/throughput. The latter scales >> well and I personally was participating in a project where we achieved >> million operations per second on around 30 servers cluster.
For this project of 30 servers cluster that you participated, can I get more details? - What's the running version, Java or .net? Dev language, C# or Java? - What's the total data volume? - What's the real used memory per node? - How big is the data key/value? - What's the peak read/write QPS of this scenario? - More details about the usage? like streamer? Entry Processor? Sql query? or just put/get? - What's the 90%-tile and 99%-tile latency? - Completely in memory? 7x24? - What's the consistency requirement? - For million operations per second, what's the atomicity and sync mode, ATOMIC and FULL_ASYNC? BTW, if we want to run a cluster with over 200 servers and 1T-2T data volume, is there any special guide/suggestion? Thanks, -Jason -- 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-tp6748p6866.html Sent from the Apache Ignite Users mailing list archive at Nabble.com.
