Use of Network Latency Profiling and Redundancy for Cloud Server Selection

摘要: As servers are placed in diverse locations networked services today, it becomes vital to direct a client's request the best server(s) achieve both high performance and reliability. In this distributed setting, non-negligible latency server availability become two major concerns, especially for highly-interactive applications. Profiling latencies sending redundant data have been investigated as solutions these issues. The notion of cloudlet mobile-cloud computing is also relevant context, can supply solution approaches on behalf mobile. paper, we investigate effects profiling redundancy when client has choice multiple connect to, using measurements from real experiments simulations. We devise test different selection partitioning strategies terms redundancy. Our key findings summarized follows. First, intelligent algorithms help find optimal group that minimize with profiling. Second, good relatively simple analysis provides insight designers determine how many which select reduce latency.