2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID) (2018)
Washington, DC, USA
May 1, 2018 to May 4, 2018
Big data and large-scale Java applications often aggregate the resources of many servers. Low-latency and high-throughput network communication is important, if the applications have to process many concurrent interactive queries. We designed DXNet to address these challenges providing fast object de-/serialization, automatic connection management and zero-copy messaging. The latter includes sending of asynchronous messages as well as synchronous requests/responses and an event-driven message receiving approach. DXNet is optimized for small messages (<; 64 bytes) in order to support highly interactive web applications, e.g., graph-based information retrieval, but works well with larger messages (e.g., 8 MB) as well. DXNet is available as standalone component on Github and its modular design is open for different transports currently supporting Ethernet and InfiniBand. The evaluation with micro benchmarks and YCSB using Ethernet and InfiniBand shows request-response latencies sub 10 μs (round-trip) including object de-/serialization, as well as a maximum throughput of more than 9 GByte/s.
computer centres, Internet, Java, local area networks, storage management
K. Beineke, S. Nothaas and M. Schottner, "Efficient Messaging for Java Applications Running in Data Centers," 2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), Washington, DC, USA, 2018, pp. 589-598.