U-Net: a user-level network interface for parallel and distributed computing
SOSP '95 Proceedings of the fifteenth ACM symposium on Operating systems principles
An implementation of the Hamlyn sender-managed interface architecture
OSDI '96 Proceedings of the second USENIX symposium on Operating systems design and implementation
When the CRC and TCP checksum disagree
Proceedings of the conference on Applications, Technologies, Architectures, and Protocols for Computer Communication
EMP: zero-copy OS-bypass NIC-driven gigabit ethernet message passing
Proceedings of the 2001 ACM/IEEE conference on Supercomputing
HPDC '00 Proceedings of the 9th IEEE International Symposium on High Performance Distributed Computing
MPI: A Message-Passing Interface Standard
MPI: A Message-Passing Interface Standard
SoftRDMA: implementing iWARP over TCP kernel sockets
IBM Journal of Research and Development
A case for RDMA in clouds: turning supercomputer networking into commodity
Proceedings of the Second Asia-Pacific Workshop on Systems
Hi-index | 0.00 |
Zero-copy, RDMA, and protocol offload are three very important characteristics of high performance interconnects. Previous networks that made use of these techniques were built upon proprietary, and often expensive, hardware. With the introduction of iWarp, it is now possible to achieve all three over existing low-cost TCP/IP networks. iWarp is a step in the right direction, but currently requires an expensive RNIC to enable zero-copy, RDMA, and protocol offload. While the hardware is expensive at present, given that iWarp is based on a commodity interconnect, prices will surely fall. In the meantime only the most critical of servers will likely make use of iWarp, but in order to take advantage of the RNIC both sides must be so equipped. It is for this reason that we have implemented the iWarp protocol in software. This allows a server equipped with an RNIC to exploit its advantages even if the client does not have an RNIC. While throughput and latency do not improve by doing this, the server with the RNIC does experience a dramatic reduction in system load. This means that the server is much more scalable, and can handle many more clients than would otherwise be possible with the usual sockets/TCP/IP protocol stack.