LogP: towards a realistic model of parallel computation
PPOPP '93 Proceedings of the fourth ACM SIGPLAN symposium on Principles and practice of parallel programming
The importance of non-data touching processing overheads in TCP/IP
SIGCOMM '93 Conference proceedings on Communications architectures, protocols and applications
Computer architecture (2nd ed.): a quantitative approach
Computer architecture (2nd ed.): a quantitative approach
FAST '03 Proceedings of the 2nd USENIX Conference on File and Storage Technologies
Making the Most Out of Direct-Access Network Attached Storage
FAST '03 Proceedings of the 2nd USENIX Conference on File and Storage Technologies
Storage Over IP: When Does Hardware Support Help?
FAST '03 Proceedings of the 2nd USENIX Conference on File and Storage Technologies
TCP offload is a dumb idea whose time has come
HOTOS'03 Proceedings of the 9th conference on Hot Topics in Operating Systems - Volume 9
End system optimizations for high-speed TCP
IEEE Communications Magazine
Integrated network interfaces for high-bandwidth TCP/IP
Proceedings of the 12th international conference on Architectural support for programming languages and operating systems
Evaluating network processing efficiency with processor partitioning and asynchronous I/O
Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems 2006
Server network scalability and TCP offload
ATEC '05 Proceedings of the annual conference on USENIX Annual Technical Conference
Connection handoff policies for TCP offload network interfaces
OSDI '06 Proceedings of the 7th symposium on Operating systems design and implementation
On the Benefit of Caching Traffic Flow Data in the Link Buffer
SAMOS '08 Proceedings of the 8th international workshop on Embedded Computer Systems: Architectures, Modeling, and Simulation
Protocol offload analysis by simulation
Journal of Systems Architecture: the EUROMICRO Journal
SpringSim '09 Proceedings of the 2009 Spring Simulation Multiconference
Design and development of Ethernet-based storage area network protocol
Computer Communications
Network interfaces for programmable NICs and multicore platforms
Computer Networks: The International Journal of Computer and Telecommunications Networking
IsoStack: highly efficient network processing on dedicated cores
USENIXATC'10 Proceedings of the 2010 USENIX conference on USENIX annual technical conference
CacheCard: caching static and dynamic content on the NIC
Proceedings of the 5th ACM/IEEE Symposium on Architectures for Networking and Communications Systems
Trace system of iSCSI storage access and performance improvement
DASFAA'05 Proceedings of the 10th international conference on Database Systems for Advanced Applications
HotOS'13 Proceedings of the 14th USENIX conference on Hot Topics in Operating Systems
Leveraging bandwidth improvements to web servers through enhanced network interfaces
The Journal of Supercomputing
Hi-index | 0.00 |
Periodic order-of-magnitude jumps in Ethernet bandwidth regularly reawaken interest in TCP/IP transport protocol offload. This time the jump to 10-Gigabit Ethernet coincides with the emergence of new network storage protocols (iSCSI and DAFS), and vendors are combining these with offload NICs to position IP as a competitor to FibreChannel and other SAN interconnects. But what benefits will offload show for application performance?Several recent studies have presented conflicting data to argue that offload either does or does not benefit applications. But the evidence from empirical studies is often little better than anecdotal. The principles that determine the results are not widely understood, except for the first principle: Your Mileage May Vary.This paper outlines fundamental performance properties of transport offload and other techniques for low-overhead I/O in terms of four key ratios that capture the CPU-intensity of the application and the relative speeds of the host, NIC device, and network path. The study also reflects the role of offload as an enabler for direct data placement, which eliminates some communication overheads rather than merely shifting them to the NIC. The analysis applies to Internet services, streaming data, and other scenarios in which end-to-end throughput is limited by network bandwidth or processing overhead rather than latency.