Using Packet Scheduling to Enhance I-Cache Behavior of Protocol Processing

Authors:
Zhibin Zhang;Li Guo;Binxing Fang
Affiliations:
Graduate School of the Chinese Academy of Sciences;Chinese Academy of Sciences;Chinese Academy of Sciences
Venue:
HPCASIA '05 Proceedings of the Eighth International Conference on High-Performance Computing in Asia-Pacific Region
Year:
2005

Citing 9
Cited 0

The importance of non-data touching processing overheads in TCP/IP

SIGCOMM '93 Conference proceedings on Communications architectures, protocols and applications
Analysis of techniques to improve protocol processing latency

Conference proceedings on Applications, technologies, architectures, and protocols for computer communications
Speeding up protocols for small messages

Conference proceedings on Applications, technologies, architectures, and protocols for computer communications
Eliminating receive livelock in an interrupt-driven kernel

ACM Transactions on Computer Systems (TOCS)
Networking support for high-performance servers

Networking support for high-performance servers
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Issues in High-Speed Internet Security

Computer
Speeding up TCP/IP: faster processors are not enough

PCC '02 Proceedings of the Performance, Computing, and Communications Conference, 2002. on 21st IEEE International
Improving UNIX kernel performance using profile based optimization

WTEC'94 Proceedings of the USENIX Winter 1994 Technical Conference on USENIX Winter 1994 Technical Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the increase of network bandwidth, high performance protocol processing has shown its importance in network systems. Experimental results show that some advances in computer architecture, such as faster processors and larger cache, are not enough for TCP/IP processing [12]. In this paper, we present a formal analysis on I-Cache behavior of batch protocol processing. We prove that achieving the optimal I-Cache behavior is an NP-hard problem, and then suggest an off-line scheduling method.