Communications of the ACM
High-speed policy-based packet forwarding using efficient multi-dimensional range matching
Proceedings of the ACM SIGCOMM '98 conference on Applications, technologies, architectures, and protocols for computer communication
Robust Multiclass Signaling Overload Control
ICNP '05 Proceedings of the 13TH IEEE International Conference on Network Protocols
The 3G IP Multimedia Subsystem (IMS): Merging the Internet and the Cellular Worlds, Second Edition
The 3G IP Multimedia Subsystem (IMS): Merging the Internet and the Cellular Worlds, Second Edition
Network Algorithmics,: An Interdisciplinary Approach to Designing Fast Networked Devices (The Morgan Kaufmann Series in Networking)
Real-time monitoring of SIP infrastructure using message classification
Proceedings of the 3rd annual ACM workshop on Mining network data
Algorithms for packet classification
IEEE Network: The Magazine of Global Internetworking
SIP message classification: design and performance
ACM SIGOPS Operating Systems Review
The impact of TLS on SIP server performance
Principles, Systems and Applications of IP Telecommunications
The impact of TLS on SIP server performance: measurement and modeling
IEEE/ACM Transactions on Networking (TON)
| Hi-index | 0.00 |
Session Initiation Protocol (SIP) has begun to be widely deployed for multiple services such as VoIP, Instant Messaging and Presence. Each of these services uses different SIP messages, and depending on the value of a service, e.g. revenue, the associated messages may need to be prioritized accordingly. Even within the same service, different messages may be assigned different priorities. In this paper, we present the design and implementation of a programmable classification engine for SIP messages in the Linux kernel. This design uses a novel algorithm that in addition to classifying messages can extract and maintain state information across multiple messages. We apply the classifier for overload control using operator-specified rules for categorizing messages and associated actions, augmented with a protocol-level understanding of SIP message structure. When faced with loads beyond their capacity (e.g., during catastrophic situations and major network outages), SIP servers must drop messages. It is therefore desirable that the server process high-value messages in preference to lower-value messages. We evaluated our in-kernel classifier implementation with an open source SIP server (SER) for such an overload scenario. The workload consists of a mix of call setup and call handoff messages, and the classifier is programmed with rules that prioritize handoffs over call setups. We show that, while SER can process about 40K messages/sec (in a FIFO manner), our classifier can examine and prioritize 105K messages/sec during overload. With the classifier operating at peak throughput, SER's processing rate drops to 31.6K messages/sec, but all of the available high-value messages are processed.