Congestion Manager (CM)
Abstract:
Congestion Manager:
The CM is an end-to-end framework for congestion control and management, bandwidth sharing, independent of specific transport protocols (like TCP) and applications. Its end-system architecture enables logically different flows (such as multiple concurrent Web downloads, concurrent audio and video streams, etc.) to adapt to congestion, share network information, and share (varying) available bandwidth well. Rather than have each stream act in isolation and thereby adversely interact with the others, the CM maintains host- and domain-specific path information, and orchestrates all transmissions. The CM's internal algorithms ensure social and stable network behavior; its API enables a variety of applications and transport protocols to adapt to congestion and varying bandwidth. Internet traffic patterns and applications have been evolving rapidly in recent years and network congestion is becoming a problem of extreme importance. While the Internet's transport protocol, TCP, incorporates congestion control machinery and has largely been responsible for the stability of the Internet to date, two problematic trends threaten this situation:
Concurrent flows. Several applications are characterized by multiple concurrent flows between sender and receiver. Today, these flows compete with each other for network resources, prove overly aggressive on the network, and do not share information about the network with each other.
Lack of adaptation. An increasing number of applications use UDP-based flows without sound congestion control because they do not need the reliable, in-order service provided by TCP. Today, they do not learn about or adapt well to changing network conditions. Unfortunately, current protocol architectures do not provide adequate support for this.
Motivated by these trends, we take a fresh look at Internet congestion management from an end-system perspective and proposes a new architecture built around the CM. The CM maintains network statistics across flows, orchestrates data transmissions governed by robust control principles, and obtains feedback from the receiver, using a Congestion Controller, Flow Scheduler, and Feedback Prober. It also exports a simple yet powerful API for applications to learn about network state and adapt their data transmissions to obtain the best possible performance. We are also exploring several new algorithms for end-to-end congestion control, especially for streaming real-time audio and video. The CM framework provides a modular implementation platform for these ideas.
False Sharing:
Several recent proposals have been made for sharing congestion information across concurrent flows between end-systems. In these proposals, the granularity for sharing has ranged from all flows to a common host, to all hosts on a shared LAN.
However, all these proposals have been plagued by deployment concerns despite their many demonstrated benefits, primarily due to one reason: false sharing. False sharing of congestion management systems arises because such systems might unknowingly force flows to share congestion information, where they should not. Two or more flows sharing congestion state may in fact not share the same bottleneck.
This work presents a detailed study of this problem, investigating various sources of false sharing and analyzing its negative impact. We categorize the origins of this false sharing into two distinct cases: (i) networks with QoS enhancements such as differentiated services, where a flow classifier segregates flows into different queues, and (ii) networks with path diversity where different flows to the same destination address are routed differently.
Project Website: Congestion Manager, False Sharing
People: Aditya Akella, Srinivasan Seshan and Hari Balakrishnan (MIT)
Recent Publications:
The Impact of False Sharing on Shared Congestion Management
Srinivasa Aditya Akella, Srinivasan Seshan and Hari Balakrishnan
CS Technical Report Number CMU-CS-01-135, Pittsburgh, PA, 2001.Postscript, PDF Congestion Manager
16th IEEE Annual Computer Communications Workshop, Charlottsville, VA September 2001
Presentation by: Srinivasan Seshan
Powerpoint Congestion Management and Service Differentiation
PDL Retreat 2001
Presentation by: Aditya Akella
Powerpoint The Impact of False Sharing on Shared Congestion Management
PDL Retreat 2001 Poster Session
Presentation by: Aditya Akella
The Impact of False Sharing on Shared Congestion Management
Sigcomm 2001 Poster Session
Presentation by: Aditya Akella
Powerpoint System Support for Bandwidth Management and Content Adaptation in Internet Applications
David Andersen, Deepak Bansal, Dorothy Curtis, Srinivasan Seshan and Hari Balakrishnan,
Proc. USENIX OSDI Conf., San Diego, CA October 2000
Postscript, PDF Implementation and Evaluation of a Congestion Manager
OSDI 2000, San Diego, CA. October 24, 2000.
Presentation by: