Distributed Admission Control for Anycast Flows with QoS Requirements (original) (raw)
Related papers
Distributed Admission Control for Anycast Flows
IEEE Transactions on Parallel and Distributed Systems, 2004
Anycasting has recently become an important research topic, especially for replicated servers. With anycasting, applications can request the "nearest" server for provision of desired (multimedia) service. In this paper, we study efficient Distributed Admission Control (DAC) for anycast flows. We focus on algorithms that perform destination selection and efficient path establishment. Taking advantage of anycasting, our distributed algorithms differ from each other in their dependence on system status information. Performance data obtained through mathematical analysis and simulations show that, in terms of admission probabilities, DAC systems that are based on local status information have performance levels close to those that utilize global and dynamic status information. This renders our DAC algorithms useful not only for the network layer, but also for the application layer admission control for anycast flows.
Efficient distributed admission control for anycast flows
2003 International Conference on Computer Networks and Mobile Computing, 2003. ICCNMC 2003.
Anycasting becomes an important research topic recently especially for the replicated servers where availability and fault-tolerance are critical for quality of service. With anycasting, applications can request the "nearest" server for provision of a desired services. In this paper, we study efficient Admission Control for Anycast (ACA) flows. We focus on algorithms that perform smart destination selection and efficient route establishment weighing at the probe message round trip time (RTT). Taking advantages of anycasting, our ACA algorithms differ from other approach in their dependence on system status information. Performance data obtained through simulation show that our ACA system performs efficiently in terms of admission delay, overhead and admission probability.
Delay Control and Parallel Admission Algorithms for Real-Time Anycast Flow
The Journal of Supercomputing, 2004
An anycast flow is a flow that can be connected to any one of the members in a group of designated (replicated) servers (called anycast group). In this paper, we derive a set of formulas for calculating the end-to-end delay bound for the anycast flows and present novel admission control algorithms for anycast flows with real-time constraints. Given such an anycast group, our algorithms can effectively select the paths for anycast flows' admission and connection based on the least end-to-end delay bounds evaluated. We also present a parallel admission control algorithm that can effectively calculate the available paths with a short delay bound for different destinations in the anycast group so that a best path with the shortest delay bound can be chosen.
Effective real-time anycast flow connection algorithm and delay analysis
2003 International Conference on Parallel Processing, 2003. Proceedings., 2003
Define anycast services as a group of replicated servers that may provide similar or identical services. Using anycast services can significantly simplify some applications such as to seek appropriate servers to provide quality of service and to achieve the load balance and fault-tolerance for service availability. An anycast flow is a sequence of packet that can be established between a user and any server in an anycast (replicated) service group. This paper studies a set of efficient distributed connection setup algorithms for real-time anycast flows. Given an anycast flow between a server j and a request node s with end-to-end deadline D s,j and minimum bandwidth requirement B s,j , our algorithms can effectively seek multiple destination connections in parallel thus the best path which satisfies the requirements of the anycast flow is chosen. The deterministic approach for worst delay bound analysis is also given.
Network Layer Implemented Anycast Load Balancing
2007 IEEE Symposium on Computers and Communications, 2007
This paper presents a server selection method where the server selection is performed by the network, at the first router from the client. This method, usable in networks under single administrative control, combines network metrics (such as traffic or latency) with common server load balancing metrics (such as load, CPU utilisation or response time), allowing network conditions to be taken into account when selecting the server which will handle the request.
Load-balanced anycast routing in computer networks
Proceedings ISCC 2000. Fifth IEEE Symposium on Computers and Communications, 2000
We present a practical approach to routing and anycasting with near-optimum delays taking into account the processing loads at routers and processing elements of a computer network. To accomplish this, the minimum-delay routing problem formulated by Gallager is generalized into the problem of minimum-delay routing with load-balancing to account for processing delays in network nodes (servers and routers). Gallager's theorem for necessary and sufficient conditions for minimum-delay routing is modified to include processing delays and changes of traffic levels at network nodes. The first distributed algorithm for load balanced anycasting and routing in computer networks is presented. This algorithm, named MIDAS, provides approximate solutions to the modified necessary and sufficient conditions for minimum-delay routing. Simulations are use to compare the performance of the new algorithm with the performance of a traditional approach to sever load balancing.
Distributed Load Management Algorithms in Anycast-based CDNs
Anycast is an internet addressing protocol where multiple hosts share the same IP-address. A popular architecture for modern Content Distribution Networks (CDNs) for geo-replicated services consists of multiple layers of proxy nodes for service and co-located DNS-servers for load-balancing among different proxies. Both the proxies and the DNS-servers use anycast addressing, which offers simplicity of design and high availability of service at the cost of partial loss of routing control. Due to the very nature of anycast, redirection actions by a DNS-server also affects loads at nearby proxies in the network. This makes the problem of optimal distributed load management highly challenging. In this paper, we propose and evaluate an analytical framework to formulate and solve the load-management problem in this context. We consider two distinct algorithms. In the first half of the paper, we pose the load-management problem as a convex optimization problem. Following a Kelly-type dual decomposition technique, we propose a fully-distributed load-management algorithm by introducing FastControl packets. This algorithm utilizes the underlying anycast mechanism itself to enable effective coordination among the nodes, thus obviating the need for any external control channel. In the second half of the paper, we consider an alternative greedy
1997
The anycasting communication paradigm is designed to support server replication by allowing applications to easily select and communicate with the “best” server, according to some performance or policy criteria, in a group of content-equivalent servers. We examine the definition and support of the anycasting paradigm at the application layer, providing a service that maps anycast domain names into one or more IP addresses using anycast resolvers. In addition to being independent from network-layer support, our definition includes the notion of filters, functions that are applied to groups of addresses to affect the selection process. We consider both metric-based filters (e.g., server response time) and policy-based filters
A routing protocol for anycast messages
IEEE Transactions on Parallel and Distributed Systems, 2000
An anycast packet is one that should be delivered to one member in a group of designated recipients. Using anycast services may considerably simplify some applications. Little work has been done on routing anycast packets. In this paper, we propose and analyze a routing protocol for anycast message. It is composed of two sub-protocols: the routing table establishment sub-protocol and the packet forwarding sub-protocol. In the routing table establishment sub-protocol, we propose four methods (SSP, MIND , SBT, and CBT) for enforcing an order among routers for the purpose of loop prevention. These methods differ from each other on information used to maintain orders, the impact on QoS, and the compatibility to the existing routing protocols. In the packet forwarding subprotocol, we propose a weighted-random selection (WRS) approach for multiple path selection in order to balance network traffic. In particular, the fixed and adaptive methods are proposed to determine the weights. Both of them explicitly take into account the characteristics of distribution of anycast recipient group while the adaptive method uses the dynamic information of the anycast traffic as well. Correctness property of the protocol is formally proved. Extensive simulation is performed to evaluate our newly designed protocol. Performance data show that the loop-prevention methods and the WRS approaches have great impact on the performance in terms of average end-to-end packet delay. In particular, the protocol using the SBT or CBT loop-prevention methods and the adaptive WRS approach performs very close to a dynamic optimal routing protocol in most cases.
Distributed load management in anycast-based CDNs
2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2015
Anycast is an internet addressing protocol where multiple hosts share the same IP-address. A popular architecture for modern Content Distribution Networks (CDNs) for georeplicated HTTP-services consists of multiple layers of proxy nodes for service and co-located DNS-servers for load-balancing on different proxies. Both the proxies and the DNS-servers use anycast addressing, which offers simplicity of design and high availability of service at the cost of partial loss of routing control. Due to the very nature of anycast, load-management decisions by a co-located DNS-server also affects loads at nearby proxies in the network. This makes the problem of distributed load management highly challenging. In this paper, we propose an analytical framework to formulate and solve the load-management problem in this context. We consider two distinct algorithms. In the first half of the paper, we pose the load-management problem as a convex optimization problem. Following a dual decomposition technique, we propose a fully-distributed loadmanagement algorithm by introducing FastControl packets. This algorithm utilizes the underlying anycast mechanism itself to enable effective coordination among the nodes, thus obviating the need for any external control channel. In the second half of the paper, we consider an alternative greedy load-management heuristic, currently in production in a major commercial CDN. We study its dynamical characteristics and analytically identify its operational and stability properties. Finally, we critically evaluate both the algorithms and explore their optimality-vscomplexity trade-off using trace-driven simulations.