A simulation study of the OSPF-OMP routing algorithm
Introduction
Open shortest path first (OSPF) is a link-state routing protocol developed by the Internet Engineering Task Force (IETF), and it is the internal gateway protocol currently recommended by the Internet Advisory Board [1], [2]. Like any link-state protocol, it may identify a number of distinct equal-cost paths between source/destination pairs. However, unless the protocol has been explicitly configured to take advantage of these multiple paths, it arbitrarily chooses one route and uses it in all forwarding operations.
One of the earliest attempts at exploiting equal-cost routes was the OSPF variant called OSPF-ECMP, an acronym for equal-cost multipath [3]. ECMP divides the total volume of traffic across all equal-cost paths using fixed, unchanging measures such as line speed or hop count. Referring to the sample four-node network in Fig. 1, if our distance metric is hop count, then there are two equal-cost paths from A to D––ABD with cost 2 and ACD, also with cost 2. OSPF would arbitrarily choose one of these two paths and use it for all traffic arriving at A destined for D. On the other hand, ECMP would split traffic equally between these two routes. This splitting process could be done using round-robin forwarding, in which messages 1,3,5,… go one way, while 2,4,6,… go the other, or via hashing in which the source and destination host identifiers are hashed to produce a numerical value that determines the specific route taken.
However, since ECMP does not dynamically adjust its division of traffic based on a knowledge of current loads, its allocation may be sub-optimal. For example, referring again to Fig. 1, assume that all links have capacity 1, the traffic volume from A to D is 1.2 units, from B to D, 0.5 units, and from C to D, 0.2 units. Using OSPF, all A to D traffic travels via a single route. If that chosen route is ABD, then the BD link is utilized 170% (1.2+0.5 units of traffic, with a link capacity of 1 unit) while the CD link is utilized only 20%. If OSPF instead chooses the ACD path, then the BD and CD links will be used 50% and 140% respectively. In both cases links are overloaded, and the system is unstable. With OSPF-ECMP, traffic from A to D is divided evenly between the two equal-cost routes. This produces utilizations along the BD and CD lines of 110% and 80% respectively––more closely balanced, but still unstable. An optimal split, based on given loads, would allocate 35% of the A to D traffic to path ABD and 65% to ACD, resulting in a utilization of 85% on both BD and CD––a stable system. Unfortunately, since ECMP does not dynamically examine loading values, it is unable to determine this optimal split.
There have been previous attempts to create adaptive routing algorithms that respond to changing traffic loads and patterns. Unfortunately, they have generally met with limited success due to oscillation and protocol overhead [4]. Referring once more to Fig. 1, if ABD were the optimal route from A to D, then a dynamic protocol would shift most traffic to it, causing increased delays and longer queues along that route. This will eventually cause ACD to become the better route, which will cause longer delays and queues along it, causing us to switch back again to ABD, etc. Dynamic algorithms are extremely sensitive to the “granularity” of change. That is, if the protocol discovers a better route but switches too much traffic too quickly, that route becomes overloaded and sub-optimal, quickly leading to oscillation and instability. On the other hand, if too little traffic is switched, then we are not exploiting the adaptive nature of the protocol and will not gain much when compared to traditional static algorithms.
A second major problem with dynamic routing methods is overhead. If we update too often then nodes will always have current loading information but at the cost of excessive network overhead. If updates are infrequent, then the loading information is out-of-date, and decisions about how to distribute traffic may be quite poor.
OSPF-OMP, an acronym for “optimized multipath” is the most recent attempt to create a load-sensitive routing algorithm. It was proposed by Curtis Villamizar of UUNET Corp. in October, 1997 and initially presented to the IETF in March 1998 [5]. Modifications to the original proposal were made in both 1998 and 1999, and the most recent IETF draft is entitled draft-ietf-ospf-omp-03, dated August 18, 1999, and available on the Web at http://www.brookfield.ans.net/ospf-omp/. For additional information about any aspect of OSPF-OMP, check the OMP home page at http://www.brookfield.ans.net/omp/.
This paper gives an overview of the OSPF-OMP protocol and then describes a discrete event simulation model created by the authors to analyze the performance of the entire OSPF family of routing algorithms. It then presents the results of experiments conducted with this model to study the performance of OSPF, OSPF-ECMP, and OSPF-OMP under both normal and highly stressed traffic loads. Our observations are compared with the results of earlier simulation experiments on OSPF conducted by the IETF. Our results demonstrate the important performance improvements that can potentially be achieved using the OSPF-OMP adaptive routing protocol.
Section snippets
The OSPF-OMP routing algorithm
OSPF-OMP belongs to the general category of routing methods called link-state routing algorithms in which every node has a complete copy of the network map that is updated on a regular basis. Using this map each node executes a shortest-path first algorithm to determine the optimal routes. (For more information about the family of link-state routing methods, refer to [6], [10].)
The three fundamental stages of the OSPF-OMP adaptive routing protocol are
- •
flooding of loading information,
- •
load
The simulator
The authors designed and built a packet-based, discrete event simulator capable of modeling the behavior of autonomous systems running either “pure” OSPF or one of the two variants described in Section 2: OSPF-ECMP and OSPF-OMP. A configuration preprocessor allows users to describe the exact network they want to simulate, including the number of nodes, processing speed, the speed and location of communication links, the amount of memory, the arrival rate, size and destination of packets, and
The experiments
We ran a series of simulation experiments using the model in Section 3 to investigate the behavior of OSPF, OSPF-ECMP, and OSPF-OMP under a range of traffic intensities and distributions. All experiments were run using the 13 node, 16-link network shown in Fig. 5. This network roughly corresponds to the structure of the NSF Internet Backbone that existed in 1989 [10].
All communication links have the same speed, which translates to equal cost for all segments. As a result, of the possible
Conclusions
Our experiments with the network simulator have allowed us to get some preliminary estimates of the improvements in message delivery times and packet loss rates that are possible using the OSPF-OMP routing protocol in place of existing implementations of OSPF. Of course, the results presented in this paper apply only to the specific conditions that existed within our experiments, and these results cannot be generalized to statements about the overall performance that can be expected from OMP
G. Michael Schneider is Professor and Chair of the Department of Mathematics and Computer Science at Macalester College, St. Paul, Minnesota. He received his Ph.D. in Computer Science from the University of Wisconsin in 1974 and taught at the University of Minnesota for 8 years before moving to Macalester in 1982. His areas of research include computer networks, network protocols, and distributed systems. He is also the author of seven textbooks in computer science.
References (11)
- et al.
The new routing algorithm for the ARPANET
IEEE Trans. Commun.
(1980) OSPF
(1998)- J. Moy, OSPF, Version 2, IETF Technical Report RFC 2328, 1998. Available from...
- S.H. Low, P. Varaiya, Dynamic behavior of a class of adaptive routing protocols, Proceedings of the Conference on...
- Internet Engineering Task Force, Report RFC 1247, March...
Cited by (18)
Enabling efficient routing for traffic engineering in SDN with Deep Reinforcement Learning
2024, Computer NetworksA survey of low-latency transmission strategies in software defined networking
2021, Computer Science ReviewCitation Excerpt :In addition to ECMP and MPCTP, two commonly used multipath algorithms in SDN, there are other flexible multipath calculation algorithms and traffic segmentation algorithms that deserve our attention. A variant of OSPF, OSPF-OMP (optimized multipath), is implemented by exchanging special traffic load control messages to allow traffic to be divided unevenly on equal-cost paths, and a hash function is used to generate the probability of each path [152,153]. Inspired by MPTCP, Viernickel et al. [154]extended and designed Multi-path Quick UDP Internet Connection (MPQUIC), which enables the QUIC protocol developed by Google to accelerate web traffic to support different paths, such as WiFi and LTE on smart devices, or IPv4 and IPv6 on hosts.
Towards low-complexity Internet traffic engineering: The Adaptive Multi-Path algorithm
2008, Computer NetworksCitation Excerpt :In order to bridge the seemingly contrary objectives of fast load adjustment and the stability of network-wide routing, OMP load balancing defines a very sophisticated mechanism for controlling the dynamics of load shifting, which enables reaching the fix point in traffic distribution very fast and with a minimum of overshoots. In [38], the performance of the Optimized Multi-Path algorithm is evaluated and compared to the performance of two standard routing strategies, i.e., shortest path routing (SPR) and Equal-Cost Multi-Path routing (ECMP) throughout the investigated simulation scenarios. All experiments have been performed using a 13-node, 16-link network topology which corresponds to the National Science Foundation’s (NSF) Internet backbone in 1989 [39], carrying non-elastic traffic according to the Poisson model [40].
A high-reliability and determinacy architecture for smart substation process-level network based on cobweb topology
2014, IEEE Transactions on Power DeliveryEnhancing survivability in virtualized data centers: A service-aware approach
2013, IEEE Journal on Selected Areas in Communications
G. Michael Schneider is Professor and Chair of the Department of Mathematics and Computer Science at Macalester College, St. Paul, Minnesota. He received his Ph.D. in Computer Science from the University of Wisconsin in 1974 and taught at the University of Minnesota for 8 years before moving to Macalester in 1982. His areas of research include computer networks, network protocols, and distributed systems. He is also the author of seven textbooks in computer science.
Tamas Nemeth was born in Kaposvar, Hungary. He received a Bachelor's degree in Computer Science, Mathematics and Physics from Macalester College in Saint Paul, Minnesota. He currently works at ORC Macro as a Senior Programmer Analyst. Among other honors, he received the first place prize from the Society of Industrial and Applied Mathematics and the Institute for Operations Research and Management Sciences in the International Mathematical Modeling Contest with his submission entitled “A Tricubic Interpolation Algorithm for MRI Image Cross-Sections”. His interests include ornithology and snow sculpting at the annual International Snow Sculpting Championships in Breckenridge, Colorado.