* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download a sequence preserving efficient packet scheduler using
Survey
Document related concepts
Backpressure routing wikipedia , lookup
Recursive InterNetwork Architecture (RINA) wikipedia , lookup
Network tap wikipedia , lookup
Computer network wikipedia , lookup
Airborne Networking wikipedia , lookup
Distributed firewall wikipedia , lookup
Asynchronous Transfer Mode wikipedia , lookup
Multiprotocol Label Switching wikipedia , lookup
Serial digital interface wikipedia , lookup
TCP congestion control wikipedia , lookup
Cracking of wireless networks wikipedia , lookup
Packet switching wikipedia , lookup
Transcript
Proceedings of the International Conference , “Computational Systems and Communication Technology” 8th , MAY 2010 - by Cape Institute of Technology, Tirunelveli Dt-Tamil Nadu,PIN-627 114,INDIA ORDERED ROUND ROBIN SCHEME FOR EFFICIENT PACKET SCHEDULER J.JENIFERJOSE, PG scholar, Department of IT, Francis Xavier Engineering College, Tirunelveli. E-mail:[email protected] J.Monica Esther , Lect/IT - Francis Xavier Engineering College, Tirunelveli. ABSTRACT Network processors (NPs) has many computation-intensive tasks such as routing table lookup, classification, IPSec, and multimedia transcoding can be accomplished more easily in a router. An NP consists of a number of on-chip processors to carry out packet level parallel processing operations. Ensuring good load balancing among theprocessors increases throughput. However, such multiprocessing also gives rise to increased out-of-order departure of processed packets. In this paper, we propose an Ordered Round-Robin (ORR) scheme to schedule packets in a heterogeneous NP assuming that the workload is perfectly divisible. The processed loads from the processors are ordered perfectly. We analyze the throughput and derive expressions for the batch size, scheduling time, and maximum number of schedulable processors. To effectively schedule variable length packets in an NP, we propose a Packetized ORR (P-ORR) scheme by applying a combination of deficit round-robin (DRR) and surplus round-robin (SRR) schemes. Index Tterms- Load balancing, in-order delivery, Scheduler, Ordered round robin I. INTRODUCTION Round-robin is one of the simplest scheduling algorithms for processes in an operating system, which assigns time slices to each process in equal portions and in circular order, handling all processes without priority. Round-robin scheduling is both simple and easy to implement, and starvation-free. Round-robin scheduling can also be applied to other scheduling problems, such as data packet scheduling in computer networks. Round-robin job scheduling may not be desirable if the size of the jobs or tasks are strongly varying. A process that produces large jobs would be favored over other processes. This problem may be solved by time-sharing, i.e. by giving each job a time slot or quantum allowance of and interrupt the job if it is not completed by then. The job is resumed next time a time slot is assigned to that process. A multiplexer, switch or router that provides round-robin scheduling has a separate queue for every data flow, where a data flow may be identified by its source and destination address. The algorithm lets every active data flow to take turns in transferring packets on a shared channel in a periodically repeated order. The scheduling is non-work conserving, meaning that if one flow is out of packets, next data flow will take its place. These services demand service differentiated and application oriented processing at network nodes with quality of service provision .Given the processing power limitation of single processor and the inherent parallelism associated with network traffic, parallel processing is becoming increasingly attractive. Applicationoriented services often carry stringent performance requirements, which are increasingly handled by multicore processors. As such, several companies have Introduced powerful network processors (NPs) that can be placed in routers to execute various tasks in the network. These tasks can range from IP level table lookup algorithm to application level multimedia transcoding applications. Such an NP-based router permits sophisticated computations within the network by allowing their users to inject customized programs into the nodes of the network. Proceedings of the International Conference , “Computational Systems and Communication Technology” 8th , MAY 2010 - by Cape Institute of Technology, Tirunelveli Dt-Tamil Nadu,PIN-627 114,INDIA Fig.1. Packet scheduling model for network processor Objective The aim of this project is to derive an efficient packet scheduling algorithm in an NP that comprises a number of processors for packet processing. It should provide Load balancing for processing variable length Packets using a group of heterogeneous Processors . In-order delivery of packets without considering receiver’s rearranging capability. II. RELATED WORKS In [6] we propose a new version of TCP that maintains high throughput when reordering occurs and yet, when packet reordering does not occur, is friendly to other versions of TCP. The proposed TCP variant, or TCP-PR, does not rely on duplicate acknowledgments to detect a packet loss. Instead, timers are maintained to keep track of how long ago a packet was transmitted. In case the corresponding acknowledgment has not yet arrived and the elapsed time since the packet was sent is larger than a given threshold, the packet is assumed lost. Because TCP-PR does not rely on duplicate acknowledgments, packet reordering has no effect on TCP-PR's performance In Existing system First-Come-First- Serve (FCFS) basis and combines the traffic back into a single stream onto the output port. The aim of the packet scheduling algorithm is twofold. The input load is balanced among the processors P1 through Pm. The flow order is maintained when the packets are transmitted to the transmitting processor pt. In NPs, the packets are processed on the worker processors Finally, the transmitting processor in an NP removes the packets from the worker processors on an FCFS basis, whereas the receiving processor in the striping model executes a resequencing algorithm. In[4]we first propose an Ordered Round Robin (ORR) scheme to schedule packets in a heterogeneous network processor assuming that the workload is perfectly divisible. The processed loads from the processors are ordered perfectly. We analyze the throughput and derive expressions for the batch size, scheduling time and maximum number of schedulable processors. To effectively schedule variable length packets in an NP, we propose a Packetized Ordered Round Robin (P-ORR) scheme by applying a combination of deficit round robin (DRR) and surplus round robin (SRR) schemes. We extend the algorithm to handle multiple flows based on a fair scheduling of flows depending on their reservations. Extensive sensitivity results are provided through analysis and simulation to show that the proposed algorithms satisfy both the load balancing and in-order requirements for parallel packet processing. III. WORKING OF EFFICIENT PACKET SCHEDULER USING ORDERED ROUND ROBIN SCHEME : An efficient packet scheduling algorithm, P-ORR, that is capable of scheduling variable length packets among a group of heterogeneous processors to ensure both load balancing and minimal out of- order packet delivery. P-ORR is based on the ORR algorithm, which we developed from rigorous theoretical derivation by assuming that the workload is perfectly divisible. Proceedings of the International Conference , “Computational Systems and Communication Technology” 8th , MAY 2010 - by Cape Institute of Technology, Tirunelveli Dt-Tamil Nadu,PIN-627 114,INDIA Fracti on1 Packet1 Packet 2 Packe tn Dispa tcher Fracti on2 Fractio nm processed loads from the processors are ordered perfectly. Work processor1 Work Processor2 Transmit ter Process or Term inal Work Processor m Fig :2 System model In the proposed system packets are processed in an NP, there are three steps: 1. D-step: the dispatching processor dispatches the packet worker processor 2. P-step: the worker processor processes the packet Fig.5.1. Congestion Detection 3. T-step: the worker processor sends the packet to the transmitting processor. This figure shows how to detect the congestion in variable length packets. IV. FUTURE WORKS Fair Scheduling Among Multiple Flows A P-ORR algorithm is used to schedule incoming packets among multiple processors with basic assumption that all the incoming packets are a treated equally. However packets may belong to different network flows that have made different reservations. In order to handle such packets PORR algorithm is extended to provide fair scheduling among multiple flows. Congestion control concerns controlling traffic entry into a telecommunications network, so as to avoid congestive collapse by attempting to avoid oversubscription of any of the processing or link capabilities of the intermediate nodes and networks and taking resource reducing steps, such as reducing the rate of sending packets. It should not be confused with flow control, which prevents the sender from overwhelming the receiver. A Packetized ORR (P-ORR) scheme by applying a combination of deficit round-robin and surplus round-robin schemes. V. EXPERIMENTAL RESULTS V. CONCLUSION Ordered Round-Robin (ORR) scheme to schedule packets in a heterogeneous NP assuming that the workload is perfectly divisible. The In this phase, an efficient packet scheduling algorithm PORR is implemented, which is capable of scheduling variable length Fig.5.2. Packetized Ordered Round Robin Proceedings of the International Conference , “Computational Systems and Communication Technology” 8th , MAY 2010 - by Cape Institute of Technology, Tirunelveli Dt-Tamil Nadu,PIN-627 114,INDIA packets among a group of heterogeneous processors to ensure both load balancing and minimal out of-order packet delivery. P-ORR is based on the ORR algorithm, which assumes that the workload is perfectly divisible. The PORR algorithm satisfies both the load balancing and in-order requirements for packet transmission. In order to minimize the performance discrepancy between ORR and PORR, a new packetized technique to better address the problem of variable packet length is also used in this project This work can be extended to design an optimal mapping between multiple flows and processors and the derivation of fairness bounds. VI. REFERENCES 1. M.Shreedhar and G. Varghese, “Efficient Fair Queuing Using Deficit Round Robin,” IEEE/ACM Trans. Networking, vol. 4,pp. 375-385, June 1996. 2. Y.C. Cheng and T.G. Robertazzi, “Distributed Computation with Communication Delays,” IEEE Trans. Aerospace and Electronic Systems, vol. 24, no. 6, pp. 700-712, Nov. 1988. 3. L. Kencl and J.Y.L. Boudec, “Adaptive Load Sharing for Network Processors,” Proc. IEEE INFOCOM, 2002. 4. J.A. Cobb and M. Lin, “A Theory of MultiChannel Schedulers for Quality of Service,” J. High Speed Networks, vol. 12, nos. 1,2, pp. 61-86, 2002. 5. J. Guo, F. Chen, L. Bhuyan, and R. Kumar, “A Cluster-Based Active Router Architecture Supporting Video/Audio StreamTranscoding Services,” Proc. 17th Int’l Parallel and Distributed Processing Symp. (IPDPS ’03), Apr. 2003. 6. T.G. Robertazzi, “Ten Reasons to Use Divisible Load Theory,” Computer, vol. 36, no. 5, pp. 63-68, May 2003. 7. B. Wu, Y. Xu, H. Lu, and B. Liu, “An Efficient Scheduling Mechanism with Flow-Based Packet Reordering in a High-Speed Network Processor,” Proc. IEEE Workshop High Performance Switching and Routing (HPSR), 2005 8. J. Guo, J. Yao, and L. Bhuyan, “An Efficient Packet Scheduling Algorithm in Network Processors,” Proc. IEEE INFOCOM ’05,vol. 2, pp. 807-818, Mar. 2005. 9. S. Bohacek, J.P. Hespanha, and J. Lee, “A New TCP for Persistent Packet Reordering,” IEEE/ACM Trans. Networking, vol. 14, no. 2,pp. 369-382, Apr. 2006. 10. Shi and L. Kencl, “Sequence-Preserving Adaptive Load Balancers,” Proc. ACM/IEEE Symp. Architectures for Networking and Comm. Systems (ANCS ’06), pp. 143-152, Dec. 2006.