99,149 Hits in 6.3 sec

A case for run-time adaptation in packet processing systems

Ravi Kokku, Taylor L. Riché, Aaron Kunze, Jayaram Mudigonda, Jamie Jason, Harrick M. Vin
2004 Computer communication review  
In this paper, we explore the benefits and challenges of adapting allocations of processors to packet types in packet processing systems.  ...  We show that, of these two factors, allocating processing power to packet types in small granularity is more important-if the allocation granularity is large, then even a very fine adaptation time-scale  ...  Run-time Adaptation: Challenges In the previous section, we have demonstrated that run-time adaptation of processor allocation can yield significant benefits for packet processing systems.  ... 
doi:10.1145/972374.972393 fatcat:htypkxgul5bf7bvmwq3dgoyygu

Design considerations for network processor operating systems

Tilman Wolf, Ning Weng, Chia-Hui Tai
2005 Proceedings of the 2005 symposium on Architecture for networking and communications systems - ANCS '05  
Network processors (NPs) promise a flexible, programmable packet processing infrastructure for network systems.  ...  run-time environment for network processors.  ...  In this case, processing tasks are allocated to processors offline and no changes are made during run-time.  ... 
doi:10.1145/1095890.1095901 dblp:conf/ancs/WolfWT05 fatcat:jjdsrip2lbcrzizrfxmmy6742a

SURGNET: An Integrated Surgical Data Transmission System for Telesurgery

Sriram Natarajan, Aura Ganz
2009 International Journal of Telemedicine and Applications  
In this paper we propose SURGNET, a telesurgery system for which we developed the architecture, algorithms and implemented it on a testbed.  ...  The algorithms include adaptive packet prediction and buffer time adjustment techniques which reduce the negative effects caused by the lossy and time varying networks.  ...  Acknowledgment This project was supported in part by the following Grants: NSF-ANI-0434985, NSF-ANI-0319871, and NSF-EIA-0080119.  ... 
doi:10.1155/2009/435849 pmid:19503803 pmcid:PMC2688654 fatcat:cs3g3yz6k5hcdgcccfdvvs5m5i

A methodology for evaluating runtime support in network processors

Xin Huang, Tilman Wolf
2006 Proceedings of the 2006 ACM/IEEE symposium on Architecture for networking and communications systems - ANCS '06  
In this paper, we present a model for network processors that can aid in evaluating different run-time support systems.  ...  Traditionally, network processor applications have been optimized for a single static workload scenario, but recently several approaches for run-time adaptation have been proposed.  ...  Performance over Time To illustrate the behavior of a run-time system, it is easiest to consider the case of the Full Processor Allocation system.  ... 
doi:10.1145/1185347.1185363 dblp:conf/ancs/HuangW06 fatcat:7azb6niku5ha3lwnisljyebb34

Adaptive traffic monitoring for software dataplanes

Gioacchino Tangari, Marinos Charalambides, Daphne Tuncer, George Pavlou
2017 2017 13th International Conference on Network and Service Management (CNSM)  
Although advances in packet capture have enabled intercepting packets from network cards at high rates, bottlenecks can still arise in the monitoring process as a result of concurrent access to shared  ...  To demonstrate the capabilities of our approach we implemented it as part of a generic packet-processing pipeline and show that lossless traffic monitoring can be achieved for a wide range of conditions  ...  Run time overhead The overhead is dominated by the time for counting the number of packets that have been processed, by the Monitoring States in the case of Method 1, or for controller queries in Method  ... 
doi:10.23919/cnsm.2017.8255988 dblp:conf/cnsm/TangariCTP17 fatcat:6i26y4ug45ee3gwstcwoxveoiy

End-System Aware, Rate-Adaptive Protocol for Network Transport in LambdaGrid Environments

Pallab Datta, Wu-chun Feng, Sushant Sharma
2006 ACM/IEEE SC 2006 Conference (SC'06)  
We propose the idea of a end-system aware, rate-adaptive protocol for network transport, based on end-system performance monitoring.  ...  These dedicated high-speed connections eliminate network congestion as seen in traditional Internet, but they effectively push the network congestion to the end systems, as processing speeds cannot keep  ...  When the process makes a system call while in user mode (State 3), it moves into State 4 where it begins to run in kernel mode.  ... 
doi:10.1109/sc.2006.26 fatcat:hsbioemqprcbnjmarj5jy7fb2y

Connecting Embedded Devices Using a Component Platform for Adaptable Protocol Stacks [chapter]

Sam Michiels, Nico Janssens, Lieven Desmet, Tom Mahieu, Wouter Joosen, Pierre Verbaeten
2005 Lecture Notes in Computer Science  
Yet, to handle this complex challenge effectively and efficiently, we claim that it is essential for protocol stacks to be developed with run-time adaptability in mind.  ...  This chapter presents a software architecture tailored to build highly adaptable protocol stacks, along with a component platform that enforces this architecture.  ...  run-time adaptability in the domain of protocol stack software (whether or not in an embedded system).  ... 
doi:10.1007/11591962_10 fatcat:tt4ckm7ssfe6vkt547stblqs5u

MetaSockets: design and operation of runtime reconfigurable communication services

S. M. Sadjadi, P. K. McKinley, E. P. Kasten, Z. Zhou
2006 Software, Practice & Experience  
realize run-time adaptability in real-time communication services.  ...  The main contribution of this work is to propose a language-based approach to run-time adaptability and, through the case study, to reveal several subtle design issues that need to be addressed in the  ...  ACKNOWLEDGEMENTS This work was supported in part by the U.S.  ... 
doi:10.1002/spe.748 fatcat:efy4gkqxojhthp3l4g4npuqqc4

Making a Case for Proactive Flow Control in Optical Circuit-Switched Networks [chapter]

Mithilesh Kumar, Vineeta Chaube, Pavan Balaji, Wu-Chun Feng, Hyun-Wook Jin
2008 Lecture Notes in Computer Science  
We address the shortcomings of such approaches using a two-step process. First, we improve the adaptivity of the reactive approach by proposing an asynchronous, fine-grained, rate-based approach.  ...  in dynamically varying end-host conditions.  ...  These points are always located in the same time interval when the load process is running, depriving the network process of CPU resource and thus causing it to drop packets.  ... 
doi:10.1007/978-3-540-89894-8_43 fatcat:3z3reb53t5hdradpzmopo4wofe

Middleware approaches for adaptivity of Kahn Process Networks on Networks-on-Chip

Emanuele Cannella, Onur Derin, Todor Stefanov
2011 Proceedings of the 2011 Conference on Design & Architectures for Signal & Image Processing (DASIP)  
All of the presented solutions allow for run-time system adaptivity. We implement the approaches on a Network-on-Chip multiprocessor platform prototyped on an FPGA.  ...  In the other case study, which has a higher computation/communication ratio, the middleware approaches show similar performance.  ...  It is clear that in our NoC system we sacrifice performance (especially for communication intensive applications) for adaptivity, the ability of managing the system at run-time, and generality, since the  ... 
doi:10.1109/dasip.2011.6136862 dblp:conf/dasip/CannellaDS11 fatcat:7ox4j4p4czcfjcwouzadpfbujq

Run-Time System for Scalable Network Services

U. Shevade, R. Kokku, H. M. Vin
2008 IEEE INFOCOM 2008 - The 27th Conference on Computer Communications  
In this paper, we describe the design and implementation of Oboe, a run-time system for DM-MP platforms that addresses the above challenge through two foundations: (1) categoryspecific management of shared  ...  state, and (2) adaptive flowlevel load distribution for addressing persistent processor overload.  ...  a case for adaptive flow-level parallelism.  ... 
doi:10.1109/infocom.2008.244 dblp:conf/infocom/ShevadeKV08 fatcat:brwk5mpnfberrnbfzhg5f2xmly

Run-Time System for Scalable Network Services

U. Shevade, R. Kokku, H. M. Vin
2008 2008 Proceedings IEEE INFOCOM - The 27th Conference on Computer Communications  
In this paper, we describe the design and implementation of Oboe, a run-time system for DM-MP platforms that addresses the above challenge through two foundations: (1) categoryspecific management of shared  ...  state, and (2) adaptive flowlevel load distribution for addressing persistent processor overload.  ...  a case for adaptive flow-level parallelism.  ... 
doi:10.1109/infocom.2007.244 fatcat:stiqj34gdfazpjd7uurgsgpj5u

Comparative Analysis of SMP Click Scheduling Techniques [chapter]

Giorgio Calarco, Carla Raffaelli, Giovanni Schembra, Giovanni Tusa
2005 Lecture Notes in Computer Science  
The interest of the scientific and commercial telecommunications community for the use of software routers running in general purpose (PC) hardware, as an alternative to the traditional special purpose  ...  In addition, the diffusion of multiprocessor systems due to the progress in the semiconductor technologies allows software routers to obtain high performance if supported by multiprocessor PC hardware.  ...  Eddie Kohler for his precious suggestions and opinions about data analysis.  ... 
doi:10.1007/978-3-540-30573-6_29 fatcat:oybqqzj6ufemxaapavha3nqtku

NBA (network balancing act)

Joongi Kim, Keon Jang, Keunhong Lee, Sangwook Ma, Junhyun Shim, Sue Moon
2015 Proceedings of the Tenth European Conference on Computer Systems - EuroSys '15  
We also show that our adaptive CPU/GPU load balancer reaches near-optimal throughput in various combinations of sample applications and traffic conditions.  ...  Its abstraction resembles Click but also hides the details of architecturespecific optimization, batch processing that handles the path diversity of individual packets, CPU/GPU load balancing, and complex  ...  members for last-minute reviews, and KyoungSoo Park for general discussion.  ... 
doi:10.1145/2741948.2741969 dblp:conf/eurosys/KimJLMSM15 fatcat:466mfqu3drfyvpgpim37aequhq

Shrinking the hypervisor one subsystem at a time

Julian Stecklina
2014 Proceedings of the 10th ACM SIGPLAN/SIGOPS international conference on Virtual execution environments - VEE '14  
We reduced per-packet overhead by using a run-to-completion model and are able to outperform the unmodified system for VM-to-VM traffic by a large margin when packet rates are high.  ...  Efficient and secure networking between virtual machines is crucial in a time where a large share of the services on the Internet and in private datacenters run in virtual machines.  ...  Acknowledgments The author would like to thank Björn Döbel for invaluable input on drafts of this paper and Luke Gorrie and the team for the occasional dose of motivation and time spent discussing  ... 
doi:10.1145/2576195.2576202 dblp:conf/vee/Stecklina14 fatcat:l32m2jacyrdz3oxrgeu3sqlt5e
« Previous Showing results 1 — 15 out of 99,149 results