Filters








11,659 Hits in 6.6 sec

Delay, memory, and messaging tradeoffs in distributed service systems [article]

David Gamarnik, John N. Tsitsiklis, Martin Zubeldia
2017 arXiv   pre-print
We consider the following distributed service model: jobs with unit mean, exponentially distributed, and independent processing times arrive as a Poisson process of rate λ n, with 0<λ<1, and are immediately  ...  in sharp contrast to the delay obtained when no messages are used (α = 0), which grows as 1/(1-λ) when λ↑ 1, or when the popular power-of-d-choices is used, in which the delay grows as (1/(1-λ)).  ...  This paper addresses the tradeoffs between performance (delay) and resources (local memory and communication overhead) in large-scale queueing systems.  ... 
arXiv:1709.04102v1 fatcat:7zhmexcvrbguxakob3tyzrqzz4

Delay, Memory, and Messaging Tradeoffs in Distributed Service Systems

David Gamarnik, John N. Tsitsiklis, Martin Zubeldia
2016 Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science - SIGMETRICS '16  
We study the fundamental resource requirements (memory bits and message exchange rate), in order to drive the expected steady-state queueing delay of a typical job to zero, as N increases.  ...  We consider the following distributed service model: jobs with unit mean, exponentially distributed, and independent processing times arrive as a Poisson process of rate λN , with 0 < λ < 1, and are immediately  ...  INTRODUCTION This paper addresses the tradeoffs between various measures of performance (delay, message rate and memory) in the context of large scale queueing systems.  ... 
doi:10.1145/2896377.2901478 dblp:conf/sigmetrics/GamarnikTZ16 fatcat:cveucexobzhcxcjypfizy7ytou

Delay, Memory, and Messaging Tradeoffs in Distributed Service Systems

David Gamarnik, John N. Tsitsiklis, Martin Zubeldia
2016 Performance Evaluation Review  
We study the fundamental resource requirements (memory bits and message exchange rate), in order to drive the expected steady-state queueing delay of a typical job to zero, as N increases.  ...  We consider the following distributed service model: jobs with unit mean, exponentially distributed, and independent processing times arrive as a Poisson process of rate λN , with 0 < λ < 1, and are immediately  ...  INTRODUCTION This paper addresses the tradeoffs between various measures of performance (delay, message rate and memory) in the context of large scale queueing systems.  ... 
doi:10.1145/2964791.2901478 fatcat:mdanpoufafegrpwt5s7xylpgxy

Delay, Memory, and Messaging Tradeoffs in Distributed Service Systems

David Gamarnik, John N. Tsitsiklis, Martin Zubeldia
2018 Stochastic Systems  
We study the fundamental resource requirements (memory bits and message exchange rate), in order to drive the expected steady-state queueing delay of a typical job to zero, as N increases.  ...  We consider the following distributed service model: jobs with unit mean, exponentially distributed, and independent processing times arrive as a Poisson process of rate λN , with 0 < λ < 1, and are immediately  ...  INTRODUCTION This paper addresses the tradeoffs between various measures of performance (delay, message rate and memory) in the context of large scale queueing systems.  ... 
doi:10.1287/stsy.2017.0008 fatcat:tohnmn5wgbg3vpnsuq272bjlaq

Stability, memory, and messaging tradeoffs in heterogeneous service systems [article]

David Gamarnik, John N. Tsitsiklis, Martin Zubeldia
2020 arXiv   pre-print
We consider a heterogeneous distributed service system, consisting of n servers with unknown and possibly different processing rates.  ...  First, for the case of Poisson arrivals and exponential service times, we present a policy that is maximally stable while using a positive (but arbitrarily small) message rate, and log_2(n) bits of memory  ...  In this paper, we consider a heterogeneous distributed service system, where servers can have different and unknown processing rates, and explore the tradeoff between the stability region of the system  ... 
arXiv:2007.07219v1 fatcat:zmlsuquqn5g3fkf3dbcvciiymu

Overview of 5ESS-2000 switch performance

Richard Singer
1998 Proceedings of the first international workshop on Software and performance - WOSP '98  
The 5ESS82000 Switch is Lucent Technologies ' premier global digital switch with over lOO,OOO,OOO lines operational in the U.S. and International markets.  ...  The switch can successfully complete 1,500,OOO landline calls/hour and supports over 200,000 lines or 94,000 trunks. Landline and wireless calls are supported as are voice, data and video.  ...  The added delay and processor usage of an intermediate routing SM is another example of a memory versus performance tradeoff.  ... 
doi:10.1145/287318.287321 dblp:conf/wosp/Singer98 fatcat:w3wt4pcy6bfbplrhmsfzdxtqy4

Collaborative overlay power management based on the delay-power tradeoffs

Han Yan, Cedric Gueguen, Bernard Cousin, Jean-Paul Vuichard
2014 Third International Conference on Future Generation Communication Technologies (FGCT 2014)  
Regarding research on the different power consumption and waiting delay tradeoffs, our proposition allows for satisfying different user requirements on power consumption and waiting delay.  ...  Therefore, in this paper, we propose a collaborative overlay power management system in which appliances can be partially turned on depending on the request of the services.  ...  In our system, we assume that the overlay power control messages will be sent by a ZigBee or BLE module in order to ensure a low-power and always-on network.  ... 
doi:10.1109/fgct.2014.6933228 dblp:conf/fgct/YanGCV14 fatcat:7jx5jcq6vfcqvpulf42i3adufq

Autonomous Pull-Push Community Construction Technology for High-Assurance

Khalid MAHMOOD, Xiaodong LU, Yuji HORIKOSHI, Kinji MORI
2009 IEICE transactions on information and systems  
In order to meet crucial goal of real-time and context-aware community construction (provision of service/ service information to users with common interests), and defining flexible service area in highly  ...  mechanism; while service area construction shares the discovered service among members in defined area to further improve timeliness and reduce network cost.  ...  Moreover, target discovery in Peer to Peer systems [19] and distributed computing systems [20] for load distribution and efficient discovery of web services [22] only TTL based n-ring model is used  ... 
doi:10.1587/transinf.e92.d.1836 fatcat:bxadgbijdzfxldzn4u57dl66sa

Stretching Multi-Ring Paxos [article]

Samuel Benz, Leandro Pacheco de Sousa, Fernando Pedone
2015 arXiv   pre-print
Moreover, to reduce user-perceived response times and tolerate disasters (i.e., the failure of a whole datacenter), services are increasingly becoming geographically distributed.  ...  Internet-scale services rely on data partitioning and replication to provide scalable performance and high availability.  ...  System model and definitions We assume a distributed system composed of interconnected processes that communicate through message passing.  ... 
arXiv:1504.04942v1 fatcat:ipncz5mh7jb3flmqfg3deghvyu

An OPNET based novel cross-layer model for analyzing SOA-based information services

Aleksandar Kolarov, Keith Kim
2012 Singidunum Journal of Applied Sciences  
Service Oriented Architecture (SOA) based information systems and services are finding wider applicability in complex, mission-critical operational environments.  ...  In order to effectively help design and prepare information sharing services for such complex operational environments, designers have to consider various architecture tradeoffs and interactions across  ...  the message processing delays occurred in the SOA layer.  ... 
doi:10.5937/sjas1201051k fatcat:zvtznkpvozhv7oabjtpokcg6ja

Toward Development of Adaptive Service-Based Software Systems

Stephen S. Yau, Nong Ye, Hessem S. Sarjoughian, Dazhi Huang, Auttawut Roontiva, Mustafa Baydogan, Mohammed A. Muqsith
2009 IEEE Transactions on Services Computing  
states, and QoS in servicebased systems are presented.  ...  The rapid adoption of service-oriented architecture (SOA) in many large-scale distributed applications requires the development of adaptive service-based software systems (ASBS) with the capability of  ...  system delay of the simulated and real subscriber.  ... 
doi:10.1109/tsc.2009.17 fatcat:vf6lzcepkvc7bdfij54rzulq3m

Page 3538 of Mathematical Reviews Vol. , Issue 82h [page]

1982 Mathematical Reviews  
Multiple users sharing the links of the network each attempt to adjust their message rates to achieve an ideal network operating point or an ‘ideal tradeoff point between high throughput and low delay’  ...  “A generalized definition of ideal tradeoff is then introduced to provide more flexibility in the choice of message rates.  ... 

Resource and performance tradeoffs in delay-tolerant wireless networks

Tara Small, Zygmunt J. Haas
2005 Proceeding of the 2005 ACM SIGCOMM workshop on Delay-tolerant networking - WDTN '05  
SWIM is an example of the way that non-critical performance could be traded off for insufficient resources, such as the tradeoffs between energy, delay, storage, capacity, and processing complexity.  ...  For instance, power and memory/storage constraints of miniaturized network nodes reduce the throughput capacity and increase the network latency.  ...  Message ferrying [14] uses special mobile nodes called message ferries to aid communication services, similar to dataMULEs.  ... 
doi:10.1145/1080139.1080144 fatcat:ltljqevznrgspowiqeglwyxttm

Dependability Evaluation of a Replication Service for Mobile Applications in Dynamic Ad-Hoc Networks [chapter]

Erling V. Matthiesen, Ossama Hamouda, Mohamed Kaâniche, Hans-Peter Schwefel
2008 Lecture Notes in Computer Science  
For mobile services in dynamic ad-hoc networks, such replication mechanisms have to be adapted to deal with the frequently higher communication delays and with the intermittent connectivity.  ...  Traditional solutions for high-availability rely on redundancy offered by cluster implementations, in which Middleware services [1] support the timely replication and fail-over in case of crash failures  ...  First we describe the scenario and then we go into the problem of data consistency in a distributed shared memory area and also the problems involved with service replication in ad-hoc networks.  ... 
doi:10.1007/978-3-540-68129-8_14 fatcat:mb73d2t7hrfufhkcjxsl6iclye

Distributed Model Checking: From Abstract Algorithms to Concrete Implementations

Christophe Joubert
2003 Electronical Notes in Theoretical Computer Science  
In this paper, we consider one fundamental aspect of Dmc design: message passing communication, the implementation of which presents hidden tradeoffs often dismissed in Dmc related literature.  ...  Distributed Model Checking (Dmc) is based on several distributed algorithms, which are often complex and error prone.  ...  Acknowledgement We are grateful to Hubert Garavel and Radu Mateescu (Inria Vasy) for their insightful comments about the content of the paper.  ... 
doi:10.1016/s1571-0661(05)80100-8 fatcat:bzs56ogzpzh5lmwoldojnigf6a
« Previous Showing results 1 — 15 out of 11,659 results