Scheduling On-Demand Broadcast Items

Size: px
Start display at page:

Download "Scheduling On-Demand Broadcast Items"

Transcription

1 Scheduling On-Demand Broadcast Items Miao Wang Advisor: Ilias Michalarias Freie Universität Berlin, Institute for Computer Science Abstract. The demand for various information delivery services has enormously increased over the past few years and data broadcast has become more and more popular because of its nearly infinite scalability. In a broadcast scenario the key consideration is the scheduling algorithm that determines the next data item to be delivered over the network. The goal is to find a well performing algorithm in terms of average and worstcase performance. To efficiently use data broadcast different scheduling algorithms need to be developed and evaluated according to different metrics and measures. The algorithms must meet criteria to minimize response time and decision overhead and provide good scalability and applicability. Key words: broadcast, on-demand, pull-based, scheduling algorithm, LDCF, RxW 1 Introduction Due to recent developments in telecommunications, data networks, and mobile computing the transferred bandwidth as well as the demand for various information delivery services has enormously increased over the past few years. The World Wide Web today provides a universal platform to distribute information around the world. But most web-based systems fail to meet high user demands under peak loads resulting in slow response or poor availability. The delivery by unicast performs poorly with a large client population because every data item must be transmitted individually, increasing load on the server and the network. A considerable number of researches have been done in the field of largescale data-dissemination to find more efficient methods for data delivery. Many of those relied on broadcasting, where one server delivers information to a large number of clients [1],[2],[3],[4],[5],[6],[7],[8]. Broadcast technology is very popular because one response can potentially satisfy many users and therefore highly scalable because it can support additional clients without the need for major changes in the infrastructure. Satellite, terrestrial and cable TV networks have the capabilities to establish a platform for digital data broadcast. The information messaging system in cellular

2 2 Scheduling On-Demand Broadcast Items phones or other mobile devices provide traffic information, volatile time-sensitive information such as stock prices and weather information as well as periodic news distribution. The television information retrieval service called teletext is another example of broadcast application. Broadcast delivery can either be push-based or pull-based. In a push-based environment the server does not receive any direct requests by its clients but schedules the data packages based on the statistics or profiles of the clients request pattern. On the other hand in a pull-based setting the server would receive all requests by its clients and transmits the data packages for certain clients according to a scheduling algorithm. A pull system can potentially achieve better performance than a push system but requires the cost of an extra return channel, resulting in suggestions for hybrid architectures [9],[10],[11]. In this paper, I will examine pull-based broadcast also known as on-demand broadcast, where the server delivers on the requests by one of its clients. The scheduling algorithm, that determines which data item will be delivered over the network next, is critical for the broadcast performance. The goal is to find a well performing algorithm in terms of average and worst-case performance. Furthermore the algorithm needs to scale well in terms of increasing client population, request arrival rates, database sizes and bandwidth. The scheduling has to be evaluated against responsiveness and robustness and the decision overhead should be minimized. Previous algorithms established in operating system design have failed to address one or more of these issues when used for broadcasting. This paper reviews several previous algorithms for broadcast scheduling as well as promising new suggestions. In Section 2, I will give background information about the used model and used metrics to measure individual and overall system performance. Then I will review few of the previous algorithms used for scheduling in Section 3. Afterwards in section 4, I describe and discuss related work that have introduced new algorithms specialized for broadcast scheduling. Finally, Section 5 will provide a conclusion. 2 Background 2.1 Model To visualize our broadcast setting, I will present a model as an example similar to the one in Figure 1. The environment consists of a large population of clients c i that use an uplink channel to make requests for a data item to one single server s. These requests are queued up at the server upon arrival. The server then determines the next data item to be scheduled and transmits it via the downlink channel as a broadcast. The clients monitor the broadcast to pull of the requested data item. You can almost pick any network system for both uplink and downlink channel like terrestrial, satellite or even phone line. In our model we assume that there is only one broadcast channel monitored by the clients and that the channel bandwidth is fully dedicated for the data broadcast. The effect of transmission errors is not taken into consideration, i.e.

3 Scheduling On-Demand Broadcast Items 3 Fig. 1. Example model for a broadcast environment every broadcasted item is received by the waiting clients. We further simplify the scheduling of data items which can be split into fixed-length pages, such as database or memory pages. 2.2 Metrics and Measures To evaluate the quality and performance of different scheduling algorithms, there is the measure of individual and overall average system performance. Both must be looked at collectively since a good algorithm for an individual case does not satisfy the large number of clients in the average. On the other hand overall average performance may favor the majority and adversely affect a few individuals. We will therefore look at different metrics and measures that have been introduced in recent works to evaluate different scheduling algorithms in a couple of dimensions. Response Time The response time of a request is typically used as an individual performance measure which is the time between the request submission and receipt of the response. The goal is to minimize the response time, since it also indicates the total time spent by a client actively listening to the channel. A longer response time would cause more power consumption for clients with limited battery supply. Stretch Recent work also took the stretch of a request into consideration which is defined to be the ratio of the response time of a request to its service time. The stretch translates more directly to user-perceived performance since it takes the service time of each request into account. Thus, longer requests are expected to

4 4 Scheduling On-Demand Broadcast Items be in the system longer than shorter ones. Minimizing both response time and stretch gives us a metric to improve system performance. However, it is hard and sometimes impossible to exactly determine the service time of a request. Decision Overhead The rationale for this metric is to have a key dimension to improve the responsiveness of an algorithm. A good scheduler shouldn t only deliver the data items in a short time frame but also have little decision overhead. Therefore the cost of making the decision which item to deliver next must be minimized to make the most of the given broadcast bandwidth. An algorithm that makes decisions slowly will stall the broadcast and waste bandwidth that could be used. Fairness Furthermore scheduling should be fair. The fairness is a rather abstract measure that ensures that no data item has to face starvation, i.e. wait for an indefinite time to be broadcasted because there are always data items that need to be broadcasted before. Thus, the worst-case wait time has also to be measured and ensured that unpopular data items do not suffer this fate. Scalability Another consideration is the scalability of scheduling algorithms that must be provided when the scheduling problem grows in the number of request arrival rates, data item sizes or broadcast rate. In any case the algorithm should handle the heavy traffic and still perform well enough and not be a bottleneck. 3 Related Work In this section we review a number of relevant pull-based scheduling algorithms proposed in previous work. Most of them have similarities with scheduling algorithms used in operating systems. Thus, there are well-known and easy to understand but also not always applicable for a broadcast setting. Later, we will introduce several newly proposed algorithms that perform better in a broadcast scenario. 3.1 Previous Algorithms FCFS The easiest scheduling algorithm is a simple queue where data items are scheduled in the order they arrived in. This First-Come-First-Served (FCFS) strategy is straight-forward and known to minimize the maximum response time. Similarly to a checkout line at the supermarket the data requests form a queue and wait until their turn to be processed. This is extremely fair because requests are ensured to get processed after a finite period and will not wait endlessly. Furthermore the decision overhead is constant, there is no expensive calculation that needs to be done. However, FCFS performs extremely poor in a broadcast

5 Scheduling On-Demand Broadcast Items 5 setting because it only takes the requested time into account and never considers the difference of access frequencies of various data items. Hence, it is not considered a good algorithm for broadcast scheduling [2]. MRF / MRFL The Most-Request-First (MRF) and the Most-Request-First- Lowest (MRFL) scheduling algorithm take the number of requests as a measure to determine the next broadcasted page [12],[13]. In MRF the data item with the largest number of requests is always delivered, so that popular items are favored which are most likely to be requested again. But that is not fair: data items with only a few requests will come up short and maybe wait endlessly to be processed. The MRFL scheme is similar to MRF, but it breaks ties in favor of pages with the lowest request access probability and is slightly better. LWF The Longest-Wait-First (LWF) algorithm chooses the data item with the largest total waiting time (the sum of the total time that all pending requests for that item have been waiting for). LWF takes both the number of requests and the waiting time into account and usually outperforms FCFS and MRF. It therefore reduces the problem of endless waiting items but does not resolve it. Also, it is very expensive to implement and mostly replaced by RxW which will be described later [2]. SSTF If the service time of a request can be estimated or even exactly calculated, the Shortest-Service-Time-First (SSTF) scheduling algorithm can be used which broadcasts the data item with the shortest service time. This has the advantage that short requests can be processed really fast, but the scheduling is not fair since large jobs may be always excluded by many short jobs that arrive frequently often [2]. LTSF The Longest-Total-Stretch-First (LTSF) algorithm is based on the stretch metric. It tries to calculate the stretch value for each request and broadcasts the item with the largest total current stretch value (the sum of the current stretches of all pending requests for the item). If the stretch value can be approximated adequately, this is an algorithm that also performs well and fairly for data items with variable data sizes [2]. EDF In [14], the authors propose requests associated with a deadline. With Earliest-Deadline-First (EDF) the requests with the nearest deadline is processed in favor of the others. Although the EDF strategy is guaranteed to find a feasible scheduling in a point-to-point case, it does not necessarily in a broadcast case. The problem is that processing large jobs may cause many other jobs to miss their deadline. A way to prevent this is to allow the preemption of processed requests which leads to a better stretch, but it can be easily shown that it will also lead to starvation with endless waiting time [2].

6 6 Scheduling On-Demand Broadcast Items 4 Newly proposed algorithms We see that the previous algorithms each lack a little in order to be efficiently used in a broadcast setting. Hence, many authors have come up with new solutions for the scheduling problem which will be outlined and discussed here. LDCF (Longest Delay Cost First) The Longest Delay Cost First scheduling algorithm was proposed in 2003 [7] which key consideration is the costs for each broadcast. It also takes request failures into account, if the server could not broadcast an item within a response time limit (RTL). LDCF tries to minimize a weighted sum of the access time cost elapsed between request and response (C AT ), the tuning time cost a user has to spend actively listening to the channel (C T T ) and the cost of handling failed requests (C F ) because the request could not be satisfied in a certain time period. For each scheduling decision the data item with the largest cost is calculated and selected to broadcast. The idea to minimize the tuning time and the number of failed requests for clients is promising for low-energy devices with limited battery supply. The average cost evaluated for the LDCF algorithm in several experiments is little lower than for LWF or MRF. But LDCF is much more complex and complicated and requires more scheduling decision overhead to calculate the costs for each request. Fig. 2. LDCF performance compared to various pervious algorithms RxW In [3] a new broadcast scheduling algorithm called RxW is presented which provides excellent performance across a various range of scenarios. To combine the benefits of MRF and FCFS, the RxW algorithm calculates the

7 Scheduling On-Demand Broadcast Items 7 product of R (the number of outstanding requests for that page) and W (the time of the oldest outstanding request for that page). It therefore maintains two values with each service queue and always chooses to broadcast the page with the maximal RxW-value. The decision overhead is O(n) since the algorithm has to go through each data item and calculate its RxW-value. This could be too time consuming and wasting downstream bandwidth. Figure 3 shows an example: For each R-W-pair the RxW-value is calculated. The item d has the highest RxW-value which is 600. Thus d will be broadcasted in the next cycle. Fig. 3. RxW algoritm RxW.α To reduce the search overhead of RxW an approximate version RxW.α has been developed where α is a tunable parameter in percent that controls the desired level of approximation. The idea is to prune the search space since the chosen data item will most likely be one with high R-value or high W-value. The algorithm works as follows: the server maintains two sorted lists: the R-list based on the number of outstanding requests and the W-list based on the waiting time of the oldest request. The search starts at the top of the R-list, were the RxW value for that data item is computed and recorded as the current maximum. Thereafter the top of the W-list is examined and its RxW value compared to the current maximum. The algorithm then keeps alternating between the two lists and stops when it encounters an item with a RxW value greater than or equal to α times the threshold. The threshold is the running average of the RxW values that have been broadcasted so far. After each broadcast the threshold is updated and the data item removed from the service queue. Thus, the α value regulates the tradeoff between schedule quality and decision overhead. A smaller α lowers the decision overhead, whereas a greater α tends to exacter decisions. Figure 4 shows an example based on the one shown in Figure 3: The threshold is set to 500 and α is 0.9 (RxW.90). Thus we look until we will find a item with RxW-value higher than = 450. The RxW-value for item c with the highest R-value is calculated first as 440. It does not satisfy our criteria, so the next RxW-value for item b with highest W-value is calculated as 540, which meets our criteria. Item b will be broadcasted and our threshold updated.

8 8 Scheduling On-Demand Broadcast Items Fig. 4. RxW.α algoritm Aksoy has demonstrated the performance, scalability, and robustness of the RxW and RxW.α variants through an extensive set of performance experiments and analysis. They have shown that RxW performs significantly better than previous algorithms (LWF, FCFS) and provides an efficient use of broadcast resources [3]. The tradeoff between request rate and average waiting time indicate a inherent scalability of broadcast delivery and makes it an ideal technology for large-scale data-dissemination. Furthermore RxW is easily integrable with opportunistic scheduling techniques such as cache-residence and server cache management such as love/hate-hints as well as prefetching [1]. Fig. 5. RxW.α algoritm

9 Scheduling On-Demand Broadcast Items 9 Multi-item and Transactional Requests So far we have only considered broadcast decisions at the data item level where we only consider the case of single-item requests. But in reality there is often the setting where clients attempt to download multiple data items with one request in a transactional way. For example database clients often access multiple items to complete a read transaction; similarly web clients try to access HTML documents with all its embedded objects. For such a given landscape it is more favorable to consider the set of transactions on the data items. In [5] an on-demand algorithm is outlined for transactional settings. Fig. 6. Transaction data request table In Figure 6 a transaction data request table is illustrated. A transaction t 1 requests d 1, d 2 and d 7. Equally the data item d 3 is required by transactions t 2, t 3 and t 4. A scheduling decision on data item level, like MRF, would have a broadcast schedule like d 1, d 2, d 3, d 4, d 5, d 6, and d 7. This is very unfortunate for transaction t 1 who has to wait until the 7th broadcast tick. Not only does this increase the waiting time but the longer the waiting time the more probable it is to have a inconsistent state when values are updated in between. In a transactional setting the scheduling decision is not made after each broadcast but at periodic intervals referred to as broadcast cycles. One scheduling decision makes a decision for the entire broadcast cycle to come. In a initial step the temperature of transactions is calculated. The temperature T emp i of a transaction t i gives the average measure of the number of hot data items (frequently accessed data items) in a transaction. It is calculated as the sum of the number of requests for each data item in the transaction divided by the number of data items in the transaction. In our example the temperature T emp 1 of transaction t 1 would be ( )/3 = 10/3. Afterwards, all transactions are sorted in descending order according to their T emp i x W i value where W i is the wait time of the transaction t i. Then data items are chosen to be broadcasted from the sorted transaction list until the maximum capacity to broadcast in a broadcast cycle is reached. Furthermore indexing and filtering can be used

10 10 Scheduling On-Demand Broadcast Items to further improve the scheduling. Thus, transactions will have shorter waiting times to be completed than in a scheduling based on single-item requests. Fig. 7. LDCF performance compared to various previous algorithms In a transactional context this algorithm has certain advantages over previous algorithms like FCFS, MRF or RxW because it drastically improves the average transaction wait time. But the decision overhead is time consuming and dependent on arriving transactions. In a setting where transactions are not that time critical RxW is sufficient to use. 5 Conclusion In this paper we have introduced the problem of on-demand broadcast scheduling in a pull-based model. The scheduling algorithm that determines the next data item to be delivered over the network is the key consideration of broadcast scheduling. We have shown several previous algorithms for broadcast scheduling

11 Scheduling On-Demand Broadcast Items 11 that are easy to understand and implement but do not perform as well as modern algorithms in certain metrics and measures. We have described some newly proposed algorithms that perform promisingly well. The LDCF algorithm does not only try to minimize the access time but also the tuning time and the number of failed requests for clients. This is very promising for low-energy devices but the scheduling decision is rather complicated on the other hand. The RxW algorithm shows excellent performance across a range of scenarios and is fairly easy to understand. The idea is to choose the data item with the highest product of R (the number of outstanding requests for that page) and W (the time of the oldest outstanding request for that page). Therefore RxW maintains two queues holding R- and W-values. In this basic variant RxW has to go through both lists linearly and has a decision overhead of O(n). The RxW.α is a little improvement over the basic RxW. The goal is to prune the search space with a tunable parameter α that controls the desired level of approximation. Since either a value with high R- or W-value is most likely to be selected, those are the ones that are first checked alternatively for broadcast. If a RxW-value is found which is higher than α times a threshold, this item is broadcasted and the threshold updated. Different approaches have to be made in a transactional context. Prabhu and Kumar have introduced an algorithm for multi-item and transactional requests to lower the transactional waiting time. The algorithm does not work on data item level but on a transactional level and chooses the data item for the transaction with the highest temperature (average measure of the number of frequently accessed data items). This algorithm can prove very useful in a transactional context where transactional waiting time is critical. Table 1 gives an overview of the discussed scheduling algorithms in this paper and their evaluation towards different measures. Response Stretch Decision Fairness Scalability Time Overhead FCFS MRF LWF SSTF LTSF EDF LDCF RxW Trans Table 1. Conclusion of introduced algorithms

12 12 Scheduling On-Demand Broadcast Items As data broadcast becomes more and more popular because of its nearly infinite scalability, different scheduling algorithms need to be developed. We have introduced a few modern ones that have advantages in certain fields. The RxW algorithm is a generic method which performs well in many scenarios. All methods have made the implicit assumption that all of the data items to be disseminated are readily available at the server when they are scheduled. However, the items may reside in secondary or tertiary storage and require a certain service time to be fetched. This can destroy the performance of the broadcast scheduling heuristics. In order to prevent this, methods like opportunistic scheduling techniques, server cache management and prefetching can be used which all work great with RxW [1]. References 1. Demet Aksoy, Michael J. Franklin, and Stanley B. Zdonik. Data staging for ondemand broadcast. pages , Swamp Acharya and S. Mutlutkrislulan. Scheduling on demand broadcasts new metrics and algorithms. ACM Press, pages 43 54, Demet Aksoy and Michael Franklin. Rxw: A scheduling approach for large-scale on-demand data broadcast. IEEE/ACM Transactions on Networking, Volume 7, No. 6: , N. Kamiyama. Broadcast scheduling for large contents distribution with guaranteed response time. ICC 06. IEEE International Conference on Communications, 2006, 4: , Nitin Prabhu and Vijay Kumar. Data scheduling for multi-item and transactional requests in on-demand broadcast. pages 48 56, Majid Raissi-Dehkordi and John S. Baras. Broadcast scheduling in information delivery systems. Global Telecommunications Conference, GLOBECOM 02. IEEE, 3: , Weiwei Sun, Weibin Shi, Bole Shi, and Yijun Yu. A cost-efficient scheduling algorithm of on-demand broadcasts. Wirel. Netw., 9(3): , Chi-Jiun Su and Leandros Tassiulas. Broadcast scheduling for information distribution. pages , J. W. Wong and M. H. Ammar. Analysis of broadcast delivery in a videotex system. IEEE Trans. Comput., 34(9): , Swarup Acharya, Michael Franklin, and Stanley Zdonik. Balancing push and pull for data broadcast. pages , Konstantinos Stathatos, Nick Roussopoulos, and John S. Baras. Adaptive data broadcast in hybrid networks. pages , J. W. Wong. Broadcast delivery. IEEE, 76(12), M. H. Ammar H. D. Dykeman and J. W. Wong. Scheduling algorithms for videotex systems under broadcast delivery. First International Workshop on Satellite-based Information Services, O. Gonzalez J. Fernandez P. Xuan, S. Sen and K. Ramamritham. Broadcast ondemand: Efficiently and timely disseminating of data in mobile environment. IEEE RTAS, 1997.

Periodic Scheduling in On-Demand Broadcast System

Periodic Scheduling in On-Demand Broadcast System Periodic Scheduling in On-Demand Broadcast System Nitin Prabhu, Vijay Kumar SCE, Computer Networking University of Missouri-Kansas City Kansas City, MO 64110 npp21c (kumarv)@umkc.edu Indrakshi Ray Computer

More information

Stretch-Optimal Scheduling for On-Demand Data Broadcasts

Stretch-Optimal Scheduling for On-Demand Data Broadcasts Stretch-Optimal Scheduling for On-Demand Data roadcasts Yiqiong Wu and Guohong Cao Department of Computer Science & Engineering The Pennsylvania State University, University Park, PA 6 E-mail: fywu,gcaog@cse.psu.edu

More information

Pull vs Push: A Quantitative Comparison for Data Broadcast

Pull vs Push: A Quantitative Comparison for Data Broadcast Pull vs Push: A Quantitative Comparison for Data Broadcast Demet Aksoy Mason Sin-Fai Leung Computer Science Department University of California, Davis (aksoy,leungm)@cs.ucdavis.edu Abstract Advances in

More information

Volume 3, Issue 9, September 2013 International Journal of Advanced Research in Computer Science and Software Engineering

Volume 3, Issue 9, September 2013 International Journal of Advanced Research in Computer Science and Software Engineering Volume 3, Issue 9, September 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Optimal Round

More information

Stretch-Optimal Scheduling for On-Demand Data Broadcasts

Stretch-Optimal Scheduling for On-Demand Data Broadcasts COMBINATORIAL OPTIMIZATION IN COMMUNICATION NETWORKS Maggie Cheng, Yingshu Li and Ding-Zhu Du (Eds.) pp. 622-637 c 2005 Springer Science + Business Media Stretch-Optimal Scheduling for On-Demand Data Broadcasts

More information

Pull vs. Hybrid: Comparing Scheduling Algorithms for Asymmetric Time-Constrained Environments

Pull vs. Hybrid: Comparing Scheduling Algorithms for Asymmetric Time-Constrained Environments Pull vs. Hybrid: Comparing Scheduling Algorithms for Asymmetric Time-Constrained Environments Jesus Fernandez-Conde and Daniel Mozos Department of Computer Architecture Universidad Complutense de Madrid,

More information

Evaluation of a Broadcast Scheduling Algorithm

Evaluation of a Broadcast Scheduling Algorithm Evaluation of a Broadcast Scheduling Algorithm Murat Karakaya 1 and Özgür Ulusoy2 1 Department of Technical Sciences Turkish Land Forces Academy, Ankara 06100, Turkey 2 Department of Computer Engineering

More information

Competitive Analysis of On-line Algorithms for On-demand Data Broadcast Scheduling

Competitive Analysis of On-line Algorithms for On-demand Data Broadcast Scheduling Competitive Analysis of On-line Algorithms for On-demand Data Broadcast Scheduling Weizhen Mao Department of Computer Science The College of William and Mary Williamsburg, VA 23187-8795 USA wm@cs.wm.edu

More information

A Simulation-Based Analysis of Scheduling Policies for Multimedia Servers

A Simulation-Based Analysis of Scheduling Policies for Multimedia Servers A Simulation-Based Analysis of Scheduling Policies for Multimedia Servers Nabil J. Sarhan Chita R. Das Department of Computer Science and Engineering The Pennsylvania State University University Park,

More information

SLA-Aware Adaptive Data Broadcasting in Wireless Environments. Adrian Daniel Popescu

SLA-Aware Adaptive Data Broadcasting in Wireless Environments. Adrian Daniel Popescu SLA-Aware Adaptive Data Broadcasting in Wireless Environments by Adrian Daniel Popescu A thesis submitted in conformity with the requirements for the degree of Masters of Applied Science Graduate Department

More information

Data Dissemination Techniques in Mobile Computing Environment

Data Dissemination Techniques in Mobile Computing Environment ABSTRACT 2016 IJSRST Volume 2 Issue 6 Print ISSN: 2395-6011 Online ISSN: 2395-602X Themed Section: Science and Technology Data Dissemination Techniques in Mobile Computing Environment R. Kavitha *1, S.

More information

A Cost-Efficient Scheduling Algorithm of On-Demand Broadcasts

A Cost-Efficient Scheduling Algorithm of On-Demand Broadcasts Wireless Networks 9, 239 247, 2003 2003 Kluwer Academic Publishers. Manufactured in The Netherlands. A Cost-Efficient Scheduling Algorithm of On-Demand Broadcasts WEIWEI SUN, WEIBIN SHI and BOLE SHI Department

More information

An Adaptive Query Processing Method according to System Environments in Database Broadcasting Systems

An Adaptive Query Processing Method according to System Environments in Database Broadcasting Systems An Query Processing Method according to System Environments in Database Broadcasting Systems M. KASHITA T. TERADA T. HARA Graduate School of Engineering, Cybermedia Center, Graduate School of Information

More information

Ch 4 : CPU scheduling

Ch 4 : CPU scheduling Ch 4 : CPU scheduling It's the basis of multiprogramming operating systems. By switching the CPU among processes, the operating system can make the computer more productive In a single-processor system,

More information

SLA-Aware Adaptive On-Demand Data Broadcasting in Wireless Environments

SLA-Aware Adaptive On-Demand Data Broadcasting in Wireless Environments 2009 Tenth International Conference on Mobile Data Management: Systems, Services and Middleware SLA-Aware Adaptive On-Demand Data Broadcasting in Wireless Environments Adrian Daniel Popescu Mohamed A.

More information

Last Class: Processes

Last Class: Processes Last Class: Processes A process is the unit of execution. Processes are represented as Process Control Blocks in the OS PCBs contain process state, scheduling and memory management information, etc A process

More information

CS 326: Operating Systems. CPU Scheduling. Lecture 6

CS 326: Operating Systems. CPU Scheduling. Lecture 6 CS 326: Operating Systems CPU Scheduling Lecture 6 Today s Schedule Agenda? Context Switches and Interrupts Basic Scheduling Algorithms Scheduling with I/O Symmetric multiprocessing 2/7/18 CS 326: Operating

More information

Frequently asked questions from the previous class survey

Frequently asked questions from the previous class survey CS 370: OPERATING SYSTEMS [CPU SCHEDULING] Shrideep Pallickara Computer Science Colorado State University L14.1 Frequently asked questions from the previous class survey Turnstiles: Queue for threads blocked

More information

Reduction of Periodic Broadcast Resource Requirements with Proxy Caching

Reduction of Periodic Broadcast Resource Requirements with Proxy Caching Reduction of Periodic Broadcast Resource Requirements with Proxy Caching Ewa Kusmierek and David H.C. Du Digital Technology Center and Department of Computer Science and Engineering University of Minnesota

More information

Pervasive data access in wireless and mobile computing environments

Pervasive data access in wireless and mobile computing environments WIRELESS COMMUNICATIONS AND MOBILE COMPUTING Wirel. Commun. Mob. Comput. 2008; 8:25 44 Published online 12 September 2006 in Wiley InterScience (www.interscience.wiley.com). DOI: 10.1002/wcm.424 Pervasive

More information

Broadcast Disks: Scalable solution for an asymmetric environment

Broadcast Disks: Scalable solution for an asymmetric environment Broadcast Disks: Scalable solution for an asymmetric environment Byungho Lee Computer Science & Engineering, University of Texas at Arlington blee@cse.ute.edu Abstract As mobile computing gains more popularity,

More information

Energy-Conserving Access Protocols for Transmitting Data in Unicast and Broadcast Mode

Energy-Conserving Access Protocols for Transmitting Data in Unicast and Broadcast Mode Energy-Conserving Access Protocols for ransmitting Data in Unicast and Broadcast Mode I. Papadimitriou and M. Paterakis Laboratories of elecommunication and Information and Computer etworks Department

More information

AODV-PA: AODV with Path Accumulation

AODV-PA: AODV with Path Accumulation -PA: with Path Accumulation Sumit Gwalani Elizabeth M. Belding-Royer Department of Computer Science University of California, Santa Barbara fsumitg, ebeldingg@cs.ucsb.edu Charles E. Perkins Communications

More information

Scheduling of processes

Scheduling of processes Scheduling of processes Processor scheduling Schedule processes on the processor to meet system objectives System objectives: Assigned processes to be executed by the processor Response time Throughput

More information

15-740/ Computer Architecture Lecture 20: Main Memory II. Prof. Onur Mutlu Carnegie Mellon University

15-740/ Computer Architecture Lecture 20: Main Memory II. Prof. Onur Mutlu Carnegie Mellon University 15-740/18-740 Computer Architecture Lecture 20: Main Memory II Prof. Onur Mutlu Carnegie Mellon University Today SRAM vs. DRAM Interleaving/Banking DRAM Microarchitecture Memory controller Memory buses

More information

OPERATING SYSTEMS CS3502 Spring Processor Scheduling. Chapter 5

OPERATING SYSTEMS CS3502 Spring Processor Scheduling. Chapter 5 OPERATING SYSTEMS CS3502 Spring 2018 Processor Scheduling Chapter 5 Goals of Processor Scheduling Scheduling is the sharing of the CPU among the processes in the ready queue The critical activities are:

More information

Episode 5. Scheduling and Traffic Management

Episode 5. Scheduling and Traffic Management Episode 5. Scheduling and Traffic Management Part 3 Baochun Li Department of Electrical and Computer Engineering University of Toronto Outline What is scheduling? Why do we need it? Requirements of a scheduling

More information

A Self-Adaptive Scheduling Algorithm of On-Demand Broadcasts

A Self-Adaptive Scheduling Algorithm of On-Demand Broadcasts A Self-Adaptive Scheduling Algorithm of On-Demand Broadcasts Weiwei Sun, Weibin Shi, Bole Shi, Wenyun Ji and Yijun Yu Department of Compute Science, Fudan University Shanghai 200433, P.R. China 86-21-65646451

More information

Uniprocessor Scheduling. Aim of Scheduling

Uniprocessor Scheduling. Aim of Scheduling Uniprocessor Scheduling Chapter 9 Aim of Scheduling Response time Throughput Processor efficiency Types of Scheduling Long-Term Scheduling Determines which programs are admitted to the system for processing

More information

Uniprocessor Scheduling. Aim of Scheduling. Types of Scheduling. Long-Term Scheduling. Chapter 9. Response time Throughput Processor efficiency

Uniprocessor Scheduling. Aim of Scheduling. Types of Scheduling. Long-Term Scheduling. Chapter 9. Response time Throughput Processor efficiency Uniprocessor Scheduling Chapter 9 Aim of Scheduling Response time Throughput Processor efficiency Types of Scheduling Long-Term Scheduling Determines which programs are admitted to the system for processing

More information

In examining performance Interested in several things Exact times if computable Bounded times if exact not computable Can be measured

In examining performance Interested in several things Exact times if computable Bounded times if exact not computable Can be measured System Performance Analysis Introduction Performance Means many things to many people Important in any design Critical in real time systems 1 ns can mean the difference between system Doing job expected

More information

Process- Concept &Process Scheduling OPERATING SYSTEMS

Process- Concept &Process Scheduling OPERATING SYSTEMS OPERATING SYSTEMS Prescribed Text Book Operating System Principles, Seventh Edition By Abraham Silberschatz, Peter Baer Galvin and Greg Gagne PROCESS MANAGEMENT Current day computer systems allow multiple

More information

CPU Scheduling. CSE 2431: Introduction to Operating Systems Reading: Chapter 6, [OSC] (except Sections )

CPU Scheduling. CSE 2431: Introduction to Operating Systems Reading: Chapter 6, [OSC] (except Sections ) CPU Scheduling CSE 2431: Introduction to Operating Systems Reading: Chapter 6, [OSC] (except Sections 6.7.2 6.8) 1 Contents Why Scheduling? Basic Concepts of Scheduling Scheduling Criteria A Basic Scheduling

More information

Multiprocessor and Real- Time Scheduling. Chapter 10

Multiprocessor and Real- Time Scheduling. Chapter 10 Multiprocessor and Real- Time Scheduling Chapter 10 Classifications of Multiprocessor Loosely coupled multiprocessor each processor has its own memory and I/O channels Functionally specialized processors

More information

CS370: System Architecture & Software [Fall 2014] Dept. Of Computer Science, Colorado State University

CS370: System Architecture & Software [Fall 2014] Dept. Of Computer Science, Colorado State University Frequently asked questions from the previous class survey CS 370: SYSTEM ARCHITECTURE & SOFTWARE [CPU SCHEDULING] Shrideep Pallickara Computer Science Colorado State University OpenMP compiler directives

More information

Kernel Korner I/O Schedulers

Kernel Korner I/O Schedulers Kernel Korner I/O Schedulers Here's how I/O schedulers contribute to disk performance in Linux and the improvements you can get from the new I/O schedulers in the 2. by Robert Love Although most Linux

More information

Episode 3. Principles in Network Design

Episode 3. Principles in Network Design Episode 3. Principles in Network Design Part 2 Baochun Li Department of Electrical and Computer Engineering University of Toronto Recall: Designing the network as a system Last episode: Every complex computer

More information

Preview. Process Scheduler. Process Scheduling Algorithms for Batch System. Process Scheduling Algorithms for Interactive System

Preview. Process Scheduler. Process Scheduling Algorithms for Batch System. Process Scheduling Algorithms for Interactive System Preview Process Scheduler Short Term Scheduler Long Term Scheduler Process Scheduling Algorithms for Batch System First Come First Serve Shortest Job First Shortest Remaining Job First Process Scheduling

More information

Scheduling. The Basics

Scheduling. The Basics The Basics refers to a set of policies and mechanisms to control the order of work to be performed by a computer system. Of all the resources in a computer system that are scheduled before use, the CPU

More information

Start of Lecture: February 10, Chapter 6: Scheduling

Start of Lecture: February 10, Chapter 6: Scheduling Start of Lecture: February 10, 2014 1 Reminders Exercise 2 due this Wednesday before class Any questions or comments? 2 Scheduling so far First-Come-First Serve FIFO scheduling in queue without preempting

More information

CPET 565/CPET 499 Mobile Computing Systems. Lecture 8. Data Dissemination and Management. 2 of 3

CPET 565/CPET 499 Mobile Computing Systems. Lecture 8. Data Dissemination and Management. 2 of 3 CPET 565/CPET 499 Mobile Computing Systems Lecture 8 and Management 2 of 3 Based on the Text used in the course: Fundamentals of Mobile & Pervasive Computing, 2005, by Frank Adelstein, et. al, from McGraw-Hill

More information

A Comparative Study of High Performance Computing on the Cloud. Lots of authors, including Xin Yuan Presentation by: Carlos Sanchez

A Comparative Study of High Performance Computing on the Cloud. Lots of authors, including Xin Yuan Presentation by: Carlos Sanchez A Comparative Study of High Performance Computing on the Cloud Lots of authors, including Xin Yuan Presentation by: Carlos Sanchez What is The Cloud? The cloud is just a bunch of computers connected over

More information

ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT

ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT PhD Summary DOCTORATE OF PHILOSOPHY IN COMPUTER SCIENCE & ENGINEERING By Sandip Kumar Goyal (09-PhD-052) Under the Supervision

More information

On Improving the Performance of Cache Invalidation in Mobile Environments

On Improving the Performance of Cache Invalidation in Mobile Environments Mobile Networks and Applications 7, 291 303, 2002 2002 Kluwer Academic Publishers. Manufactured in The Netherlands. On Improving the Performance of Cache Invalidation in Mobile Environments GUOHONG CAO

More information

Chapter 6: CPU Scheduling. Operating System Concepts 9 th Edition

Chapter 6: CPU Scheduling. Operating System Concepts 9 th Edition Chapter 6: CPU Scheduling Silberschatz, Galvin and Gagne 2013 Chapter 6: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms Thread Scheduling Multiple-Processor Scheduling Real-Time

More information

Adaptive Scheduling for On-Demand Time-Critical Information Dissemination over Data Broadcast Channel *

Adaptive Scheduling for On-Demand Time-Critical Information Dissemination over Data Broadcast Channel * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 27, 1959-1983 (211) Adaptive Scheduling for On-Demand Time-Critical Information Dissemination over Data Broadcast Channel * Department of Communication Engineering

More information

Segregating Data Within Databases for Performance Prepared by Bill Hulsizer

Segregating Data Within Databases for Performance Prepared by Bill Hulsizer Segregating Data Within Databases for Performance Prepared by Bill Hulsizer When designing databases, segregating data within tables is usually important and sometimes very important. The higher the volume

More information

Linux (Fedora or Slackware) CPU Scheduling

Linux (Fedora or Slackware) CPU Scheduling Linux (Fedora or Slackware) CPU Scheduling DHEYAULDEEN MAHMOOD Student no. 163104411 Department: IT Submit to Prof.Dr.Hassan Huseyin Balik Outline Introduction Linux Fedora CPU scheduler in Linux fedora

More information

Network Working Group Request for Comments: 1046 ISI February A Queuing Algorithm to Provide Type-of-Service for IP Links

Network Working Group Request for Comments: 1046 ISI February A Queuing Algorithm to Provide Type-of-Service for IP Links Network Working Group Request for Comments: 1046 W. Prue J. Postel ISI February 1988 A Queuing Algorithm to Provide Type-of-Service for IP Links Status of this Memo This memo is intended to explore how

More information

A Time-To-Live Based Reservation Algorithm on Fully Decentralized Resource Discovery in Grid Computing

A Time-To-Live Based Reservation Algorithm on Fully Decentralized Resource Discovery in Grid Computing A Time-To-Live Based Reservation Algorithm on Fully Decentralized Resource Discovery in Grid Computing Sanya Tangpongprasit, Takahiro Katagiri, Hiroki Honda, Toshitsugu Yuba Graduate School of Information

More information

Process Synchroniztion Mutual Exclusion & Election Algorithms

Process Synchroniztion Mutual Exclusion & Election Algorithms Process Synchroniztion Mutual Exclusion & Election Algorithms Paul Krzyzanowski Rutgers University November 2, 2017 1 Introduction Process synchronization is the set of techniques that are used to coordinate

More information

Real-time Scheduling of Skewed MapReduce Jobs in Heterogeneous Environments

Real-time Scheduling of Skewed MapReduce Jobs in Heterogeneous Environments Real-time Scheduling of Skewed MapReduce Jobs in Heterogeneous Environments Nikos Zacheilas, Vana Kalogeraki Department of Informatics Athens University of Economics and Business 1 Big Data era has arrived!

More information

Operating Systems Unit 3

Operating Systems Unit 3 Unit 3 CPU Scheduling Algorithms Structure 3.1 Introduction Objectives 3.2 Basic Concepts of Scheduling. CPU-I/O Burst Cycle. CPU Scheduler. Preemptive/non preemptive scheduling. Dispatcher Scheduling

More information

CPU Scheduling. Daniel Mosse. (Most slides are from Sherif Khattab and Silberschatz, Galvin and Gagne 2013)

CPU Scheduling. Daniel Mosse. (Most slides are from Sherif Khattab and Silberschatz, Galvin and Gagne 2013) CPU Scheduling Daniel Mosse (Most slides are from Sherif Khattab and Silberschatz, Galvin and Gagne 2013) Basic Concepts Maximum CPU utilization obtained with multiprogramming CPU I/O Burst Cycle Process

More information

OVERHEADS ENHANCEMENT IN MUTIPLE PROCESSING SYSTEMS BY ANURAG REDDY GANKAT KARTHIK REDDY AKKATI

OVERHEADS ENHANCEMENT IN MUTIPLE PROCESSING SYSTEMS BY ANURAG REDDY GANKAT KARTHIK REDDY AKKATI CMPE 655- MULTIPLE PROCESSOR SYSTEMS OVERHEADS ENHANCEMENT IN MUTIPLE PROCESSING SYSTEMS BY ANURAG REDDY GANKAT KARTHIK REDDY AKKATI What is MULTI PROCESSING?? Multiprocessing is the coordinated processing

More information

Lecture Topics. Announcements. Today: Uniprocessor Scheduling (Stallings, chapter ) Next: Advanced Scheduling (Stallings, chapter

Lecture Topics. Announcements. Today: Uniprocessor Scheduling (Stallings, chapter ) Next: Advanced Scheduling (Stallings, chapter Lecture Topics Today: Uniprocessor Scheduling (Stallings, chapter 9.1-9.3) Next: Advanced Scheduling (Stallings, chapter 10.1-10.4) 1 Announcements Self-Study Exercise #10 Project #8 (due 11/16) Project

More information

Improving VoD System Efficiency with Multicast and Caching

Improving VoD System Efficiency with Multicast and Caching Improving VoD System Efficiency with Multicast and Caching Jack Yiu-bun Lee Department of Information Engineering The Chinese University of Hong Kong Contents 1. Introduction 2. Previous Works 3. UVoD

More information

A DYNAMIC RESOURCE ALLOCATION STRATEGY FOR SATELLITE COMMUNICATIONS. Eytan Modiano MIT LIDS Cambridge, MA

A DYNAMIC RESOURCE ALLOCATION STRATEGY FOR SATELLITE COMMUNICATIONS. Eytan Modiano MIT LIDS Cambridge, MA A DYNAMIC RESOURCE ALLOCATION STRATEGY FOR SATELLITE COMMUNICATIONS Aradhana Narula-Tam MIT Lincoln Laboratory Lexington, MA Thomas Macdonald MIT Lincoln Laboratory Lexington, MA Eytan Modiano MIT LIDS

More information

Fixed-Priority Multiprocessor Scheduling

Fixed-Priority Multiprocessor Scheduling Fixed-Priority Multiprocessor Scheduling Real-time Systems N periodic tasks (of different rates/periods) r i T i C i T i C C J i Ji i ij i r i r i r i Utilization/workload: How to schedule the jobs to

More information

Dynamic Broadcast Scheduling in DDBMS

Dynamic Broadcast Scheduling in DDBMS Dynamic Broadcast Scheduling in DDBMS Babu Santhalingam #1, C.Gunasekar #2, K.Jayakumar #3 #1 Asst. Professor, Computer Science and Applications Department, SCSVMV University, Kanchipuram, India, #2 Research

More information

Subject Name: OPERATING SYSTEMS. Subject Code: 10EC65. Prepared By: Kala H S and Remya R. Department: ECE. Date:

Subject Name: OPERATING SYSTEMS. Subject Code: 10EC65. Prepared By: Kala H S and Remya R. Department: ECE. Date: Subject Name: OPERATING SYSTEMS Subject Code: 10EC65 Prepared By: Kala H S and Remya R Department: ECE Date: Unit 7 SCHEDULING TOPICS TO BE COVERED Preliminaries Non-preemptive scheduling policies Preemptive

More information

Unit 3 : Process Management

Unit 3 : Process Management Unit : Process Management Processes are the most widely used units of computation in programming and systems, although object and threads are becoming more prominent in contemporary systems. Process management

More information

Scheduling in Multiprocessor System Using Genetic Algorithms

Scheduling in Multiprocessor System Using Genetic Algorithms Scheduling in Multiprocessor System Using Genetic Algorithms Keshav Dahal 1, Alamgir Hossain 1, Benzy Varghese 1, Ajith Abraham 2, Fatos Xhafa 3, Atanasi Daradoumis 4 1 University of Bradford, UK, {k.p.dahal;

More information

Network Load Balancing Methods: Experimental Comparisons and Improvement

Network Load Balancing Methods: Experimental Comparisons and Improvement Network Load Balancing Methods: Experimental Comparisons and Improvement Abstract Load balancing algorithms play critical roles in systems where the workload has to be distributed across multiple resources,

More information

Chapter -5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS

Chapter -5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS Chapter -5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS Chapter 5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS 5.1 Introduction For successful

More information

Coding and Scheduling for Efficient Loss-Resilient Data Broadcasting

Coding and Scheduling for Efficient Loss-Resilient Data Broadcasting Coding and Scheduling for Efficient Loss-Resilient Data Broadcasting Kevin Foltz Lihao Xu Jehoshua Bruck California Institute of Technology Department of Computer Science Department of Electrical Engineering

More information

Course Syllabus. Operating Systems

Course Syllabus. Operating Systems Course Syllabus. Introduction - History; Views; Concepts; Structure 2. Process Management - Processes; State + Resources; Threads; Unix implementation of Processes 3. Scheduling Paradigms; Unix; Modeling

More information

Multi-Level Feedback Queues

Multi-Level Feedback Queues CS 326: Operating Systems Multi-Level Feedback Queues Lecture 8 Today s Schedule Building an Ideal Scheduler Priority-Based Scheduling Multi-Level Queues Multi-Level Feedback Queues Scheduling Domains

More information

Today s class. Scheduling. Informationsteknologi. Tuesday, October 9, 2007 Computer Systems/Operating Systems - Class 14 1

Today s class. Scheduling. Informationsteknologi. Tuesday, October 9, 2007 Computer Systems/Operating Systems - Class 14 1 Today s class Scheduling Tuesday, October 9, 2007 Computer Systems/Operating Systems - Class 14 1 Aim of Scheduling Assign processes to be executed by the processor(s) Need to meet system objectives regarding:

More information

A COMPARATIVE STUDY OF CPU SCHEDULING POLICIES IN OPERATING SYSTEMS

A COMPARATIVE STUDY OF CPU SCHEDULING POLICIES IN OPERATING SYSTEMS VSRD International Journal of Computer Science &Information Technology, Vol. IV Issue VII July 2014 / 119 e-issn : 2231-2471, p-issn : 2319-2224 VSRD International Journals : www.vsrdjournals.com REVIEW

More information

Paging algorithms. CS 241 February 10, Copyright : University of Illinois CS 241 Staff 1

Paging algorithms. CS 241 February 10, Copyright : University of Illinois CS 241 Staff 1 Paging algorithms CS 241 February 10, 2012 Copyright : University of Illinois CS 241 Staff 1 Announcements MP2 due Tuesday Fabulous Prizes Wednesday! 2 Paging On heavily-loaded systems, memory can fill

More information

Operating Systems. Scheduling

Operating Systems. Scheduling Operating Systems Scheduling Process States Blocking operation Running Exit Terminated (initiate I/O, down on semaphore, etc.) Waiting Preempted Picked by scheduler Event arrived (I/O complete, semaphore

More information

Chapter 9 Uniprocessor Scheduling

Chapter 9 Uniprocessor Scheduling Operating Systems: Internals and Design Principles, 6/E William Stallings Chapter 9 Uniprocessor Scheduling Patricia Roy Manatee Community College, Venice, FL 2008, Prentice Hall Aim of Scheduling Assign

More information

Welfare Navigation Using Genetic Algorithm

Welfare Navigation Using Genetic Algorithm Welfare Navigation Using Genetic Algorithm David Erukhimovich and Yoel Zeldes Hebrew University of Jerusalem AI course final project Abstract Using standard navigation algorithms and applications (such

More information

Buffer Management in Delay Tolerant Networks

Buffer Management in Delay Tolerant Networks Buffer Management in Delay Tolerant Networks Rachana R. Mhatre 1 And Prof. Manjusha Deshmukh 2 1,2 Information Technology, PIIT, New Panvel, University of Mumbai Abstract Delay tolerant networks (DTN)

More information

Efficient Remote Data Access in a Mobile Computing Environment

Efficient Remote Data Access in a Mobile Computing Environment This paper appears in the ICPP 2000 Workshop on Pervasive Computing Efficient Remote Data Access in a Mobile Computing Environment Laura Bright Louiqa Raschid University of Maryland College Park, MD 20742

More information

WHITE PAPER Application Performance Management. The Case for Adaptive Instrumentation in J2EE Environments

WHITE PAPER Application Performance Management. The Case for Adaptive Instrumentation in J2EE Environments WHITE PAPER Application Performance Management The Case for Adaptive Instrumentation in J2EE Environments Why Adaptive Instrumentation?... 3 Discovering Performance Problems... 3 The adaptive approach...

More information

System Design. An Engineering Approach to Computer Networking

System Design. An Engineering Approach to Computer Networking System Design An Engineering Approach to Computer Networking What is system design? A computer network provides computation, storage and transmission resources System design is the art and science of putting

More information

INTERNATIONAL JOURNAL OF RESEARCH SCIENCE & MANAGEMENT

INTERNATIONAL JOURNAL OF RESEARCH SCIENCE & MANAGEMENT MOBILE OFFLOADING USING POWER BASED DECISION IN WIRELESS COMMUNICATION M.Nivethamani 1*, Soma Prathinha 2 1* PG Scholar, Student Member, IEEE, Sri Sairam Engineering College, Chennai 2 Associate Professor,

More information

Project Report, CS 862 Quasi-Consistency and Caching with Broadcast Disks

Project Report, CS 862 Quasi-Consistency and Caching with Broadcast Disks Project Report, CS 862 Quasi-Consistency and Caching with Broadcast Disks Rashmi Srinivasa Dec 7, 1999 Abstract Among the concurrency control techniques proposed for transactional clients in broadcast

More information

WHITE PAPER: ENTERPRISE AVAILABILITY. Introduction to Adaptive Instrumentation with Symantec Indepth for J2EE Application Performance Management

WHITE PAPER: ENTERPRISE AVAILABILITY. Introduction to Adaptive Instrumentation with Symantec Indepth for J2EE Application Performance Management WHITE PAPER: ENTERPRISE AVAILABILITY Introduction to Adaptive Instrumentation with Symantec Indepth for J2EE Application Performance Management White Paper: Enterprise Availability Introduction to Adaptive

More information

Fast, Efficient, and Robust Multicast in Wireless Mesh Networks

Fast, Efficient, and Robust Multicast in Wireless Mesh Networks fast efficient and robust networking FERN Fast, Efficient, and Robust Multicast in Wireless Mesh Networks Ian Chakeres Chivukula Koundinya Pankaj Aggarwal Outline IEEE 802.11s mesh multicast FERM algorithms

More information

CPU scheduling. Alternating sequence of CPU and I/O bursts. P a g e 31

CPU scheduling. Alternating sequence of CPU and I/O bursts. P a g e 31 CPU scheduling CPU scheduling is the basis of multiprogrammed operating systems. By switching the CPU among processes, the operating system can make the computer more productive. In a single-processor

More information

Hybrid Cooperative Caching in a Mobile Environment

Hybrid Cooperative Caching in a Mobile Environment Hybrid Cooperative Caching in a Mobile Environment Hong Va Leong 1, Chi-yin Chow 2 1 Department of Computing, The Hong Kong Polytechnic University Hong Kong cshleong@comp.polyu.edu.hk 2 Department of Computing

More information

The Best Protocol for Real-time Data Transport

The Best Protocol for Real-time Data Transport The Definitive Guide to: The Best Protocol for Real-time Data Transport Assessing the most common protocols on 6 important categories Identifying the Best Protocol For strategic applications using real-time

More information

Maintaining Mutual Consistency for Cached Web Objects

Maintaining Mutual Consistency for Cached Web Objects Maintaining Mutual Consistency for Cached Web Objects Bhuvan Urgaonkar, Anoop George Ninan, Mohammad Salimullah Raunak Prashant Shenoy and Krithi Ramamritham Department of Computer Science, University

More information

Operating Systems. Process scheduling. Thomas Ropars.

Operating Systems. Process scheduling. Thomas Ropars. 1 Operating Systems Process scheduling Thomas Ropars thomas.ropars@univ-grenoble-alpes.fr 2018 References The content of these lectures is inspired by: The lecture notes of Renaud Lachaize. The lecture

More information

Splitting Algorithms

Splitting Algorithms Splitting Algorithms We have seen that slotted Aloha has maximal throughput 1/e Now we will look at more sophisticated collision resolution techniques which have higher achievable throughput These techniques

More information

Optimizing On-Demand Data Broadcast Scheduling in Pervasive Environments

Optimizing On-Demand Data Broadcast Scheduling in Pervasive Environments Optimizing On-Demand Data Broadcast Scheduling in Pervasive Environments Rinku Dewri, Indrakshi Ray, Indrajit Ray and Darrell Whitley Department of Computer Science Colorado State University Fort Collins,

More information

Example: CPU-bound process that would run for 100 quanta continuously 1, 2, 4, 8, 16, 32, 64 (only 37 required for last run) Needs only 7 swaps

Example: CPU-bound process that would run for 100 quanta continuously 1, 2, 4, 8, 16, 32, 64 (only 37 required for last run) Needs only 7 swaps Interactive Scheduling Algorithms Continued o Priority Scheduling Introduction Round-robin assumes all processes are equal often not the case Assign a priority to each process, and always choose the process

More information

Computer Architecture Lecture 24: Memory Scheduling

Computer Architecture Lecture 24: Memory Scheduling 18-447 Computer Architecture Lecture 24: Memory Scheduling Prof. Onur Mutlu Presented by Justin Meza Carnegie Mellon University Spring 2014, 3/31/2014 Last Two Lectures Main Memory Organization and DRAM

More information

Performance Monitoring

Performance Monitoring Performance Monitoring Performance Monitoring Goals Monitoring should check that the performanceinfluencing database parameters are correctly set and if they are not, it should point to where the problems

More information

Study of Load Balancing Schemes over a Video on Demand System

Study of Load Balancing Schemes over a Video on Demand System Study of Load Balancing Schemes over a Video on Demand System Priyank Singhal Ashish Chhabria Nupur Bansal Nataasha Raul Research Scholar, Computer Department Abstract: Load balancing algorithms on Video

More information

Disk Scheduling COMPSCI 386

Disk Scheduling COMPSCI 386 Disk Scheduling COMPSCI 386 Topics Disk Structure (9.1 9.2) Disk Scheduling (9.4) Allocation Methods (11.4) Free Space Management (11.5) Hard Disk Platter diameter ranges from 1.8 to 3.5 inches. Both sides

More information

Fault tolerant scheduling in real time systems

Fault tolerant scheduling in real time systems tolerant scheduling in real time systems Afrin Shafiuddin Department of Electrical and Computer Engineering University of Wisconsin-Madison shafiuddin@wisc.edu Swetha Srinivasan Department of Electrical

More information

Operating Systems. Lecture Process Scheduling. Golestan University. Hossein Momeni

Operating Systems. Lecture Process Scheduling. Golestan University. Hossein Momeni Operating Systems Lecture 2.2 - Process Scheduling Golestan University Hossein Momeni momeni@iust.ac.ir Scheduling What is scheduling? Goals Mechanisms Scheduling on batch systems Scheduling on interactive

More information

Optimal Query Mapping in Mobile OLAP

Optimal Query Mapping in Mobile OLAP Optimal Query Mapping in Mobile OLAP Ilias Michalarias and Hans -J. Lenz Freie Universität Berlin {ilmich,hjlenz}@wiwiss.fu-berlin.de Overview I. mobile OLAP Research Context II. Query Mapping in molap

More information

SYSTEM UPGRADE, INC Making Good Computers Better. System Upgrade Teaches RAID

SYSTEM UPGRADE, INC Making Good Computers Better. System Upgrade Teaches RAID System Upgrade Teaches RAID In the growing computer industry we often find it difficult to keep track of the everyday changes in technology. At System Upgrade, Inc it is our goal and mission to provide

More information

Routing Protocol comparison

Routing Protocol comparison Routing Protocol comparison Introduction to routing Networks allow people to communicate, collaborate, and interact in many ways. Networks are used to access web pages, talk using IP telephones, participate

More information

Virtual Memory. Chapter 8

Virtual Memory. Chapter 8 Virtual Memory 1 Chapter 8 Characteristics of Paging and Segmentation Memory references are dynamically translated into physical addresses at run time E.g., process may be swapped in and out of main memory

More information