39 citations found. Retrieving documents...
R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.

 Home/Search   Document Details and Download   Summary   Related Articles   Check  

This paper is cited in the following contexts:

First 50 documents

Enhanced Fixed-Priority Scheduling with (m,k)-Firm Guarantee - Quan, Hu (2000)   (1 citation)  (Correct)

....(m,k) model can be readily incorporated into system Quality of Service (QoS) requirements, and is applicable to many real time systems such as those in multimedia and automotive control. In this paper, we use the (m,k) model to study the scheduling problem of overloaded systems. Some approaches [1, 2, 3, 5, 7, 9, 11, 19] apply dynamic scheduling techniques to handle overloaded realtime systems. However, in many applications, a fixedpriority scheduling algorithm is usually more attractive than a dynamic priority one because (i) it incurs lower overhead; ii) the implementation is relatively simple; iii) it gives ....

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. The 6th International Conference on Multimedia Computing and Systems, Jun 1999.


Enhanced Fixed-Priority Scheduling with (m,k)-Firm Guarantee - Gang Quan Xiaobo (2000)   (1 citation)  (Correct)

....(m,k) model can be readily incorporated into system Quality of Service (QoS) requirements, and is applicable to many real time systems such as those in multimedia and automotive control. In this paper, we use the (m,k) model to study the scheduling problem of overloaded systems. Some approaches [1, 2, 3, 5, 7, 9, 12, 19] apply dynamic sheduling techniques to handle overloaded real time systems. However, in many applications, fixed priority scheduling algorithms are usually more attractive than dynamic priority ones because (i) it incurs lower overhead; ii) the implementation is relatively simple; iii) it gives ....

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. The 6th International Conference on Multimedia Computing and Systems, Jun 1999. 17


Deadline Fair Scheduling: Bridging the Theory and.. - Chandra, Adler, Shenoy (2001)   (14 citations)  (Correct)

....with each application and allocate bandwidth in proportion to the specified rates. Schedulers based on generalized processor sharing (GPS) 15] such as weighted fair sharing [9] start time fair queuing [11] and borrowed virtual time [10] are one class of proportional share schedulers. West et al. [20] have described a deadline based proportional share scheduler which takes into account acceptable loss rates for multiple streams. Recently, several studies have focused on proportional share scheduling in multiprocessors. Jones et al. have proposed a reservation based scheduler for ....

R. West and K. Schwan. Dynamic Window-Constrained Scheduling for Multimedia Applications. In IEEE International Conference on Multimedia Computing and Systems, Florence, Italy, 1999.


An Adaptive QoS Mechanism for Multimedia Applications in.. - Desai (2001)   (1 citation)  (Correct)

....to improved processing and network resource utilization as compared to user specified configurations and connection time configurations. Furthermore better compliance to specific application needs can be achieved by using customized configuration algorithms. An end to end communication layer [24] [25] is proposed for service adaptation in the context of a single data stream. This layer configures the communication protocol based on application resource requirement and the network resource availability. The communication layer utilizes a payoff based technique for evaluating benefits of ....

R. West and K. Schwan, "Dynamic Window-Constrained Scheduling for Multimedia Applications", 6th International Conference on Multimedia Computing and Systems (ICMCS'99), Vol. 2, pp. 87-91, Florence, Italy, June 1999.


Dynamic Window-Constrained Scheduling of Real-Time.. - West, Zhang.. (2004)   Self-citation (West Schwan)   (Correct)

No context found.

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


Dynamic Window-Constrained Scheduling for Real-Time Media .. - West, Schwan, Poellabauer (2003)   Self-citation (West Schwan)   (Correct)

No context found.

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


An Optimal, On-Line Window-Constrained Scheduler for.. - West, Poellabauer   Self-citation (West)   (Correct)

No context found.

Richard West and Karsten Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


Implicit Quality Channels (IQC): Distributed Quality.. - Poellabauer, Schwan (2001)   Self-citation (Schwan)   (Correct)

No context found.

R. West and K. Schwan, \Dynamic Window-Constrained Scheduling for Multimedia Applications," in 6th International Conference on Multimedia Computing and Systems, ICMCS'99, IEEE, June 1999.


Dynamic Window-Constrained Scheduling of Real-Time.. - West, Zhang.. (2004)   Self-citation (West Schwan)   (Correct)

No context found.

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


Dynamic Window-Constrained Scheduling for Real-Time Media .. - West, Schwan, Poellabauer (2003)   Self-citation (West Schwan)   (Correct)

No context found.

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


Dynamic Window-Constrained Scheduling for Real-Time Media .. - West, Schwan, Poellabauer (2003)   Self-citation (West Schwan)   (Correct)

No context found.

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


Window-Constrained Process Scheduling for Linux Systems - West, Ganev, Schwan (2001)   Self-citation (West Schwan)   (Correct)

....Boston University Boston, MA 02215 richwest cs.bu. edu Ivan Ganev and Karsten Schwan College of Computing Georgia Institute of Technology Atlanta, GA 30332 fganev,schwang cc.gatech.edu Abstract This paper describes our experience using Dynamic Window Constrained Scheduling (DWCS) [13, 14, 12, 11] to schedule processes (and threads) on available CPUs in a Linux system. We describe the implementation of a kernel loadable module that replaces the default Linux scheduler. Each process scheduled using DWCS has a request period of T time units and a window constraint , x=y. The end of one ....

....is exceeded it may be impossible to interpret the received video sequence at the client. Likewise, if frames are generated too fast, playout bu ers at the client might over ow and some frames will again be lost. We have developed an algorithm called Dynamic Window Constrained Scheduling (DWCS) [13, 14, 12] to support real time and multimedia applications requiring rate based service constraints like those described above. DWCS was originally designed as a packet scheduler to provide (m; k) rm deadline guarantees [5] and fair queueing [2, 15, 3, 1, 4, 9, 10] for loss and delay constrained trac ....

R. West and K. Schwan. Dynamic windowconstrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GITCC -98-18, Georgia Institute of Technology.


Lightweight Kernel/User Communication for Real-Time and.. - Poellabauer, Schwan.. (2001)   (2 citations)  Self-citation (West Schwan)   (Correct)

....scheduling may be changed according to the desired event rates and the number of events pending for applications. In the current implementation, ECalls supports the cooperation with both the standard Linux scheduler and a novel real time CPU scheduler based on the DWCS scheduling algorithm [32]. Event Scheduling with the Linux Scheduler. The Linux scheduler has been modified as follows. If a real time process (a process in either the SCHED FIFO or the SCHED RR queue) has any Kernel ECalls pending, it will be given preference over processes with the same or smaller priority. If only ....

....of the current window constraint are decremented and there fore the window constraint is relaxed. On the other hand, if a process misses to be scheduled within its period T, only the numerator is decremented, resulting in a tighter window constraint. Details about DWCS can be found in [32, 34]. The original DWCS algorithm works according to the following (simplified) rules: The process with the closest deadline (i.e. the time until its current period T expires) will be selected. If several processes have the same deadline, the process with the tightest current window constraint x y ....

[Article contains additional citation context not shown here]

R. West and K. Schwan. Dynamic Window-Constrained Scheduling for Multimedia Applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999.


Architecture and Hardware for Scheduling Gigabit.. - Krishnamurthy.. (2002)   Self-citation (West Schwan)   (Correct)

....division for streams. In fact, DWCS can be configured to operate as an EDF scheduler (loss tolerances are 0 0) static priority scheduler (infinite deadline, static priority is original losstolerance of streams) and fair scheduler (WFQ weights can be set using deadlines and loss tolerances) [2, 6]. The reader is referred to [2] where it is also shown that DWCS can ensure that the delay bound of any given stream is independent of other streams, delay of service to real time packet streams is bounded even when the DWCS scheduler is overloaded and also that no more than x packets miss ....

.... scheduling framework to realize a range of scheduling disciplines for real time and best effort streams coupled with our experiences with software implementations of the scheduling framework have prompted us to adopt this scheduling framework for architectural exploration and hardware realization[ 1, 3, 6]. A hardware realization of a dynamic scheduling discipline will need state storage for every stream, pairwise ordering logic for determining the winner stream, priority update logic that updates stream state every scheduling or decision cycle and a control unit to orchestrate progression through ....

R. West and K. Schwan. Dynamic Window- constrained scheduling for multimedia applications. In 6 th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999.


Efficient Implementation of Packet Scheduling Algorithm.. - Shi, Zhuang, Paul..   Self-citation (Schwan)   (Correct)

....Paul Karsten Schwan Georgia Institute of Technology, College of Computing, 801 Atlantic Drive Atlanta, GA, 30332 0280 Shiw, xt2000, schwan cc.gatech.edu indrani ece.gatech.edu Abstract. This paper describes the design and implementation of the Dynamic Window Constrained Scheduling (DWCS)[1][2] 3] algorithm to schedule packets on network processors. The DWCS algorithm characterizes multimedia streams with diverse Quality of Service (QoS) requirements. Earlier implementations of DWCS on Linux and Solaris machines use a heap based implementation, which requires O(n) time to find ....

....media servers need to serve hundreds to thousands of clients, each with its own Quality of Service (QoS) requirements. Critical QoS properties like packet loss rate, deadline and delay variance need to be maintained without compromising the processing speed of incoming data streams. Many papers [1][4] 5] have addressed the problem of scheduling priority ordered input packets that packets from different flows are processed in an appropriate order, the order being determined by the QoS requirement of each stream. Packets of less priority not able to meet their QoS may be dropped to save ....

[Article contains additional citation context not shown here]

Richard West and Karsten Schwan, "Dynamic Window-Constrained Scheduling for Multimedia Applications," in Proceedings of the IEEE International Conference on Multimedia Computing and Systems (ICMCS), 1999.


Stream Handlers: Application-specific Message.. - Gavrilovska.. (2002)   Self-citation (Schwan)   (Correct)

.... being filtering to transmit only those data items that are actually currently viewed in a remote scientific visualization [9, 12] 2) they address multimedia applications, by executing scheduling algorithms that reduce data by discarding packets based on loss tolerance and deadline information [11, 17]; and (3) they concern execution of codes for large scale operational information systems (OISs) used by companies that include Delta Air Lines [6] where data mirroring services improve both the response times and the reliability of the information captured, processed, and distributed on a 24 7 ....

R. West and K. Schwan. Dynamic Window-Constrained Scheduling for Multimedia Applications. In Proc. of 6th International Conference on Multimedia Computing and Systems (ICMCS'99), Florence, Italy, June 1999.


A Quality-of-Service Enhanced Socket API in GNU/Linux - Abbasi, Poellabauer..   Self-citation (West Schwan)   (Correct)

....network stack can also be retrieved for even more flexible adaptation. Such information includes bu#er sizes, receive windows, etc. 3 API usage In this section we describe common usage scenarios for QSockets with code excerpts. For the purpose of our examples we use the DWCS queueing discipline [8], ported to Linux kernel version 2.4.17. DWCS provides soft real time guarantees for continuous media streams, and also allows the developer to specify a loss tolerance in the presence of transient overload situations. DWCS supports three parameters, ipg, oln and old. The stream rate is defined ....

R. West and K. Schwan. Dynamic windowconstrained scheduling for multimedia applications. In ICMCS, Vol. 2, pages 87--91, 1999.


Lightweight Kernel/User Communication for Real-Time and.. - Poellabauer, Schwan (2001)   (2 citations)  Self-citation (West Schwan)   (Correct)

....scheduling may be changed according to the desired event rates and the number of events pending for applications. In the current implementation, ECalls supports the cooperation with both the standard Linux scheduler and a novel real time CPU scheduler based on the DWCS scheduling algorithm [32]. Event Scheduling with the Linux Scheduler. The Linux scheduler has been modi ed as follows. If a realtime process (a process in either the SCHED FIFO or the SCHED RR queue) has any Kernel ECalls pending, it will be given preference over processes with the same or smaller priority. If only ....

....denominator of the current window constraint are decremented and therefore the window constraint is relaxed. On the other hand, if a process misses to be scheduled within its period T, only the numerator is decremented, resulting in a tighter windowconstraint. Details about DWCS can be found in [32, 34]. The original DWCS algorithm works according to the following (simpli ed) rules: The process with the closest deadline (i.e. the time until its current period T expires) will be selected. If several processes have the same deadline, the process with the tightest current window constraint x y ....

[Article contains additional citation context not shown here]

R. West and K. Schwan. Dynamic Window-Constrained Scheduling for Multimedia Applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999.


Coordinated CPU and Event Scheduling for Distributed.. - Poellabauer, Schwan (2001)   (1 citation)  Self-citation (West Schwan)   (Correct)

.... overview of the ECalls mechanism and its realization for the Linux operating system (see Section 2) In Section 3, we describe the rules used to coordinate event delivery with CPU scheduling in detail, using a novel hard real time CPU scheduler, called DWCS (Dynamic Window Constrained Scheduler) [23]. Coordinated scheduling is performed such that task responsiveness to events is maximized while minimizing the variations of inter frame times experienced by the application s media streams. Section 4 demonstrates experimentally the importance of event awareness and shows how ECalls supports its ....

....Handler Thread) which is taken from a thread pool. This approach is similar to the functionality of optimistic message handlers [21] Finally, ECalls is able to cooperate with the CPU scheduler, currently including both the standard UNIX scheduler and a novel hard realtime scheduler, termed DWCS [23], to in uence scheduling decisions in conjunction with event communications. This feature of ECalls, called ECalls based CPU Scheduling, is the topic of the remainder of this paper. 3. COORDINATED SCHEDULING OF CPU AND EVENTS Most systems deploy CPU schedulers that ignore important ....

[Article contains additional citation context not shown here]

R. West and K. Schwan. Dynamic Window-Constrained Scheduling for Multimedia Applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999.


Coordinated CPU and Event Scheduling for Distributed.. - Poellabauer, Schwan.. (2001)   (1 citation)  Self-citation (West Schwan)   (Correct)

.... an overview of the ECalls mechanism and its realization for the Linux operating system (see Section 2) In Section 3, we describe the rules used to coordinate event delivery with CPU scheduling in detail, using a novel hard real time CPU scheduler, called DWCS (Dynamic WindowConstrained Scheduler) [19]. Coordinated scheduling is performed such that task responsiveness to events is maximized while minimizing the variations of inter frame times experienced by the application s media streams. Section 4 demonstrates experimentally the importance of event awareness and shows how ECalls supports its ....

....Handler Thread) which is taken from a thread pool. This approach is similar to the functionality of optimistic message handlers [20] Finally, ECalls is able to cooperate with the CPU scheduler, currently including both the standard UNIX scheduler and a novel hard real time scheduler, termed DWCS [19], to in uence scheduling decisions in conjunction with event communications. This feature of ECalls, called ECalls based CPU Scheduling, is the topic of the remainder of this paper. 3 Coordinated Scheduling of CPU and Events Most systems deploy CPU schedulers that ignore important ....

[Article contains additional citation context not shown here]

R. West and K. Schwan, \Dynamic Window-Constrained Scheduling for Multimedia Applications," in 6th International Conference on Multimedia Computing and Systems, ICMCS'99, IEEE, June 1999.


Analysis of a Window-Constrained Scheduler for Real-Time and .. - West, Poellabauer (2000)   (8 citations)  Self-citation (West)   (Correct)

....access points (and, possibly, switches) must be able to schedule the transmission of packets from various streams so that the objectives of as many of the most important packets as possible are met. This paper describes the real time properties of Dynamic Window Constrained Scheduling (DWCS)[23, 24], an algorithm which is suitable for packet scheduling in real time communications. DWCS is designed to explicitly service packet streams in accordance with their loss and delay constraints, using just two attributes per packet stream. Furthermore, DWCS has the desirable property of supporting ....

....service packet streams in accordance with their loss and delay constraints, using just two attributes per packet stream. Furthermore, DWCS has the desirable property of supporting fair allocation of bandwidth to packet streams, in proportion to their loss constraints and per packet deadlines[23]. In fact, DWCS can behave as a static priority (SP) earliest deadline first (EDF) and fair scheduling algorithm[7, 25, 9, 2, 10, 18, 22] Moreover, DWCS is intended to support multimedia traffic streams in the same manner as the SMART scheduler[17] but DWCS is less complex and requires ....

[Article contains additional citation context not shown here]

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


Flexible User/Kernel Communication For Real-Time.. - Poellabauer.. (2000)   Self-citation (West Schwan)   (Correct)

....speci cally targeting the real time domain. These extensions are implemented as kernel loadable modules. Real Time CPU Scheduling. One of the extensions o ered by ELinux is a hard real time scheduler that replaces the standard Linux scheduler. DWCS (Dynamic Window Constrained Scheduler) [11, 12] schedules processes according to their service constraints: a request period T and a window constraint x y. The request period is the maximum tolerable interval between servicing two requests of a process, where the end of a request period determines a deadline by which a process must be ....

....pool. 4. User handler function: Again, as in 2. but the function resides in user space (locked into memory) This method raises severe security problems, which we will not address in this paper. 5. ECall Scheduling: We modi ed the standard Linux scheduler and a real time CPU scheduler (DWCS [11, 12, 9]) to support the integrated scheduling of tasks and Kernel ECalls. KernelECalls have priorities assigned in uencing the scheduling decision in case several processes have Kernel ECalls pending. 4 Implementation Details In the following sections we investigate some of the mechanisms introduced ....

[Article contains additional citation context not shown here]

R. West and K. Schwan, Dynamic WindowConstrained Scheduling for Multimedia Applications, Proc. 6th International Conference on Multimedia Computing and Systems (ICMCS), 1999.


Flexible Event Delivery for Kernel Extensions in ELinux - Poellabauer, Schwan, West   Self-citation (West Schwan)   (Correct)

....speci cally targeting the real time domain. These extensions are implemented as kernel loadable modules. Real Time CPU Scheduling. One of the extensions o ered by ELinux is a hard real time scheduler that replaces the standard Linux scheduler. DWCS (Dynamic Window Constrained Scheduler) [19, 21] schedules processes according to their service constraints: a request period T and a window constraint x y. The end of a request period determines a deadline by which a process must be serviced. The numerator x of the window constraint is the number of times a request for a process can be ....

....with events pending can be favored over other processes. In addition to delivering events, ECalls is therefore able to cooperate with the CPU scheduler to minimize the delay of event delivery. For this purpose, we modi ed the standard Linux scheduler and also a novel real time CPU scheduler (DWCS [19, 21, 20]) The intent is to support the integrated scheduling of tasks and events. Event Scheduling with the Linux Scheduler. The Linux scheduler has been modi ed as follows. If a real time process (a process in either the SCHED FIFO or the SCHED RR queue) has any Kernel ECalls pending, it will be given ....

[Article contains additional citation context not shown here]

R. West and K. Schwan, \Dynamic Window-Constrained Scheduling for Multimedia Applications," in 6th International Conference on Multimedia Computing and Systems, ICMCS'99, IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.


Analysis of a Window-Constrained Scheduler for Real-Time and .. - West, Poellabauer (2000)   (8 citations)  Self-citation (West)   (Correct)

....discipline, for scheduling the transmission of packets from loss tolerant applications, must attempt to guarantee that no more than x packets are serviced late for every y packets requiring service. This paper analyzes the real time properties of Dynamic Window Constrained Scheduling (DWCS) [18, 19], an algorithm that is suitable for packet scheduling in real time communications. DWCS is designed to explicitly service packet streams in accordance with their loss and delay constraints, using just two attributes per packet stream. Furthermore, DWCS has the desirable property of supporting ....

....service packet streams in accordance with their loss and delay constraints, using just two attributes per packet stream. Furthermore, DWCS has the desirable property of supporting fair allocation of bandwidth to packet streams, in proportion to their loss constraints and per packet deadlines [18]. In fact, DWCS can behave as a static priority (SP) earliest deadline first (EDF) and fair scheduling algorithm [6, 20, 7, 2, 8, 15, 16] Moreover, DWCS is intended to support multimedia traffic streams in the same manner as the SMART scheduler [14] but DWCS is less complex and requires ....

[Article contains additional citation context not shown here]

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999.


A Network Co-processor-Based Approach to Scalable.. - Krishnamurthy.. (2000)   (3 citations)  Self-citation (West Schwan)   (Correct)

.... for server software is attained by using dynamic load balancing across parallel distributed server resources, by using admission control and online request scheduling[28] to control resource usage, improve throughput, and guarantee service for resources like CPUs[17, 12] network links [26, 25, 28], and disks[5] In addition, developers employ application level or end to end solutions[13] that adapt server and or client behavior in response to user needs and resource availability. For instance, for clients, media caching buffering and runtime variation of delivered service quality[20] are ....

....schedulers running on host CPUs are easily affected even by transient loading conditions whereas media sched ulers running directly on I2O NIs are immune to host CPU loading. The traffic elimination we demonstrate for media applications utilizes window and time constrained scheduling techniques[26, 25]. Specifically, when a server streams video to some number of clients, packet scheduling is performed in order to guarantee differential packet rates and deadlines to meet clients individual QoS needs. By performing packet scheduling on the NI rather than the host, traffic is eliminated for the ....

[Article contains additional citation context not shown here]

R. West and K. Schwan. Dynamic window-constrained scheduling for multimedia applications. In 6th International Conference on Multimedia Computing and Systems, ICMCS'99. IEEE, June 1999. Also available as a Technical Report: GIT-CC-98-18, Georgia Institute of Technology.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC