J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken. Specifying and Measuring Quality of Service in Distributed Object Systems. In Proceedings of the First IEEE International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC '98), Apr. 1998.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....in the environment. The notion of adaptation is hardwired into particular applications or services [5,9,18] Again, our architecture based approach provides a general solution that supports adaptation of applications and systems for which it is not explicitly supported. The BBN QuO system [20] extends CORBA to support applications that adapt to resource availability. One aspect of the system is that users can define operating regions. The runtime system monitors the application and execution environment, and invokes application specific handlers when the application changes operating ....

Loyall, J.P., Schantz, R.E., Zinky, J.A., and Bakken, D.E. Specifying and Measuring Qual- ity of Service in Distributed Object Systems. In Proceedings of the 1 st IEEE Symposium on Object-oriented Real-time Distributed Computing, Kyoto, Japan, April 1998.

....In this extension, MagPie still recognizes only a two layer communication network, but through parameterized studies of the network they determine primal packet sizes. Various projects have investigated programming model extensions to enable ap plication management of QoS, for example, Quo [40]. The only other relevant effort in the context of MPI is work on real time extensions to MPI. MPI RT [44] provides a QoS interface but is not an established standard and introduces a new programming interface. Furthermore, the focus is on real time needs such as predictability of performance and ....

J.P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken. Specifying and measuring quality of service in distributed object systems. In Proeeedmgs of the First Iteratioal 5'ymposium o Object-Orieted Real-Time Distributed Computing (IS'ORC '98), 1998. Kyoto, Japan.

....of the ORB at runtime. 5 Related Work The classification of QoS as an aspect in the sense of AOP is recognized by other groups as well. The Quality Objects (QuO) project addresses QoS concerns by an AOP based approach on the application layer and through an augmented ORB on transport layer [12] [11], 19] Composition Filters [6] are a different approach which address layered QoS mechanisms as aspects in distributed middleware architectures in combination with reflection. Meta Spaces [7] address the same topic as composition filters. Again, there is a combination of aspect separation on ....

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken. Specifying and Measuring Quality of Service in Distributed Object Systems. In Proceedings of ISORC'98, Kyoto/Japan, April 1998.

....group communication system provides group membership protocols to detect process crash failures and to maintain replica consistencies by transferring the state for each new group member. In order to provide a way for an application to specify its dependability requirements, a Quality Object (QuO) [43], 44] can be used. It allows distributed applications to process and invoke dependability requests, and to receive information regarding the level of dependability that is being provided by the current system. QuO may run either in the same process as an application, or as a separate process. For ....

....c reactions to the callbacks. 2. 3 Quality Objects In order to provide a simple way for application objects to specify the levels of dependability they desire, the AQuA architecture provides an interface for applications to specify their desires directly or through the Quality Objects (QuO) [43], 44] which allows distributed applications to specify QoS requirements at the application level using the notion of a contract. A contract speci es actions to be taken based on the state of the distributed system and desired application requirements. The goal of QuO is to develop a common ....

J. P.Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken, \Specifying and measuring quality of service in distributed object systems," in Proceedings of the First International Symposium on Object-orientedReal-time Distributed Computing (ISORC'98), Kyoto, Japan, April 1998, pp. 43-52.

....systems. In particular, the AQuA architecture provides adaptive fault toler1 This research has been supported by DARPA Contracts F30602 96 C 0315, F30602 97 C 0276, and F30602 98C 0187. ance to CORBA applications by replicating objects, has a high level method (using Quality Objects (QuO) [Zin97, Loy98]) that applications use to specify their desired dependability levels, and has a dependability manager that attempts to reconfigure a system at runtime so that dependability requests are satisfied. AQuA uses the Maestro Ensemble [Hay98, Vay98] group communication system to provide reliable ....

....this detection mechanism to detect crash failures. Maestro [Vay98] provides an objectoriented interface (in C ) to Ensemble. In order to provide a simple way for application objects to specify and adapt the levels of dependability they desire, the AQuA architecture uses the Quality Objects (QuO) [Zin97, Loy98] framework to process and invoke dependability requests. QuO allows distributed applications to specify QoS requirements at the application level using the notion of a contract. Note that the AQuA architecture intentionally provides dependability to a distributed application in a semitransparent ....

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken, "Specifying and Measuring Quality of Service in Distributed Object Systems," Proc. of the First International Symposium on Object-oriented Real-time Distributed Computing (ISORC '98), pp. 43-52, Kyoto, Japan, April 1998.

....to 4 provide the desired level of fault tolerance. Therefore, the AQuA system aims to adapt to changes in the system configuration while providing fault tolerance. The AQuA architecture is layered. The four layers, from top to bottom, are the CORBA application itself, Quality Objects (QuO) [4, 5], Proteus, and Maestro Ensemble [6, 7] Each layer only communicates with the layer immediately above or below it. The QuO layer provides the CORBA application with an interface to specify its fault tolerance requirements at a high level. Proteus aims to translate the high level requirements of ....

....of Service (QoS) requirements. In the case of AQuA, the dependability of a remote CORBA application is the QoS being specified. QuO works something like a CORBA ORB. The application developer specifies QoS regions and their associated requirements through a Contract Definition Language (CDL) [5]. Based on this specified contract, a QuO runtime process handles the dynamic QoS requirements of the application. In AQuA, a CORBA application requests a region of dependability to the QuO runtime, instead of binding to remote CORBA objects directly through the naming service. When the QoS for ....

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken, "Specifying and measuring quality of service in distributed object systems," in Proceedings of the 1st IEEE International Symposium on Object-oriented Real-time distributed Computing, Kyoto, Japan, April 1998.

....group communication system provides group membership protocols to detect process crash failures and to maintain replica consistencies by transferring the state for each new group member. In order to provide a way for an application to specify its dependability requirements, Quality Objects (QuO) [Loy98, Zin97] can be used. They allow distributed applications to process and invoke dependability requests, and to receive information regarding the level of dependability that is being provided by the current system. In AQuA, Proteus provides adaptive fault tolerance. Proteus consists of a dependability ....

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken, "Specifying and Measuring Quality of Service in Distributed Object Systems," Proc. of the First International Symposium on Object-oriented Real-time Distributed Computing (ISORC '98), pp. 43-52, Kyoto, Japan, April 1998.

....in user level specifications between groups of users with different levels of technical knowledge, temperaments and in different situations. Each element in an interaction may specify what it requires and what it is capable of delivering for each QoS parameter it manages. FLORISSI 95, FRLUND 98, LOYALL 98] are interesting examples of work on languages for the specification of QoS requirements, and behaviour in relation to actual QoS experienced. QoS negotiation is the process of reaching an agreement between parties in an interaction, on the acceptable bounds on the QoS to be delivered, to form ....

Loyall, J.P., Schantz, R., Zinky, J.A., Bakken, D.E.: Specifying and Measuring Quality of Service in Distributed Object Systems Proc. ISORC'98, Kyoto, Japan (IEEE, 1998)

No context found.

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken. "Specifying and measuring quality of service in distributed object systems". Proc.1st IEEE International Symposium on Object-oriented Real-time distributed Computing (ISORC 98), April 1998.

....3 Network Centric QoS Interface and Control as Part of a Layered Architecture elsewhere, and we provide pointers to the individual project web sites for additional information on the particular technologies. Quality Objects (QuO) is a distributed object based middleware framework developed at BBN [33, 30, 13]. QuO facilitates the creation and integration of distributed and embedded applications that can specify Their QoS requirements, The system elements that must be monitored and controlled to measure and provide QoS, and the behavior for adapting to QoS variations that occur at run time. QuO adds ....

J.P. Loyall, R.E. Schantz, J.A. Zinky, and D.E. Bakken. Specifying and measuring quality of service in distributed object systems. In IEEE Int'l Symp. Object-Oriented Real-Time Distributed Comp., April 1998. Kyoto, Japan.

....to a number of QoS management areas is fundamental. In particular, we have integrated several forms of advanced middleware capabilities within the WSOA testbed, including the following technologies that constitute a layered middleware architecture (from top to bottom; see Figure 3: QuO[QuO], an end to end QoS management middleware framework developed at BBN Technologies . RT ARM[RT ARM] a real time adaptive resource manager developed at Honeywell Technologies . Kokyu[Kokyu] a real time scheduling and dispatching framework developed at Washington University in St. Louis . ....

Loyall J, Schantz R, Zinky J, Bakken D. "Specifying and Measuring Quality of Service in Distributed Object Systems", Proceedings of The 1st IEEE International Symposium on Object -oriented Real-time distributed Computing (ISORC 98), 1998.

....good software engineering. It is only natural to put the latter into middleware [1] which acts as an intermediary between the application and the infrastructure and provides various services to the application transparently. In addition, advanced middleware such as QuO (short for Quality Objects)[10], provides support for adaptive behavior and QoS awareness which is especially useful for defensive adaptation and monitoring. This way the functionality and the defense mechanisms can be developed in a deconpied manner. Ideally, defensive strategies and mechanisms would be reusable for many ....

....code transformations on an application program. 8. CONCLUSION We are implementing technology for defense enabling under the DARPA project titled Applications that Participate in their Own Defense (APOD) The defense strategies have been implemented using the QuO adaptive middieware [10]. The implementation is discussed in detail in [12] The Intrusion Tolerance by Unpredictable Adaptation (ITUA) project[3] also being conducted at BBN Technologies, in cooperation with University of Illinois and The Boeing Company, is exploring two related issues: 1. Tolerating planned and ....

J. Loyall, R. Schantz, J. Zinky, and D. Bakken. Specifying and measuring quality of service in distributed object systems. In 1st IEEE Intl Syrup. on Object-Oriented Real-Time Distributed Computing (ISORC'98), Apr. 1998. Kyoto, Japan.

....good software engineering. It is only natural to put the latter into middleware [1] which acts as an intermediary between the application and the infrastructure and provides various services to the application transparently. In addition, advanced middleware such as QuO (short for Quality Objects)[9], provides support for adaptive behavior and QoS awareness which is especially useful for defensive adaptation and monitoring. This way the functionality and the defense mechanisms can be developed in a decoupled manner. Ideally, defensive strategies and mechanisms would be reusable for many ....

....code transformations on an application program. 7 Conclusion We are implementing technology for defense enabling under the DARPA project titled Applications that Participate in their Own Defense (APOD) The defense strategies have been implemented using the QuO adaptive middleware[9]. The implementation is discussed in detail in [10] The Intrusion Tolerance by Unpredictable Adaptation (ITUA) project[3] also being conducted at BBN Technologies, in cooperation with University of Illinois and The Boeing Company, is exploring two related issues: 1. Tolerating planned and ....

J. Loyall, R. Schantz, J. Zinky, and D. Bakken. Specifying and measuring quality of service in distributed object systems. In 1st IEEE Intl Symp. on Object-Oriented RealTime Distributed Computing (ISORC'98), Apr. 1998. Kyoto, Japan.

....requirements. The AQuA architecture is composed of several components: Quality Objects, Proteus, Maestro Ensemble, and gateways. In order to provide a simple way for application objects to specify the level of dependability they desire, the AQuA architecture uses the Quality Objects (QuO) [Zin97, Loy98] framework to process and invoke dependability requests. QuO allows distributed applications to specify quality of service (QoS) requirements at the application level using the notion of a contract, which specifies actions to be taken based on the state of the distributed system and desired ....

J. P. Loyall, R. E. Schantz, J. A. Zinky, D. E. Bakken, "Specifying and Measuring Quality of Service in Distributed Object Systems," Proc. of the First International Symposium on Object-oriented Real-time Distributed Computing (ISORC '98), pp. 43-52, Kyoto, Japan, April 1998.

No context found.

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken. Specifying and Measuring Quality of Service in Distributed Object Systems. In Proceedings of the First IEEE International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC '98), Apr. 1998.

No context found.

Joseph P. Loyall, Richard E. Schantz, John A.Zinky, and David E.Bakken. Specifying and Measuring Quality of Service in Distributed Object Systems. Proceedings of ISORC98, 1998.

No context found.

John A. Zinky Joseph P. Loyall, Richard E. Schantz and David E. Bakken. Specifying and Measuring Quality of Service in Distributed Object Systems. In In Proceedings of ISORC'98, Kyoto, Japan, Apr. 1998.

No context found.

J. P. Loyall,R. E. Schantz, J. A. Zinky, and D. E. Bakken. Specifying and measuring Quality of Service in Distributed Object Systems, Proceedings of the first IEEE International Symposium on Object-Oriented Real-tim Distributed Computing (ISORC'98), April, 1998, Japan.

No context found.

Loyall J.P., Schantz R.E., Zinky J.A. and Bakken D.E. Specifying and Measuring Quality of Service in Distributed Object Systems. Proceedings of 1 st International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC'98), April 1998.

No context found.

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken. Specifying and Measuring Quality of Service in Distributed Object Systems. In Proceedings of the First International Symposium on ObjectOriented Real-Time Distributed Computing. (ISORC '98), April 1998. Kyoto, Japan.

No context found.

Joseph P. Loyall, Richard E. Schantz, John A. Zinky, David E. Bakken. Specifying and Measuring Quality of Service in Distributed Object Systems. In Proceedings of SORC'98, 20-22 April 1998 in Kyoto, Japan.

No context found.

JP Loyall, RE Schantz, JA Zinky, and DE Bakken. Specifying and measuring quality of service in distributed object systems. In Proceedings of the First International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC), 1998.

No context found.

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken. Specifying and measuring quality of service in distributed object systems. In Proceedings of the First International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC '98), 1998. Kyoto, Japan.

No context found.

J. P. Loyall, et al., "Specifying and Measuring Quality of Service in Distributed Object Systems, " in Proc. First IEEE International Symposium on Object-Oriented Real-Time Distributed Computing (IEEE Computer Society Press, Los Alamitos, CA, Apr. 20-22, 1998).

No context found.

J. P. Loyall, R. E. Schantz, J. A. Zinky, and D. E. Bakken, "Specifying and Measuring Quality of Service in Distributed Object Systems," Proc. of the First International Symposium on Object-oriented Real-time Distributed Computing (ISORC '98), Kyoto, Japan, pp. 43-52, April 1998.

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