A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. In Seventh IFIP/IEEE International Symposium on Integrated Network Management, Seattle, WA, May 2001.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....agents on network devices and or management applications, e.g. ping or traceroute. In higher layers, due to the lack of the appropriate management information bases, other methods have to be proposed. Several reports on the automatic obtaining of the system dependencies have been published, e.g. [4]. Performance problems diagnosis E business customers increasingly demand support for quality of service (QoS) guarantees. QoS parameters are negotiated between the customer and the e business as a part of Service Level Agreements [13] SLAs) which also specify pricing rules for the offered ....

A. Brown, G. Kar, and A. Keller. An active approach to characterizing dynamic dependencies for problem determination in a distributed application environment. In IM'01 [16]. (to appear).

....techniques, including event correlation systems, are based on static dependency models describing the relationships among the hardware and software components in the system. These dependency models are used to determine which components might be responsible for the symptoms of a given problem [5, 25, 6, 13]. The first major limitation Hotmail 7000 [11] Google 8000 [14] of traditional dependency models is the difficulty of generating and maintaining an accurate model of a constantly evolving Internet service. Their second major limitation is that they typically only model a logical system, and ....

....used per dynamically generated page request techniques. The second approach uses dependency models [25, 6, 13] However, these systems do not consider how the required dependency models are obtained. More recent research has focused on automatically generating dependency models. Brown et al. [5] use active perturbation of the system to identify dependencies and use statistical modeling of the system to compute dependency strengths. The dependency strengths can be used to order the potential root causes, but they do not uniquely identify the root cause of the problem, whereas our approach ....

A. Brown and D. Patterson. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. In Seventh IFIP/IEEE International Symposium on Integrated Network Management, Seattle, WA, May 2001.

....proper behavior of dependent components by explicitly injecting realistic test inputs and checking the resulting outputs for both correctness and performance. To aid in diagnosis, ROC systems should automatically track the health of all components, and use techniques such as dependency analysis [1] to automatically pinpoint the root cause of detected problems. Finally, to carry out the exercising of recovery mechanisms needed to guarantee their proper behavior, ROC systems should have integrated mechanisms for fault injection to simulate failures and to trigger recovery mechanisms. 4 ....

A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. To appear in Proceedings of the Seventh IFIP/IEEE International Symposium on Integrated Network Management (IM VII), Seattle, WA, May 2001.

....their root causes. Current root cause analysis techniques use approaches that do not sufficiently capture the dynamic complexity of large systems, and they require people to input extensive knowledge about the systems [22, 4] Recent event correlation techniques based on dependency models [5, 23, 6, 12] use statically generated dependencies of components to determine which components are responsible for the symptoms of a given problem. Two limitations of using dependency models are that they are difficult to generate accurately and they are difficult to keep consistent with an evolving system. ....

....The second approach uses dependency models, such as Yemini et al. 23] Choi et al. 6] and Gruschke[12] However, these systems do not consider how the required dependency models are obtained. More recent research has focused on automatically generating dependency models. Brown et al. [5] use active perturbation of the system to identify dependencies and use statistical modeling of the system to compute dependency strengths. The dependency strengths can be used to order the potential root causes, but they do not uniquely identify the root cause of the problem, whereas our approach ....

Aaron Brown and David Patterson. An active approach to characterizing dynamic dependencies for problem determination in a distributed environment. In Seventh IFIP/IEEE International Symposium on Integrated Network Management, Seattle, WA, May 2001.

No context found.

A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. To appear in Proceedings of the Seventh IFIP/IEEE International Symposium on Integrated Network Management (IM VII), Seattle, WA, May 2001.

....and protocol design, which has only recently been applied to service and application management is the active perturbation of components within a system (i.e. injecting faults in a controlled manner and observing the behavior of the components) while running synthetic transactions against it. [1] describes how active perturbation can be used to obtain the required dependency information; however, great care has to be taken if this technique is used on production systems. Other approaches come from the area of Artificial Intelligence. 3] uses Neural Networks to automatically derive ....

A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Application Environment. In N. Anerousis and G. Pavlou, editors, Proceedings of the 7th IFIP/IEEE International Symposium on Integrated Network Management. IEEE Publishing, May 2001.

....truly at fault. One promising approach to root cause analysis is a technique known as dependency analysis, in which a model of dependencies between system modules is used to identify possible culprits of observed symptoms while eliminating those modules that could not possibly be the root cause [6] [31] Unfortunately, one of our main tenets of repair centric systems is that a priori models (like the required dependency model) are not knowable for complex, dynamic systems. The solution again lies in module interfaces. As a request is processed by the system, work is done on its behalf by ....

.... models either assumes the unlikely existence of a system configuration repository [31] requires a compiler that can statically extract resource hierarchies [43] or uses perturbation experiments that are unlikely to work in the complex, asynchronous systems that underlie Internet services [6]. While our proposed direct approach to tracing request dependencies is similar to existing work that uses request stamping to track resource utilization in distributed systems [47] we believe that its application as a diagnostic aid is unique and that it solves the problem of obtaining ....

A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. To appear in Proceedings of the Seventh IFIP/IEEE International Symposium on Integrated Network Management (IM VII), Seattle, WA, May 2001.

....mainframes [Merenda92] Problem diagnosis: There are several standard approaches to problem diagnosis. One is to use models and dependency graphs to perform diagnosis [Choi99] Gruschke98] Katker97] Lee00] Yemini96] When models are not available, they can either be discovered [Kar00] Brown01] Miller95] Zave98] or alternate techniques can be used, such as Bangas system specific combination of monitoring, protocol augmentation, and cross layer correlation [Banga00] Our Pinpoint example demonstrates another approach by tracking requests through the system as is done in distributed ....

A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. Proc 7th IFIP/IEEE Int'l. Symp. on Integrated Network Management, Seattle, WA, May 2001.

....we find that some of the techniques used here have been seen before in existing work. Brown, Keller, and Kar have carried out a study that used perturbation of database tables to extract hidden dependency information between database performance and enduser transaction quality of service [2]; the perturbation techniques in that paper can be seen as a mild form of the fault injection described in this report. Furthermore, although in the authors had a very different end goal, they used a similar technique of examining quality of service during system perturbation as a way of ....

A. Brown, A. Keller, and G. Kar. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Application Environment. Submitted to the Seventh IFIP/IEEE International Symposium on Integrated Network Management (IM

No context found.

A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. In Seventh IFIP/IEEE International Symposium on Integrated Network Management, Seattle, WA, May 2001.

No context found.

A. Brown, G. Kar, and A. Keller. An active approach to characterizing dynamic dependencies for problem determination in a distributed environment. In Seventh IFIP/IEEE International Symposium on Integrated Network Management, Seattle, WA, 2001.

No context found.

A. Brown, G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. In Seventh IFIP/IEEE International Symposium on Integrated Network Management, Seattle, WA, May 2001.

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