ReMoS: A Resource Monitoring System for Network-Aware Applications
نویسندگان
چکیده
Network-aware applications can adjust their resource demands in response to changes in the availability of resources. Such applications must be able to obtain information about the status of the network resources. Providing such information to an application is conceptually simple, yet de ning an interface that addresses the needs of applications, as well as the realities of current and future networks, is far from easy. The Remos interface described in this paper allows network-aware applications to obtain information about network capabilities and network status. Interesting network informationmay be generated by the network hardware (switches), the network interface, or the network software, and is often in a system-speci c format. Further, network architectures signi cantly di er in their ability to provide such information in a timely and accurate manner. Remos provides a standard interface format that is independent of the details of any particular type of network. When hosted on an advanced network architecture, Remos provides access to accurate status and capability information. On legacy networks, Remos provides as much information as is feasible, using best-e ort approximation where appropriate. Using Remos, network-aware applications can be written independent of any particular network architecture, yet have the ability to tune their execution behavior to the dynamic state of the network. In this paper we motivate and describe the Remos interface. We also sketch our rst implementation of the interface for an IP-based testbed. Our experience in de ning and implementing Remos indicates that providing accurate feedback in an network-independent manner is a signi cant challenge and we identify a number of areas for future work. The network-independent Remos interface establishes a framework that can form the basis for further research.
منابع مشابه
Collecting Network Status Information for Network-Aware Applications
Network-aware applications, i.e., applications that adapt to network conditions in an application specific way, need both static and dynamic information about the network to be able to adapt intelligently to network conditions. The CMU Remos interface gives applications access to a wide range of information in a network-independent fashion. Remos uses a logical topology to capture the network i...
متن کاملA Perspective on Application/Network Coupling
Networked applications execute in a distributed environment that is shared with many users, so the level of service they receive from the network can be highly variable. Since the characteristics of the network often determine overall application performance, network-aware applications attempt to adjust to changes in the network conditions. Therefore, such applications must be able to obtain pe...
متن کاملThe Architecture of the Remos System
Remos provides resource information to distributed applications. Its design goals of scalability, flexibility, and portability are achieved through an architecture that allows components to be positioned across the network, each collecting information about its local network. To collect information from different types of networks and from hosts on those networks, Remos provides several collect...
متن کاملAdaptive Distributed Applications on Heterogeneous Networks
Distributed applications execute in environments that can include different network architectures as well as a range of compute platforms. Furthermore, these resources are shared by many users. Therefore these applications receive varying levels of service from the environment. Since the availability of resources in a networked environment often determines overall application performance, adapt...
متن کاملReliability and Performance Evaluation of Fault-aware Routing Methods for Network-on-Chip Architectures (RESEARCH NOTE)
Nowadays, faults and failures are increasing especially in complex systems such as Network-on-Chip (NoC) based Systems-on-a-Chip due to the increasing susceptibility and decreasing feature sizes. On the other hand, fault-tolerant routing algorithms have an evident effect on tolerating permanent faults and improving the reliability of a Network-on-Chip based system. This paper presents reliabili...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1997