We have implemented an object-oriented real-time database system called BeeHive. Using BeeHive, the performance of two data-deadline cognizant scheduling policies', called EDDF and EDF-DC, and a baseline EDF policy all with/without admission control are evaluated through extensive experiments'. We identify the ranges where data-deadline cognizant scheduling policies are effective. We also show that when admission control is used it plays a more significant role than slecialized real-time data cognizant policies. Our admission control policy considers' not only CPU utilizations', but also I/0 requirements' and utilizations. These results' represent one of the few sets' of experimental results' found for an implemented real-time database; almost all previous results' are via simulation.

As part of the Legion metacomputing project, we have developed a reflective model, the Reflective Graph & Event (RGE) model, for incorporating functionality into applications. In this paper we apply the RGE model to the problem of making applications more robust to failures. RGE encourages system developers to express fault-tolerance algorithms in terms of transformations on the data structures that represent computations--- messages and methods---hence enabling the construction of generic and reusable fault-tolerance components. We illustrate the expressive power of RGE by encapsulating the following fault-tolerance techniques into RGE components: two-phase commit distributed checkpointing, passive replication, pessimistic method logging, and forward recovery. 1 Introduction The advent of fast networks and the wide availability of computing resources make possible the realization of powerful virtual computers, or metasystems, that harness resources on a national or global ...

Recently, cheap and large capacity non-volatile memory such as flash memory is rapidly replacing disks in embedded systems. While the access time of flash memory is highly predictable, deadline misses may occur if data objects in flash memory are not properly managed in real-time embedded databases. Buffer cache can be used to mitigate this problem. However, since the workload of a real-time database cannot be precisely predicted, it may not be feasible to provide enough buffer space to satisfy all timing constraints. Several deadline miss ratio management schemes have been proposed, but they do not consider I/O activities. In this paper, we present an I/O-aware deadline miss ratio management scheme in real-time embedded databases whose secondary storage is flash memory. We propose an adaptive I/O deadline assignment scheme, in which I/O deadlines are derived from up-to-date system status. We also present a deadline miss ratio management architecture where a control theory-based feedback control loop prevents resource overload both in I/O and CPU. A simulation study shows that our approach can effectively cope with both I/O and CPU overload to achieve the desired deadline miss ratio. 1

Abstract not found

Legion is a large-scale metacomputing project at the University of Virginia. Legion users have requirements in many dimensions, including scheduling, security, fault tolerance, programming languages and environments, and performance. Not all users have the same needs. Further, as higher levels of services generally imply higher costs, users should be allowed to make tradeoffs and select the combination of services that is best suited for their purpose. To support diverse requirements Legion presents system developers with a reflective model, the Reflective Graph and Event model (RGE), for building metacomputing applications. The RGE model uses graphs and events to specify computations and enables first-class program graphs as event handlers. We demonstrate the RGE model in several areas of interest to metacomputing using Legion as our testbed. We unify the concepts of exceptions and events; by making exceptions a special case of events. Furthermore, using RGE, we demonstrat...

Several projects are currently underway to build the nation's next generation computing infrastructure. These projects are sometimes called metasystems projects and seek to provide the illusion of a single, unified, virtual computing environment to end users. We expect metasystems to consist of millions of hosts and billions of objects, and on this scale, resource failures will be the norm and no longer the exception. One of the technical challenges that must be solved before such systems become usable is the widespread adoption of fault-tolerance techniques for both system level services and user applications. As part of the Legion metasystem project, we have developed an architecture for incorporating fault-tolerance techniques into user applications. Our approach is based on reflective dynamic transformation techniques that manipulate the control and data flow characteristics of an application to achieve the desired fault-tolerance policies. In this paper, we present our...

Abstract—QeDB (Quality-aware real-time Embedded DataBase) is a database for data-intensive real-time applications running on embedded devices. Currently, databases for embedded systems are best effort, providing no guarantees on their timeliness and data freshness. Existing real-time database (RTDB) technology cannot be applied to these embedded databases since it hypothesizes that the main memory of a system is large enough to hold the entire database. This, however, might not be true in data-intensive real-time applications. QeDB uses a novel feedback control scheme to support QoS in such embedded systems without requiring all data to reside in main memory. In particular, our approach is based on simultaneous control of both I/O and CPU resources to guarantee the desired timeliness. Unlike existing work on feedback control of RTDB performance, we implement and evaluate the proposed scheme on a modern embedded device. The experimental results show that our approach supports the desired timeliness of transactions while still maintaining high data freshness compared to baseline approaches.

The Next Generation Internet (NGI) will provide an order of magnitude improvement in the computer/communication infrastructure. What is needed is a corresponding order of magnitude improvement at the application level. I believe that this will come in the form of global virtual databases. Such databases will be enterprise specific and offer features along real-time, fault tolerance, quality of service for audio and video, and security dimensions. Support of all these features and tradeoffs between them will provide an order of magnitude improvement over browsers, browsers connected to databases, and, in general, today's distributed databases. Such global virtual databases will not ONLY be enterprise specific, but also interact (given proper protections) with the worldwide information base via wrappers. Such wrappers may be based on Java and Java Data Base Connectivity standards. Different global virtual databases with their own real-time, fault tolerant, QoS, and security requirements ...

this paper, we describe the architecture of the BeeHive Resource Manager and the BeeHive Transaction Object Model. While the general QoS aspects of this architecture resemble most QoS architectures, the difference is the direct support in our architecture for transactions. In particular, we present both the scheduling algorithm that we developed for QoS at the transaction level and its associated performance results. 1. Introduction

Recently, cheap and large capacity non-volatile memory such as flash memory is rapidly replacing disks in embedded systems. While the access time of flash memory is highly predictable, deadline misses may occur if data objects in flash memory are not properly managed in real-time embedded databases. Buffer cache can be used to mitigate this problem. However, since the workload of a real-time database cannot be precisely predicted, it may not be feasible to provide enough buffer space to satisfy all timing constraints. Several deadline miss ratio management schemes have been proposed, but they do not consider I/O activities. In this paper, we present an I/O-aware deadline miss ratio management scheme in real-time embedded databases whose secondary storage is flash memory. We propose an adaptive I/O deadline assignment scheme, in which I/O deadlines are derived from up-to-date system status. We also present a deadline miss ratio management architecture where a control theory-based feedback control loop prevents resource overload both in I/O and CPU. A simulation study shows that our approach can effectively cope with both I/O and CPU overload to achieve the desired deadline miss ratio. 1