Chandra M. R. Kintala

Software rejuvenation: analysis, module and applications

Software rejuvenation is the concept of gracefully terminating an application and immediately restarting it at a clean internal state. In a client-server type of application where the server is intended to ran perpetually for providing a service to its clients, rejuvenating the server process periodically during the most idle time of the server increases the availability of that service. In a long-running computation-intensive application, rejuvenating the application periodically and restarting it at a previous checkpoint increases the likelihood of successfully completing the application execution. We present a model for analyzing software rejuvenation in such continuously-running applications and express downtime and costs due to downtime during rejuvenation in terms of the parameters in that model. Threshold conditions for rejuvenation to be beneficial are also derived. We implemented a reusable module to perform software rejuvenation. That module can be embedded in any existing application on a UNIX platform with minimal effort. Experiences with software rejuvenation in a billing data collection subsystem of a telecommunications operations system and other continuously-running systems and scientific applications in AT&T are described.<<ETX>>

ONE-IP: techniques for hosting a service on a cluster of machines

Abstract With the explosive growth of the World Wide Web, some popular web sites are getting thousands of hits per second. As a result, clients (browsers) experience slow response times and sometimes may not be able to access some web sites at all. Upgrading the server nodes to more powerful machines may not always be cost-effective. A natural solution is to deploy a set of machines, or a cluster, and have them work together to host a single service. Such a server cluster should preferably publicize only one server name for the entire cluster so that any configuration change inside the cluster does not affect client applications. In this paper, we first discuss existing approaches to distributing clients requests for a single service to different machines in a cluster. We then propose two new techniques, collectively called ONE-IP , based on dispatching packets at the IP level. They have the advantages of fast dispatching, and ease of implementation. Ideas presented here are generic and should be applicable to other services as well.

Checkpointing and its applications

The paper describes our experience with the implementation and applications of the Unix checkpointing library libckp, and identifies two concepts that have proven to be the key to making checkpointing a powerful tool. First, including all persistent states, i.e., user files, as part of the process state that can be checkpointed and recovered provides a truly transparent and consistent rollback. Second, excluding part of the persistent state from the process state allows user programs to process future inputs from a desirable state, which leads to interesting new applications of checkpointing. We use real-life examples to demonstrate the use of libckp for bypassing premature software exits, for fast initialization and for memory rejuvenation.<<ETX>>

Refining Nondeterminism in Relativized Polynomial-Time Bounded Computations

Let

On measuring nondeterminism in regular languages

\mathcal {P}_{g(n)}

Amounts of nondeterminism in finite automata

denote the class of languages acceptable by polynomial-time bounded Turing machines making at most

Performance and reliability evaluation of passive replication schemes in application level fault tolerance

g(n)

Dependability enhancement for IEEE 802.11 wireless LAN with redundancy techniques

nondeterministic moves on inputs of length n. For any constructible

Real-time computations with restricted nondeterminism

g(n)

Components for software fault tolerance and rejuvenation

,