Browsing by Author "Dr. Robert Callaway, Committee Member"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Multi-point to single-point service traffic shaping
    (2009-04-15) Boloor, Keerthana; Dr. Yannis Viniotis, Committee Chair; Dr. George Rouskas, Committee Member; Dr. Michael Devetsikiotis, Committee Member; Dr. Robert Callaway, Committee Member
    Service providers within an enterprise network are often governed by Client Service Contracts (CSC) that specify, among other constraints, the rate at which a particular service instance may be accessed. The service can be accessed via multiple points (typically middleware appliances) in a proxy tier configuration. The CSC and thus the rate specified have to be collectively respected by all the middleware appliances. The appliances locally shape the service requests to respect the global contract. We investigate the case where the CSC limits the rate to a service to X requests with an enforcement/observation interval of T seconds across all the middleware appliances. In this thesis, we define and evaluate the performance of Credit-based Algorithm for Service Traffic Shaping (CASTS), a decentralized algorithm for service traffic shaping in middleware appliances, in both a simulation and a realistic production level enterprise network setting. We show that CASTS respects the CSC and improves the responsiveness of the system to the variations of the input rate and leads to larger service capacity when compared to the traditional static allocation approach.
  • No Thumbnail Available
    Provisioning Algorithms for Service Differentiation in Middleware Appliance Clusters
    (2009-07-07) Habib, Mursalin; Dr. Robert Callaway, Committee Member; Dr. Michael Devetsikiotis, Committee Member; Dr. Yannis Viniotis, Committee Chair
    Service oriented architectures (SOA) and XML-based Web Services have become the technology of choice in enterprise networks. These networks support multiple services and are typically architected in multiple computing tiers, with a main service tier for the business logic and a separate, offload" tier, for, say, the CPU-intensive XML processing. The offload tier is typically populated by clusters of middleware appliances, usually hardware-assisted devices that are optimized for their tasks. Service differentiation refers to the generic problem of managing the enterprise network resources in order to achieve desired performance objectives on a per service basis. In our research, we defined SAA/SDA (Service Activation Algorithm/Service Deactivation Algorithm) and its variations that manages the CPU allocation in the appliance tier, in order to provide service differentiation. The main design objective of SAA/SDA is to overcome the disadvantages of the present known, static solutions. We analyze the performance of SAA/SDA via simulations.