Hewlett-Packard

About: Hewlett-Packard is a company organization based out in Palo Alto, California, United States. It is known for research contribution in the topics: Signal & Substrate (printing). The organization has 34663 authors who have published 59808 publications receiving 1467218 citations. The organization is also known as: Hewlett Packard & Hewlett-Packard Company.

Dynamic proportional share scheduling in Hadoop

Abstract: We present the Dynamic Priority (DP) parallel task scheduler for Hadoop. It allows users to control their allocated capacity by adjusting their spending over time. This simple mechanism allows the scheduler to make more efficient decisions about which jobs and users to prioritize and gives users the tool to optimize and customize their allocations to fit the importance and requirements of their jobs. Additionally, it gives users the incentive to scale back their jobs when demand is high, since the cost of running on a slot is then also more expensive. We envision our scheduler to be used by deadline or budget optimizing agents on behalf of users. We describe the design and implementation of the DP scheduler and experimental results. We show that our scheduler enforces service levels more accurately and also scales to more users with distinct service levels than existing schedulers.

Time-domain skin-effect model for transient analysis of lossy transmission lines

Abstract: A skin-effect equivalent circuit consisting of resistors and inductors is derived from the skin-effect differential equations for simulating the loss of a transmission line. A numerical method is used to analyze the transmission-line differential equations and the skin-effect equivalent circuit, yielding a model which relates the new values of node voltages and line currents to their values at the previous time step. Based on this model, a very simple program was written on a desk-top computer for the transient analysis of lossy trammission lines. Two examples are presented. The first example is an analysis of the step and pulse responses of a 600-m RG-8/U coaxial cable. The computed results show excellent agreement with measured data. The second example studies the current at the end of a 12-in 7-Ω strip line under different loading conditions. Very good agreement has been obtained between the calculated steady-state solution and that obtained by the frequency-domain method.

Object oriented distributed computing system processing request to other object model with code mapping by object managers located by manager of object managers

Abstract: An object oriented distributed computing system is provided. Processing means call a location service within automatically generated stubs in response to a request for a service provided by a particular object. The location service is automatically called on behalf of the requester to locate the target object when the request is issued. Multiple Object Managers reflecting multiple Object Models are permitted in the system. Programmers and users do not need to know the Object Model adhered to by an Object Manager. A request to any object in the system is independent of the Object Model of the sought object's Object Manager. A generic interface enables new Object Managers reflecting new Object Models to be easily added to the system. Availability of the target object is independent of association of the target object with a process at the time the request was issued. Deactivation of processes is automatically accomplished in response to the system needing resources.

Gatekeeper: supporting bandwidth guarantees for multi-tenant datacenter networks

Abstract: Cloud environments should provide network performance isolation for co-located untrusted tenants in a virtualized datacenter. We present key properties that a performance isolation solution should satisfy, and present our progress on Gatekeeper, a system designed to meet these requirements. Experiments on our Xen-based implementation of Gatekeeper in a datacenter cluster demonstrate effective and flexible control of ingress/egress link bandwidth for tenant virtual machines under both TCP and greedy unresponsive UDP traffic.

Modeling and analysis of multichip module power supply planes

Abstract: A method that would allow accurate modeling of arbitrarily shaped planes with bypass capacitors has been developed. It is compatible with a SPICE-based modeling method for the rest of the power supply hierarchy and the devices. A modified SPICE is used to accommodate distributed circuits. The distributed circuits are built with microwave analysis software and connected to SPICE by s-parameter files. The modeling process is described and examples of thick and thin-film power supply planes are presented with comparison to measured results. The method is used to explore potential design choices for a large MCM with many simultaneously switching drivers. >