Method and system for dynamically allocating servers to compute-resources using capacity thresholds

Abstract

Servers are allocated for use in one of a plurality of compute-resources or for stand-by storage in a free-pool. Server load metrics are selected (e.g., ping-reply time or CP utilization) for measuring load in the servers. Metrics are measured for the servers allocated to the compute-resources. Several metrics can be measured simultaneously. The metrics for each compute-resource are normalized and averaged. Then, the metrics for each compute-resource are combined using weighting coefficients, producing a global load value, G, for each compute-resource. The G value is recalculated at timed intervals. Upper and lower thresholds are set for each compute-resource, and the G values are compared to the thresholds. If the G value exceeds the upper threshold, then a server in the free-pool is reallocated to the compute-resource; if the G value is less than the lower threshold, then a server is moved from the compute-resource to the free-pool.

Description

BACKGROUND OF THE INVENTION [0001] 1. Field of the Invention [0002] The present invention relates generally to compute-resources (sets of servers that are logically and physically isolated from one another for the purpose of security and dedicated usage) and methods for allocating servers between compute-resources based on a new capacity threshold. More specifically, the present invention relates to a method for setting capacity thresholds, monitoring the computation load on each compute-resource, and reallocating servers when thresholds are exceeded. [0003] 2. Background Description [0004] Compute-resources are commonly used for applications supporting large numbers of users, and those that are central processor unit (CPU) intensive and highly parallizable. Examples of such compute-resources include web-applications hosted by Internet service providers (ISPs), and many scientific applications in areas such as Computational Fluid Dynamics Often in such computing environments, load c...

AI Technical Summary

Benefits of technology

The present invention provides a method and system for dynamically allocating servers among a plurality of connected server compute-resources and a free-pool of servers. The system monitors various metrics, such as CPU usage, memory usage, and network traffic, for each server and calculates a global load value based on the normalized average metric values. The global load value is compared to lower and upper thresholds to determine if a server is overloaded or under loaded. If a server is overloaded, it is removed from the free-pool and allocated to the overloaded compute-resource. If a server is under loaded, it is removed from it and allocated to the free-pool. This helps to efficiently allocate servers and optimize resource utilization.

Problems solved by technology

Compute-resources are commonly used for applications supporting large numbers of users, and those that are central processor unit (CPU) intensive and highly parallizable.

Currently, there are few systems that support dynamic allocation of servers.

There are no automated effective and efficient methods for determining when a particular compute-resource is overloaded or under loaded that is relatively independent of application modifications.

Images