Browse Prior Art Database

A new mechanism for the application server cluster optimization in scalable balance way

IP.com Disclosure Number: IPCOM000240283D
Publication Date: 2015-Jan-21
Document File: 4 page(s) / 169K

Publishing Venue

The IP.com Prior Art Database

Abstract

As the web traffic is becoming more and more heavy these days, the cluster technology is inevitably widely used in our app's deploy environment. But in most of the situation, the cluster's resource is not fully used, some are just occupy less than 20% of the whole cluster resource(cpu, memory, network). This disclosure describes a new way to switch the cluster strategy in the cluster environment based on the stress of the current traffic, it provides a new methodology to analysis the current situation and process the cluster's behavior in real time in order to make full use of existing resource, which can bring us better value in most of the situations.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 72% of the total text.

Page 01 of 4

A new mechanism for the application server cluster optimization in scalable balance way

Traditional application server cluster includes several different cluster strategy, e.g. High performance cluster, Load balance cluster, High availability cluster etc... These strategy is mainly for different purpose, we always choose the corresponding one for our application server. But as the server is often happened to have different request/access load in different time period, so sometimes the server is not take full advantage of when traffic(request/access load) is low, and sometime it is not enough for busy traffic.

This disclosure describes a new mechanism to optimize the application server cluster in a scalable load balance way which can make us to take full advantage of the existing server resource and also scale in/out when traffic is low/busy.

The main claim points of this disclosure is:
1> a cluster negotiator which monitoring the request dispatcher of the cluster and also the resource occupancy rate of the target cluster server in order to make decision on the balance strategy.
2> reconcile among different balance strategy(e.g. Session balance, request balance, availability balance etc..) based on the analysis result.

The advantages of this disclosure is:
1> take full advantage of the existing server
2> scale in/out to match the traffic based on the capability of existing server resources

Detail description


1. cluster negotiator and strategy processor

- cluster nego...