Aggregate system resource analysis including correlation matrix and metric-based analysis

• US 7,379,994 B2
• Filed: 10/26/2001
• Issued: 05/27/2008
• Est. Priority Date: 10/26/2000
• Status: Expired due to Fees

• Current Assignee: Jason M. Donahue Trust
• Original Assignee: Metilinx
• Inventors: Collazo, Carlos M.
• Primary Examiner(s): Vaughn; William
• Assistant Examiner(s): BENGZON, GREG C
• Application Number:
  US10/040,012
• Publication Number:
  US 20020152304A1
• Time in Patent Office: 2,405 Days
• Field of Search: 709224-225, 709/223, 702/182, 702/186
• US Class Current: 709/224
• CPC Class Codes: H04L 41/0233 Object-oriented techniques, for representation of network management data, e.g. common object request broker architecture [CORBA]
• CPC Class Codes: H04L 41/042 comprising distributed management centres cooperatively managing the network
• CPC Class Codes: H04L 41/0853 by actively collecting configuration information or by backing up configuration information
• CPC Class Codes: H04L 41/142 using statistical or mathematical methods
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 41/5009 Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level

Abstract

A system for gathering data for purposes of analyzing a network. The data is gathered based on values that are passed from node-to-node within processing devices, such as servers, in a network. The values are generated from characteristics obtained from measuring device performance and resource utilization. Values are passed peer-to-peer and successively combined with values at each receiving system so that, ultimately, a value is obtained that reflects the operation of a group of devices. A correlation matrix is maintained to indicate discrepancies in value meanings from different devices. The correlation matrix is used to more accurately combine values to achieve meaningful composite values.

Claims

1. A computer implemented method for assessing computer server and communications network capacity, the method comprising:

calculating two integer values representing a Local Node Value (LNV) and a Composite Node Value (CNV);

calculating the LNV of a server as an integer value through a combination of measured counters at the same instantaneous point in time, the LNV reflecting the capacity of the server to receive work loads; and

,

calculating the CNV of a beginning server as an integer value through a combination of the LNVs of a sub-network of servers that begins with the beginning server, the calculation of the CNV including the LNV of the beginning server, the CNV reflecting the capacity of the sub-network beginning with the beginning server to collectively receive work-loads wherein said LNV and CNV allow a user to analyze network device performance and network resource utilization in a peer-to-peer, real-time relationship, without requiring a multi-tier polling data collection process via a central console, said peer-to-peer real-time relationship comprising a peer-to-peer value including said CNV and said LNV and capable of changing dynamically, in one to many, many to one, and bi-directional relationships between a plurality of calculated values wherein said CNV and LNV values are displayed in a client interface device and associated with a new network resource configuration wherein one or more network elements are communicatively coupled in a different manner from a previous network resource configuration.

2. The method in accordance with claim 1, further comprising:

obtaining a plurality of characteristics or counters at a specific point in time that are combined through correlation matrixes and weighted sums to produce the two integer values for the same point of time, the correlation matrixes and weighted sums being updated over a period of time to reflect historical changes over the period of time wherein an intelligent object (IO) is installed on each server in the network in a peer-to-peer architecture, said IO'"'"'s measuring real-time behavior of network components.

3. A network performance aggregate resource analysis system comprising:

one or more processor readable storage devices having processor readable code embodied on said processor readable storage devices, said processor readable code for programming one or more processors to perform a method of providing a control function for a computer system, the method comprising;

receiving a process code from a remote server; and

operating the computer system according to the process code;

to implement the method comprising the following steps;

providing one or more intelligence objects (IO) populating a network communicatively coupled to one or more nodes executing on one or more servers, computers, or other network components;

providing a composite value wherein said composite value is derived from said lO'"'"'s;

providing one or more system level object'"'"'s (SLO) that monitor and report on one or more network performance parameters in a host computer server;

providing one or more transaction level objects (TLO) that monitor transaction loads with respect to said host computer wherein said IO'"'"'s are installed on each server in the network in a peer-to-peer network architecture, said IO'"'"'s measuring real-time behavior of network components.

4. A network performance aggregate resource analysis system comprising:

one or more processor readable storage devices having processor readable code embodied on said processor readable storage devices, said processor readable code for programming one or more processors to perform a method of providing a control function for a computer system;

receiving a process code from the remote server; and

operating the computer system according to the process code;

to implement the method comprising the following steps;

providing one or more intelligence objects (IO) populating a network communicatively coupled to one or more nodes executing on one or more servers, computers, or other network components;

providing a composite value wherein said composite value is derived from said IO'"'"'s;

providing one or more system level object'"'"'s (SLO) that monitor and report on one or more network performance parameters in a host computer server;

providing one or more transaction level objects (TLO) that monitors transaction loads with respect to said host computer wherein said IO'"'"'s are installed on each server in the network in a peer-to-peer network architecture, said IO'"'"'s measuring real-time behavior of network components wherein said objects measure a plurality of network performance values;

representing said values in a binary value, said binary value represented in an initial local utilization value and subsequent local utilization values, said initial local utilization value relating only to said host computer server;

providing said localization values capable of being modified to a first composite utilization value;

providing said first composite utilization value capable of being passed directly to a second composite utilization value communicatively coupled to a data record tag;

providing a plurality of tags and segments to said first and second composite utilization values such that a plurality of local utilization values, composite utilization values and initial local utilization values differentiate host data in a bi-directional relationship.

5. A computer implemented method for assessing computer server and communications network capacity, said network having processor readable storage devices and processor readable code stored thereon for executing instructions on a processor, the method comprising:

calculating two integer values representing a Local Node Value (LNV) and a Composite Node Value (CNV), by;

calculating the LNV of a server as an integer value through a combination of measured counters at the same instantaneous point in time, the LNV reflecting the capacity of the server to receive work loads;

calculating the CNV of a beginning server as an integer value through a combination of the LNVs of a sub-network of servers that begins with the beginning server, the calculation of the CNV including the LNV of the beginning server, the CNV reflecting the capacity of the sub-network beginning with the beginning server to collectively receive work-loads wherein said LNV and CNV allow a user to analyze network device performance and network resource utilization in a peer-to-peer, real-time relationship, without requiring a multi-tier polling data collection process wherein said CNV and LNV values are displayed in a client interface device and associated with a new network resource configuration and wherein one or more network elements are communicatively coupled in a different manner from a previous network resource configuration.

6. A computer implemented method for assessing computer server and communications network capacity, said network having processor readable storage devices and processor readable code stored thereon for executing instructions on a processor, the method comprising:

calculating two integer values representing a Local Node Value (LNV) and a Composite Node Value (CNV), by;

calculating the LNV of a server as an integer value through a combination of measured counters at the same instantaneous point in time, the LNV reflecting the capacity of the server to receive work loads;

calculating the CNV of a beginning server as an integer value through a combination of the LNVs of a sub-network of servers that begins with the beginning server, the calculation of the CNV including the LNV of the beginning server, the CNV reflecting the capacity of the sub-network beginning with the beginning server to collectively receive work-loads wherein said LNV and CNV allow a user to analyze network device performance and network resource utilization in a peer-to-peer, real-time relationship, without requiring a multi-tier polling data collection process and capable of changing dynamically, in one to many, many to one, and bi-directional relationships between a plurality of calculated values wherein said CNV and LNV values are displayed in a client interface device and associated with a new network resource configuration and wherein one or more network elements are communicatively coupled in a different manner from a previous network resource configuration.

7. A computer implemented method for assessing computer server and communications network capacity, said network having processor readable storage devices and processor readable code stored thereon for executing instructions on a processor, the method comprising:

calculating two integer values representing a Local Node Value (LNV) and a Composite Node Value (CNV), by;

calculating the LNV of a server as an integer value through a combination of measured counters at the same instantaneous point in time, the LNV reflecting the capacity of the server to receive work loads;

calculating the CNV of a beginning server as an integer value through a combination of the LNVs of a sub-network of servers that begins with the beginning server, the calculation of the CNV including the LNV of the beginning server, the CNV reflecting the capacity of the sub-network beginning with the beginning server to collectively receive work-loads wherein said LNV and CNV allow a user to analyze network device performance and network resource utilization in a peer-to-peer, real-time relationship, without requiring a multi-tier polling data collection process via a central console, said peer-to-peer real-time relationship comprising a peer-to-peer value including said CNV and said LNV wherein said CNV and LNV values are displayed in a client interface device and associated with a new network resource configuration and wherein one or more network elements are communicatively coupled in a different manner from a previous network resource configuration.