PROCESS AND METHODOLOGY FOR GENERIC ANALYSIS OF METRICS RELATED TO RESOURCE UTILIZATION AND PERFORMANCE

• US 20080320123A1
• Filed: 06/21/2007
• Published: 12/25/2008
• Est. Priority Date: 06/21/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: McGowan, Dilton Monroe II, Houlihan, John Richard
• Granted Patent: US 7,882,216 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/815 Virtual
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455

Abstract

A generic algorithm for analysis of resource metrics. A threshold is calculated in a stack tier policy for the performance state of a metric in a virtualized process collection (VPC). Responsive to determining that the metric is a critical metric, a weighted average of all metrics in the VPC is determined. Responsive to determining that the weighted average exceeds the threshold in the stack tier policy, if the value of the metric is determined to be higher than values for all recorded metrics, the value of the metric is stored as a highest value. A weighted average performance state of all metrics is calculated as the weight property of the performance metric divided by the weight factor total. Responsive to determining that the highest value is higher than the weighted average performance state of all metrics, the highest value is used as the performance state of the VPC.

Claims

1. A computer implemented method for analyzing performance metrics for a virtualized process collection, the computer implemented method comprising:

calculating a threshold in a stack tier policy for a performance state of a metric in the virtualized process collection;

responsive to determining that the metric is a critical metric, determining a weighted average of all metrics in the virtualized process collection;

responsive to determining that the weighted average exceeds the threshold in the stack tier policy, determining that a value of the metric is higher than values for all recorded metrics and storing the value of the metric as a highest value;

calculating a weighted average performance state of all metrics as the weight property of the performance metric divided by the weight factor total; and

responsive to determining that the highest value is higher than the weighted average performance state of all metrics, using the highest value as the performance state of the virtualized process collection.

2. The computer implemented method of claim 1, wherein determining a weighted average of all metrics in the virtualized process collection further comprises:

calculating the performance state of the metric as a weight adjusted total of all metric values divided by a weight factor total.

3. The computer implemented method of claim 1, wherein the performance state of metrics in the virtualized process collection is based on common property values comprising metadata describing the metrics.

4. The computer implemented method of claim 3, wherein the metadata includes a weight property, limit property, critical property, and maximum property.

5. The computer implemented method of claim 3, wherein metadata is represented as a numeric rate or a percentage value representing a data point.

6. The computer implemented method of claim 1, wherein the critical metric has a boolean property indicating the metric has a critical monitor value.

7. A data processing system for analyzing performance metrics for a virtualized process collection, the data processing system comprising:

a bus;

a storage device connected to the bus, wherein the storage device contains computer usable code;

at least one managed device connected to the bus;

a communications unit connected to the bus; and

a processing unit connected to the bus, wherein the processing unit executes the computer usable code to calculate a threshold in a stack tier policy for a performance state of a metric in the virtualized process collection;

determine a weighted average of all metrics in the virtualized process collection in response to determining that the metric is a critical metric;

determine that a value of the metric is higher than values for all recorded metrics and storing the value of the metric as a highest value in response to determining that the weighted average exceeds the threshold in the stack tier policy;

calculate a weighted average performance state of all metrics as the weight property of the performance metric divided by the weight factor total; and

use the highest value as the performance state of the virtualized process collection in response to determining that the highest value is higher than the weighted average performance state of all metrics.

8. A computer program product for analyzing performance metrics for a virtualized process collection, the computer program product comprising:

a computer usable medium having computer usable program code tangibly embodied thereon, the computer usable program code comprising;

computer usable program code for calculating a threshold in a stack tier policy for a performance state of a metric in the virtualized process collection;

computer usable program code for determining a weighted average of all metrics in the virtualized process collection in response to determining that the metric is a critical metric;

computer usable program code for determining that a value of the metric is higher than values for all recorded metrics and storing the value of the metric as a highest value in response to determining that the weighted average exceeds the threshold in the stack tier policy;

computer usable program code for calculating a weighted average performance state of all metrics as the weight property of the performance metric divided by the weight factor total; and

computer usable program code for using the highest value as the performance state of the virtualized process collection in response to determining that the highest value is higher than the weighted average performance state of all metrics.