Optimized performance data collection at client nodes

Patent metadata

Field	Value
Publication number	US-2019312801-A1
Application number	US-201815949081-A
Country	US
Kind code	A1
Filing date	Apr 10, 2018
Priority date	Apr 10, 2018
Publication date	Oct 10, 2019
Grant date	—

Abstract

Techniques for optimized performance data collection at client nodes are disclosed. In one embodiment, a client node in a client-server environment may include at least one processing resource and a computer-readable storage medium having computer-readable program code embodied therewith. The computer-readable program code being configured to obtain resource utilization data associated with a plurality of processes running on the client node, determine a list of processes having resource utilization greater than a threshold based on the resource utilization data, organize the list of processes based on predetermined criteria and the resource utilization data, generate a report including a predefined number of processes from the organized list, and transmit the report to a management node for performance monitoring.

First claim

What is claimed is:

1 . A client node in a client-server environment, comprising:
at least one processing resource; a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code being configured to:
obtain resource utilization data associated with a plurality of processes running on the client node;
determine a list of processes having resource utilization greater than a threshold based on the resource utilization data;
organize the list of processes based on predetermined criteria and the resource utilization data;
generate a report including a predefined number of processes from the organized list; and
transmit the report to a management node for performance monitoring.

2 . The client node of claim 1 , wherein the predefined number comprises a top “N” number of processes that consume high resource utilization in the list of processes.

3 . The client node of claim 1 , wherein the computer readable program code being configured to:
sort the list of processes based on the resource utilization; rank the sorted list of processes until the predefined number starting from a process with a high resource utilization; and generate the report including details associated with the predefined number of processes based on the ranked list of processes.

4 . The client node of claim 1 , wherein the resource utilization data is associated with a plurality of resources.

5 . The client node of claim 4 , wherein the computer-readable program code being configured to:
consolidate data associated with the predefined number of processes for each of the plurality of resources by removing duplicate entries of the processes; and generate the report including the predefined number of processes for each of the plurality of resources based on the consolidated data.

6 . The client node of claim 1 , wherein the resource utilization data is associated with at least one resource, wherein the at least one resource is a hardware resource or a software resource.

7 . The client node of claim 1 , wherein the report including the predefined number of processes is generated in an operating system (OS) agnostic manner.

8 . A cloud computing system comprising:
a management node; and a plurality of client nodes communicatively coupled to the management node, wherein each client node comprises:
a monitoring unit to fetch resource utilization data for a plurality of processes running on the client node, wherein the resource utilization data is associated with a plurality of resources;
a structuring unit to organize the plurality of processes corresponding to each of the resources based on predetermined criteria and the resource utilization data;
a report generation unit to generate a report including a predefined number of processes corresponding to each of the resources based on the organized processes; and
a transmitting unit to transmit the report to the management node for performance monitoring.

9 . The cloud computing system of claim 8 , wherein the predefined number comprises a top “N” number of processes that consume high resource utilization corresponding to each of the resources.

10 . The cloud computing system of claim 8 , wherein each client node comprises a receiving unit to receive a request from the management node to determine the predefined number of processes having high resource utilization.

11 . The cloud computing system of claim 8 , wherein the structuring unit is to:
filter the resource utilization data to generate a list of processes having resource utilization for each resource greater than a threshold; sort the list of processes for each of the resources based on the resource utilization; and rank the sorted list of processes for each of the resources until the predefined number starting from a process with a high resource utilization.

12 . The cloud computing system of claim 8 , wherein the report generation unit is to:
consolidate data associated with the predefined number of processes for the plurality of resources by removing duplicate entries of the processes; and generate the report including the predefined number of processes based on the consolidated data.

13 . The cloud computing system of claim 8 , wherein the client nodes operate on different cloud computing environments or platforms, and wherein the client nodes are selected from a group consisting of a physical computing device, a virtual machine, a physical gateway device, and a virtual gateway device.

14 . The cloud computing system of claim 8 , wherein the report including the predefined number of processes is operating system (OS) agnostic.

15 . The cloud computing system of claim 8 , wherein the resource utilization data is selected from a group consisting of central processing unit (CPU) utilization, memory utilization, input/output (I/O) usage, cache usage, and network bandwidth usage.

16 . A method for managing a cloud computing system, comprising:
obtaining, by operation of a top process agent in a client node, resource utilization data for a plurality of processes running on the client node, wherein the client node is running in the cloud computing system; organizing the plurality of processes based on predetermined criteria and the resource utilization data by the top process agent; generating a report to include a predefined number of processes from the organized processes by the top process agent; and transmitting the report to a management node by the top process agent for performance monitoring.

17 . The method of claim 16 , wherein the predefined number comprises a top “N” number of processes that consume high resource utilization corresponding to each resource.

18 . The method of claim 16 , wherein organizing the plurality of processes comprises:
filtering the resource utilization data to generate a list of processes having resource utilization for each resource greater than a threshold; sorting the list of processes based on the resource utilization data; and ranking the sorted list of processes until the predefined number by the top process agent starting from a process with a high resource utilization.

19 . The method of claim 18 , wherein generating the report to include the predefined number of processes, comprises:
generating the report to include the predefined number of processes starting from the process with the high resource utilization based on the ranking.

20 . The method of claim 16 , wherein the client node is selected from a group consisting of a physical computing device, a virtual machine, a physical gateway device, and a gateway device, and wherein the resource utilization data is selected from a group consisting of CPU utilization, memory utilization, input/output (I/O) usage, cache usage, and network bandwidth usage.

21 . The method of claim 16 , wherein generating the report to include the predefined number of processes from the organized processes comprises:
generating the report including the predefined number of processes in an operating system (OS) agnostic manner.

22 . The method of claim 16 , wherein the operation of the top process agent is triggered by the management node at periodic time intervals, at predefined intervals as set by an administrator, or based on a request from the administrator.

23 . A non-transitory machine-readable storage medium encoded with instructions that, when executed by a processor,

Assignees

• Vmware Inc

Inventors

• Kandula Srinivas
• Thirumalachar Padmini Sampige
• Umapathi Gangadharaswamy Hindiskere
• CHOUDHARY Aditya

Classifications

• H04L43/065

  related to network devices · CPC title

• H04L41/046

  comprising network management agents or mobile agents therefor · CPC title

• H04L43/0817

  by checking functioning · CPC title

• H04L43/16

  Threshold monitoring · CPC title

• G06F11/3006

  where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50) · CPC title