METHOD AND APPARATUS FOR SCALABLE MONITORING OF VIRTUAL MACHINE ENVIRONMENTS

• US 20100318990A1
• Filed: 06/12/2009
• Published: 12/16/2010
• Est. Priority Date: 06/12/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hou, Kai-Yuan, Shaikh, Anees A., Ruan, Yaoping, Sahu, Sambit, Huang, Hai
• Granted Patent: US 8,650,562 B2
• Time in Patent Office: Days
• US Class Current: 718/1
• CPC Class Codes: G06F 11/301 where the computing system is a virtual computing platform, e.g. logically partitioned systems virtual machines G06F9/45533; logical partitioning of resources G06F9/5077
• CPC Class Codes: G06F 11/3096 wherein the means or processing minimize the use of computing system or of computing system component resources, e.g. non-intrusive monitoring which minimizes the probe effect: sniffing, intercepting, indirectly deriving the monitored data from other directly available data
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 2009/45591 Monitoring or debugging support
• CPC Class Codes: G06F 2201/815 Virtual
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

A method monitors machine activity of multiple virtual computing devices operating through at least one physical computing device by running a monitoring agent. The monitoring agent monitors performance of the multiple virtual computing devices. The method measures simple operating characteristics of only a base level virtual computing device. The method monitors complex operating characteristics using the monitoring agent by: measuring the complex operating characteristics for each of the multiple virtual computing devices (using each of the multiple virtual computing devices); recording the complex operating characteristics of each of the multiple virtual computing devices on a corresponding memory page of each of the multiple virtual computing devices; and sharing each the corresponding memory page with the base level virtual computing device through an interdomain communications channels to transfer the complex operating characteristics to the monitoring agent. The method identifies simple events and complex events for each of the multiple virtual computing devices by evaluating the simple operating characteristics and the complex operating characteristics and outputs the simple events and the complex events for each of the multiple virtual computing devices.

Claims

1. A computer-implemented method for monitoring machine activity of multiple virtual computing devices operating through at least one physical computing device, said method comprising:

running a monitoring agent on a physical computing device, said monitoring agent collecting data from said multiple virtual computing devices;

measuring simple operating characteristics of only abase level virtual computing device, said simple operating characteristics comprising operating characteristics that are similar for said base level virtual computing device and said multiple virtual computing devices;

monitoring complex operating characteristics using said monitoring agent by;

creating an interdomain communications channel between said base level virtual computing device and said multiple virtual computing devices to gather information from said multiple virtual computing devices;

measuring said complex operating characteristics for each of said multiple virtual computing devices using each of said multiple virtual computing devices, said complex operating characteristics comprising operating characteristics that are not similar for said base level virtual computing device and said multiple virtual computing devices;

recording, by each of said multiple virtual computing devices, said complex operating characteristics of each of said multiple virtual computing devices and

sharing, by each of said multiple virtual computing devices, said complex operating characteristics with said base level virtual computing device through said interdomain communications channels to transfer said complex operating characteristics to said monitoring agent;

identifying simple events and complex events for each of said multiple virtual computing devices by evaluating said simple operating characteristics and said complex operating characteristics using said monitoring agent; and

outputting said simple events and said complex events for each of said multiple virtual computing devices using said monitoring agent.

2. The method according to claim 1, said simple operating characteristics comprising hardware measures of said physical computing device.

3. The method according to claim 1, said simple operating characteristics comprising at least one of:

a processor model of said physical computing device;

a processor speed of said physical computing device;

processor busy and idle time of said physical computing device;

input/output traffic statistics of said physical computing device; and

file system information of said physical computing device.

4. The method according to claim 1, said complex operating characteristics comprising memory utilization information of each of said multiple virtual computing devices.

5. The method according to claim 1, said monitoring agent being positioned only on said base level virtual computing device, wherein no monitoring agents are positioned on said multiple virtual computing devices,

6. A computer-implemented method for monitoring machine activity of multiple virtual computing devices operating through at least one physical computing device, said method comprising:

running a monitoring agent on a base level virtual computing device through a hypervisor of said physical computing device, said monitoring agent collecting data from said multiple virtual computing devices, said hypervisor comprising a layer of software running between hardware of said physical computing device and an operating system of each virtual computing device, said hypervisor providing an illusion of said multiple virtual computing devices from said physical computing device;

measuring simple operating characteristics of only said base level virtual computing device, said simple operating characteristics comprising operating characteristics that are similar for said base level virtual computing device and said multiple virtual computing devices;

monitoring complex operating characteristics using said monitoring agent by;

creating an interdomain communications channel between said base level virtual computing device and said multiple virtual computing devices to gather information from said multiple virtual computing devices;

allocating a memory page within each of said multiple virtual computing devices that is shared with said base level virtual computing device through said interdomain communications channel;

measuring said complex operating characteristics for each of said multiple virtual computing devices using each of said multiple virtual computing devices, said complex operating characteristics comprising operating characteristics that are not similar for said base level virtual computing device and said multiple virtual computing devices;

recording, by each of said multiple virtual computing devices, said complex operating characteristics of each of said multiple virtual computing devices on a corresponding memory page of each of said multiple virtual computing devices; and

sharing each said corresponding memory page with said base level virtual computing device through said interdomain communications channels to transfer said complex operating characteristics to said monitoring agent;

identifying simple events and complex events for each of said multiple virtual computing devices by evaluating said simple operating characteristics and said complex operating characteristics using said monitoring agent; and

outputting said simple events and said complex events for each of said multiple virtual computing devices using said monitoring agent,

7. The method according to claim 6, said simple operating characteristics comprising hardware measures of said physical computing device.

8. The method according to claim 6, said simple operating characteristics comprising at least one of:

a processor model of said physical computing device;

a processor speed of said physical computing device;

processor busy and idle time of said physical computing device;

input/output traffic statistics of said physical computing device; and

file system information of said physical computing device.

9. The method according to claim 6, said complex operating characteristics comprising memory utilization information of each of said multiple virtual computing devices.

10. The method according to claim 6, said monitoring agent being positioned only on said base level virtual computing device, wherein no monitoring agents are positioned on said multiple virtual computing devices.

11. A device for monitoring machine activity of multiple virtual computing devices, said device comprising:

at least one physical computing device, said physical computing device comprising at least one processor, at least one storage medium, and at least one input/output interface;

a monitoring agent operating through said physical computing device, said monitoring agent collecting data from said multiple virtual computing devices, said monitoring agent measuring simple operating characteristics of only a base level virtual computing device, said simple operating characteristics comprising operating characteristics that are similar for said base level virtual computing device and said multiple virtual computing devices; and

an interdomain communications channel between said base level virtual computing device and said multiple virtual computing devices used to gather information from said multiple virtual computing devices and allow said monitoring agent to monitor complex operating characteristics;

each of said multiple virtual computing devices measuring said complex operating characteristics for each of said multiple virtual computing devices, said complex operating characteristics comprising operating characteristics that are not similar for said base level virtual computing device and said multiple virtual computing devices,

each of said multiple virtual computing devices recording said complex operating characteristics of each of said multiple virtual computing devices,

each of said multiple virtual computing devices sharing said complex operating characteristics with said base level virtual computing device through said interdomain communications channels to transfer said complex operating characteristics to said monitoring agent;

said monitoring agent identifying simple events and complex events for each of said multiple virtual computing devices by evaluating said simple operating characteristics and said complex operating characteristics, and

said input/output interface outputting said simple events and said complex events for each of said multiple virtual computing devices.

12. The device according to claim 11, said simple operating characteristics comprising hardware measures of said physical computing device.

13. The device according to claim 11, said simple operating characteristics comprising at least one of:

a processor model of said physical computing device;

a processor speed of said physical computing device;

processor busy and idle time of said physical computing device;

input/output traffic statistics of said physical computing device; and

file system information of said physical computing device.

14. The device according to claim 11, said complex operating characteristics comprising memory utilization information of each of said multiple virtual computing devices.

15. The device according to claim 11, said monitoring agent being positioned only on said base level virtual computing device, wherein no monitoring agents are positioned on said multiple virtual computing devices.

16. A device for monitoring machine activity of multiple virtual computing devices, said device comprising:

at least one physical computing device, said physical computing device comprising at least one processor, at least one storage medium, and at least one input/output interface;

a hypervisor comprising a layer of software running between hardware of said physical computing device and an operating system of each virtual computing device, said hypervisor providing an illusion of said multiple virtual computing devices from said physical computing device

a monitoring agent operating on a base level virtual computing device through said hypervisor of said physical computing device, said monitoring agent collecting data from said multiple virtual computing devices, said monitoring agent measuring simple operating characteristics of only said base level virtual computing device, said simple operating characteristics comprising operating characteristics that are similar for said base level virtual computing device and said multiple virtual computing devices,

an interdomain communications channel between said base level virtual computing device and said multiple virtual computing devices used to gather information from said multiple virtual computing devices and allow said monitoring agent to monitor complex operating characteristics; and

a memory page within each of said multiple virtual computing devices that is shared with said base level virtual computing device through said interdomain communications channel,

each of said multiple virtual computing devices measuring said complex operating characteristics for each of said multiple virtual computing devices, said complex operating characteristics comprising operating characteristics that are not similar for said base level virtual computing device and said multiple virtual computing devices,

each of said multiple virtual computing devices recording said complex operating characteristics of each of said multiple virtual computing devices on a corresponding memory page of each of said multiple virtual computing devices,

each of said multiple virtual computing devices sharing each said corresponding memory page with said base level virtual computing device through said interdomain communications channels to transfer said complex operating characteristics to said monitoring agent;

said monitoring agent identifying simple events and complex events for each of said multiple virtual computing devices by evaluating said simple operating characteristics and said complex operating characteristics, and

said input/output interface outputting said simple events and said complex events for each of said multiple virtual computing devices,

17. The device according to claim 16, said simple operating characteristics comprising hardware measures of said physical computing device.

18. The device according to claim 16, said simple operating characteristics comprising at least one of:

a processor model of said physical computing device;

a processor speed of said physical computing device;

processor busy and idle time of said physical computing device;

input/output traffic statistics of said physical computing device; and

file system information of said physical computing device.

19. The device according to claim 16, said complex operating characteristics comprising memory utilization information of each of said multiple virtual computing devices.

20. The device according to claim 16, said monitoring agent being positioned only on said base level virtual computing device, wherein no monitoring agents are positioned on said multiple virtual computing devices.

21. A computer storage medium tangibly storing instructions executable by a computer for performing a computer-implemented method for monitoring machine activity of multiple virtual computing devices operating through at least one physical computing device, said method comprising:

running a monitoring agent on a base level virtual computing device operating through said physical computing device, said monitoring agent collecting data from said multiple virtual computing devices;

measuring simple operating characteristics of only said base level virtual computing device, said simple operating characteristics comprising operating characteristics that are similar for said base level virtual computing device and said multiple virtual computing devices;

monitoring complex operating characteristics using said monitoring agent by;

creating an interdomain communications channel between said base level virtual computing device and said multiple virtual computing devices to gather information from said multiple virtual computing devices;

allocating a memory page within each of said multiple virtual computing devices that is shared with said base level virtual computing device through said interdomain communications channel;

measuring said complex operating characteristics for each of said multiple virtual computing devices using each of said multiple virtual computing devices, said complex operating characteristics comprising operating characteristics that are not similar for said base level virtual computing device and said multiple virtual computing devices;

recording, by each of said multiple virtual computing devices, said complex operating characteristics of each of said multiple virtual computing devices on a corresponding memory page of each of said multiple virtual computing devices; and

sharing each said corresponding memory page with said base level virtual computing device through said interdomain communications channels to transfer said complex operating characteristics to said monitoring agent;

identifying simple events and complex events for each of said multiple virtual computing devices by evaluating said simple operating characteristics and said complex operating characteristics using said monitoring agent; and

outputting said simple events and said complex events for each of said multiple virtual computing devices using said monitoring agent.

22. The computer storage medium according to claim 21, said simple operating characteristics comprising hardware measures of said physical computing device.

23. The computer storage medium according to claim 21, said simple operating characteristics comprising at least one of:

a processor model of said physical computing device;

a processor speed of said physical computing device;

processor busy and idle time of said physical computing device;

input/output traffic statistics of said physical computing device; and

file system information of said physical computing device.

24. The computer storage medium according to claim 21, said complex operating characteristics comprising memory utilization information of each of said multiple virtual computing devices.

25. The computer storage medium according to claim 21, said monitoring agent being positioned only on said base level virtual computing device, wherein no monitoring agents are positioned on said multiple virtual computing devices.