Statistical profiling of cluster tasks

• US 8,621,070 B1
• Filed: 12/17/2010
• Issued: 12/31/2013
• Est. Priority Date: 12/17/2010
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Kownacki, Ronald William, Venneti, Satya, Katepalli, Sundeep, DeGraaf, John
• Primary Examiner(s): Ashraf, Waseem
• Application Number:
  US12/971,870
• Time in Patent Office: 1,110 Days
• Field of Search: 709/224
• US Class Current: 709/224
• CPC Class Codes: G06F 11/3003 Monitoring arrangements specially adapted to the computing system or computing system component being monitored
• CPC Class Codes: G06F 11/3082 the data filtering being achieved by aggregating or compressing the monitored data
• CPC Class Codes: G06F 11/3089 Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents software debugging using additional hardware using a specific debug interface G06F11/3656; performance evaluation by tracing or monitoring G06F11/3466
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3452 Performance evaluation by statistical analysis
• CPC Class Codes: G06F 11/3476 Data logging G06F11/14, G06F11/2205 take precedence
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06F 2201/865 Monitoring of software
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks

Abstract

A variety of complex multiphase tasks may execute within a cluster network environment. It may be advantageous to track and analyze the processing of such multiphase tasks. Accordingly, one or more techniques and/or systems are disclosed for tracking the processing of a multiphase task within a cluster network environment. In particular, runtime support for recording task processing annotations may be embedded into a multiphase task using an analysis model. The analysis model may specify task processing annotations that are to be recorded during one or more phases of processing the multiphase task. During execution, task processing annotations may be recorded and associated with corresponding phases of the multiphase task. Task processing annotations may be aggregated into aggregated statistical task data. The aggregated statistical task data may be used to generate views of statistical data, which may provide insight into the cluster network environment (e.g., problematic nodes, bottlenecks, etc.).

Claims

1. A method for incorporating an analysis model into a multiphase task, comprising:

incorporating an analysis model into a multiphase task to be processed within a clustered network environment, the analysis model specifying task processing annotations to be recorded during one or more phases of processing the multiphase task; and

during the processing of the multiphase task across one or more nodes within the clustered network environment;

recording the task processing annotations specified by the analysis model, the recording comprising;

recording the task processing annotations as subvectors within one or more remote procedures calls to the one or more nodes within the clustered network environment; and

building a statistics vector from the subvectors, the statistics vector representing the task processing annotations recorded during the processing of the multiphase task; and

associating the task processing annotations with corresponding phases of the multiphase task.

2. The method of claim 1, the multiphase task comprising a first phase and a second phase, the first phase comprising a first identifier of a first task, the second phase comprising a second identifier of a second task.

3. The method of claim 1, comprising:

recording first task processing annotations during a first phase associated with a first node within the clustered network environment and recording second task processing annotations during a second phase associated with a second node within the clustered network environment.

4. The method of claim 1, the recording the task processing annotations specified by the analysis model and the associating performed within a process thread owned by the multiphase task.

5. The method of claim 1, comprising:

uploading the task processing annotations to a node within the clustered network environment.

6. The method of claim 1, comprising:

aggregating the task processing annotations with previously recorded task processing annotations to generate aggregated statistical task data.

7. The method of claim 6, the aggregating comprising:

averaging the task processing annotations with the previously recorded task processing annotations.

8. The method of claim 6, comprising:

receiving a request to generate a view of statistical data, the request comprising user defined statistical criteria; and

generating the view of statistical data based upon at least a portion of the aggregated statistical task data corresponding to the user defined statistical criteria.

9. The method of claim 8, the view of statistical data corresponding to a phase of the multiphase task during one or more executions of the multiphase task.

10. The method of claim 6, comprising:

storing the aggregated statistical task data as one or more entries within a data store.

11. The method of claim 1, comprising:

presenting a view of statistical data based upon the statistics vector.

12. The method of claim 1, a phase of the one or more phases comprising an identifier and one or more associated task processing annotations to be recorded.

13. The method of claim 1, the multiphase task comprising at least one of:

a data replication task;

a quorum maintenance task;

a health task;

a configuration task;

an administrative job monitoring task;

a volume data movement task;

or

a backup task.

14. The method of claim 1, the task processing annotations comprising at least one of:

start time of a phase;

end time of the phase;

processing time of the phase;

health information of a node;

a user defined label;

a user defined measurement criteria;

a type designation;

a volume size designation;

or

a source node designation.

15. A system for incorporating an analysis model into a multiphase task, comprising:

one or more processors;

and a memory comprising an injection component and a recording component that when executed by at least one of the one or more processors executes;

the injection component to;

incorporate an analysis model into a multiphase task to be processed within a clustered network environment, the analysis model specifying task processing annotations to be recorded during one or more phases of processing the multiphase task; and

the recording component to;

during the processing of the multiphase task across one or more nodes within the clustered network environment;

record the task processing annotations specified by the analysis model, comprising;

recording the task processing annotations as subvectors within one or more remote procedures calls to the one or more nodes within the clustered network environment; and

building a statistics vector from the subvectors, the statistics vector representing the task processing annotations recorded during the processing of the multiphase task; and

associate the task processing annotations with corresponding phases of the multiphase task.

16. The system of claim 15, the multiphase task comprising a first phase and a second phase, the first phase comprising a first identifier of a first task, the second phase comprising a second identifier of a second task.

17. The system of claim 15, the recording component configured to:

record the task processing annotations within a thread owed by the multiphase task.

18. The system of claim 15, wherein the memory further comprises an analysis component that when executed by the at least one of the one or more processors executes:

the analysis component to;

receive the task processing annotations from the recording component; and

aggregate the task processing annotations with previously recorded task processing annotations to generate aggregated statistical task data.

19. The system of claim 18, the analysis component configured to:

receive a request to generate a view of statistical data, the request comprising user defined statistical criteria; and

generate the view of statistical data based upon at least a portion of the aggregated statistical task data corresponding to the user defined statistical criteria.

20. A non-transitory computer readable storage medium comprising computer executable instructions that when executed via a microprocessor perform a method for tracking the processing of a multiphase task within a clustered network environment, comprising:

incorporating an analysis model into a multiphase task to be processed within a clustered network environment, the analysis model specifying task processing annotations to be recorded during one or more phases of processing the multiphase task; and

during the processing of the multiphase task across one or more nodes within the clustered network environment;

recording the task processing annotations specified by the analysis model, the recording comprising;

recording the task processing annotations as subvectors within one or more remote procedures calls to the one or more nodes within the clustered network environment; and

building a statistics vector from the subvectors, the statistics vector representing the task processing annotations recorded during the processing of the multiphase task; and

associating the task processing annotations with corresponding phases of the multiphase task.

21. The method of claim 20, comprising:

presenting performance data of the clustered network environment based upon the statistics vector.