Storage infrastructure scenario planning

• US 10,361,925 B1
• Filed: 06/23/2016
• Issued: 07/23/2019
• Est. Priority Date: 06/23/2016
• Status: Active Grant

• Current Assignee: Nutanix Incorporated
• Original Assignee: Nutanix Incorporated
• Inventors: Shukla, Himanshu, Beedu, Bharat Kumar, Nagpal, Abhinay
• Primary Examiner(s): Sall, El Hadji M
• Application Number:
  US15/191,387
• Time in Patent Office: 1,125 Days
• Field of Search: 709224, 709200
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 41/40 using virtualisation of network functions or resources, e.g. SDN or NFV entities
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 43/20 the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

Systems and methods for “what-if” scenario planning of a distributed data storage system. A scenario planning engine has a user interface to facilitate user interactions to describe “what if” scenarios. A method comprises steps to collect system performance measurements pertaining to measurable characteristics of the distributed storage system. A predictive model is generated and formatted for use as a predictor of one or more predictive model parameters that are derived from the collected system performance measurements and/or any calculated predictions and/or correlations. A user can vary a set of scenario input parameters so as to characterize one or more “what if” scenarios. The user-defined scenario input parameters are formatted and used as predictive model inputs. The predictive model is used to simulate predicted system performance parameters corresponding to respective “what-if” planning scenarios. A user interface is provided to present a graphical depiction of predicted system performance corresponding to the scenarios.

Claims

1. A method comprising:

identifying a cluster in a distributed storage system, the cluster comprising one or more nodes, the distributed storage system comprising a storage pool having a first local storage on a first node of the one or more nodes and a second local storage on a second node of the one or more nodes, wherein the first node utilizes a first virtualized controller to manage storage and I/O activities on a plurality of storage devices in the storage pool and the second node utilizes a second virtualized controller to manage storage and I/O activities on the plurality of storage devices in the storage pool; and

implementing, on any node with a virtualized controller in the cluster of nodes, a scenario planning engine to manage the distributed storage system, the scenario planning engine having a user interface to facilitate interactions with the scenario planning engine by at least one user, and the scenario planning engine to perform operations comprising,

collecting one or more system performance measurements that are stored in any local storage in the storage pool, the system performance measurements characterizing respective occurrences of measured system performance metrics of the distributed storage system, wherein the storage pool is accessible by any virtualized controller on a node of the one or more nodes;

generating a predictive model comprising one or more predictive model parameters derived from the system performance measurements by accessing the system performance measurements stored in the storage pool;

receiving one or more scenario input parameters, at least some of the scenario input parameters that quantify aspects of one or more planning scenarios;

generating one or more predicted system performance parameters by applying the scenario input parameters to the predictive model parameters; and

presenting the one or more predicted system performance at the user interface to facilitate selecting one or more selected system management parameters.

2. The method of claim 1, wherein the one or more system performance measurements are derived from storage I/O commands issued by a user virtual machine and wherein the storage I/O commands are processed by a virtualized controller that accesses a storage pool.

3. The method of claim 1, further comprising determining one or more recommended plan parameters based at least in part on the predicted system performance parameters.

4. The method of claim 3, further comprising adjusting at least one of the scenario input parameters based on the recommended plan parameters.

5. The method of claim 3, wherein the determining the recommended plan parameters is based at least in part on one or more planning rules.

6. The method of claim 1, wherein the one or more predicted system performance parameters being used to simulate the one or more planning scenarios that identify a remediation plan if it is determined that the predicted system performance parameters exceeds a constraint, wherein the remediation plan generates one or more updated predicted system performance parameters by adjusting at least one of the scenario input parameters before applying the at least one adjusted scenario input parameter to the predictive model parameters.

7. The method of claim 1, wherein the scenario input parameters correspond to at least one of, a constraint, or an objective.

8. The method of claim 1, wherein the scenario input parameters are based at least in part on a target runway time period, or a recovery period objective time limit, or a maximum data loss limit, or a maximum storage utilization metric, or a maximum CPU utilization limit, or a minimum CPU headroom limit, or any combination thereof.

9. The method of claim 1, wherein at least one of, the measured system performance, or the predicted system performance, is characterized by a set of time series data.

10. The method of claim 1, wherein the selected system management parameters influence a behavior of the distributed storage system.

11. A computer readable medium, embodied in a non-transitory computer readable medium, the non-transitory computer readable medium having stored thereon a sequence of instructions which, when stored in memory and executed by a processor causes the processor to perform a set of acts, the acts comprising:

identifying a cluster in a distributed storage system, the cluster comprising one or more nodes, the distributed storage system comprising a storage pool having a first local storage on a first node of the one or more nodes and a second local storage on a second node of the one or more nodes, wherein the first node utilizes a first virtualized controller to manage storage and I/O activities on a plurality of storage devices in the storage pool and the second node utilizes a second virtualized controller to manage storage and I/O activities on the plurality of storage devices in the storage pool; and

implementing, on any node with a virtualized controller in the cluster of nodes, a scenario planning engine to manage the distributed storage system, the scenario planning engine having a user interface to facilitate interactions with the scenario planning engine by at least one user, and the scenario planning engine to perform operations comprising,

collecting one or more system performance measurements that are stored in any local storage in the storage pool, the system performance measurements characterizing respective occurrences of measured system performance metrics of the distributed storage system, wherein the storage pool is accessible by any virtualized controller on a node of the one or more nodes;

generating a predictive model comprising one or more predictive model parameters derived from the system performance measurements by accessing the system performance measurements stored in the storage pool;

receiving one or more scenario input parameters, at least some of the scenario input parameters that quantify aspects of one or more planning scenarios;

generating one or more predicted system performance parameters by applying the scenario input parameters to the predictive model parameters; and

presenting the one or more predicted system performance at the user interface to facilitate selecting one or more selected system management parameters.

12. The computer readable medium of claim 11, further comprising instructions which, when stored in memory and executed by the processor causes the processor to perform acts of determining one or more recommended plan parameters based at least in part on the predicted system performance parameters.

13. The computer readable medium of claim 12, further comprising instructions which, when stored in memory and executed by the processor causes the processor to perform acts of adjusting at least one of the scenario input parameters based on the recommended plan parameters.

14. The computer readable medium of claim 12, wherein the determining the recommended plan parameters is based at least in part on one or more planning rules.

15. The computer readable medium of claim 14, wherein the planning rules comprise at least one remediation rule.

16. The computer readable medium of claim 11, wherein at least one of, the scenario input parameters, or the selected system management parameters, are selected by the user at the user interface of the scenario planning engine.

17. The computer readable medium of claim 11, wherein the scenario input parameters correspond to at least one of, a constraint, or an objective.

18. The computer readable medium of claim 11, wherein the scenario input parameters are based at least in part on a target runway time period, or a recovery period objective time limit, or a maximum data loss limit, or a maximum storage utilization metric, or a maximum CPU utilization limit, or a minimum CPU headroom limit, or any combination thereof.

19. A system comprising:

a storage medium having stored thereon a sequence of instructions; and

a processor or processors that execute the instructions to cause the processor or processors to perform a set of acts,

identifying a cluster in a distributed storage system, the cluster comprising one or more nodes, the distributed storage system comprising a storage pool having a first local storage on a first node of the one or more nodes and a second local storage on a second node of the one or more nodes, wherein the first node utilizes a first virtualized controller to manage storage and I/O activities on a plurality of storage devices in the storage pool and the second node utilizes a second virtualized controller to manage storage and I/O activities on the plurality of storage devices in the storage pool; and

implementing, on any node with a virtualized controller in the cluster of nodes, a scenario planning engine to manage the distributed storage system, the scenario planning engine having a user interface to facilitate interactions with the scenario planning engine by at least one user, and the scenario planning engine to perform operations comprising,

collecting one or more system performance measurements that are stored in any local storage in the storage pool, the system performance measurements characterizing respective occurrences of measured system performance metrics of the distributed storage system, wherein the storage pool is accessible by any virtualized controller on a node of the one or more nodes;

generating a predictive model comprising one or more predictive model parameters derived from the system performance measurements by accessing the system performance measurements stored in the storage pool;

receiving one or more scenario input parameters, at least some of the scenario input parameters that quantify aspects of one or more planning scenarios;

generating one or more predicted system performance parameters by applying the scenario input parameters to the predictive model parameters; and

presenting the one or more predicted system performance at the user interface to facilitate selecting one or more selected system management parameters.

20. The system of claim 19, wherein the scenario input parameters correspond to at least one of, a constraint, or an objective.

21. A method comprising:

receiving an input parameter at a user interface of a scenario planning engine, the scenario planning engine configured to manage a distributed storage system, the distributed storage system comprising a storage pool having a local storage on a node, wherein the node utilizes a virtualized controller to manage storage and I/O activities in the storage pool, wherein the virtualized controller comprises the scenario planning engine; and

applying, via the virtualized controller comprising the scenario planning engine, the input parameter to generate a predictive performance parameter characterizing a simulated scenario for the distributed storage system; and

presenting the predictive performance parameter at the user interface to facilitate selection of the simulated scenario, wherein the distributed storage system is configured based at least in part on the predictive performance parameter that corresponds to the simulated scenario selected.

22. The method of claim 21, further comprising determining a recommended plan parameter based at least in part on the predicted performance parameter.

23. The method of claim 22, further comprising adjusting the scenario input parameter based on the recommended plan parameter.

24. The method of claim 22, wherein the determining the recommended plan parameter is based at least in part on a planning rule.

25. A computer readable medium, embodied in a non-transitory computer readable medium, the non-transitory computer readable medium having stored thereon a sequence of instructions which, when stored in memory and executed by a processor causes the processor to perform a set of acts, the acts comprising:

receiving an input parameter at a user interface of a scenario planning engine, the scenario planning engine configured to manage a distributed storage system, the distributed storage system comprising a storage pool having a local storage on a node, wherein the node utilizes a virtualized controller to manage storage and I/O activities in the storage pool, wherein the virtualized controller comprises the scenario planning engine; and

applying, via the virtualized controller comprising the scenario planning engine, the input parameter to generate a predictive performance parameter characterizing a simulated scenario for the distributed storage system; and

presenting the predictive performance parameter at the user interface to facilitate selection of the simulated scenario, wherein the distributed storage system is configured based at least in part on the predictive performance parameter that corresponds to the simulated scenario selected.

26. The computer readable medium of claim 25, further comprising instructions which, when stored in memory and executed by the processor causes the processor to perform acts of determining a recommended plan parameter based at least in part on the predicted performance parameter.

27. The computer readable medium of claim 26, further comprising instructions which, when stored in memory and executed by the processor causes the processor to perform acts of adjusting the scenario input parameter based on the recommended plan parameter.

28. The computer readable medium of claim 26, wherein the determining the recommended plan parameter is based at least in part on a planning rule.