Predictive storage management system
A predictive storage management system includes a storage system having storage devices, and a predictive storage management device coupled to the storage system via a network. The predictive storage management device includes a statistical time-series storage device usage sub-engine that retrieves first storage device usage data from a first storage device in the storage system and uses it to generate a first storage device usage trend model. A machine-learning storage system usage sub-engine in the predictive storage management device retrieves storage system implementation information from the storage system and uses it to generate a storage system implementation model. A storage management sub-engine in the predictive storage management device analyzes the first storage device usage trend model and the storage system implementation model to predict future usage of the first storage device and, based on that predicted future usage, performs a management action associated with the first storage device.
1. A predictive storage management system, comprising:
a first storage system including a plurality of storage devices; and
a predictive storage management device that is coupled to the first storage system via a network, wherein the predictive storage management device includes:
a statistical time-series storage device usage sub-engine that is configured to:
retrieve first storage device usage data from a first storage device that is included in the plurality of storage devices in the first storage system and that is a first type of storage device; and
generate, using the first storage device usage data, a first storage device usage trend model;
a machine-learning storage system usage sub-engine that is configured to:
retrieve first storage system implementation information from the first storage system; and
generate, using 1) the first storage system implementation information, 2) second storage system implementation information from at least one second storages system that is implemented the same as the first storage system and that includes a second storage device that is the first type of storage device, and 3) an unsupervised machine learning model, a storage system implementation model that identifies storage system characteristics that influence at least one of a use or a behavior of a storage device that is the first type of storage device and that is included in a storage system that is implemented the same as the first storage system and the second storage system; and
a storage management sub-engine that is configured to:
extrapolate the first storage device usage data in the first storage device usage trend model with non-linear time-series trends included in the storage system implementation model to determine a predicted future usage of the first storage device; and
perform, based on the predicted future usage of the first storage device, a management action associated with the first storage device.
2. The system of claim 1 , further comprising:
a Hyper-Converged Infrastructure (HCI) system that includes the first storage system and that is configured to utilize the first storage system to provide a virtualized Storage Area Network (vSAN).
3. The system of claim 1 , wherein the first storage system implementation information identifies a configuration of the plurality of storage devices in the first storage system.
4. The system of claim 1 , wherein the first storage system implementation information identifies a cache storage device capacity for the first storage system.
5. The system of claim 1 , wherein the first storage system implementation information identifies a number of server devices used to provide the first storage system.
6. The system of claim 1 , wherein the first storage system implementation information identifies a number of virtual machines utilizing the first storage system.
7. An Information Handling System (IHS), comprising:
a processing system; and
a memory system that is coupled to the processing system and that includes instructions that, when executed by the processing system, cause the processing system to provide a predictive storage management engine that is configured to:
retrieve first storage device usage data from a first storage device that is included in a first storage system and that is a first type of storage device;
generate, using the first storage device usage data, a first storage device usage trend model;
retrieve first storage system implementation information from the first storage system;
generate, using 1) the first storage system implementation information, 2 second storage system implementation information from at least one second storage system that is implemented the same as the first storage system and that includes a second storage device that is the first type of storage device, and 3) an unsupervised machine learning model, a storage system implementation model that identifies storage system characteristics that influence at least one of a use or a behavior of a storage device that is the first type of storage device and that is included in a storage system that is implemented the same as the first storage system and the second storage system;
extrapolate the first storage device usage data in the first storage device usage trend model with non-linear time-series trends included in the storage system implementation model to determine a predicted future usage of the first storage device; and
perform, based on the predicted future usage of the first storage device, a management action associated with the first storage device.
8. The IHS of claim 7 , wherein the first storage system is included in a Hyper-Converged Infrastructure (HCI) system and provide as a virtualized Storage Area Network (vSAN) by the HCI system.
9. The IHS of claim 7 , wherein the first storage system implementation information identifies a configuration of the plurality of storage devices in the first storage system.
10. The IHS of claim 7 , wherein the first storage system implementation information identifies a cache storage device capacity for the first storage system.
11. The IHS of claim 7 , wherein the first storage system implementation information identifies a number of server devices used to provide the first storage system.
12. The IHS of claim 7 , wherein the first storage system implementation information identifies a number of virtual machines utilizing the first storage system.
13. The IHS of claim 7 , wherein the management action associated with the first storage device includes at least one of:
a data purging operation that is performed on the first storage device and that purges data from the first storage device;
a data defragmentation operation that is performed on the first storage device and that defragments data on the first storage device; and
a storage reconfiguration operation that is performed on the first storage device and that reconfigures the first storage device.
14. A method for predictively managing storage devices, comprising:
retrieving, by a predictive storage management device from a first storage device that is included in a first storage system and that is a first type of storage device, first storage device usage data;
generating, by the predictive storage management device using the first storage device usage data, a first storage device usage trend model;
retrieving, by the predictive storage management device from the first storage system, first storage system implementation information;
generating, by the predictive storage management device using 1) the first storage system implementation information, 2) second storage system implementation information from at least one second storage system that is implemented the same as the first storage system and that includes a second storage device that is the first type of storage device, and 3) an unsupervised machine learning model, a storage system implementation model that identifies storage system characteristics that influence at least one of a use or a behavior of a storage device that is the first type of storage device and that is included in a storage system that is implemented the same as the first storage system and the second storage system;
extrapolating, by the predictive storage management device, the first storage device usage data in the first storage device usage trend model with non-linear time-series trends included in the storage system implementation model to predict future usage of the first storage device; and
performing, by the predictive storage management device based on the predicted future usage of the first storage device, a management action associated with the first storage device.
15. The method of claim 14 , wherein the first storage system is included in a Hyper-Converged Infrastructure (HCI) system and the method further comprises:
providing, by the HCI system, the first storage system as a virtualized Storage Area Network (vSAN).
16. The method of claim 14 , wherein the first storage system implementation information identifies a configuration of the plurality of storage devices in the first storage system.
17. The method of claim 14 , wherein the first storage system implementation information identifies a cache storage device capacity for the first storage system.
18. The method of claim 14 , wherein the first storage system implementation information identifies a number of server devices used to provide the first storage system.
19. The method of claim 14 , wherein the first storage system implementation information identifies a number of virtual machines utilizing the first storage system.
20. The method of claim 14 , wherein the management action associated with the first storage device includes at least one of:
a data purging operation that is performed on the first storage device and that purges data from the first storage device;
a data defragmentation operation that is performed on the first storage device and that defragments data on the first storage device; and
a storage reconfiguration operation that is performed on the first storage device and that reconfigures the first storage device.