Lazy mechanism for preventing unneeded data replication in a multi-tier storage environment
AssigneeInternational Business Machines Corporation
InventorsLior Aronovich, Samuel M. Black
Life of this patent
Estimating the term…
Abstract
Embodiments for managing data stored in a tiered data storage system, by a processor device. Upon submission of a workload to a queue of workloads of a workload manager, a set of storage demands included in metadata associated with the workload is received by an optimization policy generator. A current state of each one of a plurality of storage tiers within the storage system is combined with information comprising the set of storage demands to create data scheduling and placement policies such that the optimization policy generator controls which storage tier in the tiered data storage system incoming data is written to while a scheduling logic determines at what time to dispatch at least a portion of the workload.
Claims18
A method for managing data stored in a tiered data storage system, by a processor device, comprising:
- upon submission of a workload to a queue of workloads of a workload manager, receiving a set of storage demands included in metadata associated with the workload by an optimization policy generator;
- combining a current state of each one of a plurality of storage tiers within the tiered data storage system with information comprising the set of storage demands to create data scheduling and placement policies such that the optimization policy generator controls which storage tier in the tiered data storage system incoming data is written to while a scheduling logic determines at what time to dispatch at least a portion of the workload;
- identifying, by the optimization policy generator, a list of which workloads in the queue which may proceed and which workloads in the queue may not proceed, based upon the current state of each of the plurality of storage tiers and the set of storage demands associated with each of the respective workloads;
- and
- providing the list to the scheduling logic to dispatch each of the workloads in the queue in which the set of storage demands associated with the respective workload can be satisfied.
A system for managing data stored in a tiered data storage system, the system comprising:
- a processor device executing instructions stored in a memory, wherein the processor device:
- upon submission of a workload to a queue of workloads of a workload manager, receives a set of storage demands included in metadata associated with the workload by an optimization policy generator;
- combines a current state of each one of a plurality of storage tiers within the tiered data storage system with information comprising the set of storage demands to create data scheduling and placement policies such that the optimization policy generator controls which storage tier in the tiered data storage system incoming data is written to while a scheduling logic determines at what time to dispatch at least a portion of the workload;
- identifies, by the optimization policy generator, a list of which workloads in the queue which may proceed and which workloads in the queue may not proceed, based upon the current state of each of the plurality of storage tiers and the set of storage demands associated with each of the respective workloads;
- and
- provides the list to the scheduling logic to dispatch each of the workloads in the queue in which the set of storage demands associated with the respective workload can be satisfied.
A computer program product for managing data stored in a tiered data storage system, by a processor device, the computer program product embodied on a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
- an executable portion that, upon submission of a workload to a queue of workloads of a workload manager, receives a set of storage demands included in metadata associated with the workload by an optimization policy generator;
- an executable portion that combines a current state of each one of a plurality of storage tiers within the tiered data storage system with information comprising the set of storage demands to create data scheduling and placement policies such that the optimization policy generator controls which storage tier in the tiered data storage system incoming data is written to while a scheduling logic determines at what time to dispatch at least a portion of the workload;
- an executable portion that identifies, by the optimization policy generator, a list of which workloads in the queue which may proceed and which workloads in the queue may not proceed, based upon the current state of each of the plurality of storage tiers and the set of storage demands associated with each of the respective workloads;
- and
- an executable portion that provides the list to the scheduling logic to dispatch each of the workloads in the queue in which the set of storage demands associated with the respective workload can be satisfied.
Dependencies are inferred from the claim text.