Methods and systems for managing a resource in a networked storage environment
Methods and systems for a networked storage system are provided. One method includes receiving a resource identifier identifying a resource of a network storage environment as an input to a processor executable application programming interface (API); and predicting available performance capacity of the resource by using an optimum utilization of the resource, a current utilization and a predicted utilization based on impact of a workload change at the resource, where the optimum utilization is an indicator of resource utilization beyond which throughput gains for a workload is smaller than increase in latency in processing the workload.
1. A method, comprising:
utilizing select queuing models for evaluating resources of a network storage environment by:
selecting a first queuing model for evaluating N node resources based upon the network storage environment including the N node resources to model;
selecting a second queuing model for evaluating homogeneous aggregates based upon I/O requests targeting the homogeneous aggregates being uniformly served by storage devices of the network storage environment; and
selecting the second queuing model under a shortest job first scheduling policy for evaluating a hybrid aggregate based upon I/O requests targeting the hybrid aggregate being served at varying rates;
determining latencies for the resources utilizing the selected queuing models;
computing an optimal point and confidence factor for the optimal point based upon the latencies; and
provisioning a resource based upon the optimal point and confidence factor.
2. The method of claim 1 , further comprising:
utilizing the second queuing model based upon varying service times for I/O requests targeting the hybrid aggregate.
3. The method of claim 1 , further comprising:
utilizing the first queuing model based upon a determination that I/O requests arrive according to a stochastic process by a single node according to a first come first service methodology.
4. The method of claim 1 , further comprising:
utilizing the second queuing model for the hybrid aggregate based upon a determination that service times for I/O requests are variable where some I/O requests are served at a faster rate than other I/O requests.
5. The method of claim 1 , further comprising:
determining latencies using inter-arrival times and service times.
6. The method of claim 1 , further comprising:
managing traffic at a storage module according to priority levels assigned to high priority traffic, lower priority traffic, and consistency point operations.
7. The method of claim 1 , wherein the optimal point is an indicator of resource utilization beyond which throughput gains for a workload is smaller than an increase in latency.
8. A non-transitory machine readable medium comprising instructions for performing a method, which when executed by a machine, causes the machine to:
utilize select queuing models for evaluating resources of a network storage environment by:
selecting a first queuing model for evaluating N node resources based upon the network storage environment including the N node resources to model;
selecting a second queuing model for evaluating homogeneous aggregates based upon I/O requests targeting the homogeneous aggregates being uniformly served by storage devices of the network storage environment; and
selecting the second queuing model under a shortest job first scheduling policy for evaluating a hybrid aggregate based upon I/O requests targeting the hybrid aggregate being served at varying rates;
determine latencies for the resources utilizing the selected queuing models;
compute an optimal point and confidence factor for the optimal point based upon the latencies; and
provision a resource based upon the optimal point and confidence factor.
9. The non-transitory machine readable medium of claim 8 , wherein the instructions cause the machine to:
utilize the second queuing model based upon varying service times for I/O requests targeting the hybrid aggregate.
10. The non-transitory machine readable medium of claim 8 , wherein the instructions cause the machine to:
utilize the first queuing model based upon a determination that I/O requests arrive according to a stochastic process by a single node according to a first come first service methodology.
11. The non-transitory machine readable medium of claim 8 , wherein the instructions cause the machine to:
utilize the second queuing model for the hybrid aggregate based upon a determination that service times for I/O requests are variable where some I/O requests are served at a faster rate than other I/O requests.
12. The non-transitory machine readable medium of claim 8 , wherein the instructions cause the machine to:
determine latencies using inter-arrival times and service times.
13. The non-transitory machine readable medium of claim 8 , wherein the instructions cause the machine to:
manage traffic at a storage module according to priority levels assigned to high priority traffic, lower priority traffic, and consistency point operations.
14. The non-transitory machine readable medium of claim 8 , wherein the optimal point is an indicator of resource utilization beyond which throughput gains for a workload is smaller than an increase in latency.
15. A computing device comprising:
a memory comprising machine executable code; and
a processor coupled to the memory, the processor configured to execute the machine executable code to cause the computing device to:
utilize select queuing models for evaluating resources of a network storage environment by:
selecting a first queuing model for evaluating N node resources based upon the network storage environment including the N node resources to model;
selecting a second queuing model for evaluating homogeneous aggregates based upon I/O requests targeting the homogeneous aggregates being uniformly served by storage devices of the network storage environment; and
selecting the second queuing model under a shortest job first scheduling policy for evaluating a hybrid aggregate based upon I/O requests targeting the hybrid aggregate being served at varying rates;
determine latencies for the resources utilizing the selected queuing models;
compute an optimal point and confidence factor for the optimal point based upon the latencies; and
provision a resource based upon the optimal point and confidence factor.
16. The computing device of claim 15 , wherein the machine executable code causes the machine to:
utilize the second queuing model based upon varying service times for I/O requests targeting the hybrid aggregate.
17. The computing device of claim 15 , wherein the machine executable code causes the machine to:
utilize the first queuing model based upon a determination that I/O requests arrive according to a stochastic process by a single node according to a first come first service methodology.
18. The computing device of claim 15 , wherein the machine executable code causes the machine to:
utilize the second queuing model for the hybrid aggregate based upon a determination that service times for I/O requests are variable where some I/O requests are served at a faster rate than other I/O requests.
19. The computing device of claim 15 , wherein the machine executable code causes the machine to:
determine latencies using inter-arrival times and service times.
20. The computing device of claim 15 , wherein the machine executable code causes the machine to:
manage traffic at a storage module according to priority levels assigned to high priority traffic, lower priority traffic, and consistency point operations.