Data reduction management
AssigneeDell Products L.P.
InventorsOwen Martin, Ramesh Doddaiah
Life of this patent
Estimating the term…
Abstract
One or more aspects of the present disclosure relate to managing data reduction in a storage system during burst workloads. In embodiments, input/output (IO) operations received by a storage array are monitored to identify a burst workload based on a predefined threshold of IO operations per second (IOPS). In addition, the compression of data corresponding to IO write operations in the burst workload is deferred during the identified burst workload by temporarily storing the data in an uncompressed format. Further, the data is compressed during a self-healing period after a delay period. For example, the delay period is after the identified burst workload.
Claims20
A method comprising:
- monitoring input/output (IO) operations received by a storage array to identify a burst workload based on a predefined threshold of IO operations per second (IOPS), wherein the monitoring includes tracking a number, type, size, and frequency of IO operations targeting each storage group of the storage array and maintaining a data structure of metrics corresponding to the monitored IO operations;
- deferring compression of data corresponding to IO write operations in the burst workload during the identified burst workload by temporarily storing the data in an uncompressed format, wherein the deferring includes allocating a portion of persistent storage to temporarily destage the IO write requests and their corresponding data to disk during the burst workload;
- and
- compressing the data during a data compression self-healing period after a delay period, wherein the delay period is after the identified burst workload, and wherein the data compression self-healing period is a period when the storage array has available resources to perform compression operations on the temporarily stored uncompressed data, and wherein the data compression self-healing period is triggered by detecting that the storage array has transitioned from a high resource utilization state during the burst workload to a lower resource utilization state with processing capacity available for background compression operations.
An apparatus with a memory and processor, the apparatus configured to:
- monitor input/output (IO) operations received by a storage array to identify a burst workload based on a predefined threshold of IO operations per second (IOPS), wherein the monitoring includes tracking a number, type, size, and frequency of IO operations targeting each storage group of the storage array and maintaining a data structure of metrics corresponding to the monitored IO operations;
- defer compression of data corresponding to IO write operations in the burst workload during the identified burst workload by temporarily storing the data in an uncompressed format, wherein the deferring includes allocating a portion of persistent storage to temporarily destage the IO write requests and their corresponding data to disk during the burst workload;
- and
- compress the data during a data compression self-healing period after a delay period, wherein the delay period is after the identified burst workload, and wherein the data compression self-healing period is a period when the storage array has available resources to perform compression operations on the temporarily stored uncompressed data, and wherein the data compression self-healing period is triggered by detecting that the storage array has transitioned from a high resource utilization state during the burst workload to a lower resource utilization state with processing capacity available for background compression operations.
Dependencies are inferred from the claim text.