Dynamic use of raid levels responsive to workload requirements
View Patent ↗Data associated with a workload is stored in a first composite array of data storage devices that meets first data storage requirements of the workload, and is automatically stored in a second composite array in response to detecting second data storage requirements of the workload, wherein the second composite array of data storage devices meets the second data storage requirements. The data may be stored in the second composite array by either converting the first array or migrating the data to another array that more closely meets the current data storage requirements of the workload. Alternatively, the array conversion or the data migration may be performed in response to a predictive failure alert from one of the data storage devices in the first composite array.
1. A method comprising:
storing data associated with a workload in a first composite array of physical data storage devices configured as a redundant array of inexpensive disks (RAID) at a first level that meets first data storage requirements of the workload; and automatically and dynamically storing the data associated with the workload in a second composite array of physical data storage devices configured as a redundant array of inexpensive disks (RAID) at a second level that is different than the first level in response to detecting second data storage requirements of the workload, wherein the second composite array of data storage devices meets the second data storage requirements, wherein automatically storing the data associated with the workload in a second composite array of physical data storage devices in response to detecting second data storage requirements of the workload, includes migrating the data from the first composite array to the second composite array.
2. The method of claim 1 , wherein the first composite array differs from the second composite array in one or more parameters selected from level of striping, mirroring, parity, and nesting.
3. The method of claim 1 , wherein the first and second data storage requirements differ in a data resilience requirement.
4. The method of claim 1 , wherein the first and second data storage requirements differ in a workload performance requirement.
5. The method of claim 1 , wherein the data is migrated to the second composite array of physical data storage devices in response to the workload running at greater than a workload performance setpoint, wherein the second composite array has greater performance than the first composite array.
6. The method of claim 1 , wherein the data is migrated to the second composite array of physical data storage devices in response to the workload causing the first composite array to run at full capacity for more than a setpoint period of time, wherein the second composite array has greater performance than the first composite array.
7. The method of claim 1 , wherein the data is migrated to the second composite array of physical data storage devices in response to the first composite array running at less than a workload performance setpoint, wherein the second composite array has a higher resilience than the first composite array.
8. The method of claim 1 , wherein the data is migrated to the second composite array of physical data storage devices in response to the first composite array running at idle capacity for more than a setpoint period of time, wherein the second composite array has a higher resilience than the first composite array.