Dynamic storage tiering based on performance SLAs
Data objects are stored on storage devices, taking into account service level agreements or other quality of service parameters. In one aspect, data objects grouped into storage volumes. In addition, the storage devices are classified into different level storage tiers, where higher level storage tiers have higher performance and lower level storage tiers have lower performance. Ranks for the data objects are calculated, based on both a data usage pattern for the data object (e.g., recency and frequency) and on quality of service (QOS) parameters for the storage volume containing the data object. Examples of QOS parameters include service level agreements, priority, minimum and maximum input/output operations per second. The data objects are then stored on storage devices, based on the data objects' ranks and the storage devices' storage tiers.
1. A method of storing data objects on storage devices, the data objects grouped into storage volumes, the storage devices classified into different level storage tiers, wherein higher level storage tiers have higher performance and lower level storage tiers have lower performance, the method comprising:
calculating ranks for the data objects, a rank for a data object based on a data usage pattern for the data object and on quality of service (QOS) parameters for the storage volume containing the data object; and
storing the data objects on the storage devices, based on the data objects' ranks and the storage devices' storage tiers.
2. The method of claim 1 , wherein the QOS parameters for the storage volumes comprise service level agreements for the storage volumes.
3. The method of claim 1 , wherein the QOS parameters for the storage volumes comprise priority for the storage volumes.
4. The method of claim 1 , wherein the QOS parameters for the storage volumes comprise minimum input/output operations per second for the storage volumes.
5. The method of claim 1 , wherein the QOS parameters for the storage volumes comprise maximum input/output operations per second for the storage volumes.
6. The method of claim 1 , wherein the data usage patterns for the data objects comprise recency of access for the data objects.
7. The method of claim 1 , wherein the data usage patterns for the data objects comprise frequency of access for the data objects.
8. The method of claim 1 , wherein calculating ranks for the data objects comprises:
calculating an object sub-rank, the object sub-rank for the data object based on data usage pattern for the data object;
calculating a volume sub-rank, the volume sub-rank for the data object based on quality of service (QOS) parameters for the storage volume containing the data object; and
calculating the rank by combining the object sub-rank and volume sub-rank.
9. The method of claim 8 , wherein the object sub-rank is more significant than the volume sub-rank.
10. The method of claim 8 , wherein the object sub-rank is calculated using a circular counter array.
11. The method of claim 1 , wherein:
calculating ranks for the data objects comprises updating the ranks for the data objects based on usage of the data objects; and
storing the data objects on the storage devices comprises storing the data objects on higher level storage tiers based on their updated ranks.
12. The method of claim 1 , wherein:
storing the data objects on the storage devices comprises storing new data objects on higher level storage tiers and demoting previously stored data objects to lower level storage tiers, based on the ranks of the data objects.
13. A non-transitory computer-readable storage medium storing computer program modules for storing data objects on storage devices, the data objects grouped into storage volumes, the storage devices classified into different level storage tiers, wherein higher level storage tiers have higher performance and lower level storage tiers have lower performance, the computer program modules executable to perform steps comprising:
calculating ranks for the data objects, a rank for a data object based on a data usage pattern for the data object and on quality of service (QOS) parameters for the storage volume containing the data object; and
storing the data objects on the storage devices, based on the data objects' ranks and the storage devices' storage tiers.
14. A system for storing data objects on storage devices, the data objects grouped into storage volumes, the system comprising:
a persistence layer comprising multiple storage devices, the storage devices classified into different level storage tiers, wherein higher level storage tiers have higher performance and lower level storage tiers have lower performance;
a non-transitory computer-readable storage medium storing computer program modules executable to perform steps comprising:
calculating ranks for the data objects, a rank for a data object based on a data usage pattern for the data object and on quality of service (QOS) parameters for the storage volume containing the data object; and
storing the data objects on the storage devices, based on the data objects' ranks and the storage devices' storage tiers; and
a computer processor for executing the computer program modules.