Data storage within hybrid storage aggregate
Among other things, one or more techniques and/or systems are provided for storing data within a hybrid storage aggregate comprising a lower-latency storage tier and a higher-latency storage tier. In particular, frequently accessed data, randomly accessed data, and/or short lived data may be stored (e.g., read caching and/or write caching) within the lower-latency storage tier. Infrequently accessed data and/or sequentially accessed data may be stored within the higher-latency storage tier. Because the hybrid storage aggregate may comprise a single logical container derived from the higher-latency storage tier and the lower-latency storage tier, additional storage and/or file system functionality may be implemented across the storage tiers. For example, deduplication functionality, caching functionality, backup/restore functionality, and/or other functionality may be provided through a single file system (or other type of arrangement) and/or a cache map implemented within the hybrid storage aggregate.
1. A method for storing data, comprising:
receiving an I/O operation associated with a hybrid storage aggregate comprising a higher-latency storage tier and a lower-latency storage tier, the I/O operation comprising writeable data;
storing the writeable data within the higher-latency storage tier;
providing an indication, for the writeable data within the higher-latency storage tier, specifying that the writeable data is to be cached within the lower-latency storage tier; and
caching the writeable data within the lower latency storage tier based upon the indication;
maintaining a temperature metric for the writeable data; and
responsive to the temperature metric falling below a threshold, evicting the writeable data from the lower-latency storage tier.
2. The method of claim 1 , the storing comprising:
storing the writeable data within both the higher-latency storage tier and the lower-latency storage tier, and refraining from providing the indication.
3. The method of claim 1 , the providing comprising:
providing the indication responsive to at least one of:
determining that the writeable data is to be written to random block offsets; or
predicting that the writeable data will be accessed above a threshold frequency.
4. A method for storing data, comprising:
receiving an I/O operation associated with a hybrid storage aggregate comprising a lower-latency storage tier and a higher-latency storage tier, the I/O operation comprising writeable data;
storing the writeable data within the lower-latency storage tier based upon at least one of determining that the I/O operation comprises a non-sequential write operation of the writeable data or predicting that the writeable data will be stored within memory below a timespan threshold; and
maintaining a temperature metric for the writeable data; and
responsive to the temperature metric falling below a threshold, evicting the writeable data from the lower-latency storage tier, the evicting comprising migrating the writeable data from the lower-latency storage tier to the higher-latency storage tier.
5. The method of claim 4 , the storing comprising:
refraining from storing the writeable data within the higher-latency storage tier.
6. The method of claim 4 , comprising:
storing a volume of data across the lower-latency storage tier and the higher-latency storage tier.
7. A system for storing data, comprising:
a write caching component configured to:
receive an I/O operation associated with a hybrid storage aggregate comprising a lower-latency storage tier and a higher-latency storage tier, the I/O operation comprising writeable data;
store the writeable data within the lower-latency storage tier based upon at least one of determining that the I/O operation comprises a non-sequential read operation of the writeable data, determining that the I/O operation comprises data designated for low latency access, or predicting that the writeable data will be stored within memory below a timespan threshold; and
responsive to storing the writeable data within the lower-latency storage tier, refrain from storing the writeable data within the higher-latency storage tier.
8. The system of claim 7 , the write caching component configured to:
store the writable data within the lower-latency storage tier based upon predicting that the writeable data will be accessed above a threshold frequency.
9. The system of claim 7 , the write caching component comprised within a node configured to manage storage of data within the hybrid storage aggregate.
10. The system of claim 7 , comprising:
an eviction component configured to:
maintain a temperature metric for the writeable data; and
responsive to the temperature metric falling below a threshold, evict the writeable data from the lower-latency storage tier.
11. The system of claim 10 , the eviction component configured to:
migrate the writeable data from the lower-latency storage tier to the higher-latency storage tier for eviction of the writeable data from the lower-latency storage tier.
12. The system of claim 7 , comprising:
a migration component configured to:
migrate archival data from the lower-latency storage tier to the higher-latency storage tier within the hybrid storage aggregate.
13. The system of claim 7 , comprising:
a migration component configured to:
migrate active data from the higher-latency storage tier to the lower-latency storage tier.
14. The system of claim 7 , comprising:
a failure recovery component configured to:
responsive to detecting a failure of a first storage server associated with the hybrid storage aggregate, assign ownership of the hybrid storage aggregate from the first storage server to a second storage server.
15. The system of claim 7 , the write caching component configured to:
store a volume of data across the lower-latency storage tier and the higher-latency storage tier.
16. The system of claim 7 , the write caching component configured to: store the writeable data within the lower-latency storage tier based upon determining that the writeable data is to be written to random block offsets.