Coordination of caching and I/O management in a multi-layer virtualized storage environment
View Patent ↗Systems and methods are disclosed for performing cache and I/O management in a multi-layer storage virtualization environment. Block virtualization may be implemented at various layers, each with one or more storage entities. One storage entity may coordinate and leverage the cache and the caching mechanism available with another storage entity. The storage entities may be at the same layer (horizontal cache coordination) or at different layers (vertical cache coordination). Cache coordination may include application-assisted read-ahead.
1. A system comprising:
a first layer of virtualized storage, wherein the first layer of virtualized storage comprises a first storage entity; and
a second layer of virtualized storage, wherein the second layer of virtualized storage comprises a second storage entity;
wherein the first storage entity is configured to request the second storage entity to store data in a cache, wherein the cache is managed by the second storage entity, and wherein the cache is readable by the first storage entity.
2. The system of claim 1 ,
wherein the first storage entity or the second storage entity comprises a host.
3. The system of claim 1 ,
wherein the first storage entity or the second storage entity comprises a storage appliance.
4. The system of claim 1 ,
wherein the first storage entity or the second storage entity comprises a switch.
5. The system of claim 1 ,
wherein the first storage entity or the second storage entity comprises a disk array.
6. The system of claim 1 , further comprising:
a third layer of virtualized storage, wherein the third layer of virtualized storage comprises a third storage entity, and wherein an I/O path from the first storage entity to the second storage entity comprises the third storage entity;
wherein the first storage entity is configured to request the third storage entity to store the data in an additional cache, wherein the additional cache is managed by the third storage entity, and wherein the additional cache is readable by the first storage entity;
wherein the second storage entity is configured to stop storing the data in the cache in response to storage of the data in the additional cache.
7. The system of claim 1 ,
wherein the first storage entity is configured to identify a region of storage comprising a block of data likely to be accessed by the first storage entity; and
wherein the first storage entity is configured to request the second storage entity to pre-fetch the block of data from the region of storage and store the data in the cache.
8. The system of claim 7 ,
wherein the second storage entity is configured to determine whether to pre-fetch the data from the region of storage based on a current load level at the second storage entity.
9. The system of claim 7 ,
wherein the second storage entity is configured to determine whether to pre-fetch the data from the region of storage based on an estimated expense of the prefetch operation.
10. The system of claim 1 ,
wherein the second storage entity is configured to identify a block of data likely to be accessed by the first storage entity, pre-fetch the block of data and store the block in the cache.
11. The system of claim 1 ,
wherein the first layer of virtualized storage comprises a third storage entity; and
wherein the first storage entity is configured to request the third storage entity to store additional data in an additional cache, wherein the additional cache is managed by the third storage entity, and wherein the additional cache is readable by the first storage entity.
12. The system of claim 11 ,
wherein the first storage entity is configured to identify a region of storage comprising one or more blocks of data likely to be accessed by the first storage entity; and
wherein the first storage entity is configured to request the third storage entity to pre-fetch the data from the region of storage and store the data in the additional cache.
13. The system of claim 1 , further comprising:
a cache manager configured to provide information to the first storage entity indicative of a caching capability of the second storage entity.
14. A method, comprising:
a first storage entity requesting a second storage entity to store data in a cache managed by the second storage entity, wherein a first layer of virtualized storage comprises the first storage entity, and wherein a second layer of virtualized storage comprises the second storage entity; and
the first storage entity reading the data from the cache.
15. The method of claim 14 , further comprising:
the first storage entity requesting a third storage entity to store the data in an additional cache, wherein a third layer of virtualized storage comprises the third storage entity, wherein an I/O path from the first storage entity to the second storage entity comprises the third storage entity, wherein the additional cache is managed by the third storage entity, and wherein the additional cache is readable by the first storage entity; and
the second storage entity discontinuing storing the data in the cache in response to the first storage entity requesting the third storage entity to store the data in the additional cache.
16. The method of claim 14 , further comprising:
identifying a region of storage comprising one or more blocks of data likely to be accessed by the first storage entity;
the second storage entity pre-fetching the one or more blocks of data from the region of storage; and
the second storage entity storing the data in the cache.
17. The method of claim 14 , further comprising:
the first storage entity requesting a third storage entity to store additional data in an additional cache, wherein the additional cache is managed by the third storage entity, wherein the first layer of virtualized storage comprises the third storage entity, and wherein the additional cache is readable by the first storage entity.
18. A computer-accessible storage medium storing program instructions, wherein the program instructions are computer-executable to:
send a request from a first storage entity to a second storage entity to store data in a cache managed by the second storage entity, wherein a first layer of virtualized storage comprises the first storage entity, and wherein a second layer of virtualized storage comprises the second storage entity; and
reading the data at the first storage entity from the cache.
19. The computer-accessible storage medium of claim 18 , wherein the instructions are further computer-executable to:
send a request from the first storage entity to a third storage entity to store the data in an additional cache, wherein a third layer of virtualized storage comprises the third storage entity, wherein an I/O path from the first storage entity to the second storage entity comprises the third storage entity, wherein the additional cache is managed by the third storage entity, and wherein the additional cache is readable by the first storage entity; and
discontinue storing the data in the cache managed by the second storage entity in response to the first storage entity requesting the third storage entity to store the data in the additional cache.
20. The computer-accessible storage medium of claim 18 , wherein the instructions are further computer-executable to:
identify a region of storage comprising one or more blocks of data likely to be accessed by the first storage entity;
pre-fetch the one or more blocks of data at the second storage entity from the region of storage; and
store the data in the cache managed by the second storage entity.