Techniques for determining and using caching scores for cached data

1. A method of performing cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with one or more criteria including one or more of a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the deduplication score for said one page of data stored in the cache, and wherein the deduplication score for said one page of data stored in the cache is determined in accordance with a deduplication reference count indicating a number of times said one page of data is referenced by a logical address.

2. The method of claim 1 , wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the compression score for said one page of data stored in the cache.

3. The method of claim 1 , wherein the each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria, and wherein the one or more criteria further includes an access score determined in accordance with when the one page of data was last accessed.

4. The method of claim 1 , wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria, and wherein the one or more criteria further includes an access score determined in accordance with a frequency of accesses of the one page of data that occurred within a specified window of time.

5. The method of claim 1 , wherein the one or more criteria include the neighbor score, the deduplication score, the compression score, and an access score.

6. The method of claim 1 , wherein the cache is a read cache that includes only read data for read I/O operations.

7. The method of claim 1 , further comprising:

sorting the plurality of pages stored in the cache in accordance with the plurality of page scores; and

selecting a first page of the plurality of pages stored in the cache for eviction, wherein the first page is determined by said sorting as having a lowest page score of the plurality of pages scores.

8. A method of performing cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with one or more criteria including one or more of a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the compression score for said one page of data stored in the cache, wherein said one page of data is stored in the cache in a compressed form, and wherein the compression score for said one page of data stored in the cache is determined in accordance with an amount of cache consumed to store the compressed form of said one page of data.

9. The method of claim 8 , wherein the cache includes a plurality of buckets of cache pages, wherein each of the plurality of buckets is associated with a different one of a plurality of cache page sizes, and wherein cache pages included in a same one of the plurality of buckets are a same size that is equal to the different one of a plurality of cache page sizes associated with the same one of the plurality of buckets.

10. The method of claim 9 , wherein each of the plurality of pages of data is stored in the cache in a compressed form and wherein the compressed form of said each page of data has an associated compressed size, and wherein the compressed form is stored in a cache page selected from one of the plurality of buckets having an associated cache size that is a smallest of the plurality of cache page sizes capable of storing the compressed form.

11. A method of performing cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with one or more criteria including one or more of a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the neighbor score for said one page of data stored in the cache, wherein the neighbor score uses a popularity metric based on deduplication related criteria of neighboring pages of data.

12. The method of claim 11 , wherein the neighbor score for said one page of data stored in the cache is determined based on one or more neighboring pages of data with respect to said one page of data, and wherein each of the one or more neighboring pages of data and said one page of data are located in a logical address space, and wherein each of the one or more neighboring pages are located in logical addresses adjacent to other logical addresses mapped to said one page of data.

13. The method of claim 12 , further comprising:

determining that a first of the one or more neighboring pages of said one page of data is stored in the cache; and

determining whether the first neighboring page is popular in accordance with the popularity metric, wherein the popularity metric determines that the first neighboring page is popular in accordance the deduplication related criteria of the first neighboring page.

14. The method of claim 13 , wherein the deduplication related criteria of the first neighboring page indicates that the first neighboring page is popular if it has an associated deduplication reference count above a specified threshold.

15. The method of claim 13 , wherein the popularity metric determines that the first neighboring page is popular of the first neighboring page stored in the cache has a last access time that is within a specified window of time.

16. A method of performing cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with criteria including a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data, and an access score; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data stored in the cache is determined using a function that takes a plurality of inputs for the one page of data, wherein the plurality of inputs includes the neighbor score, the deduplication score, the compression score, and the access score.

17. The method of claim 16 , wherein the function computes said each page score for the one page of data stored in the cache as a weighted sum of a plurality of terms in which each of the plurality of terms includes one of the plurality of inputs and a weight corresponding to said one input.

18. A system comprising:

one or more processors; and

a memory comprising code stored therein that, when executed, performs a method of cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with one or more criteria including one or more of a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the deduplication score for said one page of data stored in the cache, and wherein the deduplication score for said one page of data stored in the cache is determined in accordance with a deduplication reference count indicating a number of times said one page of data is referenced by a logical address.

19. A non-transitory computer readable medium comprising code stored thereon that, when executed, performs a method of cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with one or more criteria including one or more of a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the deduplication score for said one page of data stored in the cache, and wherein the deduplication score for said one page of data stored in the cache is determined in accordance with a deduplication reference count indicating a number of times said one page of data is referenced by a logical address.

20. A system comprising:

one or more processors; and

a memory comprising code stored therein that, when executed, performs a method of cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with one or more criteria including one or more of a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the compression score for said one page of data stored in the cache, wherein said one page of data is stored in the cache in a compressed form, and wherein the compression score for said one page of data stored in the cache is determined in accordance with an amount of cache consumed to store the compressed form of said one page of data.

21. A system comprising:

one or more processors; and

a memory comprising code stored therein that, when executed, performs a method of cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with one or more criteria including one or more of a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data is determined in accordance with the one or more criteria including the neighbor score for said one page of data stored in the cache, wherein the neighbor score uses a popularity metric based on deduplication related criteria of neighboring pages of data.

22. A system comprising:

one or more processors; and

a memory comprising code stored therein that, when executed, performs a method of cache management comprising:

receiving a plurality of pages of data having a plurality of page scores, wherein each of the plurality of pages of data is associated with a corresponding one of the plurality of page scores, wherein the corresponding one of the plurality of page scores associated with said each page of data is determined in accordance with criteria including a deduplication score, a compression score, and a neighbor score that uses a popularity metric based on deduplication related criteria of neighboring pages of data, and an access score; and

storing the plurality of pages of data in a cache in accordance with the plurality of page scores, wherein each of the plurality of page scores associated with one of the plurality of pages of data stored in the cache is determined using a function that takes a plurality of inputs for the one page of data, wherein the plurality of inputs includes the neighbor score, the deduplication score, the compression score, and the access score.