Tiering between storage media in a content aware storage system

1. A method for tiering data between storage media in a content aware storage system, comprising:

for each metadata page of a plurality of metadata pages in the content aware storage system:

storing a first copy of the metadata page in a high tier storage;

storing a second copy of the metadata page in an intermediate tier storage; and

storing a third copy of the metadata page in low tier storage;

maintaining a per region delta log for changes to the active journal entries of the metadata pages in the low tier storage;

upon determining, in response to monitoring available space in the high tier storage, usage of the high tier storage exceeds a threshold value:

identifying a least recently used (LRU) metadata page of the plurality of metadata pages;

deleting the LRU metadata page from the high tier storage; and

destaging active entries of a metadata journal for the LRU metadata page;

receiving a request to read one of the plurality of metadata pages; and

upon determining the one of the plurality of metadata pages is the LRU metadata page that was deleted from the high tier storage, reading the one of the plurality of metadata pages from the intermediate tier storage.

2. The method of claim 1 , further comprising:

upon determining the one of the plurality of metadata pages is not the LRU metadata page, reading the one of the plurality of metadata pages from the high tier storage.

3. The method of claim 1 , wherein destaging the active entries of the metadata journal for the LRU metadata page includes writing changes corresponding to the active entries to second and third copies of the LRU metadata page.

4. The method of claim 1 , wherein destaging the active entries of the metadata journal for the LRU metadata page includes writing changes corresponding to the active entries only to a second copy of the LRU metadata page, the method further comprising:

monitoring amortization of write activities of the metadata pages; and

upon determining a threshold value of the amortization has been reached for one of the metadata pages in the low tier storage, writing the changes from the per region delta log with respect to the one of the metadata pages to the corresponding one of the metadata pages in the low tier storage.

5. The method of claim 1 , further comprising:

writing user data corresponding to the metadata page of the plurality of metadata pages to the low tier storage;

upon determining read activity for the metadata page has exceeded a threshold frequency value:

copying the user data to the intermediate tier storage;

maintaining an existing copy of the user data in the low tier storage; and

marking a copy of the user data in the intermediate tier storage in cache; and

upon receiving a request to read the user data, reading the copy of the user data from the intermediate tier storage.

6. The method of claim 5 , further comprising:

upon determining the read activity for the metadata page has not reached or exceeded the threshold frequency value, reading a copy of the user data from the low tier storage.

7. The method of claim 6 , wherein the high tier storage is random access memory, the intermediate storage is storage class memory, and the low tier storage is a solid state drive.

8. A system for tiering data between storage media, the system comprising:

a memory comprising computer-executable instructions; and

a processor operable by a storage system, the processor executing the computer-executable instructions, the computer-executable instructions when executed by the processor cause the processor to perform operations comprising:

for each metadata page of a plurality of metadata pages in a content aware storage system:

storing a first copy of the metadata page in a high tier storage;

storing a second copy of the metadata page in an intermediate tier storage; and

storing a third copy of the metadata page in low tier storage;

maintaining a per region delta log for changes to the active journal entries of the metadata pages in the low tier storage;

upon determining, in response to monitoring available space in the high tier storage, usage of the high tier storage exceeds a threshold value:

identifying a least recently used (LRU) metadata page of the plurality of metadata pages;

deleting the LRU metadata page from the high tier storage; and

destaging active entries of a metadata journal for the LRU metadata page;

receiving a request to read one of the plurality of metadata pages; and

upon determining the one of the plurality of metadata pages is the LRU metadata page that was deleted from the high tier storage, reading the one of the plurality of metadata pages from the intermediate tier storage.

9. The system of claim 8 , wherein the operations further comprise:

upon determining the one of the plurality of metadata pages is not the LRU metadata page, reading the one of the plurality of metadata pages from the high tier storage.

10. The system of claim 8 , wherein destaging the active entries of the metadata journal for the LRU metadata page includes writing changes corresponding to the active entries to second and third copies of the LRU metadata page.

11. The system of claim 8 , wherein destaging the active entries of the metadata journal for the LRU metadata page includes writing changes corresponding to the active entries only to a second copy of the LRU metadata page, the operations further comprising:

monitoring amortization of write activities of the metadata pages; and

upon determining a threshold value of the amortization has been reached for one of the metadata pages in the low tier storage, writing the changes from the per region delta log with respect to the one of the metadata pages to the corresponding one of the metadata pages in the low tier storage.

12. The system of claim 8 , wherein the operations further comprise:

writing user data corresponding to the metadata page of the plurality of metadata pages to the low tier storage;

upon determining read activity for the metadata page has exceeded a threshold frequency value:

copying the user data to the intermediate tier storage;

maintaining an existing copy of the user data in the low tier storage; and

marking a copy of the user data in the intermediate tier storage in cache; and

upon receiving a request to read the user data, reading the copy of the user data from the intermediate tier storage.

13. The system of claim 12 , wherein the operations further comprise:

upon determining the read activity for the metadata page has not reached or exceeded the threshold frequency value, reading a copy of the user data from the low tier storage.

14. The system of claim 13 , wherein the high tier storage is random access memory, the intermediate storage is storage class memory, and the low tier storage is a solid state drive.

15. A computer program product embodied on a non-transitory computer readable medium, the computer program product including instructions that, when executed by a computer, causes the computer to perform operations comprising:

for each metadata page of a plurality of metadata pages in a content aware storage system:

storing a first copy of the metadata page in a high tier storage;

storing a second copy of the metadata page in an intermediate tier storage; and

storing a third copy of the metadata page in low tier storage;

maintaining a per region delta log for changes to the active journal entries of the metadata pages in the low tier storage;

upon determining, in response to monitoring available space in the high tier storage, usage of the high tier storage exceeds a threshold value:

identifying a least recently used (LRU) metadata page of the plurality of metadata pages;

deleting the LRU metadata page from the high tier storage; and

destaging active entries of a metadata journal for the LRU metadata page;

receiving a request to read one of the plurality of metadata pages; and

upon determining the one of the plurality of metadata pages is the LRU metadata page that was deleted from the high tier storage, reading the one of the plurality of metadata pages from the intermediate tier storage.

16. The computer program product of claim 15 , wherein the operations further comprise:

upon determining the one of the plurality of metadata pages is not the LRU metadata page, reading the one of the plurality of metadata pages from the high tier storage.

17. The computer program product of claim 15 , wherein destaging the active entries of the metadata journal for the LRU metadata page includes writing changes corresponding to the active entries to second and third copies of the LRU metadata page.

18. The computer program product of claim 15 , wherein destaging the active entries of the metadata journal for the LRU metadata page includes writing changes corresponding to the active entries only to a second copy of the LRU metadata page, the operations further comprising:

monitoring amortization of write activities of the metadata pages; and

upon determining a threshold value of the amortization has been reached for one of the metadata pages in the low tier storage, writing the changes from the per region delta log with respect to the one of the metadata pages to the corresponding one of the metadata pages in the low tier storage.

19. The computer program product of claim 15 , wherein the operations further comprise:

writing user data corresponding to the metadata page of the plurality of metadata pages to the low tier storage;

upon determining read activity for the metadata page has exceeded a threshold frequency value:

copying the user data to the intermediate tier storage;

maintaining an existing copy of the user data in the low tier storage; and

marking a copy of the user data in the intermediate tier storage in cache; and

upon receiving a request to read the user data, reading the copy of the user data from the intermediate tier storage.

20. The computer program product of claim 19 , wherein the operations further comprise:

upon determining the read activity for the metadata page has not reached or exceeded the threshold frequency value, reading a copy of the user data from the low tier storage; and

wherein the high tier storage is random access memory, the intermediate storage is storage class memory, and the low tier storage is a solid state drive.