Volatile read cache in a content addressable storage system
A distributed storage system comprises a first module and a second module. The first module processes read requests for an address range, to send to the second module. The first module receives an address associated with a read request for a data page stored on the second module. A method searches a table on the first module for a content-based signature of the data page based on the address and provides the data page from a first module read cache if the content-based signature is in the read cache, where content-based signatures in the table are associated with the address range.
1. A method for maintaining read caches in a distributed storage system, the distributed storage system comprising a first module and a second module, the first module processing read requests for an address range, to send to the second module, the method comprising:
receiving, at the first module, an address associated with a read request for a data page stored on the second module, wherein the first module is selected based on an address associated with the data page, wherein the read request is to be processed by the first module transmitting a content-based signature to the second module to retrieve requested data from the second module;
searching a table on the first module for a content-based signature of the data page based on the address;
avoiding the transmitting the content-based signature to the second module to retrieve requested data from the second module by searching a first module read cache using the content-based signature, wherein the read cache is keyed on the content-based signature; and
in response to locating the content-based signature in the read cache, providing the data page from the read cache, wherein content-based signatures in the table are associated with the address range, wherein the data page from the first module read cache is a copy of a data page stored on the second module, and wherein the cached data in the read cache is not persisted.
2. The method of claim 1 further comprising:
maintaining a plurality of read caches for the distributed storage system wherein each of the plurality of read caches maintains cache consistency for a respective address range associated with each of the plurality of read caches.
3. The method of claim 1 further comprising:
transmitting the read request to the second module if the content-based signature is not in the read cache.
4. The method of claim 1 wherein the first module read cache is added to the first module, wherein a plurality of modules comprises the first module, wherein each of the plurality of modules is associated with a respective address range.
5. The method of claim 4 wherein a second module read cache is not added to a second module of the plurality of modules if the second module read cache would impact memory capacity of the second module.
6. The method of claim 1 further comprising:
removing the first module read cache from the first module if the first module read cache is impacting memory capacity of the first module.
7. The method of claim 1 further comprising:
receiving at the first module, a read request from a third module for a second data page stored on the second module; and
storing a copy of the second data page in the first module read cache if the second data page is associated with a second content-based signature stored in the table.
8. The method of claim 1 further comprising:
receiving at the first module, a write request to write a second data page on the second module; and
storing a copy of the second data page in the first module read cache if the second data page is associated with a second content-based signature stored in the table.
9. The method of claim 1 wherein the first module read cache maintains a reference count for each data page stored in the first module read cache, wherein the reference count indicates a number of times each data page has been read.
10. The method of claim 9 further comprising:
removing at least one of the each data page from the first module read cache based on the reference count.
11. The method of claim 1 further comprising:
removing the data page from the first module read cache based on memory capacity associated with the first module.
12. The method of claim 1 further comprising:
receiving instruction from the second module to remove the data page from the first module read cache.
13. The method of claim 1 further comprising:
receiving, at the first module, a second content-based signature from the second module;
removing a second data page associated with the second content-based signature from the first module if the second content-based signature is located in the first module; and
removing the second content-based signature from the first module.
14. The method of claim 1 further comprising:
receiving, at the first module, a second content-based signature from the second module; and
updating a second data page associated with the second content-based signature with a new data page if the second content-based signature is located in the first module.
15. The method of claim 1 wherein a plurality of data pages is stored in the first module read cache and wherein each of the plurality of data pages is associated with an address and a respective content-based signature, and wherein when a subset of the plurality of data pages share the content-based signature, one of the subset of the plurality of data pages is stored in the first module read cache.
16. The method of claim 1 wherein the content-based signature is a hash handle.
17. The method of claim 1 wherein the first module read cache includes volatile memory.
18. A system for use in maintaining read caches in a distributed storage system, the distributed storage system comprising a first module and a second module, the first module processing read requests for an address range, to send to the second module, the system comprising a processor configured to:
receive, at the first module, an address associated with a read request for a data page stored on the second module, wherein the first module is selected based on an address associated with the data page, wherein the read request is to be processed by the first module transmitting a content-based signature to the second module to retrieve requested data from the second module;
search a table on the first module for a content-based signature of the data page based on the address;
avoid the transmitting the content-based signature to the second module to retrieve requested data from the second module by searching a first module read cache using the content-based signature, wherein the read cache is keyed on the content-based signature; and
in response to locating the content-based signature in the read cache, provide the data page from the read cache, wherein content-based signatures in the table are associated with the address range, wherein the data page from the first module read cache is a copy of a data page stored on the second module, and wherein the cached data in the read cache is not persisted.
19. The system of claim 18 further configured to:
maintain a plurality of read caches for the distributed storage system wherein each of the plurality of read caches maintains cache consistency for a respective address range associated with each of the plurality of read caches.
20. A non-transitory computer program product for maintaining read caches in a distributed storage system, the distributed storage system comprising a first module and a second module, the first module processing read requests for an address range, to send to the second module, the computer program product comprising:
a computer readable storage medium having computer executable program code embodied therewith, the program code executable by a computer processor to:
receive, at the first module, an address associated with a read request for a data page stored on the second module, wherein the first module is selected based on an address associated with the data page, wherein the read request is to be processed by the first module transmitting a content-based signature to the second module to retrieve requested data from the second module;
search a table on the first module for a content-based signature of the data page based on the address;
avoid the transmitting the content-based signature to the second module to retrieve requested data from the second module by searching a first module read cache using the content-based signature, wherein the read cache is keyed on the content-based signature; and
in response to locating the content-based signature in the read cache, provide the data page from the read cache, wherein content-based signatures in the table are associated with the address range, wherein the data page from the first module read cache is a copy of a data page stored on the second module, and wherein the cached data in the read cache is not persisted.