System and method for improved cache performance

1. A coordination point for assigning clients to remote backup storages, comprising:

a persistent storage comprising client type to remote backup storage mappings; and

a processor programmed to:

obtain a data storage request for data from a client of the clients;

obtain, without reading the data, an inferential characterization of the client;

identify a type of the client using the inferential characterization of the client, wherein, to identify the type of the client using the inferential characterization of the client, the processor is further programmed to:

make a prediction of a content of the data based on the inferential characterization of the client, and

match the predicted content of the data to one type of a plurality of types,

wherein each type of the plurality of types is associated with a different respective contents;

select a remote backup storage of the remote backup storages based on the identified type of the client using the client type to remote backup storage mappings; and

assign the selected remote backup storage to service the data storage request.

2. The coordination point of claim 1 , wherein obtaining the inferential characterization of the client comprises:

identifying a file system of the client.

3. The coordination point of claim 1 , wherein obtaining the inferential characterization of the client comprises:

identifying a state status of the client.

4. The coordination point of claim 1 , wherein obtaining the inferential characterization of the client comprises:

identifying a size of a storage capacity of the client.

5. The coordination point of claim 1 , wherein obtaining the inferential characterization of the client comprises:

identifying an operating system of the client.

6. The coordination point of claim 1 , wherein the data is unreadable by the coordination point.

7. The coordination point of claim 1 , wherein the remote backup storage is selected while the remote backup storage has a higher workload than a second remote backup storage of the remote backup storages.

8. The coordination point of claim 1 , wherein the client type to remote backup storage mappings associate clients of different types with different remote backup storages.

9. The coordination point of claim 1 , wherein the type of the client comprises at least one selected from a group consisting of a storage capacity of the client, a file system of the client, an operating system of the client, and a state status of the client.

10. The coordination point of claim 1 , wherein assigning the selected remote backup storage to service the data storage request comprises:

sending an identifier of a gateway of the selected remote backup storage to the client.

11. The coordination point of claim 1 , wherein the processor is further programmed to:

obtain a second data storage request for second data from a second client of the clients;

obtain a second inferential characterization of the second client;

identify a second client type of the second client using the second inferential characterization;

select a second remote backup storage of the remote backup storages based on the identified second client type of the second client using the client type to remote backup mappings; and

assign the selected second remote backup storage to service the second data storage request.

12. The coordination point of claim 11 , wherein the data is of a first database type and the second data is of a second database type.

13. The coordination point of claim 12 , wherein the client type and the second client type are different.

14. The coordination point of claim 11 , wherein the data is of a first database type and the second data is of the first database type.

15. The coordination point of claim 14 , wherein the client type and the second client type are different.

16. A method of operating a coordination point for assigning clients to remote backup storages, comprising:

obtaining a data storage request for data from a client of the clients;

without reading the data:

obtaining an inferential characterization of the client;

identifying a type of the client using the inferential characterization of the client, wherein, identifying the type of the client using the inferential characterization of the client comprises:

making a prediction of a content of the data based on the inferential characterization of the client, and

matching the predicted content of the data to one type of a plurality of types,

wherein each type of the plurality of types is associated with a different respective contents;

selecting a remote backup storage of the remote backup storages based on the identified type of the client using client type to remote backup storage mappings; and

assigning the selected remote backup storage to service the data storage request.

17. A non-transitory computer readable medium comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a method for assigning clients to remote backup storages, the method comprising:

obtaining a data storage request for data from a client of the clients;

without reading the data:

obtaining an inferential characterization of the client;

identifying a type of the client using the inferential characterization of the client, wherein, identifying the type of the client using the inferential characterization of the client comprises:

making a prediction of a content of the data based on the inferential characterization of the client, and

matching the predicted content of the data to one type of a plurality of types,

wherein each type of the plurality of types is associated with a different respective contents;

selecting a remote backup storage of the remote backup storages based on the identified type of the client using client type to remote backup storage mappings; and

assigning the selected remote backup storage to service the data storage request.