Performance improvement for an active-active distributed non-ALUA system with address ownerships

1. A method, comprising:

receiving, by a routing module of a content-addressable storage system, an input/output (IO) request from a host computer;

accessing, by the routing module, an address-to-compute module (a→c) table, the (a→c) table providing a listing of addresses and compute modules having ownership to the addresses;

accessing a path table that provides a mapping between each of the compute modules and a physical path to corresponding storage controllers;

determining, by the routing module from the a→c table, a target location of the IO request, the target location specifying an address;

determining, by the routing module from the path table, an address owner of a storage controller port of a storage controller that owns the address of the IO;

selecting a physical path associated with the address owner; and

transmitting, by the routing module, the IO request to the storage controller port via a direct call.

2. The method of claim 1 , further comprising:

upon determining an event which causes a change to the address ownership, updating one or more entries of the a→c table with new address ownership data.

3. The method of claim 2 , wherein the event is one of a failover of one or more storage controllers and a cluster expansion of one of more storage controllers.

4. The method of claim 1 , further comprising initializing entries of the a→c table to provide to each of the entries the associated compute module that owns corresponding entries.

5. The method of claim 1 , wherein transmitting the IO request to the storage controller port includes transmitting the IO request without sending data via remote direct memory access (RDMA).

6. The method of claim 1 , wherein the content-addressable storage system is a distributed non-asymmetrical logical unit assignment (non-ALUA) system.

7. The method of claim 1 , wherein the a→c table includes 1024 entries, each of the entries owned by a corresponding compute module.

8. A system, comprising:

a memory comprising computer-executable instructions; and

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

receiving, by a routing module of a content-addressable storage system, an IO request from a host computer;

accessing, by the routing module, an address-to-compute module (a→c) table, the (a→c) table providing a listing of addresses and compute modules having ownership to the addresses;

accessing a path table that provides a mapping between each of the compute modules and a physical path to corresponding storage controllers;

determining, by the routing module from the a→c table, a target location of the IO request, the target location specifying an address;

determining, by the routing module from the path table, an address owner of a storage controller port of a storage controller that owns the address of the IO;

selecting a physical path associated with the address owner; and

transmitting, by the routing module, the IO request to the storage controller port via a direct call.

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

upon determining an event which causes a change to the address ownership, updating one or more entries of the a→c table with new address ownership data.

10. The system of claim 9 , wherein the event is one of a failover of one or more storage controllers and a cluster expansion of one of more storage controllers.

11. The system of claim 8 , wherein the operations further comprise initializing entries of the a→c table to provide to each of the entries the associated compute module that owns corresponding entries.

12. The system of claim 8 , wherein transmitting the IO request to the storage controller port includes transmitting the IO request without sending data via remote direct memory access (RDMA).

13. 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:

receiving, by a routing module of a content-addressable storage system, an IO request from a host computer;

accessing, by the routing module, an address-to-compute module (a→c) table, the (a→c) table providing a listing of addresses and compute modules having ownership to the addresses;

accessing a path table that provides a mapping between each of the compute modules and a physical path to corresponding storage controllers;

determining, by the routing module from the a→c table, a target location of the IO request, the target location specifying an address;

determining, by the routing module from the path table, an address owner of a storage controller port of a storage controller that owns the address of the IO;

selecting a physical path associated with the address owner; and

transmitting, by the routing module, the IO request to the storage controller port via a direct call.

14. The computer program product of claim 13 , wherein the operations further comprise:

upon determining an event which causes a change to the address ownership, updating one or more entries of the a→c table with new address ownership data.

15. The computer program product of claim 14 , wherein the event is one of a failover of one or more storage controllers and a cluster expansion of one of more storage controllers.

16. The computer program product of claim 13 , wherein the operations further comprise initializing entries of the a→c table to provide to each of the entries the associated compute module that owns corresponding entries.

17. The computer program product of claim 13 , wherein transmitting the IO request to the storage controller port includes transmitting the IO request without sending data via remote direct memory access (RDMA).