Host cache-slot aware 10 management

1. For a storage network including a storage system having a plurality of physical storage devices for storing data and a memory cache including a plurality of cache slots, and a host system having an application executing thereon that results in input/output (IO) operations being sent to the storage system, a method performed on the host system comprising:

accessing an IO operation received from the application executing on the host system;

determining that the IO operation is a sequential IO operation;

determining whether a data portion of the IO operation would fit in a current cache slot of the plurality of cache slots currently being used for IO operations of the application; and

selecting an IO path between the host system and the storage system for the IO operation based at least in part on the determination of whether a data portion would fit in the current cache slot.

2. The method of claim 1 , wherein the storage system further includes a plurality of physically discrete storage processing nodes, each storage processing node including a compute component for executing logic to process IO operations and a memory, the memory including a cache segment for use as part of a shared cache distributed across the plurality of processing nodes, wherein the shared cache includes the plurality of cache slots, the method further comprising:

determining a predefined number of cache slots to be consumed on a processing node for sequential IO operations before transitioning to a next processing node,

wherein the IO path is selected based at least in part on the predefined number of cache slots.

3. The method of claim 2 , wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would not fit in the current cache slot of the plurality of cache slots, and

wherein selecting the IO path includes selecting, based at least in part on the predefined number and the determination that the data portion would not fit in the current cache slot, an IO path corresponding to a next processing node of the plurality of processing nodes in a predefined order of the plurality or processing nodes.

4. The method of claim 2 , wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would not fit in the current cache slot of the plurality of cache slots, and

wherein selecting the IO path includes selecting, based at least in part on the predefined number and the determination that the data portion would not fit in the current cache slot, an IO path corresponding to the current processing node.

5. The method of claim 1 , wherein the storage system further includes a plurality of physically discrete storage processing nodes, each storage processing node including a compute component for executing logic to process IO operations and a memory, the memory including a cache segment for use as part of a shared cache distributed across the plurality of processing nodes, wherein the shared cache includes the plurality of cache slots,

wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would fit in the current cache slot of the plurality of cache slots, and

wherein, based at least in part on the determination that the data portion would fit in the current cache slot, the selected IO path is an IO path corresponding to the current processing node.

6. The method of claim 1 , wherein each of the plurality of cache slots has a predefined size, and wherein the method further comprises:

determining that a size of the data portion is larger than the predetermined size; and

dividing the IO operation into multiple IO operation according to the predefined size.

7. The method of claim 1 , further comprising:

tagging an IO communication including the IO operation with an indication that the IO operation is a sequential IO operation; and

sending the IO communication along the selected IO path to the storage system.

8. A host system for a storage network including a storage system having a plurality of physical storage devices for storing data and a memory cache including a plurality of cache slots, and the host system, the host system comprising:

an application executing on the host system resulting in input/output (IO) operations being sent to the storage system; and

a memory having code thereon that, when executed, performs a method including:

accessing an IO operation received from the application executing on the host system;

determining that the IO operation is a sequential IO operation;

determining whether a data portion of the IO operation would fit in a current cache slot of the plurality of cache slots currently being used for IO operations of the application; and

selecting an IO path between the host system and the storage system for the IO operation based at least in part on the determination of whether a data portion would fit in the current cache slot.

9. The host system of claim 8 , wherein the storage system further includes a plurality of physically discrete storage processing nodes, each storage processing node including a compute component for executing logic to process IO operations and a memory, the memory including a cache segment for use as part of a shared cache distributed across the plurality of processing nodes, wherein the shared cache includes the plurality of cache slots, and

wherein the method further includes determining a predefined number of cache slots to be consumed on a processing node for sequential IO operations before transitioning to a next processing node, wherein the IO path is selected based at least in part on the predefined number of cache slots.

10. The host system of claim 9 , wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would not fit in the current cache slot of the plurality of cache slots, and

wherein selecting the IO path includes selecting, based at least in part on the predefined number and the determination that the data portion would not fit in the current cache slot, an IO path corresponding to a next processing node of the plurality of processing nodes in a predefined order of the plurality or processing nodes.

11. The host system of claim 9 , wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would not fit in the current cache slot of the plurality of cache slots, and

wherein selecting the IO path includes selecting, based at least in part on the predefined number and the determination that the data portion would not fit in the current cache slot, an IO path corresponding to the current processing node.

12. The host system of claim 8 , wherein the storage system further includes a plurality of physically discrete storage processing nodes, each storage processing node including a compute component for executing logic to process IO operations and a memory, the memory including a cache segment for use as part of a shared cache distributed across the plurality of processing nodes, wherein the shared cache includes the plurality of cache slots,

wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would fit in the current cache slot of the plurality of cache slots, and

wherein, based at least in part on the determination that the data portion would fit in the current cache slot, the selected IO path is an IO path corresponding to the current processing node.

13. The host system of claim 8 , wherein each of the plurality of cache slots has a predefined size, and wherein the method further includes:

determining that a size of the data portion is larger than the predetermined size; and

dividing the IO operation into multiple IO operation according to the predefined size.

14. The host system of claim 8 , wherein the method further includes:

tagging an IO communication including the IO operation with an indication that the IO operation is a sequential IO operation; and

sending the IO communication along the selected IO path to the storage system.

15. For a storage network including a storage system having a plurality of physical storage devices for storing data and a memory cache including a plurality of cache slots, and a host system having an application executing thereon that results in input/output (IO) operations being sent to the storage system and having a computer-readable media having software stored thereon, the software comprising:

executable code that accesses an IO operation received from the application executing on the host system;

executable code that determines that the IO operation is a sequential IO operation;

executable code that determines whether a data portion of the IO operation would fit in a current cache slot of the plurality of cache slots currently being used for IO operations of the application; and

executable code that selects an IO path between the host system and the storage system for the IO operation based at least in part on the determination of whether a data portion would fit in the current cache slot.

16. The computer-readable media of claim 15 , wherein the storage system further includes a plurality of physically discrete storage processing nodes, each storage processing node including a compute component for executing logic to process IO operations and a memory, the memory including a cache segment for use as part of a shared cache distributed across the plurality of processing nodes, wherein the shared cache includes the plurality of cache slots, the software further comprising:

executable code that determines a predefined number of cache slots to be consumed on a processing node for sequential IO operations before transitioning to a next processing node,

wherein the IO path is selected based at least in part on the predefined number of cache slots.

17. The computer-readable media of claim 16 , wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would not fit in the current cache slot of the plurality of cache slots, and

wherein selecting the IO path includes selecting, based at least in part on the predefined number and the determination that the data portion would not fit in the current cache slot, an IO path corresponding to a next processing node of the plurality of processing nodes in a predefined order of the plurality or processing nodes.

18. The computer-readable media of claim 15 , wherein the storage system further includes a plurality of physically discrete storage processing nodes, each storage processing node including a compute component for executing logic to process IO operations and a memory, the memory including a cache segment for use as part of a shared cache distributed across the plurality of processing nodes, wherein the shared cache includes the plurality of cache slots,

wherein the current cache slot is on a current processing node of the plurality of processing nodes,

wherein it is determined that the data portion of the IO operation would fit in the current cache slot of the plurality of cache slots, and

wherein, based at least in part on the determination that the data portion would fit in the current cache slot, the selected IO path is an IO path corresponding to the current processing node.

19. The computer-readable media of claim 15 , wherein each of the plurality of cache slots has a predefined size, and wherein the software further comprises:

executable code that determines that a size of the data portion is larger than the predetermined size; and

executable code that divides the IO operation into multiple IO operation according to the predefined size.

20. The computer-readable media of claim 15 , wherein the software further comprises:

executable code that tags an IO communication including the IO operation with an indication that the IO operation is a sequential IO operation; and

executable code that sends the IO communication along the selected IO path to the storage system.