Distributed storage through a volume device architecture
A volume manager I/O method and system. The method includes determining a storage extent mapping of storage functionality of a plurality of storage devices and generating a logical disk extent based on the storage extent mapping. The logical disk extent is exported to a volume device component that is communicatively coupled to implement I/O for an application. An I/O request from the application is received via the volume device component. The I/O request is executed in accordance with the logical disk extent.
1. A volume manager I/O method, comprising:
determining a storage extent mapping of storage functionality of a storage resource;
generating a logical disk extent based on the storage extent mapping;
exporting the logical disk extent to a volume device component that is communicatively coupled to implement I/O for an application
receiving an I/O request from the application via the volume device component; and
executing the I/O request in accordance with the logical disk extent.
2. The method of claim 1 , wherein the logical disk extent is used to export volume layout information to the application.
3. The method of claim 2 , wherein the volume layout information comprises one or more volume policy options.
4. The method of claim 1 , wherein the volume device component is a virtual transport bus volume device component.
5. The method of claim 1 , wherein I/O requests are received from a plurality of different applications via a corresponding plurality of volume device components, and wherein the plurality of I/O requests are pooled to implement an optimal overall I/O scheduling.
6. The method of claim 5 , wherein the optimal overall I/O scheduling is based on knowledge of each of the volume device components and knowledge of a physical resource topology of the storage resource.
7. The method of claim 5 , wherein the optimal overall I/O scheduling is based on a provisioning policy, and wherein the provisioning policy is operable for alteration via real-time management input.
8. The method of claim 1 , wherein I/O signal requests and data completion interrupts are suppressed while executing a plurality of I/O request to implement streaming I/O.
9. The method of claim 1 , wherein a shared memory is used to implement a plurality of queues to support input and output between for context of the application.
10. A computer readable non-transitory storage medium having stored thereon, computer executable instructions that, if executed by a computer system cause the computer system to perform a method comprising:
instantiating a volume device manager within a hypervisor context;
determining a storage extent mapping of storage functionality of storage resources;
generating a plurality of logical disk extents based on the storage extent mapping;
exporting the logical disk extents from the volume device manager to a plurality of volume device components that are communicatively coupled to implement I/O for a plurality of applications, wherein the volume device components and the applications execute as respective virtual machine guests;
receiving a plurality of I/O request from the applications via the volume device components;
pooling the I/O requests to implement an optimal overall I/O scheduling; and
executing the I/O requests in accordance with the I/O scheduling.
11. The computer readable storage medium of claim 10 , wherein the logical disk extent is used to export volume layout information to the virtual machine guests.
12. The computer readable storage medium of claim 11 , wherein the volume layout information comprises one or more volume policy options.
13. The computer readable storage medium of claim 10 , wherein each of the volume device components are virtual transport bus volume device components.
14. The computer readable storage medium of claim 10 , wherein the optimal overall I/O scheduling is based on knowledge of each of the volume device components and knowledge of a physical resource topology of the storage resources.
15. The computer readable storage medium of claim 10 , wherein I/O signal requests and data completion interrupts are suppressed while executing a plurality of I/O request to implement streaming I/O.
16. The computer readable storage medium of claim 10 , wherein a shared memory is used to implement a plurality of queues to support input and output between a plurality of contexts of the virtual machine guests.
17. A volume device manager system, comprising:
a computer system having a processor coupled to a computer readable storage media and executing computer readable code which causes the computer system to implement a volume device manager, wherein the volume device manager:
instantiates a volume device manager within a hypervisor context;
determines a storage extent mapping of storage functionality of storage resources;
generates a plurality of logical disk extents based on the storage extent mapping;
exports the logical disk extents from the volume device manager to a plurality of volume device components that are communicatively coupled to implement I/O for a plurality of applications, wherein the volume device components and the applications execute as respective virtual machine guests;
receives a plurality of I/O request from the applications via the volume device components;
pools the I/O requests to implement an optimal overall I/O scheduling; and
executes the I/O requests in accordance with the I/O scheduling.
18. The system of claim 17 , wherein each of the volume device components are virtual transport bus volume device components.
19. The system of claim 17 , wherein the optimal overall I/O scheduling is based on knowledge of each of the volume device components and knowledge of a physical resource topology of the storage resources.
20. The system of claim 17 , wherein I/O signal requests and data completion interrupts are suppressed while executing a plurality of I/O request to implement streaming I/O.