Method, device, and program product for managing computing system

1. A method for managing a computing system, comprising:

acquiring a current state and a plurality of historical states of a computing device in the computing system, the plurality of historical states respectively describing historical states of the computing device in the computing system at a plurality of historical time points;

in response to determining that the current state matches a scheduling type for scheduling the computing device, searching the plurality of historical states for a historical state matching the current state;

in response to at least one historical state matching the current state, determining a historical scheduling policy associated with the historical state; and

based on the historical scheduling policy, allocating a computing task to be executed by the computing device to at least one other computing device in the computing system, the at least one other computing device being selected for allocation of the computing task based on at least one respective state of the at least one other computing device.

2. The method according to claim 1 , wherein acquiring the current state of the computing device comprises:

acquiring a plurality of attributes of the computing device, the plurality of attributes comprising at least any one of the following: a workload, configuration information, stored data, connected users, provided services, and states of neighboring computing devices of the computing device; and

determining the current state based on the plurality of attributes.

3. The method according to claim 1 , wherein searching the plurality of historical states for the historical state matching the current state comprises: in response to determining that a difference between the current state and a historical state among the plurality of historical states satisfies a predetermined condition, selecting the historical state.

4. The method according to claim 1 , wherein allocating the computing task to the at least one other computing device comprises:

acquiring states of a plurality of other computing devices in the computing system; and

selecting the at least one other computing device from the plurality of other computing devices based on the states of the plurality of other computing devices.

5. The method according to claim 4 , further comprising determining the plurality of other computing devices in response to at least any one of the following:

an update message of a topological structure of the computing system; and

heartbeat messages from the plurality of other computing devices.

6. The method according to claim 5 , further comprising: updating the at least one other computing device based on the states of the plurality of other computing devices.

7. The method according to claim 4 , wherein allocating the computing task to the at least one other computing device comprises: allocating the computing task to the at least one other computing device in response to determining that the at least one other computing device exists.

8. The method according to claim 1 , further comprising:

in response to no historical state matching the current state among the plurality of historical states and based on the current state and an allocation model describing an association relationship between states of the computing device and scheduling policies, determining a scheduling policy corresponding to the current state; and

allocating the computing task to other computing devices in the computing system based on the scheduling policy.

9. The method according to claim 1 , wherein the computing system comprises an edge network computing system, and the computing device comprises an edge computing device in the edge network computing system.

10. The method according to claim 1 , wherein the scheduling type comprises at least any one of the following: a reaction type, a prevention type, and a prediction type, wherein a threshold workload of the reaction type is higher than a threshold workload of the prevention type, and the threshold workload of the prevention type is higher than a threshold workload of the prediction type.

11. An electronic device, comprising:

at least one processor; and

a memory coupled to the at least one processor, wherein the memory has instructions stored therein that, when executed by the at least one processor, cause the electronic device to perform a method for managing a computing system, the method including:

acquiring a current state and a plurality of historical states of a computing device in the computing system, the plurality of historical states respectively describing historical states of the computing device in the computing system at a plurality of historical time points;

in response to determining that the current state matches a scheduling type for scheduling the computing device, searching the plurality of historical states for a historical state matching the current state;

in response to at least one historical state matching the current state, determining a historical scheduling policy associated with the historical state; and

based on the historical scheduling policy, allocating a computing task to be executed by the computing device to at least one other computing device in the computing system, the at least one other computing device being selected for allocation of the computing task based on at least one respective state of the at least one other computing device.

12. The electronic device according to claim 11 , wherein acquiring the current state of the computing device comprises:

acquiring a plurality of attributes of the computing device, the plurality of attributes comprising at least any one of the following: a workload, configuration information, stored data, connected users, provided services, and states of neighboring computing devices of the computing device; and

determining the current state based on the plurality of attributes.

13. The electronic device according to claim 11 , wherein searching the plurality of historical states for the historical state matching the current state comprises: in response to determining that a difference between the current state and a historical state among the plurality of historical states satisfies a predetermined condition, selecting the historical state.

14. The electronic device according to claim 11 , wherein allocating the computing task to the at least one other computing device comprises:

acquiring states of a plurality of other computing devices in the computing system; and

selecting the at least one other computing device from the plurality of other computing devices based on the states of the plurality of other computing devices.

15. The electronic device according to claim 14 , wherein the method further comprises determining the plurality of other computing devices in response to at least any one of the following:

an update message of a topological structure of the computing system; and

heartbeat messages from the plurality of other computing devices.

16. The electronic device according to claim 15 , wherein the method further comprises: updating the at least one other computing device based on the states of the plurality of other computing devices.

17. The electronic device according to claim 14 , wherein allocating the computing task to the at least one other computing device comprises: allocating the computing task to the at least one other computing device in response to determining that the at least one other computing device exists.

18. The electronic device according to claim 11 , wherein the method further comprises:

in response to no historical state matching the current state among the plurality of historical states and based on the current state and an allocation model describing an association relationship between states of the computing device and scheduling policies, determining a scheduling policy corresponding to the current state; and

allocating the computing task to other computing devices in the computing system based on the scheduling policy.

19. The electronic device according to claim 11 , wherein the computing system comprises an edge network computing system, and the computing device comprises an edge computing device in the edge network computing system; and

the scheduling type comprises at least any one of the following: a reaction type, a prevention type, and a prediction type, wherein a threshold workload of the reaction type is higher than a threshold workload of the prevention type, and the threshold workload of the prevention type is higher than a threshold workload of the prediction type.

20. A computer program product tangibly stored on a non-transitory computer-readable medium and comprising machine-executable instructions, wherein the machine-executable instructions are used to perform a method for managing a computing system, the method comprising:

acquiring a current state and a plurality of historical states of a computing device in the computing system, the plurality of historical states respectively describing historical states of the computing device in the computing system at a plurality of historical time points;

in response to determining that the current state matches a scheduling type for scheduling the computing device, searching the plurality of historical states for a historical state matching the current state;

in response to at least one historical state matching the current state, determining a historical scheduling policy associated with the historical state; and

based on the historical scheduling policy, allocating a computing task to be executed by the computing device to at least one other computing device in the computing system, the at least one other computing device being selected for allocation of the computing task based on at least one respective state of the at least one other computing device.