Cluster node fault processing method and apparatus, and device and readable medium

1. A method for processing cluster node failure, comprising:

circularly acquiring state information of multiple nodes in a cluster, and on basis of the state information, determining whether a corresponding node fails;

in response to failure of the node, sending failure information to multiple Object-based Storage Devices (OSDs) under the node;

in response to the multiple OSDs receiving the failure information, according to the failure information, selecting a Monitor to send down information, and setting states of the multiple OSDs to be down; and

in response to the Monitor receiving the down information, updating an OSDMap on basis of the down information, and sending the updated OSDMap to OSDs under other nodes of the multiple nodes;

wherein in response to failure of the node, sending failure information to multiple OSDs under the node comprises:

determining whether a corresponding primary Monitor is normal according to a failure node;

in response to the corresponding primary Monitor being abnormal, sending Monitor failure information to the multiple OSDs under the node.

2. The method for processing cluster node failure according to claim 1 , further comprising:

in response to the corresponding primary Monitor being normal, sending node failure information to the multiple OSDs under the node.

3. The method for processing cluster node failure according to claim 1 , wherein determining whether the corresponding primary Monitor is normal according to a failure node comprises:

determining whether the other nodes connected to the corresponding primary Monitor are failure nodes; and

in response to any one node in the other nodes connected to the corresponding primary Monitor is not a failure node, confirming that the corresponding primary Monitor is normal.

4. The method for processing cluster node failure according to claim 3 , wherein the method further comprises:

in response to all the other nodes connected to the corresponding primary Monitor being failure nodes, confirming that the corresponding primary Monitor is abnormal, and setting a state of the corresponding primary Monitor to be down.

5. The method for processing cluster node failure according to claim 1 , wherein according to the failure information, selecting a Monitor to send down information comprises:

in response to the failure information being node failure information, selecting the corresponding primary Monitor to send the down information.

6. The method for processing cluster node failure according to claim 1 , wherein according to the failure information, selecting a Monitor to send down information comprises:

in response to the failure information being primary Monitor failure information, selecting a standby Monitor to send the down information; and

selecting a new primary Monitor, and the standby Monitor synchronizing the down information to the new primary Monitor.

7. A computer device, comprising:

at least one processor; and

a memory, wherein the memory stores computer instructions that is executed executable by the at least one processor, and upon execution by the at least one processor, is configured to cause the at least processor:

circularly acquire state information of multiple nodes in a cluster, and on the basis of the state information, determine whether a corresponding node fails;

in response to failure of the node, send failure information to multiple Object-based Storage Devices (OSDs) under the node;

in response to the multiple OSDs receiving the failure information, according to the failure information, select a Monitor to send down information, and setting states of the multiple OSDs to be down; and

in response to the Monitor receiving the down information, update an OSDMap on basis of the down information, and send the updated OSDMap to OSDs under other nodes of the multiple nodes;

determine whether a corresponding primary Monitor is normal according to a failure node;

in response to the corresponding primary Monitor being abnormal, send Monitor failure information to the multiple OSDs under the node.

8. A computer-readable storage medium, storing a computer program, when executed by at least one processor, cause the at least processor to:

circularly acquire state information of multiple nodes in a cluster, and on the basis of the state information, determine whether a corresponding node fails;

in response to failure of the node, send failure information to multiple Object-based Storage Devices (OSDs) under the node;

in response to the multiple OSDs receiving the failure information, according to the failure information, select a Monitor to send down information, and set states of the multiple OSDs to be down; and

in response to the Monitor receiving the down information, update an OSDMap on the basis of the down information, and send the updated OSDMap to OSDs under other nodes of the multiple nodes;

determine whether a corresponding primary Monitor is normal according to a failure node;

in response to the corresponding primary Monitor being abnormal, send Monitor failure information to the multiple OSDs under the node.

9. The computer device according to claim 7 , the computer instructions, upon execution by the at least one processor, is further configured to cause the at least processor to:

in response to the corresponding primary Monitor being normal, send node failure information to the multiple OSDs under the node.

10. The computer device according to claim 7 , the computer instructions, upon execution by the at least one processor, is further configured to cause the at least processor to:

determine whether the other nodes connected to the corresponding primary Monitor are failure nodes; and

in response to any one node in the other nodes connected to the corresponding primary Monitor is not a failure node, confirm that the corresponding primary Monitor is normal.

11. The computer device according to claim 10 , the computer instructions, upon execution by the at least one processor, is further configured to cause the at least processor to:

in response to all the other nodes connected to the corresponding primary Monitor being failure nodes, confirm that the corresponding primary Monitor is abnormal, and setting a state of the corresponding primary Monitor to be down.

12. The computer device according to claim 7 , the computer instructions, upon execution by the at least one processor, is further configured to cause the at least processor to:

in response to the failure information being node failure information, select the corresponding primary Monitor to send the down information.

13. The computer device according to claim 7 , the computer instructions, upon execution by the at least one processor, is further configured to cause the at least processor to:

in response to the failure information being primary Monitor failure information, select a standby Monitor to send the down information; and

select a new primary Monitor, and the standby Monitor synchronizes the down information to the new primary Monitor.

14. The computer-readable storage medium according to claim 8 , the computer program, when executed by at least one processor, cause the at least processor to:

in response to the corresponding primary Monitor being normal, send node failure information to the multiple OSDs under the node.

15. The computer-readable storage medium according to claim 8 , the computer program, when executed by at least one processor, cause the at least processor to:

determine whether the other nodes connected to the corresponding primary Monitor are failure nodes; and

in response to any one node in the other nodes connected to the corresponding primary Monitor is not a failure node, confirm that the corresponding primary Monitor is normal.

16. The computer-readable storage medium according to claim 15 , the computer program, when executed by at least one processor, cause the at least processor to:

in response to all the other nodes connected to the corresponding primary Monitor being failure nodes, confirm that the corresponding primary Monitor is abnormal, and setting a state of the corresponding primary Monitor to be down.

17. The computer-readable storage medium according to claim 8 , the computer program, when executed by at least one processor, cause the at least processor to:

in response to the failure information being node failure information, select the corresponding primary Monitor to send the down information.

18. The method for processing cluster node failure according to claim 1 , wherein the node failure comprises active breakpoint or an Intelligent Platform Management Interface (IPMI) having a power-off operation.

19. The method for processing cluster node failure according to claim 1 , wherein the OSDMap being a map of the OSDs, and stores information of the OSDs in the cluster, and changes of OSD nodes.

20. The method for processing cluster node failure according to claim 19 , the changes of the OSD nodes comprising at least one of: process exit, node addition, node exit, changes of node weights.