Resource allocation method and resource borrowing method
Embodiments of this application provide example resource allocation methods. One example method includes determining, by a first node, a hash value corresponding to a first cluster. The first node can obtain a hash ring, where the hash ring includes at least one hash value interval, and each hash value interval corresponds to one second cluster. The first node can determine a target second cluster based on the hash value corresponding to the first cluster, where the hash value corresponding to the first cluster belongs to a target hash interval, the target hash interval is a hash value interval in the at least one hash value interval, and the target hash interval corresponds to the target second cluster. The first node can establish an association relationship between the first cluster and a target second cluster, where the target second cluster is allowed to apply for a resource from the first cluster.
1. A resource allocation method, wherein the method comprises:
determining, by a first node, a hash value corresponding to a first cluster;
obtaining, by the first node, a hash ring, wherein the hash ring comprises at least one hash value interval, and each hash value interval corresponds to one second cluster;
determining, by the first node, that the hash value corresponding to the first cluster belongs to a target hash value interval of the at least one hash value interval;
determining, by the first node, a second cluster corresponding to the target hash value interval as a target second cluster;
and
establishing, by the first node, an association relationship between the first cluster and the target second cluster, wherein the target second cluster is allowed to apply for a resource from the first cluster.
2. The method according to claim 1 , wherein the hash ring comprises a first hash node and a second hash node, the first hash node corresponds to the target second cluster, the first hash node is an adjacent successor node of the second hash node on the hash ring, and the target hash value interval is between a hash value of the first hash node and a hash value of the second hash node.
3. The method according to claim 1 wherein the method further comprises:
dividing, by the first node, an idle cluster comprising a plurality of computing nodes to obtain a plurality of sub-clusters, wherein the first cluster is one of the plurality of sub-clusters.
4. The method according to claim 3 , wherein the plurality of sub-clusters comprise a third sub-cluster and a fourth sub-cluster, the third sub-cluster has a maximum idle resource amount in the plurality of sub-clusters, the fourth sub-cluster has a minimum idle resource amount in the plurality of sub-clusters, and an absolute value of a difference between an idle resource amount of the third sub-cluster and an idle resource amount of the fourth sub-cluster is less than a first threshold.
5. The method according to claim 3 , wherein an absolute value of a difference between an idle resource amount of each of the plurality of sub-clusters and a preset idle resource amount is less than or equal to a second threshold, and the preset idle resource amount is related to a historical requested resource amount.
6. The method according to claim 1 , wherein the method further comprises:
receiving, by the first node, a first resource borrowing request sent by the target second cluster, wherein the first resource borrowing request comprises task data and an identifier of the first cluster; and
sending, by the first node, the task data to the first cluster based on the identifier of the first cluster.
7. The method according to claim 1 , wherein the hash ring comprises Y hash nodes, each second cluster corresponds to at least one hash node, hash values corresponding to the Y hash nodes and the hash value corresponding to the first cluster are generated according to a same hash algorithm, and Y is a positive integer.
8. The method according to claim 1 , wherein obtaining, by the first node, the hash ring comprises:
determining, by the first node, Y hash values corresponding to X second clusters, wherein each second cluster corresponds to at least one hash value, X is a positive integer, and Y is a positive integer greater than or equal to X; and
generating, by the first node, the hash ring based on the Y hash values, wherein the hash ring comprises Y hash nodes, each second cluster corresponds to at least one hash node, the Y hash nodes divide the hash ring into Y hash value intervals, and each hash node corresponds to one hash value interval.
9. An apparatus for resource allocation, wherein the apparatus comprises:
at least one processor; and
one or more memories coupled to the at least one processor and storing programming instructions for execution by the at least one processor to:
determine a hash value corresponding to a first cluster;
obtain a hash ring, wherein the hash ring comprises at least one hash value interval, and each hash value interval corresponds to one second cluster;
determine that the hash value corresponding to the first cluster belongs to a target hash value interval of the at least one hash value interval;
determine a second cluster corresponding to the target hash value interval as a target second cluster;
and
establish an association relationship between the first cluster and the target second cluster, wherein the target second cluster is allowed to apply for a resource from the first cluster.
10. The apparatus according to claim 9 , wherein the hash ring comprises a first hash node and a second hash node, the first hash node corresponds to the target second cluster, the first hash node is an adjacent successor node of the second hash node on the hash ring, and the target hash value interval is between a hash value of the first hash node and a hash value of the second hash node.
11. The apparatus according to claim 9 , wherein the programming instructions are for execution by the at least one processor to:
divide an idle cluster comprising a plurality of computing nodes to obtain a plurality of sub-clusters, wherein the first cluster is one of the plurality of sub-clusters.
12. The apparatus according to claim 11 , wherein the plurality of sub-clusters comprise a third sub-cluster and a fourth sub-cluster, the third sub-cluster has a maximum idle resource amount in the plurality of sub-clusters, the fourth sub-cluster has a minimum idle resource amount in the plurality of sub-clusters, and an absolute value of a difference between an idle resource amount of the third sub-cluster and an idle resource amount of the fourth sub-cluster is less than a first threshold.
13. A computer-readable storage medium storing a program, wherein the program comprises instructions, and when the instructions are executed by a computer, cause the computer to perform operations comprising:
determining a hash value corresponding to a first cluster;
obtaining a hash ring, wherein the hash ring comprises at least one hash value interval, and each hash value interval corresponds to one second cluster;
determining that the hash value corresponding to the first cluster belongs to a target hash value interval of the at least one hash value interval;
determining a second cluster corresponding to the target hash value interval as a target second cluster;
and
establishing an association relationship between the first cluster and the target second cluster, wherein the target second cluster is allowed to apply for a resource from the first cluster.
14. The computer-readable storage medium according to claim 13 , wherein the hash ring comprises a first hash node and a second hash node, the first hash node corresponds to the target second cluster, the first hash node is an adjacent successor node of the second hash node on the hash ring, and the target hash value interval is between a hash value of the first hash node and a hash value of the second hash node.
15. The computer-readable storage medium according to claim 13 , wherein the operations further comprise:
dividing an idle cluster comprising a plurality of computing nodes to obtain a plurality of sub-clusters, wherein the first cluster is one of the plurality of sub-clusters.
16. The computer-readable storage medium according to claim 15 , wherein the plurality of sub-clusters comprise a third sub-cluster and a fourth sub-cluster, the third sub-cluster has a maximum idle resource amount in the plurality of sub-clusters, the fourth sub-cluster has a minimum idle resource amount in the plurality of sub-clusters, and an absolute value of a difference between an idle resource amount of the third sub-cluster and an idle resource amount of the fourth sub-cluster is less than a first threshold.
17. The computer-readable storage medium according to claim 15 , wherein an absolute value of a difference between an idle resource amount of each of the plurality of sub-clusters and a preset idle resource amount is less than or equal to a second threshold, and the preset idle resource amount is related to a historical requested resource amount.