Method, electronic device and computer program product for load balance
Embodiments of the present disclosure provide a method, an electronic device and a computer program product for load balance. The method comprises: determine, in a round robin period, backup quota ratios for a plurality of servers used for data backup and associated with a cloud service platform; select, based on the backup quota ratios, one server from the plurality of servers; and in response to receiving a request for backup of data from an application on the cloud service platform, cause the backup of the data from the application to the selected server. In this way, load balance for a plurality of backup servers associated with a cloud service platform is achieved.
1. A method for load balance, comprising:
determining, in a round robin period, backup quota ratios for a plurality of servers used for data backup and associated with a cloud service platform, wherein determining backup quota ratios comprises:
calculating a weight value of each server based on a number of registered clients, free capacity, performance of a server rack, and a load index, and
rounding up and simplifying the weight value, wherein for each server, each backup quota ratio indicates a proportional relationship of a number of times each of the plurality of servers is allocated to an application on the cloud service platform in the round robin period;
selecting, based on the backup quota ratios, a server from the plurality of servers;
in response to receiving a request for backup of data from an application on the cloud service platform, causing the backup of the data from the application to the selected server;
updating, after the round robin period ends, the backup quota ratios for the plurality of servers, for subsequent backup of application data; and
storing, in a mapping table, an association between the application and the selected server for the backup.
2. The method of claim 1 , wherein determining the backup quota ratios for the plurality of servers in the round robin period comprises:
obtaining metadata of the plurality of servers, the metadata describing attributes of the plurality of servers; and
determining, based on a statistical model, the backup quota ratios with the metadata as an input, the statistical model being trained to describe associations between different values of the metadata and different backup quota ratios.
3. The method of claim 2 , wherein the attributes comprise at least one of:
the number of registered clients, free capacity, performance of a server rack, a load index, backup window duration and an increasing rate of a storage space occupancy.
4. The method of claim 2 , wherein the statistical model is generated based on an analytic hierarchy process, and wherein the analytic hierarchy process generates a dimension coefficient index RI.
5. The method of claim 4 , wherein a standard weight of the statistical model is based on the dimension coefficient index RI and a maximum eigenvalue, the dimension coefficient index RI being determined based on a matrix dimension of a standard matrix of the statistical model.
6. The method of claim 1 , wherein the round robin period is determined based on one of:
a predetermined time period;
the number of data backup operations performed by at least some of the plurality of servers,
free capacity of at least some of the plurality of servers; and
increasing rates of storage space occupancies of at least some of the plurality of servers.
7. The method of claim 1 , wherein the performance of the server rack is based on a total rack size of each server.
8. The method of claim 1 , wherein the load index represents a load of each server and is based on a total number of tasks that each server has performed in a past period of time.
9. An electronic device, comprising:
at least one processor; and
a memory coupled to the at least one processor, the memory including instructions stored therein, the instructions, when executed by the at least one processor, causing the device to perform acts, the acts comprising:
determining, in a round robin period, backup quota ratios for a plurality of servers used for data backup and associated with a cloud service platform, wherein determining backup quota ratios comprises:
calculating a weight value of each server based on a number of registered clients, free capacity, performance of a server rack, and a load index, and
rounding up and simplifying the weight value, wherein for each server, each backup quota ratio indicates a proportional relationship of a number of times each of the plurality of servers is allocated to an application on the cloud service platform in the round robin period;
selecting, based on the backup quota ratios, a server from the plurality of servers;
in response to receiving a request for backup of data from an application on the cloud service platform, causing the backup of the data from the application to the selected server;
updating, after the round robin period ends, the backup quota ratios for the plurality of servers, for subsequent backup of application data; and
storing, in a mapping table, an association between the application and the selected server for the backup.
10. The device of claim 9 , wherein determining the backup quota ratios for the plurality of servers in the round robin period comprises:
obtaining metadata of the plurality of servers, the metadata describing attributes of the plurality of servers; and
determining, based on a statistical model, the backup quota ratios with the metadata as an input, the statistical model being trained to describe an association between different values of the metadata and different backup quota ratios.
11. The device of claim 10 , wherein the attributes comprise at least one of:
the number of registered clients, free capacity, performance of a server rack, a load index, backup window duration and an increasing rate of a storage space occupancy.
12. The device of claim 9 , wherein the round robin period is determined based on one of the following factors:
a predetermined time period;
the number of data backup operations performed by at least some of the plurality of servers;
free capacity of at least some of the plurality of servers; and
increasing rates of storage space occupancies of at least some of the plurality of servers.
13. A computer program product tangibly stored on a non-transitory computer readable medium and comprising machine executable instructions that, when executed, cause a device to:
determine, in a round robin period, backup quota ratios for a plurality of servers used for data backup and associated with a cloud service platform, wherein to determine the backup quota ratios comprises:
calculating a weight value of each server based on a number of registered clients, free capacity, performance of a server rack, and a load index, and
rounding up and simplifying the weight value, wherein for each server, each backup quota ratio indicates a proportional relationship of a number of times each of the plurality of servers is allocated to an application on the cloud service platform in the round robin period;
select, based on the backup quota ratios, a server from the plurality of servers;
in response to receiving a request for backup of data from an application on the cloud service platform, cause the backup of the data from the application to the selected server;
update, after the round robin period ends, the backup quota ratios for the plurality of servers, for subsequent backup of application data; and
store, in a mapping table, an association between the application and the selected server for the backup.
14. The computer program product of claim 13 , wherein the machine executable instructions, when executed, cause the device to:
obtain metadata of the plurality of servers, the metadata describing attributes of the plurality of servers; and
determine, based on a statistical model, the backup quota ratios with the metadata as an input, the statistical model being trained to describe associations between different values of the metadata and different backup quota ratios.
15. The computer program product of claim 14 , wherein the attributes comprise at least one of: the number of registered clients, free capacity, performance of a server rack, a load index, backup window duration and an increasing rate of a storage space occupancy.
16. The computer program product of claim 13 , wherein the round robin period is determined based on one of:
a predetermined time period;
the number of data backup operations performed by at least some of the plurality of servers;
free capacity of at least some of the plurality of servers; and
increasing rates of storage space occupancies of at least some of the plurality of servers.