Granted Patent B2

US 11,150,832 · App. 16/586,863 · Granted Oct 19, 2021

Inventors: Andy Ke (Chengdu, CN); Rita Li (Chengdu, CN)

Assignee: EMC IP HOLDING COMPANY LLC

G06F3/065G06F3/0608G06F3/0619G06F3/0673G06F11/1461

Abstract

Claims (58)

1. A method for backup management, comprising:

receiving at a computing device an initial set of data items associated with a plurality of historical data backup operations, a candidate data item in the initial set of data items indicating a data amount and time consumption associated with a corresponding historical data backup operation;

determining, by the computing device, from the initial set of data items:

a first data item and a second data item associated with the candidate data item, a second data amount indicated by the first data item being less than or equal to a first data amount indicated by the candidate data item, and a third data amount indicated by the second data item being greater than or equal to the first data amount;

a first change in the time consumption per unit data amount based on the candidate data item and the first data item;

a second change in the time consumption per unit data amount based on the candidate data item and the second data item; and

a degree of change based on the first change and the second change;

removing the candidate data item from the initial set of data items based on the degree of change to generate a reference set of data items; and

storing the reference set of data items for predicting time consumption of a future data backup operation.

2. The method according to claim 1 , wherein removing the candidate data item from the initial set of data items comprises:

comparing, by the computing device, the degree of change with a predetermined change threshold; and

in response to the degree of change being less than the predetermined change threshold, removing the candidate data item from the initial set of data items.

3. The method according to claim 2 , wherein the initial set of data items are organized into at least one group, and wherein removing the candidate data item from the initial set of data items comprises:

determining, by the computing device, a group change threshold corresponding to a group including the candidate data item;

comparing the degree of change to the group change threshold; and

in response to the degree of change being less than the group change threshold, removing the candidate data item from the initial set of data items.

4. The method according to claim 2 , wherein the initial set of data items are organized into a plurality of groups, and the method further comprises:

in response to receiving a new data item, updating, by the computing device, the plurality of groups such that a difference in a number of data items between any pair of groups of the plurality of groups is less than a predetermined number threshold.

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

in response to a data backup operation performed by the computing device, determining at least one reference data item corresponding to a target data amount of the data backup operation from the reference set of data items; and

determining predicted time consumption to perform the data backup operation based on a data amount and time consumption indicated by the at least one reference data item.

6. The method according to claim 5 , wherein determining the at least one reference data comprises:

determining whether there is a first reference data item in the reference set of data items, the first reference data item indicating a same data amount as the target data amount; and

in response to existence of the first reference data item, determining the first reference data item as the reference data item corresponding to the target data amount.

7. The method according to claim 6 , wherein determining the at least one reference data comprises:

in response to absence of the first reference data item, determining, by the computing device, from the reference set of data items, a second reference data item and a third reference data item as at least one reference data item, wherein both a difference between a first data amount indicated by the second reference data item and the target data amount and a difference between a second data amount indicated by the third reference data item and the target data amount are less than a predetermined threshold.

8. The method according to claim 5 , wherein the at least one reference data item comprises at least two reference data items, and wherein determining the predicted consumption comprises:

determining, by the computing device, the predicted time consumption based on a linear fit of the at least two reference data items and the target data amount.

9. A device for backup management, comprising:

at least one processing unit; and

at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform acts comprising:

obtaining an initial set of data items associated with a plurality of historical data backup operations, a candidate data item in the initial set of data items indicating a data amount and time consumption associated with a corresponding historical data backup operation;

determining from the initial set of data items:

a first data item and a second data item associated with the candidate data item, a second data amount indicated by the first data item being less than or equal to a first data amount indicated by the candidate data item, and a third data amount indicated by the second data item being greater than or equal to the first data amount;

a first change in the time consumption per unit data amount based on the candidate data item and the first data item;

a second change in the time consumption per unit data amount based on the candidate data item and the second data item; and

a degree of change based on the first change and the second change;

removing the candidate data item from the initial set of data items based on the degree of change to generate a reference set of data items; and

storing the reference set of data items for predicting time consumption of a future data backup operation.

10. The device according to claim 9 , wherein removing the candidate data item from the initial set of data items comprises:

comparing the degree of change with a predetermined change threshold; and

in response to the degree of change being less than the predetermined change threshold, removing the candidate data item from the initial set of data items.

11. The device according to claim 10 , wherein the initial set of data items are organized into at least one group, and wherein removing the candidate data item from the initial set of data items comprises:

determining a group change threshold corresponding to a group including the candidate data item;

comparing the degree of change to the group change threshold; and

in response to the degree of change being less than the group change threshold, removing the candidate data item from the initial set of data items.

12. The device according to claim 10 , wherein the initial set of data items are organized into a plurality of groups, and the acts further comprise:

in response to receiving a new data item, updating the plurality of groups such that a difference in a number of data items between any pair of groups of the plurality of groups is less than a predetermined number threshold.

13. The device according to claim 9 , the acts further comprise:

in response to a data backup operation to be performed, determining at least one reference data item corresponding to a target data amount of the data backup operation from a reference set of data items; and

determining predicted time consumption to perform the data backup operation based on a data amount and time consumption indicated by the at least one reference data item.

14. The device according to claim 13 , wherein determining the at least one reference data comprises:

determining whether there is a first reference data item in the reference set of data items, the first reference data item indicating a same data amount as the target data amount; and

in response to existence of the first reference data item, determining the first reference data item as a reference data item corresponding to the target data amount.

15. The device according to claim 14 , wherein determining the at least one reference data comprises:

in response to absence of the first reference data item, determining, from the reference set of data items, a second reference data item and a third reference data item as at least one reference data item, wherein both a difference between a first data amount indicated by the second reference data item and the target data amount and a difference between a second data amount indicated by the third reference data item and the target data amount are less than a predetermined threshold.

16. The device according to claim 13 , wherein the at least one reference data item comprises at least two reference data items, and wherein determining the predicted consumption comprises:

determining the predicted time consumption based on a linear fit of the at least two reference data items and the target data amount.

Assignments (9)

Priority Claims (1)

Continuity (1)