Dynamically meeting slas without provisioning static capacity
View Patent ↗In one example, a method for identifying and allocating resources in a computing system, including checking, while one or more backup processes are running, database connections in an auto scaling group to determine if a number of database connections in use in connection with the backup processes has decreased since a prior check was performed. When the number of database connections in use has decreased, an identification is made as to which of a plurality of queues each respectively associated with one of the backup processes has the greatest need for additional database connections. Next, various metrics are evaluated and, based on the evaluation of the metrics, one or more available database connections are assigned to the queue with the greatest need for additional database connections.
1. A method for identifying and allocating resources in a computing system, the method comprising:
checking, while one or more backup processes are running, database connections in an auto scaling group to determine if a number of database connections in use in connection with the backup processes has decreased since a prior check was performed;
when the number of database connections in use has decreased, identifying which of a plurality of queues each respectively associated with one of the backup processes has the greatest need for additional database connections;
evaluating a plurality of metrics; and
based on the evaluation of the metrics, assigning one or more available database connections to the queue with the greatest need for additional database connections.
2. The method as recited in claim 1 , wherein the metrics include any one or more of a maximum number of database connections included in the auto scaling group, a total number of messages in each queue, and a burn down rate for each queue.
3. The method as recited in claim 1 , wherein the auto scaling group is specific to a particular object type.
4. The method as recited in claim 3 , wherein the object type is one of mail, documents, contacts, or calendars.
5. The method as recited in claim 1 , wherein each queue includes one or more messages, and each message identifies a user and an object type.
6. The method as recited in claim 1 , wherein each backup process is specific to one particular object type.
7. The method as recited in claim 1 , wherein a first backup process is an on-demand backup process, a second backup process is a scheduled backup, and a third backup process is an on-board backup.
8. A non-transitory storage medium having stored therein computer-executable instructions which, when executed by one or more hardware processors, identifies and allocates resources in a computing system by performing the following:
checking, while one or more backup processes are running, database connections in an auto scaling group to determine if a number of database connections in use in connection with the backup processes has decreased since a prior check was performed;
when the number of database connections in use has decreased, identifying which of a plurality of queues each respectively associated with one of the backup processes has the greatest need for additional database connections;
evaluating a plurality of metrics; and
based on the evaluation of the metrics, assigning one or more available database connections to the queue with the greatest need for additional database connections.
9. The non-transitory storage medium as recited in claim 8 , wherein the metrics include any one or more of a maximum number of database connections included in the auto scaling group, a total number of messages in each queue, and a burn down rate for each queue.
10. The non-transitory storage medium as recited in claim 8 , wherein the auto scaling group is specific to a particular object type.
11. The non-transitory storage medium as recited in claim 10 , wherein the object type is one of mail, documents, contacts, or calendars.
12. The non-transitory storage medium as recited in claim 8 , wherein each queue includes one or more messages, and each message identifies a user and an object type.
13. The non-transitory storage medium as recited in claim 8 , wherein each backup process is specific to one particular object type.
14. The non-transitory storage medium as recited in claim 8 , wherein a first backup process is an on-demand backup process, a second backup process is a scheduled backup, and a third backup process is an on-board backup.
15. A physical device, wherein the physical device comprises:
one or more hardware processors; and
the non-transitory storage medium as recited in claim 8 .
16. A method for backing up data in a computing system, the method comprising:
generating a list of authorized users;
identifying object types specified for backup by an authorized users;
creating a message for each user-object type combination;
creating a queue for each different object type, and populating each queue with user-object type combinations having an object type to the queue respectively corresponds;
receiving information indicating that one or more changes have occurred to user data of the specified object types;
performing a backup of the changes;
checking, while one or more backup processes are running, database connections in an auto scaling group to determine if a number of database connections in use in connection with the backup processes has decreased since a prior check was performed;
when the number of database connections in use has decreased, identifying which of a plurality of queues each respectively associated with one of the backup processes has the greatest need for additional database connections;
evaluating a plurality of metrics; and
based on the evaluation of the metrics, assigning one or more available database connections to the queue with the greatest need for additional database connections.
17. The method as recited in claim 16 , wherein the metrics include any one or more of a maximum number of database connections included in the auto scaling group, a total number of messages in each queue, and a burn down rate for each queue.
18. The method as recited in claim 16 , wherein the auto scaling group is specific to a particular object type.
19. The method as recited in claim 16 , wherein the object type is one of mail, documents, contacts, or calendars.
20. A non-transitory storage medium having stored therein computer-executable instructions which, when executed by one or more hardware processors, performs the method recited in claim 16 .