Efficient queueing and scheduling of backups in a multi-tenant cloud computing environment

Patent metadata

Field	Value
Publication number	US-10831545-B2
Application number	US-201715690243-A
Country	US
Kind code	B2
Filing date	Aug 29, 2017
Priority date	Aug 29, 2016
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

Backups of workloads in a multi-tenant cloud computing environment are efficiently queued and scheduled. A method of backing up workloads for multiple tenants of a cloud computing system, includes the steps of determining a pool of workloads to be backed up during a time window, the workloads including workloads for a first tenant and workloads for a second tenant, placing a backup task for backing up each of the workloads in the pool in a scheduling queue and prioritizing the backup tasks according to backup parameters specified by the tenants, sizes of workload data to be backed up, and hardware constraints of a backup storage device executing the backups, and instructing the backup storage device to execute the backup tasks according to an order of the backup tasks in the scheduling queue.

First claim

What is claimed is:

1. A method of backing up workloads for multiple tenants of a computing system, comprising:
determining a pool of workloads to be backed up during a first time window, the workloads including workloads for a first tenant and workloads for a second tenant;
determining a predicted total backup time for each of the workloads based on a size of the workload data to be backed up and hardware constraints of a backup storage device executing the backups;
placing a backup task for backing up each of the workloads in the pool in a scheduling queue and prioritizing the backup tasks according to backup parameters specified by the tenants, sizes of workload data to be backed up, the predicted total backup times, and the hardware constraints of the backup storage device, wherein the backup parameters include a second time window separate from the first time window, the second time window being an alternative if backup during the first time window fails; and
instructing the backup storage device to execute the backup tasks according to an order of the backup tasks in the scheduling queue.

2. The method of claim 1 , wherein the backup parameters include an SLA violation cost and a first backup task for backing up a first workload is scheduled ahead of a second backup task for backing up a second workload if the SLA violation cost for the first workload is higher than the SLA violation cost for the second workload.

3. The method of claim 1 , wherein the size of the workload data to be backed up is less than a size of the entire workload.

4. The method of claim 1 , further comprising:
responsive to a request for the backup storage device to execute a special task, placing the special task in the scheduling queue behind other special tasks and ahead of all other backup tasks.

5. The method of claim 4 , wherein the special task, when executed by the backup storage device, restores a workload from a backup image of the workload.

6. The method of claim 4 , wherein the special task is a backup task that is designated to be carried out immediately.

7. A non-transitory computer readable medium comprising instructions to be executed in a computer for managing backups of workloads for multiple tenants of a computing system, wherein the instructions when executed in the computer cause the computer to carry out the steps of:
determining a pool of workloads to be backed up during a first time window, the workloads including workloads for a first tenant and workloads for a second tenant;
determining a predicted total backup time for each of the workloads based on a size of the workload data to be backed up and hardware constraints of a backup storage device executing the backups;
placing a backup task for backing up each of the workloads in the pool in a scheduling queue and prioritizing the backup tasks according to backup parameters specified by the tenants, sizes of workload data to be backed up, the predicted total backup times, and the hardware constraints of the backup storage device, wherein the backup parameters include a second time window separate from the first time window, the second time window being an alternative if backup during the first time window fails; and
instructing the backup storage device to execute the backup tasks according to an order of the backup tasks in the scheduling queue.

8. The non-transitory computer readable medium of claim 7 , wherein the backup parameters include an SLA violation cost and a first backup task for backing up a first workload is scheduled ahead of a second backup task for backing up a second workload if the SLA violation cost for the first workload is higher than the SLA violation cost for the second workload.

9. The non-transitory computer readable medium of claim 7 , wherein the size of the workload data to be backed up is less than a size of the entire workload.

10. The non-transitory computer readable medium of claim 7 , wherein the steps carried out by the computer further include:
responsive to a request for the backup storage device to execute a special task, placing the special task in the scheduling queue behind other special tasks and ahead of all other backup tasks.

11. The non-transitory computer readable medium of claim 10 , wherein the special task, when executed by the backup storage device, restores a workload from a backup image of the workload.

12. The non-transitory computer readable medium of claim 10 , wherein the special task is a backup task that is designated to be carried out immediately.

13. A computing system comprising:
a plurality of computers in each of which virtual machines are running, the virtual machines including virtual machines for a first tenant and virtual machines for a second tenant; and
a backup storage device configured to store backup images of the virtual machines for both the first tenant and the second tenant, wherein
one of the computers has running therein a data protection service that performs the steps of:
determining a pool of virtual machines to be backed up during a first time window, the pool of virtual machines including virtual machines for the first tenant and virtual machines for the second tenant;
determining a predicted total backup time for each of the virtual machines in the pool based on a size of the virtual machine data to be backed up and hardware constraints of a backup storage device executing the backups;
placing a backup task for backing up each of the virtual machines in the pool in a scheduling queue and prioritizing the backup tasks according to backup parameters specified by the tenants, sizes of virtual machine data to be backed up, the predicted total backup times, and the hardware constraints of the backup storage device, wherein the backup parameters include a second time window separate from the first time window, the second time window being an alternative if backup during the first time window fails; and
instructing the backup storage device to execute the backup tasks according to an order of the backup tasks in the scheduling queue.

14. The computing system of claim 13 , wherein the backup storage device is configured to perform deduplication of all data stored thereby, including virtual machine data of the first tenant and virtual machine data of the second tenant.

15. The computing system of claim 13 , wherein the data protection service runs in one the virtual machines.

16. The computing system of claim 13 , wherein one of the virtual machines operates as a backup agent for preparing virtual machine data to be backed up.

17. The computing system of claim 16 , wherein the size of the virtual machine data to be backed up is less than a size of the entire virtual machine.

18. The computing system of claim 13 , wherein the steps performed by the data protection service include:
responsive to a request for the backup storage device to execute a special task, placing the special task in the scheduling queue behind other special tasks and ahead of all other backup tasks.

Assignees

• Vmware Inc

Inventors

• Rao Kotha Venu Gopala
• NAIK Pooja
• CHATHOTH Sureshbabu Koyadan
• Thakkar Sachin
• Basak Debashis

Classifications

• G06F9/5038 Primary

  considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration (scheduling strategies G06F9/4881 and subgroups) · CPC title

• G06F11/1451 Primary

  by selection of backup contents · CPC title

• G06F16/182

  Distributed file systems · CPC title

• G06F9/45558

  Hypervisor-specific management and integration aspects · CPC title

• G06F9/461

  Saving or restoring of program or task context · CPC title