Proactive resource reservation for protecting virtual machines

Patent metadata

Field	Value
Publication number	US-9846611-B2
Application number	US-201615076341-A
Country	US
Kind code	B2
Filing date	Mar 21, 2016
Priority date	Aug 24, 2012
Publication date	Dec 19, 2017
Grant date	Dec 19, 2017

Abstract

A system for proactive resource reservation for protecting virtual machines. The system includes a cluster of hosts, wherein the cluster of hosts includes a master host, a first slave host, and one or more other slave hosts, and wherein the first slave host executes one or more virtual machines thereon. The first slave host is configured to identify a failure that impacts an ability of the one or more virtual machines to provide service, and calculate a list of impacted virtual machines. The master host is configured to receive a request to reserve resources on another host in the cluster of hosts to enable the impacted one or more virtual machines to failover, calculate a resource capacity among the cluster of hosts, determine whether the calculated resource capacity is sufficient to reserve the resources, and send an indication as to whether the resources are reserved.

First claim

What is claimed is:

1. A system comprising:
a cluster of hosts, the cluster of hosts comprising a master host, a first slave host, and one or more other slave hosts, wherein the first slave host executes one or more software application instances thereon; and
wherein the first slave host is configured to identify, from the one or more software application instances, a list of software application instances whose ability to provide service is impacted by a failure;
wherein the master host is configured to:
receive, from the first slave host, a request to reserve resources on another host in the cluster of hosts to enable the impacted one or more software application instances to failover;
calculate a resource capacity among the cluster of hosts;
determine whether the calculated resource capacity is sufficient to reserve the resources; and
send, to the first slave host, an indication as to whether the resources are reserved for each of the impacted one or more software application instances.

2. The system of claim 1 , further comprising a datastore, and wherein the failure is the datastore becoming inaccessible due to an All Paths Down (APD) failure.

3. The system of claim 1 , wherein determining whether the calculated resource capacity is sufficient to reserve the resources comprises:
allocating capacity for failed software application instances; and
determining whether sufficient resource capacity is available for the impacted one or more software application instances after allocating capacity for the failed software application instances.

4. The system of claim 2 , wherein the first slave host is further configured to, upon determining that sufficient resource capacity is not available to reserve the resources, re-send the request to reserve resources to the master host until one of the following occurs: sufficient capacity for the resources becomes available, until the APD failure has cleared, or a user indicates that the impacted one or more software application instances are no longer protected.

5. The system of claim 1 , wherein the master host is further configured to:
upon determining that sufficient resource capacity is not available to reserve the resources, request a distribution resource scheduler to defragment the cluster of hosts; and
determine whether sufficient resource capacity is available for the impacted one or more software application instances.

6. The system of claim 1 , wherein sending, to the first slave host, an indication as to whether the resources are reserved for each of the impacted one or more software application instances comprises sending an indication that the requested resources are reserved, and wherein the master host is further configured to restart the impacted one or more software application instances after reserving the requested resources.

7. The system of claim 1 , wherein the list of impacted software application instances from the one or more software application instances executed on the first slave host comprises a plurality of impacted software application instances, and wherein the plurality of impacted software application instances are batched to minimize a cost of a computation of resource capacity performed by the master host.

8. A method comprising:
receiving, from a first slave host, a request to reserve resources on a plurality of other hosts to enable one or more software application instances, executed on the first slave host and impacted by a failure, to failover;
calculating a resource capacity among the plurality of other hosts;
determining whether the calculated resource capacity is sufficient to reserve the resources; and
sending, to the first slave host, an indication as to whether the resources are reserved for each of the impacted one or more software application instances.

9. The method of claim 8 , wherein the failure is a datastore becoming inaccessible due to an All Paths Down (APD) failure.

10. The method of claim 8 , wherein determining whether the calculated resource capacity is sufficient to reserve the resources comprises:
allocating capacity for failed software application instances; and
determining whether sufficient resource capacity is available for the impacted one or more software application instances after allocating capacity for the failed software application instances.

11. The method of claim 9 , further comprising:
upon determining that sufficient resource capacity is not available to reserve the resources, keeping the request to reserve resources in a queue until one of the following occurs: sufficient capacity for the resources becomes available, until the APD failure has cleared, or a user indicates that the impacted one or more software application instances are no longer protected; or
upon determining that sufficient resource capacity is not available to reserve the resources, defragmenting the plurality of other hosts and determine whether sufficient resource capacity is available for the impacted one or more software application instances after defragmenting the plurality of hosts.

12. The method of claim 8 , further comprising, upon determining that sufficient resource capacity is not available to reserve the resources, relocating one or more software application instances on a second host of the plurality of other hosts to a third host of the plurality of other hosts to create sufficient resource capacity on the second host for the impacted one or more software application instances.

13. The method of claim 8 , wherein sending an indication as to whether the resources are reserved for each of the impacted one or more software application instances comprises:
sending an indication that the requested resources are reserved; and
restarting the impacted one or more software application instances after reserving the requested resources.

14. The method of claim 13 , wherein the request to reserve resources on a plurality of other hosts is considered based on a priority applied to the request, and wherein the impacted one or more software application instances are restarted based on a priority of the impacted one or more software application instances.

15. At least one computer-readable storage medium having computer-executable instructions embodied thereon, wherein, when executed by at least one processor, the computer-executable instructions cause the at least one processor to:
receive, from a first slave host, a request to reserve resources on a plurality of other hosts to enable one or more software application instances, executed on the first slave host and impacted by a failure, to failover;
calculate a resource capacity among the plurality of other hosts;
determine whether the calculated resource capacity is sufficient to reserve the resources; and
send, to the first slave host, an indication as to whether the resources are reserved for each of the impacted one or more software application instances.

16. The at least one computer-readable storage medium of claim 15 , wherein the failure is a datastore becoming inaccessible due to an All Paths Down failure.

17. The at least one computer-readable storage medium of claim 15 , wherein determining whether the calculated resource capacity is sufficient to reserve the resources comprises:
allocating capacity for failed software application instances; and
determining whether sufficient resource capacity is available for the impacted one or more software application instances after allocating capacity for the failed software application instances.

18. The at least one computer-readable

Assignees

• Vmware Inc

Inventors

• Ren Joanne
• Farkas Keith
• Ziskind Elisha
• Tarashansky Igor
• Krishnan Manoj

Classifications

• G06F9/45558 Primary

  Hypervisor-specific management and integration aspects · CPC title

• G06F11/2069

  Management of state, configuration or failover · CPC title

• G06F11/1484

  involving virtual machines · CPC title

• G06F2009/45591

  Monitoring or debugging support · CPC title

• G06F11/2033

  switching over of hardware resources · CPC title