Preventing corruption by blocking requests

Patent metadata

Field	Value
Publication number	US-10514975-B2
Application number	US-201715830260-A
Country	US
Kind code	B2
Filing date	Dec 4, 2017
Priority date	Dec 5, 2016
Publication date	Dec 24, 2019
Grant date	Dec 24, 2019

Abstract

A method and system for managing communication connections in a virtualization environment implemented by a cluster of host machines, each of the host machines comprises a hypervisor, at least one user virtual machine (UVM), a connection manager, and an I/O controller. The system includes a virtual disk accessible by all of the I/O controllers and comprising a plurality of storage devices. The system includes a first host machine of the host machines designated as a leader node, wherein the leader node configured to confirm a second one of the host machines is unreachable; and transmit, in response to the confirmation, an update message to other host machines in the cluster. The update message identifies the unreachable host machine and causes the other host machines to block messages from the unreachable host machine and send an acknowledgement of the update message back to the leader node.

First claim

What is claimed is:

1. A system comprising:
a first host machine having programmed instructions to:
determine that a second host machine is unreachable;
request a third host machine to block requests from the second host machine upon determining that the second host machine is unreachable;
determine that the second host machine has become reachable; and
request the third host machine to stop blocking requests from the second host machine upon determining that the second host machine has become reachable.

2. The system of claim 1 , wherein after the first host machine determines that the second host machine is unreachable and the second host machine does not receive a response from the third host machine to a message sent by a virtual machine on the second host machine, the virtual machine on the second host machine suspends an operation for a predetermined period of time.

3. The system of claim 2 , wherein the virtual machine resumes operation on the second host machine after the response is received from the third host machine.

4. The system of claim 2 , wherein the virtual machine, after expiration of the predetermined period of time, again sends the message to the third host machine.

5. The system of claim 1 , wherein after the first host machine determines that the second host machine is unreachable, a virtual machine on the second host machine is transferred to a new host machine to perform an operation terminated on the second host machine.

6. The system of claim 1 , wherein the first host machine requests the third host machine to block requests from the second host machine by sending an update message to the third host machine identifying the second host machine.

7. The system of claim 6 , wherein the third host machine, upon receiving the update message, transmits an acknowledgment to the first host machine.

8. The system of claim 1 , wherein the first host machine determines that the second host machine is unreachable by transmitting an echo-request to the second host machine, and failing to receive an echo-response from the second host machine within a predetermined amount of time.

9. The system of claim 1 , wherein the first host machine determines that the second host machine has become reachable by transmitting an echo-request to the second host machine and receiving an echo-response from the second host machine within a predetermined amount of time.

10. The system of claim 1 , wherein the first host machine requests a third host machine block communication to the second host machine upon determining that the second host machine is unreachable.

11. A method comprising:
determining, by a first host machine, that a second host machine is unreachable;
requesting, by the first host machine, a third host machine to block requests from the second host machine upon determining that the second host machine is unreachable;
determining, by the first host machine, that the second host machine has become reachable; and
requesting, by the first host machine, the third host machine to stop blocking requests from the second host machine upon determining that the second host machine has become reachable.

12. The method of claim 11 , wherein the second host machine is unreachable due to a failure of a hypervisor or a corruption of the hypervisor of the second host machine.

13. The method of claim 11 , further comprising:
sending, by the first host machine, an update message to the third host machine identifying the second host machine for requesting the third host machine to block requests from the second host machine; and
receiving, by the first host machine, an acknowledgment back from the third host machine confirming the blocking of requests from the second host machine.

14. The method of claim 11 , wherein after the first host machine determines that the second host machine is unreachable and the second host machine does not receive a response from the third host machine to a message sent by a virtual machine on the second host machine, the virtual machine on the second host machine suspends an operation for a predetermined period of time.

15. The method of claim 11 , wherein after the first host machine determines that the second host machine is unreachable, a virtual machine on the second host machine is transferred to a new host machine, and wherein an operation of the virtual machine that was terminated on the second host machine is resumed on the new host machine.

16. The method of claim 11 , further comprising determining, by the first host machine, that the second host machine is unreachable by transmitting an echo-request to the second host machine, and not receiving an echo-response from the second host machine within a predetermined amount of time.

17. The method of claim 11 further comprising determining, by the first host machine, that the second host machine has become reachable by transmitting an echo-request to the second host machine and receiving an echo-response back from the second host machine within a predetermine amount of time.

18. The method of claim 11 , wherein the first host machine is a leader node in a cluster.

19. The method of claim 11 , wherein the third host machine identifies an IP address of the second host machine for blocking requests from the second host machine.

20. The method of claim 11 , further comprising requesting a third host machine block communication to the second host machine upon determining that the second host machine is unreachable.

21. A non-transitory computer readable media having computer-executable instructions embodied thereon that, when executed by a processor cause the processor to perform a process comprising:
determining that a first host machine is unreachable;
requesting a second host machine to block requests from the first host machine upon determining that the first host machine is unreachable;
determining that the first host machine has become reachable; and
requesting the second host machine to stop blocking requests from the first host machine upon determining that the first host machine has become reachable.

22. The non-transitory computer readable media of claim 21 , further comprising:
sending a first message to the first host machine and determining that the first host machine is unreachable upon not receiving a response from the first host machine to the first message within a first predetermined period of time; and
sending a second message to the second host machine upon determining that the first host machine is unreachable for requesting the blocking of requests from the first host machine to the second host machine.

23. The non-transitory computer readable media of claim 21 , further comprising determining that the second host machine is unreachable by transmitting an echo-request to the second host machine, and not receiving an echo-response from the second host machine within a predetermined amount of time.

24. The non-transitory computer readable media of claim 21 , further comprising determining, by the first host machine, that the second host machine has become reachable by transmitting an echo-request to the second host machine and receiving an echo-response back from the second host machine within a predetermine amount of time.

25. A non-transitory computer readable media having computer-executable instructions embodied thereon that, when executed by a processor cause the processor to perform a process comprising:

Assignees

• Nutanix Inc

Inventors

• Smith Gregory A
• Grobman Igor
• Cui Miao

Classifications

• H04L41/0677

  Localisation of faults · CPC title

• G06F11/0712

  in a virtual computing platform, e.g. logically partitioned systems · CPC title

• G06F11/0727

  in a storage system, e.g. in a DASD or network based storage system (drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097) · CPC title

• G06F2009/45579

  I/O management, e.g. providing access to device drivers or storage · CPC title

• G06F11/0793

  Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40) · CPC title