Disaster recovery for split storage cluster

Patent metadata

Field	Value
Publication number	US-10534767-B2
Application number	US-201715458080-A
Country	US
Kind code	B2
Filing date	Mar 14, 2017
Priority date	Mar 14, 2017
Publication date	Jan 14, 2020
Grant date	Jan 14, 2020

Abstract

A method, computer program product and/or computer system assigns access to a quorum disk in a split-storage cluster environment when a communication link between storage systems fails. Access to the quorum disk is based on storage system I/O performance. Priority is given to the storage system that has a higher performance before the link failure. When the communication link fails, both storage systems attempt to access the quorum disk. If the system that first attempts to access the quorum disk is the non-priority storage system, a timer is started. If the priority system attempts to access the quorum disk within a predetermined time interval, the priority system locks the quorum disk and forms the cluster. If the priority system does not attempt to access the quorum disk within the predetermined time interval, the non-priority system locks the quorum disk and forms the cluster.

First claim

What is claimed is:

1. A method for assigning access to a quorum disk in a split-storage cluster environment, comprising:
recording, over a time interval, a first storage system input/output (I/O) usage, and a second storage system I/O usage;
determining that a communication link between the first storage system and the second storage system is not operative;
determining that the first storage system I/O usage, over the time interval, was greater than the second storage system I/O usage;
in response to determining that the first storage system I/O usage, over the time interval, was greater than the second storage system I/O usage, assigning a higher priority to the first storage system;
determining that the second storage system attempts to access a quorum disk before the first storage system attempts to access the quorum disk;
in response to determining that the second storage system attempts to access the quorum disk before the first storage system attempts to access the quorum disk, starting a timer;
determining that the first storage system does not access the quorum disk before the timer reaches a predetermined threshold; and
in response to determining that the first storage system does not access the quorum disk before the timer reaches the predetermined threshold, accessing and locking the quorum disk by the second storage system.

2. The method of claim 1 further comprising:
determining that the first storage system attempts to access the quorum disk before the second storage system attempts to access the quorum disk; and
in response to determining that the first storage system attempts to access the quorum disk before the second storage system attempts to access the quorum disk, accessing and locking the quorum disk by the first storage system.

3. The method of claim 2 wherein accessing and locking the quorum disk means:
gaining exclusive access to the quorum disk;
reading cluster information from the quorum disk; and
forming a cluster in accordance with the cluster information stored on the quorum disk.

4. The method of claim 1 wherein the term “not operative” means the communication link is operating at a performance level that is less than a minimum threshold performance level.

5. The method of claim 4 wherein the term “performance level” indicates at least one of the following:
rate of data transfer, where a greater rate of data transfer is a higher performance level;
latency, where a shorter latency is a higher performance level; and
rejection rate, where a lower rate of rejected service requests is a higher performance level.

6. A computer program product for assigning access to a quorum disk in a split-storage cluster environment comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising instructions to perform:
recording, over a time interval, a first storage system input/output (I/O) usage, and a second storage system I/O usage;
determining that a communication link between the first storage system and the second storage system is not operative;
determining that the first storage system I/O usage, over the time interval, was greater than the second storage system I/O usage;
in response to determining that the first storage system I/O usage, over the time interval, was greater than the second storage system I/O usage, assigning a higher priority to the first storage system;
determining that the second storage system attempts to access a quorum disk before the first storage system attempts to access the quorum disk;
in response to determining that the second storage system attempts to access the quorum disk before the first storage system attempts to access the quorum disk, starting a timer;
determining that the first storage system does not access the quorum disk before the timer reaches a predetermined threshold; and
in response to determining that the first storage system does not access the quorum disk before the timer reaches the predetermined threshold, accessing and locking the quorum disk by the second storage system.

7. The computer program product of claim 6 further comprising instructions to perform:
determining that the first storage system attempts to access the quorum disk before the second storage system attempts to access the quorum disk; and
in response to determining that the first storage system attempts to access the quorum disk before the second storage system attempts to access the quorum disk, accessing and locking the quorum disk by the first storage system.

8. The computer program product of claim 7 wherein accessing and locking the quorum disk means:
gaining exclusive access to the quorum disk;
reading cluster information from the quorum disk; and
forming a cluster in accordance with the cluster information stored on the quorum disk.

9. The computer program product of claim 6 wherein the term “not operative” means the communication link is operating at a performance level that is less than a minimum threshold performance level.

10. The computer program product of claim 9 wherein the term “performance level” indicates at least one of the following:
rate of data transfer, where a greater rate of data transfer is a higher performance level;
latency, where a shorter latency is a higher performance level; and
rejection rate, where a lower rate of rejected service requests is a higher performance level.

11. A computer system for assigning access to a quorum disk in a split-storage cluster environment comprising:
one or more computer processors;
one or more computer-readable storage media;
program instructions stored on the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising instructions to perform:
recording, over a time interval, a first storage system input/output (I/O) usage and a second storage system/usage;
determining that a communication link between the first storage system and the second storage system is not operative;
determining that the first storage system I/O usage over the time interval, was greater than the second storage system I/O usage;
in response to determining that the first storage system I/O usage, over the time interval, was greater than the second storage system I/O usage, assigning a higher priority to the first storage system;
determining that the second storage system attempts to access a quorum disk before the first storage system attempts to access the quorum disk;
in response to determining that the second storage system attempts to access the quorum disk before the first storage system attempts to access the quorum disk, starting a timer;
determining that the first storage system does not access the quorum disk before the timer reaches a predetermined threshold; and
in response to determining that the first storage system does not access the quorum disk before the timer reaches the predetermined threshold, accessing and locking the quorum disk by the second storage system.

12. The computer system of claim 11 further comprising instructions to perform:
determining that the first storage system attempts to access the quorum disk before the second storage system attempts to access the quorum disk; and
in response to determining that the first storage system attempts to access the quorum disk before the second storage system attempts to access the quorum disk, accessing and locking the quorum disk by the first storage system.

13. The computer system of claim 12 wherein accessing and locking the quorum disk means:
gaining ex

Assignees

• IBM

Inventors

• Cao Miao Ke
• Yin Wei
• Zhao Ning

Classifications

• G06F2201/825

  the problem or solution involving locking · CPC title

• G06F2201/81

  Threshold · CPC title

• G06F11/1469

  Backup restoration techniques · CPC title

• G06F11/1612 Primary

  where the redundant component is persistent storage · CPC title

• G06F16/275

  Synchronous replication · CPC title