Queue management in multi-site storage systems

Patent metadata

Field	Value
Publication number	US-11079968-B1
Application number	US-202016796983-A
Country	US
Kind code	B1
Filing date	Feb 21, 2020
Priority date	Feb 21, 2020
Publication date	Aug 3, 2021
Grant date	Aug 3, 2021

Abstract

A computer-implemented method to identify redundant Input/Output (I/O) queues in a multi-site storage system. The method includes receiving, from a host, by a backup storage system, a request to process a first set of Input/Output (I/O) queues, wherein the backup storage system is a second subsystem in a multi-site storage system. The method includes, allocating memory on the backup storage system. The method includes, identifying a second set of I/O queues established at a primary storage system, a first subsystem in the multi-site storage system. The method includes, determining the first set of I/O queues and the second set of I/O queues are redundant. The method includes, responsive to determining queues are redundant: notifying via the host, that the first set of the redundancy, terminating a connection between the host and the backup storage system, and de-allocating the memory to process the first set of I/O queues.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, from a host, by a backup storage system, a request to process a first set of Input/Output (I/O) queues on the backup storage system, wherein the backup storage system is a second subsystem in a multi-site storage system;
allocating memory on the backup storage system for processing the first set of I/O queues;
identifying a second set of I/O queues established at a primary storage system, wherein the primary storage system is a first subsystem in the multi-site storage system and the backup storage system includes a backup copy of data stored on the primary storage system;
determining the first set of I/O queues are redundant, wherein the first set of I/O queues are redundant when the first set of I/O queues and the second set of I/O queues process an equivalent set of commands, as included in the request;
responsive to determining that the first set of I/O queues are redundant:
notifying via the host, that the first set of I/O queues are redundant;
terminating a connection between the host and the backup storage system; and
de-allocating the memory to process the first set of I/O queues.

2. The method of claim 1 further comprising:
monitoring processing of the second set of I/O queues;
determining a failure of the primary storage system;
notifying the host of the failure of the primary storage system;
in response to determining the failure of the primary storage system, re-establishing the connection between the host and the backup storage system and re-allocating the memory to the second set of I/O queues on the backup storage system; and
processing the second set of I/O queues on the backup storage system.

3. The method of claim 1 , wherein the host, the primary storage system, and the backup storage system use a non-volatile memory express (NVMe) protocol.

4. The method of claim 3 , wherein the notifying occurs via an asynchronous event request through an NVMe qualified name (NQN) connection.

5. The method of claim 1 , further comprising:
receiving, from the host, a second request to process the first set of I/O queues;
determining the request includes an override flag;
processing, in response to the determining that the request includes the override flag, the first set of I/O queues on the backup storage system.

6. The method of claim 1 , wherein the notifying occurs via an out-of-band communications.

7. The method of claim 6 , wherein the out of band communication includes an application programming interface call.

8. The method of claim 1 , wherein the primary storage system and the backup storage system are included in a disaster recovery system.

9. The method of claim 8 , wherein the disaster recovery system syncs data between the primary storage system and the backup storage system.

10. A system comprising:
a processor; and
a computer-readable storage medium communicatively coupled to the processor and storing program instructions which, when executed by the processor, are configured to cause the processor to:
receive, from a host, by a backup storage system, a request to process a first set of Input/Output (I/O) queues on the backup storage system, wherein the backup storage system is a second subsystem in a multi-site storage system;
allocate memory on the backup storage system for processing the first set of I/O queues;
identify a second set of I/O queues established at a primary storage system, wherein the primary storage system is a first subsystem in the multi-site storage system and the backup storage system includes a backup copy of data stored on the primary storage system;
determine the first set of I/O queues are redundant, wherein the first set of I/O queues are redundant when the first set of I/O queues and the second set of I/O queues process an equivalent set of commands, as included in the request;
responsive to determining that the first set of I/O queues are redundant:
notify via the host, that the first set of I/O queues are redundant;
terminate a connection between the host and the backup storage system; and
de-allocate the memory to process the first set of I/O queues.

11. The system of claim 10 , wherein the program instructions are further configured to cause the processor to:
monitor processing of the second set of I/O queues;
determine, a failure of the primary storage system;
notify the host of the failure of the primary storage system;
re-establish, in response to determining the failure of the primary storage system, the connection between the host and the backup storage system and re-allocate the memory to the second set of I/O queues on the backup storage system; and
process the second set of I/O queues on the backup storage system.

12. The system of claim 10 , wherein the host, the primary storage system, and the backup storage system use a non-volatile memory express (NVMe) protocol.

13. The system of claim 10 , wherein the program instructions are further configured to cause the processor to:
receive, from the host, a second request to process the first set of I/O queues;
determine, the request includes an override flag;
process, in response to determining the request includes the override flag, the first set of I/O queues on the backup storage system.

14. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing unit to cause the processing unit to:
receive, from a host, by a backup storage system, a request to process a first set of Input/Output (I/O) queues on the backup storage system, wherein the backup storage system is a second subsystem in a multi-site storage system;
allocate memory on the backup storage system for processing the first set of I/O queues;
identify a second set of I/O queues established at a primary storage system, wherein the primary storage system is a first subsystem in the multi-site storage system and the backup storage system includes a backup copy of data stored on the primary storage system;
determine the first set of I/O queues are redundant, wherein the first set of I/O queues are redundant when the first set of I/O queues and the second set of I/O queues process an equivalent set of commands, as included in the request;
responsive to determining that the first set of I/O queues are redundant:
notify via the host, that the first set of I/O queues are redundant;
terminate a connection between the host and the backup storage system; and
de-allocate the memory to process the first set of I/O queues.

15. The computer program product of claim 14 , wherein the program instructions are further configured to cause the processing unit to:
monitor processing of the second set of I/O queues;
determine, a failure of the primary storage system;
notify the host of the failure of the primary storage system;
re-establish, in response to determining the failure of the primary storage system, the connection between the host and the backup storage system and re-allocate the memory to the second set of I/O queues on the backup storage system; and
process the second set of I/O queues on the backup storage system.

16. The computer program product of claim 14 , wherein the host, the primary storage system, and the backup storage system use a non-volatile memory express (NVMe) protocol.

17. The computer program product of claim 14 , wherein the program instructions are further configured to cause the processing unit to:
receive, fro

Assignees

• IBM

Inventors

• Patel Kushal
• Roy Subhojit
• Patel Sarvesh S

Classifications

• G06F11/2048

  where the redundant components share neither address space nor persistent storage · CPC title

• G06F11/2038

  with a single idle spare processing component · CPC title

• G06F11/2025

  using centralised failover control functionality · CPC title

• G06F3/0617

  in relation to availability · CPC title

• G06F3/061 Primary

  Improving I/O performance · CPC title