Centralized, quorum-aware handling of device reservation requests in a storage system

• US 10,719,265 B1
• Filed: 12/08/2017
• Issued: 07/21/2020
• Est. Priority Date: 12/08/2017
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Pure Storage, Inc.
• Inventors: Bernat, Andrew R., Inozemtsev, Grigori, McLeary, Iris, Scholbrock, Benjamin
• Primary Examiner(s): Hur, J. H.
• Application Number:
  US15/836,652
• Time in Patent Office: 956 Days
• Field of Search: None
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality
• CPC Class Codes: G06F 11/3055 Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available error or fault processing without redundancy G06F11/0703; error detection or correction by redundancy in data representation G06F11/08; error detection or correction by redundancy in operation G06F11/14; error detection or correction by redundancy in hardware G06F11/16
• CPC Class Codes: G06F 2201/80 Database-specific techniques
• CPC Class Codes: G06F 2201/88 Monitoring involving counting
• CPC Class Codes: G06F 3/0602 specifically adapted to achieve a particular effect
• CPC Class Codes: G06F 3/0607 by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0662 Virtualisation aspects
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G06F 8/654 using techniques specially adapted for alterable solid state memories, e.g. for EEPROM or flash memories

Abstract

A method for device reservations in a storage system, performed by the storage system is provided. The method includes maintaining a list of a plurality of storage devices of the storage system or slots for the storage devices, and a status of each of the plurality of storage devices or slots for the storage devices. The method includes determining whether granting a request for a reservation of one of the plurality of storage devices or slots would result in the storage system having less than a quorum of online storage devices, and granting or rejecting the reservation, based on the determining.

Claims

1. A method for device reservations in a storage system, performed by the storage system, comprising:

maintaining a list of a plurality of storage devices of the storage system or slots for the storage devices, and a status of each of the plurality of storage devices or slots for the storage devices;

determining whether granting a request for a reservation of one of the plurality of storage devices or slots would result in the storage system having less than a quorum of online storage devices, wherein the reservation causes a storage controller of the storage system to prevent other storage controllers of the storage system from accessing the one of the plurality of storage devices or slots, the quorum of online storage devices represented by a number of storage devices that are able to write and read user data using erasure coding; and

granting or rejecting the reservation, based on the determining.

2. The method of claim 1, further comprising:

communicating a disposable data structure to a requester of the reservation, for the granting the reservation; and

terminating the reservation, responsive to release of the data structure.

3. The method of claim 1, further comprising:

updating the list to indicate which one of the plurality of storage devices or slots is reserved, responsive to the granting of the reservation.

4. The method of claim 1, further comprising:

power cycling one of the plurality of storage devices, by a requester of the reservation, responsive to the granting of the reservation.

5. The method of claim 1, further comprising:

upgrading firmware of one of the plurality of storage devices, by a requester of the reservation, responsive to the granting of the reservation.

6. The method of claim 1, further comprising:

creating a disposable data structure that indicates which of the plurality of storage devices or slots is reserved, for the granting the reservation; and

storing the disposable data structure in a portion of memory reserved by a requester of the reservation, wherein the reservation terminates when the requester releases the portion of the memory.

7. A tangible, non-transitory, computer-readable media having instructions thereupon which, when executed by a processor, cause the processor to perform a method comprising:

indicating a status of online versus reserved for each of a plurality of storage devices of a storage system or slots for the storage devices;

receiving a request for a reservation of one of the plurality of storage devices or slots, wherein the reservation causes a storage controller of a storage system to prevent other storage controllers of the storage system from accessing the one of the plurality of storage devices or slots;

determining, based on the indication, whether granting the request results in the storage system maintaining a quorum of storage devices online, the quorum of online storage devices represented by a number of storage devices that are able to write and read user data using erasure coding; and

granting the reservation, based on the determining.

8. The computer-readable media of claim 7, wherein the method further comprises:

generating a disposable data structure, responsive to granting the reservation to a requester of the reservation;

indicating the status of the one of the plurality of storage devices or slots as reserved, responsive to the granting the reservation; and

indicating in the memory the status of the one of the plurality of storage devices or slots as online, to end the reservation, responsive to release of the data structure.

9. The computer-readable media of claim 7, wherein the method further comprises:

power cycling the one of the plurality of storage devices, by a requester of the reservation, responsive to the requester receiving the granting the reservation.

10. The computer-readable media of claim 7, wherein the method further comprises:

upgrading firmware of the one of the plurality of storage devices, by a requester of the reservation, responsive to the requester receiving the granting the reservation.

11. The computer-readable media of claim 7, wherein the method further comprises:

generating a disposable data structure to indicate the one of the plurality of storage devices or slots is reserved, for the granting the reservation;

storing the disposable data structure in a portion of memory reserved by a requester of the reservation; and

releasing, by the requester, the portion of the memory.

12. A storage system, comprising:

one or more chassis having a plurality of slots for a plurality of storage devices; and

one or more processors configured to;

maintain a list of the plurality of slots or the plurality of storage devices and status for each of the plurality of slots or the plurality of storage devices indicating online or reserved;

evaluate a request for reservation of one of the plurality of slots or one of the plurality of storage devices as to whether granting the request would cause the storage system to have less than a quorum of storage devices online, the quorum of online storage devices represented by a number of storage devices that are able to write and read user data using erasure coding, wherein the reservation causes a storage controller of the storage system to prevent other storage controllers of the storage system from accessing the one of the plurality of storage devices or slots;

accept the reservation onto the list when granting the request causes the storage system to have at least the quorum of storage devices online; and

fail the reservation when granting the request would cause the storage system to have less than the quorum of storage devices online.

13. The storage system of claim 12, wherein the one or more processors are further configured to:

create a disposable data structure for a requester of the reservation, as granting the reservation; and

update the list to remove the reservation, responsive to the disposable data structure leaving scope of the requester of the reservation.

14. The storage system of claim 12, wherein the one or more processors are further configured to:

change status in the list of the requested one of the plurality of slots or the requested one of the plurality of storage devices from online to reserved, to accept the reservation onto the list as granting the request.

15. The storage system of claim 12, wherein the one or more processors are further configured to:

power cycle the requested one of the plurality of slots or the requested one of the plurality of storage devices, by a requester of the reservation, responsive to the reservation being granted.

16. The storage system of claim 12, wherein the one or more processors are further configured to:

upgrade firmware of the requested one of the plurality of storage devices, by a requester of the reservation, responsive to the reservation being granted.

17. The storage system of claim 12, wherein the one or more processors are further configured to:

generate a disposable data structure indicating a reserved one of the plurality of storage devices, to grant the request; and

write the disposable data structure into memory in the storage system, to a structure representing an operation that a requester of the reservation executes; and

end the reservation, responsive to the disposable data structure being destroyed as a result of the operation releasing the structure representing the operation.

18. The storage system of claim 12, wherein the one or more processors are further configured to:

service user I/O (input/output) when the storage system has the at least the quorum of storage devices online; and

rebuild data when the storage system has the at least the quorum of storage devices online.