Dynamic partition of PCIe disk arrays based on software configuration / policy distribution

• US 10,713,203 B2
• Filed: 02/28/2017
• Issued: 07/14/2020
• Est. Priority Date: 02/28/2017
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Bai, Yun, Li, Mengshi, Sun, Yang, Wang, Min, Chen, Yepeng
• Primary Examiner(s): Mehrmanesh, Elmira
• Application Number:
  US15/445,662
• Publication Number:
  US 20180246833A1
• Time in Patent Office: 1,232 Days
• CPC Class Codes: G06F 11/2007 using redundant communication media
• CPC Class Codes: G06F 11/203 using migration
• CPC Class Codes: G06F 11/2033 switching over of hardware resources
• CPC Class Codes: G06F 13/38 Information transfer, e.g. on bus G06F13/14 takes precedence
• CPC Class Codes: G06F 13/4022 using switching circuits, e.g. switching matrix, connection or expansion network G06F13/4009 takes precedence
• CPC Class Codes: G06F 13/4282 on a serial bus, e.g. I2C bus, SPI bus on daisy chain buses G06F13/4247
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/0658 Controller construction arrangements
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

This disclosure relates to methods and systems for dynamically partitioning of PCIe disk arrays based on software configuration/policy distribution. In one embodiment, at least one PCIe switch has an input port operatively connected to a respective CPU and at least one output port. A multiplexer is connected between the output port(s) of the at least one PCIe switch and a PCIe disk array, for example an NVMe SSD, and is configured to connect the PCIe disk array in a first configuration to a single PCIe switch in either one-x4 port or two x2 port mode, or in a second configuration to two PCIe switches in x2 port mode. The multiplexer can dynamically switch between the first configuration and the second configuration on the fly. Switching can occur, for example, in response to a hot-swap of an NVMe SSD or a policy change.

Claims

1. An apparatus comprising:

at least one Peripheral Component Interconnect Express (PCIe) switch having an input port operatively connected to a respective CPU and at least one output port; and

at least one multiplexer connected between the at least one output port of the at least one PCIe switch and a PCIe disk array, the at least one multiplexer configured to alternate a connection of the PCIe disk array between a first configuration and a second configuration in response to a change in a configuration policy, a surprise addition without notification, or a surprise removal without notification, the first configuration being the at least one multiplexer connected to a single PCIe switch in one x4 port mode or two x2 port mode, the second configuration being the at least one multiplexer connected to two PCIe switches in x2 port mode, the at least one multiplexer configured to dynamically affect a switch-over between the first configuration and the second configuration.

2. The apparatus of claim 1,

wherein,

the switch-over occurs in response to the change in the configuration policy,

and

the configuration policy is of the PCIe disk array.

3. The apparatus of claim 1,

wherein,

the switch-over occurs in response to the surprise addition without the notification, and

the surprise addition is of a PCIe disk array (hot-add).

4. The apparatus of claim 1,

wherein,

the switch-over occurs in response to the surprise removal without the notification, and

the surprise removal is of a PCIe disk array (hot-remove).

5. The apparatus of claim 1, wherein when data traffic congestion is detected at a first PCIe switch, the at least one multiplexer is configured to redirect a portion of data traffic from the first PCIe switch to a second PCIe switch for transmission to/from the PCIe disk array.

6. The apparatus of claim 1, wherein when operating in x4 port mode, the at least one multiplexer is configured to migrate all data traffic from a first PCIe switch to a second PCIe switch upon detection of a failure of the first PCIe switch for transmission to/from the PCIe disk array.

7. The apparatus of claim 1, wherein the PCIe disk array comprises a Non-Volatile Memory Express Solid-State Drive (NVMe SSD).

8. The apparatus of claim 1, further comprising:

a control logic device operatively connected to at least one PCIe switch and the at least one multiplexer and configured to monitor PCIe disk array information and PCIe disk configuration policy execution.

9. The apparatus of claim 8, wherein the control logic device is connected for communication to a management platform, with the management platform managing policy for the control logic device.

10. A method for partitioning a Peripheral Component Interconnect Express (PCIe) disk array, the method comprising:

connecting at least one multiplexer between the PCIe disk array and at least one output port of at least one PCIe switch, the at least one multiplexer configured to alternate a connection of the PCIe disk array between a first configuration and a second configuration in response to a change in a configuration policy or a surprise addition/removal without notification, the first configuration being the at least one multiplexer connected to a single PCIe switch in one x4 port mode or in two x2 port mode, the second configuration being the at least one multiplexer connected to two PCIe switches in x2 port mode, and

dynamically switching with the at least one multiplexer between the first configuration and the second configuration in response to the change.

11. The method of claim 10, wherein the PCIe disk array comprises a Non-Volatile Memory Express Solid-State Drive (NVMe SSD).

12. The method of claim 10,

wherein,

the dynamically switching between the first configuration and the second configuration takes place responsive to the surprise addition without the notification and/or the surprise removal without the notification,

the surprise addition is of a PCIe disk array (hot-add), and

the surprise removal is of a PCIe disk array (hot-remove).

13. The method of claim 10,

wherein,

the dynamically switching between the first configuration and the second configuration takes place responsive to the change in the configuration policy, and

the change in the configuration policy is of the PCIe disk array.

14. The method of claim 10, further comprising:

when data traffic congestion is detected at a first PCIe switch, redirecting a portion of the data traffic from the first PCIe switch to a second PCIe switch for transmission to/from the PCIe disk array.

15. The method of claim 10, further comprising:

when operating in x4 port mode, migrating all data traffic to a second PCIe switch upon detection of a failure of a first PCIe switch for transmission to/from the PCIe disk array.

16. The method of claim 10, wherein the dynamically switching includes managing, with a control logic device operatively connected to at least one PCIe switch and the at least one multiplexer, information of the PCIe disk array and status information of the at least one multiplexer.

17. A computer program embodied in a non-transitory computer-readable medium and comprising program instructions which, when loaded into a computer memory and executed by a processor, causes the processor to:

switch at least one multiplexer connected between a Peripheral Component Interconnect Express (PCIe) disk array and one or more output ports of one or more PCIe switches between a first configuration and a second configuration, the at least one multiplexer connecting the PCIe disk array in the first configuration to an output port of a single PCIe switch in one x4 port mode or in two x2 port mode, or in the second configuration to output ports of two PCIe switches in x2 port mode,

wherein the at least one multiplexer is dynamically switched between the first configuration and the second configuration in response to a change in a configuration policy, a surprise addition without notification, or a surprise removal without notification.

18. The computer program of claim 17,

wherein,

dynamically switching takes place responsive to the surprise addition without the notification or the surprise removal without the notification,

the surprise addition being of a PCIe disk array (hot-add), and

the surprise removal being of a PCIe disk array (hot-remove).

19. The computer program of claim 17, wherein the computer program causes a control logic device to communicate status information of the PCIe disk array and the at least one multiplexer.