In-band recovery mechanism for i/o modules in a data storage system

Patent metadata

Field	Value
Publication number	US-2016019124-A1
Application number	US-201514864059-A
Country	US
Kind code	A1
Filing date	Sep 24, 2015
Priority date	Jan 21, 2014
Publication date	Jan 21, 2016
Grant date	—

Abstract

Technology is disclosed for recovering I/O modules in a storage system using in-band alternate control path (ACP) architecture (“the technology”). The technology enables a storage server to transmit control commands, e.g., for recovering an I/O module, to the I/O module over a data path that is typically used to transmit data commands. The control commands are typically transmitted using ACP that is separate from the data path. By enabling transmission of control commands over the data path, the technology eliminates the need for separate medium for ACP, at least in part, to transmit the control commands. The technology can be implemented in a pure in-band ACP mode, which supports recovering an I/O module of a storage shelf in which at least one I/O module is responsive, and/or in a mixed in-band ACP mode, which supports recovery of I/O modules of a storage shelf in which all I/O modules are non-responsive.

First claim

What is claimed is:

1 . A method for recovery mechanism in a data storage system, the method comprising:
detecting, by a storage server, when a storage subsystem is non-responsive to a data command issued by the storage server, the storage server configured to send the data command to access data stored at a storage unit of the storage subsystem over a data path, and a control command to control the storage subsystem over an alternate control path (ACP); generating, by the storage server, an in-band control command for the control command, the in-band control command performing functions of the control command but configured to be sent over the data path; sending, by the storage server, the in-band control command to a partner storage subsystem over the data path; and causing, by the storage server, the partner storage subsystem to send the in-band control command to the I/O module for execution of the control command.

2 . The method as set forth claim 1 , wherein the control command is at least one of a command that resets the storage subsystem or a command that power cycles, powers on/off the storage subsystem.

3 . The method as set forth in claim 1 wherein, the data command is of a first protocol and the control command is of a second protocol.

4 . The method as set forth in claim 1 , wherein generating the in-band control command further comprises encapsulating, by the storage server, the control command into the first protocol to generate the in-band control command, wherein the first protocol is a Serial Attached SCSI (SAS) protocol and the second protocol is an ACP protocol.

5 . The method as set forth in claim 1 , wherein causing the partner storage subsystem to send the in-band control command to the storage subsystem further comprises:
extracting, by the storage server, the control command from the in-band control command, wherein extracting the control command from the in-band control command includes converting the in-band control command to the second protocol to obtain the control command; forwarding, by the storage server, the control command to an ACP storage subsystem of the partner storage subsystem; sending, by the storage server, the control command to a second ACP storage subsystem of the storage subsystem; and causing, by the storage server, the second ACP storage subsystem to execute the control command on a second data storage subsystem of the storage subsystem.

6 . The method as set forth in claim 4 wherein:
the data path is created by coupling the storage subsystem to a storage adapter of the storage server using SAS cables; and
the ACP is created by coupling the storage subsystem to a network adapter of the storage server using Ethernet cables.

7 . The method as set forth in claim 1 , wherein sending the in-band control command over the data communication path includes making the ACP redundant, thereby eliminating the need to use Ethernet cables.

8 . The method as set forth in claim 1 , wherein the partner storage subsystem is in the same storage shelf of the storage subsystem as the storage subsystem.

9 . A non-transitory computer readable medium having stored thereon instructions for recovery mechanism in a data storage system comprising machine executable code which when executed by at least one processor, causes the at least one processor to perform steps to and that comprise:
detect when a storage subsystem is non-responsive to a data command issued by the storage server, the storage server configured to send the data command to access data stored at a storage unit of the storage subsystem over a data path, and a control command to control the storage subsystem over an alternate control path (ACP); generate an in-band control command for the control command, the in-band control command performing functions of the control command but configured to be sent over the data path; send the in-band control command to a partner storage subsystem over the data path; and cause the partner storage subsystem to send the in-band control command to the I/O module for execution of the control command.

10 . The medium as set forth in claim 9 wherein the control command is at least one of a command that resets the storage subsystem or a command that power cycles, powers on/off the storage subsystem.

11 . The medium as set forth in claim 9 wherein, the data command is of a first protocol and the control command is of a second protocol.

12 . The medium as set forth in claim 9 wherein generating the in-band control command further comprises encapsulate the control command into the first protocol to generate the in-band control command, wherein the first protocol is a Serial Attached SCSI (SAS) protocol and the second protocol is an ACP protocol.

13 . The medium as set forth in claim 9 wherein causing the partner storage subsystem to send the in-band control command to the storage subsystem further comprises:
extract the control command from the in-band control command, wherein extracting the control command from the in-band control command includes converting the in-band control command to the second protocol to obtain the control command;
forward the control command to an ACP storage subsystem of the partner storage subsystem;
send the control command to a second ACP storage subsystem of the storage subsystem; and
cause the second ACP storage subsystem to execute the control command on a second data storage subsystem of the storage subsystem.

14 . The medium as set forth in claim 12 wherein:
the data path is created by coupling the storage subsystem to a storage adapter of the storage server using SAS cables; and
the ACP is created by coupling the storage subsystem to a network adapter of the storage server using Ethernet cables.

15 . The medium as set forth in claim 9 wherein sending the in-band control command over the data communication path includes making the ACP redundant, thereby eliminating the need to use Ethernet cables.

16 . The medium as set forth in claim 9 wherein the partner storage subsystem is in the same storage shelf of the storage subsystem as the storage subsystem.

17 . A storage management computing device comprising:
a processor; a memory, wherein the memory coupled to the processor which are configured to execute programmed instructions stored in the memory to and that comprise: detect when a storage subsystem is non-responsive to a data command issued by the storage server, the storage server configured to send the data command to access data stored at a storage unit of the storage subsystem over a data path, and a control command to control the storage subsystem over an alternate control path (ACP); generate an in-band control command for the control command, the in-band control command performing functions of the control command but configured to be sent over the data path; send the in-band control command to a partner storage subsystem over the data path; and cause the partner storage subsystem to send the in-band control command to the I/O module for execution of the control command.

18 . The device as set forth in claim 17 wherein the control command is at least one of a command that resets the storage subsystem or a command that power cycles, powers on/off the storage subsystem.

19 . The device as set forth in claim 17 wherein, the data command is of a first protocol and the control command is of a second protocol.

20 . The device as set forth in claim 17 wherein generating the in-band control

Assignees

• Netapp Inc

Inventors

• Saxena Mayank
• Mcgee Melvin

Classifications

• H04L45/22 Primary

  Alternate routing · CPC title

• G06F11/201 Primary

  between storage system components · CPC title

• G06F2201/805

  Real-time · CPC title

• G06F2201/85

  Active fault masking without idle spares · CPC title

• G06F11/2012

  and using different communication protocols · CPC title