Storage apparatus, and method for performing fault recovery of storage apparatus

• US 7,797,567 B2
• Filed: 08/24/2006
• Issued: 09/14/2010
• Est. Priority Date: 04/28/2006
• Status: Expired due to Fees

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Thielo, Omar, Otaka, Atsuhiro, Honjo, Nobuyuki, Nakamura, Daiya
• Primary Examiner(s): Wilson; Yolanda L
• Application Number:
  US11/508,913
• Publication Number:
  US 20070253232A1
• Time in Patent Office: 1,482 Days
• Field of Search: 714/4, 714/5, 714/43
• US Class Current: 714/4.2
• CPC Class Codes: G06F 11/2007 using redundant communication media

Abstract

The storage apparatus includes a plurality of storage devices for storing information, a control unit controlling the storage device, a switching unit switching a connection between the storage device and the control unit, and a network different from the connection by the switching unit and connecting the storage device and the control unit. Reading of information from the storage device and writing of information into the storage device is performed by the control unit through the switching unit, and when a fault occurs in the storage device, a fault recovery command is sent from the control unit through the network to the corresponding storage device or the switching unit.

Claims

1. A storage apparatus, comprising:

a plurality of storage devices storing information;

a plurality of first control units each controlling the storage devices;

a first network;

a switching unit connecting between the plurality of storage devices and the plurality of first control units through the first network;

a second network connecting between the plurality of storage devices and the plurality of first control units, and connecting between the plurality of first control units and the switching unit; and

a second control unit connected to the plurality of first control units, the plurality of storage devices and the switching unit through the second network,

wherein the plurality of first control units reads and writes information from the plurality of storage devices and into the plurality of storage devices through the switching unit, and, when a fault occurs for which communication between a storage device and the plurality of first control units is impossible, the plurality of first control units determines whether the first network is disconnected or not, and sends a plurality of fault recovery commands to the storage device or the switching unit through the second network when the first network is disconnected, and

the plurality of fault recovery commands are commands recovering the fault.

2. The storage apparatus according to claim 1, wherein, when the storage device or the switching unit receives a plurality of same fault recovery commands through the second network, the storage device or the switching unit integrates fault recovery processes at one time.

3. The storage apparatus according to claim 2, wherein the plurality of first control units obtains the information on the storage device through the second network.

4. The storage apparatus according to claim 1, wherein the plurality of first control units obtains the information on the storage device through the second network.

6. The storage apparatus according to claim 1, wherein the second control unit translates a fault recovery command corresponding to the first network into a command corresponding the second network.

5. A method for performing fault recovery of a storage apparatus including a plurality of storage devices storing information, a plurality of first control units each controlling the storage devices, a first network, a switching unit connecting between the plurality of storage devices and the plurality of first control units through the first network, a second network connecting between the plurality of storage devices and:

the plurality of first control units, and connecting between the plurality of first control units and the switching unit, and a second control unit connected to the plurality of first control units, the plurality of storage devices, and the switching unit through the second network, the method comprising;

reading and writing, in the plurality of first control units, information from the plurality of storage devices and into the plurality of storage devices through the switching unit;

determining, when a fault occurs for which communication between a storage device and the plurality of first control units is impossible, in the plurality of first control units, whether the first network is disconnected or not; and

sending, when the first network is disconnected, a plurality of fault recovery commands from the plurality of first control units to the storage device or the switching unit through the second network;

wherein the plurality of fault recovery commands are commands recovering the fault.

7. A method for performing fault recovery of a storage apparatus, comprising:

storing information in a plurality of storage devices;

controlling the storage devices with a plurality of first control units;

connecting the plurality of storage devices to the plurality of first control units through a first network;

connecting a second network between the plurality of storage devices and the plurality of first control units;

connecting the second network between the plurality of first control units and the switching unit;

connecting a second control unit to the plurality of first control units, the plurality of storage devices, and the switching unit through the second network;

reading the information from the plurality of storage devices in the plurality of first control units;

writing to the plurality of storage devices in the plurality of first control units;

determining, in the plurality of first control units, whether the first network is disconnected if a fault occurs for which communication between a storage device and the plurality of first control units is impossible; and

sending a plurality of fault recovery commands from the plurality of first control units to the storage device or the switching unit through the second network if the first network is disconnected;

wherein the plurality of fault recovery commands are commands recovering the fault.