Data management device and data managing method for the replication of data

• US 8,028,202 B2
• Filed: 03/30/2010
• Issued: 09/27/2011
• Est. Priority Date: 03/31/2009
• Status: Expired due to Fees

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Takagi, Shunsuke, Maruyama, Tetsutaro
• Primary Examiner(s): Beausoliel, Jr.; Robert
• Assistant Examiner(s): Mehrmanesh; Elmira
• Application Number:
  US12/749,736
• Publication Number:
  US 20100251011A1
• Time in Patent Office: 546 Days
• Field of Search: 714/6, 714/7, 714/6.12, 714/6.22, 714/47.2
• US Class Current: 714/47.2
• CPC Class Codes: G06F 11/004 Error avoidance G06F11/07 and subgroups take precedence
• CPC Class Codes: G06F 11/008 Reliability or availability analysis

Abstract

A data management device accessible to a plurality of memories includes a risk unit which determines risk of failure associated with each of the plurality of memories, a selection unit which selects a memory from among the plurality of memories on the basis of the determined risk and a transmitting unit which transmits a replication instruction to another memory of the plurality of memories. The replication instruction causes replication of the data to be replicated that is stored in the selected memory.

Claims

1. A data management device to access a plurality of memories, the data management device comprising:

a receiver to receive warning messages from the plurality of memories;

a risk unit to determine a risk of failure associated with each memory of the plurality of memories on the basis of the received warning messages;

a selection unit to select a first memory from the plurality of memories based on the determined risk of failure associated with each memory of the plurality of memories;

a replication destination unit to determine an entire amount of free capacity of each of the plurality of memories is smaller than a specified amount of free capacity, and a risk associated with each of the plurality of memories; and

a transmitting unit to transmit

a delete instruction to a second memory of the plurality of memories to delete data corresponding to a replicated spare data, the replicated spare data is a second copy of a master data, the master data or a first copy of the master data is saved in another memory of the plurality of memories respectively;

a replication instruction to the first memory to store in the second memory.

2. The data management device according to claim 1, wherein the risk associated with each of the plurality of memories is used to maintain a list ranking the plurality of memories, and the risk unit selects a highest ranked memory as the first memory, the highest ranked memory corresponding to the memory most likely to fail.

3. The data management device according to claim 1, wherein the transmitting unit transmits the replication instruction when the risk of failure of the first memory is higher than a threshold value.

4. The data management device according to claim 1,

wherein the second memory is ranked lower than a designated order.

5. The data management device according to claim 1, further comprising:

a detecting unit to detect a failed memory from among the plurality of memories, the plurality of memories including master data and replicated data corresponding to a first copy of the master data; and

a setting unit to set, in a case that data stored in the failed memory detected by the detecting unit is master data, the replicated data as the master data.

6. The data management device according to claim 5, wherein the plurality of memories further include replicated spare data corresponding to a second copy of the master data, and the setting unit, in a case that data stored in the failed memory detected by the detecting unit is master data, sets the replicated spare data as replicated data.

7. The data management device according to claim 5, wherein the setting unit causes the transmitting unit to transmit a replication instruction to make a memory, other than a memory that stores the data which has been set as the master data, replicate the data which has been set as the master data and store the replicated data.

8. A data managing method executed using a data management device accessible to a plurality of memories, the method comprising:

receiving warning messages from the plurality of memories;

determining a risk of failure associated with each memory of the plurality of memories on the basis of the received warning messages;

selecting a first memory from among the plurality of memories on the basis of the determined risk of failure associated with each memory of the plurality of memories;

determining an entire amount of free capacity of each of the plurality of memories is smaller than a specified amount of free capacity, and a risk associated with each of the plurality of memories;

transmitting a delete instruction to a second memory of the plurality of memories to delete data corresponding to a replicated spare data, the replicated spare data is a second copy of a master data, the master data or a first copy of the master data is saved in another memory of the plurality of memories respectively;

transmitting a replication instruction to the first memory to store in the second memory.

9. The method according to claim 8, wherein the risk associated with each of the plurality of memories is used to maintain a list ranking the plurality of memories, and wherein the determining determines a highest ranked memory as the first memory, the highest ranked memory corresponding to the memory most likely to fail.

10. The method according to claim 8, wherein the transmitting the replication instruction is executed when the risk of failure of the first memory is higher than a threshold value.

11. The method according to claim 8, wherein the second memory is ranked lower than a designated order.

12. A computer readable storage medium storing a data management program to be executed, by a data management device accessible to a plurality of memories, execution of the program causing the data management device to perform a process comprising:

receiving warning messages from the plurality of memories;

determining a risk of failure associated with each memory of the plurality of memories on the basis of the received warning messages;

selecting a first memory from among the plurality of memories on the basis of the determined risk of failure associated with each memory of the plurality of memories;

determining an entire amount of free capacity of each of the plurality of memories is smaller than a specified amount of free capacity, and a risk associated with each of the plurality of memories;

transmitting a delete instruction to a second memory of the plurality of memories to delete data corresponding to a replicated spare data, the replicated spare data is a second copy of a master data, the master data or a first copy of the master data is saved in another memory of the plurality of memories respectively;

transmitting a replication instruction to the first memory to store in the second memory.

13. The storage medium according to claim 12, wherein the risk associated with each of the plurality of memories is used to maintain a list ranking the plurality of memories, and wherein the determining determines a highest ranked memory as the first memory, the highest ranked memory corresponding to the memory most likely to fail.

14. The storage medium according to claim 12, wherein the transmitting the replication instruction is executed when the risk of failure of the first memory is higher than a threshold value.

15. The storage medium according to claim 12, wherein the second memory is ranked lower than a designated order.