Replicating data in a data storage system

• US 10,303,360 B2
• Filed: 09/30/2015
• Issued: 05/28/2019
• Est. Priority Date: 09/30/2015
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Beeken, Christopher B E, Canto, Christopher, Cockburn, Gordon J., Wilkinson, John P.
• Primary Examiner(s): Corrielus, Jean M
• Application Number:
  US14/871,068
• Publication Number:
  US 20170091044A1
• Time in Patent Office: 1,336 Days
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 3/06 Digital input from, or digital output to, record carriers , e.g. RAID, emulated record carriers or networked record carriers
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A first data storage device receives a first write request from a host device to update a first subset of the data regions and sends the first write request to a second data storage device. Prior to receiving a notification from the second device that it has been updated in accordance with the first write request, the first device receives a second write request from the second device to update a second subset of the data regions and one of the two devices is selected. If the first device is selected, the first device updates only its data regions that are in the second subset but not in the first subset according to the second write request. In the case that the second device is selected, the first device updates its data regions that are in the second subset according to the second write request.

Claims

1. A computer-implemented method of replicating data in a data storage system, wherein the data storage system comprises at least:

a first data storage device comprising a set of data regions;

a second data storage device comprising a set of data regions corresponding to the set of data regions of the first data storage device; and

a first host device in communication with the first data storage device and a second host device in communication with the second data storage device;

wherein the method comprises the steps of;

the first data storage device receiving a first write request from the first host device to update a first subset of the data regions;

the first data storage device updating data regions that are in the first subset in accordance with the first write request;

the first data storage device sending the first write request to the second data storage device;

the second data storage device receiving a second write request to update a second subset of the data regions from the second host device prior to receiving the first write request;

the second data storage device updating data regions that are in the second subset in accordance with the second write request;

the second data storage device receiving the first write request;

the second data storage device updating data regions that are in the first subset in accordance with the first write request;

the second data storage device sending a notification to the first data storage device indicating that the second data storage device has been updated in accordance with the first write request and a collision mask indicating the regions of the second write request overwritten by the first write request;

based on the received collision mask, the first data storage device determining that the first data storage device has not received the second write request;

based on the first data storage device being selected as a leader in the case of a collision between the first write request and the second write request, the first data storage device updating the first subset in accordance with the first write request;

the first data storage device sending a notification to the second data storage device indicating that the first data storage device has been updated in accordance with the first write request and sending a first flush message;

based on receiving the flush message, the second data storage device waiting for a notification indicating that the first data storage device has applied the second write request;

based on receiving the notification indicating that the first data storage device has applied the second write request, the second data storage device sending a second flush message to the first data storage device;

the first data storage device receiving the second write request from the second data storage device;

based on receiving the second flush message and the first data storage device being selected as the leader, the first data storage device updating only data regions that are in the second subset but not in the first subset in accordance with the second write request; and

the first data storage device sending a third flush message to the second data storage device.

2. A method as claimed in claim 1, further comprising:

based receiving the second write request, the first data storage device locking at least a portion of the set of data regions; and

based on receiving the second flush message, the first data storage device unlocking the at least the portion of the set of data regions.

3. A method as claimed in claim 1, further comprising:

based on receiving the first write request, the second data storage device locking at least a portion of the data regions; and

based on receiving the third flush message, the second data storage device locking the at least the portion of the data regions.

4. A method as claimed in claim 1, wherein the characteristic of the first data storage device and the second data storage device is the MAC address of the first data storage device and the second data storage device.

5. A computer system for replicating data in a data storage system, wherein the system comprises at least:

a first data storage device comprising a set of data regions;

a second data storage device comprising a set of data regions corresponding to the set of data regions of the first data storage device;

a first host device in communication with the first data storage device and a second host device in communication with the second data storage device; and

one or more computer-readable storage media and program instructions stored on the one or more computer-readable storage media, the program instructions comprising;

program instructions to receive, by the first data storage device, a first write request from the first host device to update a first subset of the data regions;

program instructions to update, by the first data storage device, data regions that are in the first subset in accordance with the first write request;

program instructions to send, by the first data storage device, the first write request to the second data storage device;

program instructions to receive, by the second data storage device, a second write request to update a second subset of the data regions from the second host device prior to receiving the first write request;

program instructions to update, by the second data storage device, data regions that are in the second subset in accordance with the second write request;

program instructions to receive, by the second data storage device, the first write request;

program instructions to update, by the second data storage device, data regions that are in the first subset in accordance with the first write request;

program instructions to send, by the second data storage device, a notification to the first data storage device indicating that the second data storage device has been updated in accordance with the first write request and a collision mask indicating the regions of the second write request overwritten by the first write request;

based on the received collision mask, program instructions to determine, by the first data storage device, that the first data storage device has not received the second write request;

based on the first data storage device being selected as a leader in the case of a collision between the first write request and the second write request, program instructions to update, by the first data storage device, the first subset in accordance with the first write request;

program instructions to send, by the first data storage device, a notification to the second data storage device indicating that the first data storage device has been updated in accordance with the first write request and send a first flush message;

based on receiving the flush message, program instructions to wait, by the second data storage device, for a notification indicating that the first data storage device has applied the second write request;

based on receiving the notification indicating that the first data storage device has applied the second write request, program instructions to send, by the second data storage device, a second flush message to the first data storage device;

program instructions to receive, by the first data storage device, the second write request from the second data storage device;

based on receiving the second flush message and the first data storage device being selected as the leader, program instructions to update, by the first data storage device, only data regions that are in the second subset but not in the first subset in accordance with the second write request; and

program instructions to send, by the first data storage device, a third flush message to the second data storage device.

6. The computer system of claim 5, further comprising:

based receiving the second write request, program instructions to lock, by the first data storage device, at least a portion of the set of data regions; and

based on receiving the second flush message, program instructions to unlock, by the first data storage device, the at least the portion of the set of data regions.

7. The computer system of claim 5, further comprising:

based on receiving the first write request, program instructions to lock, by the second data storage device, at least a portion of the set of data regions; and

based on receiving the third flush message, program instructions to unlock, by the second data storage device, the at least the portion of the set of data regions.

8. The computer system of claim 5, wherein the characteristic of the first data storage device and the second data storage device is the MAC address of the first data storage device and the second data storage device.

9. A computer program product for replicating data in a data storage system comprising at least:

a first data storage device comprising a set of data regions;

a second data storage device comprising a set of data regions corresponding to the set of data regions of the first data storage device;

a first host device in communication with the first data storage device and a second host device in communication with the second data storage device;

one or more computer processors, one or more computer-readable storage media, and program instructions stored on one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to receive, by the first data storage device, a first write request from the first host device to update a first subset of the data regions;

program instructions to update, by the first data storage device, data regions that are in the first subset in accordance with the first write request;

program instructions to send, by the first data storage device, the first write request to the second data storage device;

program instructions to receive, by the second data storage device, a second write request to update a second subset of the data regions from the second host device prior to receiving the first write request;

program instructions to update, by the second data storage device, data regions that are in the second subset in accordance with the second write request;

program instructions to receive, by the second data storage device, the first write request;

program instructions to update, by the second data storage device, data regions that are in the first subset in accordance with the first write request;

program instructions to send, by the second data storage device, a notification to the first data storage device indicating that the second data storage device has been updated in accordance with the first write request and a collision mask indicating the regions of the second write request overwritten by the first write request;

based on the received collision mask, program instructions to determine, by the first data storage device, that the first data storage device has not received the second write request;

based on the first data storage device being selected as a leader in the case of a collision between the first write request and the second write request, program instructions to update, by the first data storage device, the first subset in accordance with the first write request;

program instructions to send, by the first data storage device, a notification to the second data storage device indicating that the first data storage device has been updated in accordance with the first write request and send a first flush message;

based on receiving the flush message, program instructions to wait, by the second data storage device, for a notification indicating that the first data storage device has applied the second write request;

based on receiving the notification indicating that the first data storage device has applied the second write request, program instructions to send, by the second data storage device, a second flush message to the first data storage device;

program instructions to receive, by the first data storage device, the second write request from the second data storage device;

based on receiving the second flush message and the first data storage device being selected as the leader, program instructions to update, by the first data storage device, only data regions that are in the second subset but not in the first subset in accordance with the second write request; and

program instructions to send, by the first data storage device, a third flush message to the second data storage device.

10. The computer program product of claim 9, further comprising:

based receiving the second write request, program instructions to lock, by the first data storage device, at least a portion of the set of data regions; and

based on receiving the second flush message, program instructions to unlock, by the first data storage device, the at least the portion of the set of data regions.

11. The computer program product of claim 9, further comprising:

based on receiving the first write request, program instructions to lock, by the second data storage device, at least a portion of the set of data regions; and

based on receiving the third flush message, program instructions to unlock, by the second data storage device, the at least the portion of the set of data regions.

12. The computer program product of claim 9, wherein the characteristic of the first data storage device and the second data storage device is the MAC address of the first data storage device and the second data storage device.