TECHNIQUES FOR ERROR HANDLING IN PARALLEL SPLITTING OF STORAGE COMMANDS

• US 20160098330A1
• Filed: 10/02/2014
• Published: 04/07/2016
• Est. Priority Date: 10/02/2014
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Mu, Paul Yuedong, Ngan, Paul, Sundararajan, Manoj
• Granted Patent: US 9,489,275 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/07 Responding to the occurrence of a fault, e.g. fault tolerance
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 2201/82 Solving problems relating to consistency ensuring consistency in mirrored systems G06F11/2064
• CPC Class Codes: G06F 2201/85 Active fault masking without idle spares active fault masking without idle spare hardware where processing functionality is redundant G06F11/2035
• 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 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: H04L 1/08 by repeating transmission, e.g. Verdan system H04L1/1858 and H04L1/189 take precedence

Abstract

Various embodiments are generally directed to techniques for handling errors affecting the at least partially parallel performance of data access commands between nodes of a storage cluster system. An apparatus may include a processor component of a first node, an access component to perform a command received from a client device via a network to alter client device data stored in a first storage device coupled to the first node, a replication component to transmit a replica of the command to a second node via the network to enable performance of the replica by the second node at least partially in parallel, an error component to retry transmission of the replica based on a failure indicated by the second node and a status component to select a status indication to transmit to the client device based on the indication of failure and results of retrial of transmission of the replica.

Claims

1. An apparatus comprising:

a processor component of a first node of a storage cluster system;

an access component for execution by the processor component to perform a command received from a client device via a network to alter client device data stored in a first storage device coupled to the first node;

a replication component for execution by the processor component to transmit a replica of the command to a second node of the storage cluster system via the network to enable performance of the replica by the second node at least partially in parallel with the command;

an error component for execution by the processor component to retry transmission of the replica based on a failure indicated by the second node; and

a status component for execution by the processor component to select a status indication of performance of the command to transmit to the client device based on the indication of failure and results of retrial of transmission of the replica.

2. The apparatus of claim 1, the error component to determine that the failure is a short-term failure that the second node is able to correct, and to retry transmission of the replica to the second node based on the determination.

3. The apparatus of claim 2, the status component to select an indication of successful performance of the command as the status indication based on the determination that the failure is a short-term failure and based on at least one of successful acceptance, successful commencement of performance or successful performance of the replica by the second node following retrial of transmission of the replica to the second node.

4. The apparatus of claim 2, the status component to determine whether a predetermined status time period has elapsed since receipt of the command, and to select an indication of retrial of the command as currently underway as the status indication based on the determination that the failure is a short-term failure and on an elapsing of the status time period as retrial of the transmission of the replica to the second node is underway.

5. The apparatus of claim 2, the error component to further determine that the failure is a long term failure that the second node is not able to correct based on a limit of multiple retrials of the replica with the second node being met, the error component to retry the replica with a third node based on the further determination, the third node comprising a partner node of the second node in a high availability group that comprises the second and third nodes.

6. The apparatus of claim 1, the error component to determine that the failure is a long-term failure that the second node is unable to correct, and to retry transmission of the replica to a third node based on the determination, the third node comprising a partner node of the second node in a high availability group that comprises the second and third nodes.

7. The apparatus of claim 6, the status component to select an indication of successful performance of the command as the status indication based on the determination that the failure is a long-term failure and on at least one of successful acceptance, successful commencement of performance or successful performance of the replica by the third node following the retrial of transmission of the replica to the third node.

8. The apparatus of claim 6, the status component to determine whether a predetermined status time period has elapsed since receipt of the command, and to select an indication of retrial of the command as currently underway as the status indication based on the determination that the failure is a long-term failure and on an elapsing of the status time period as retrial of the transmission of the replica to the third node is underway.

9. The apparatus of claim 6, comprising an multipath component to detect an absence of an active communications session coupling the first and second nodes through the network, the error component to determine that the failure is a long term failure based on the detection.

10. The apparatus of claim 1, comprising a protocol component to translate the command from a storage service as received from the client device to a data access command, and to translate the status indication from a command response associated with the data access command to a service request response associated with the storage service request as transmitted to the client.

11. A computer-implemented method comprising:

performing at a first node of a storage cluster system a command received from a client device via a network to alter client device data stored in a first storage device coupled to the first node;

transmitting a replica of the command to a second node of the storage cluster system via the network to enable performance of the replica by the second node at least partially in parallel with the command;

retrying transmission of the replica based on a failure indicated by the second node; and

selecting a status indication of performance of the command to transmit to the client device based on the indication of failure and results of retrial of transmission of the replica.

12. The computer-implemented method of claim 11, comprising:

determining that the failure is a short-term failure that the second node is able to correct; and

retrying transmission of the replica to the second node based on the determination.

13. The computer-implemented method of claim 12, comprising selecting an indication of successful performance of the command as the status indication based on the determination that the failure is a short-term failure and based on at least one of successful acceptance, successful commencement of performance or successful performance of the replica by the second node following retrial of transmission of the replica to the second node.

14. The computer-implemented method of claim 12, comprising:

determining whether a predetermined status time period has elapsed since receipt of the command; and

selecting an indication of retrial of the command as currently underway as the status indication based on the determination that the failure is a short-term failure and on an elapsing of the status time period as retrial of the transmission of the replica to the second node is underway.

15. The computer-implemented method of claim 12, comprising:

further determining that the failure is a long-term failure that the second node is unable to correct based on a limit of multiple retrials of the replica with the second node being met; and

retrying transmission of the replica to a third node based on the further determination, the third node comprising a partner node of the second node in a high availability group that comprises the second and third nodes.

16. The computer-implemented method of claim 11, comprising:

determining that the failure is a long-term failure that the second node is unable to correct; and

retrying transmission of the replica to a third node based on the determination, the third node comprising a partner node of the second node in a high availability group that comprises the second and third nodes.

17. The computer-implemented method of claim 16, comprising selecting an indication of successful performance of the command as the status indication based on the determination that the failure is a long-term failure and based on at least one of successful acceptance, successful commencement of performance or successful performance of the replica by the third node following the retrial of transmission of the replica to the third node.

18. The computer-implemented method of claim 16, comprising:

determining whether a predetermined status time period has elapsed since receipt of the command; and

selecting an indication of retrial of the command as currently underway as the status indication based on the determination that the failure is a long-term failure and on an elapsing of the status time period as retrial of the transmission of the replica to the third node is underway.

19. The computer-implemented method of claim 11, comprising transmitting the status indication to the client device at least partially in parallel with at least one of performing of the command at the first node or performing the replica at the third node.

20. At least one machine-readable storage medium comprising instructions that when executed by a processor component, cause the processor component to:

perform at a first node of a storage cluster system a command received from a client device via a network to alter client device data stored in a first storage device coupled to the first node;

transmit a replica of the command to a second node of the storage cluster system via the network to enable performance of the replica by the second node at least partially in parallel with the command;

retry transmission of the replica based on a failure indicated by the second node; and

select a status indication of performance of the command to transmit to the client device based on the indication of failure and results of retrial of transmission of the replica.

21. The at least one machine-readable storage medium of claim 20, the processor component caused to:

determine that the failure is a short-term failure that the second node is able to correct; and

retry transmission of the replica to the second node based on the determination.

22. The at least one machine-readable storage medium of claim 21, the processor component caused to select an indication of successful performance of the command as the status indication based on the determination that the failure is a short-term failure and based on at least one of successful acceptance, successful commencement of performance or successful performance of the replica by the second node following retrial of transmission of the replica to the second node.

23. The at least one machine-readable storage medium of claim 21, the processor component caused to:

determine whether a predetermined status time period has elapsed since receipt of the command; and

select an indication of retrial of the command as currently underway as the status indication based on the determination that the failure is a short-term failure and on an elapsing of the status time period as retrial of the transmission of the replica to the second node is underway.

24. The at least one machine-readable storage medium of claim 21, the processor component caused to:

further determine that the failure is a long-term failure that the second node is unable to correct based on a limit of multiple retrials of the replica with the second node being met; and

retry transmission of the replica to a third node based on the further determination, the third node comprising a partner node of the second node in a high availability group that comprises the second and third nodes.

25. The at least one machine-readable storage medium of claim 20, the processor component caused to:

determine that the failure is a long-term failure that the second node is unable to correct; and

retry transmission of the replica to a third node based on the determination, the third node comprising a partner node of the second node in a high availability group that comprises the second and third nodes.

26. The at least one machine-readable storage medium of claim 25, the processor component caused to select an indication of successful performance of the command as the status indication based on the determination that the failure is a long-term failure and based on at least one of successful acceptance, successful commencement of performance or successful performance of the replica by the third node following the retrial of transmission of the replica to the third node.

27. The at least one machine-readable storage medium of claim 25, the processor component caused to:

determine whether a predetermined status time period has elapsed since receipt of the command; and

select an indication of retrial of the command as currently underway as the status indication based on the determination that the failure is a long-term failure and on an elapsing of the status time period as retrial of the transmission of the replica to the third node is underway.

28. The at least one machine-readable storage medium of claim 20, the processor component caused to transmit the status indication to the client device at least partially in parallel with at least one of performing of the command at the first node or performing the replica at the third node.

29. The at least one machine-readable storage medium of claim 20, the processor component caused to condition transmission of the replica to the second node on at least one of successful acceptance or successful commencement of performance of the command.