Bandwidth sizing in replicated storage systems

• US 20080177963A1
• Filed: 01/24/2007
• Published: 07/24/2008
• Est. Priority Date: 01/24/2007
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Rogers, Thomas Kidder
• Granted Patent: US 7,734,950 B2
• Time in Patent Office: Days
• US Class Current: 711/162
• CPC Class Codes: G06F 11/2071 using a plurality of controllers
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3452 Performance evaluation by statistical analysis
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: H04L 47/10 Flow control; Congestion control
• CPC Class Codes: H04L 47/25 with rate being modified by the source upon detecting a change of network conditions
• CPC Class Codes: H04L 47/30 in combination with information about buffer occupancy at either end or at transit nodes
• CPC Class Codes: H04L 49/90 Buffering arrangements
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/62 Establishing a time schedule for servicing the requests
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06

Abstract

Embodiments include methods, apparatus, and systems for determining bandwidth in storage systems. One embodiment includes a method receiving a recovery point objective (RPO) for a disaster recovery (DR) system that uses asynchronous replication. The method then computes a queue depth for queued data waiting to be transmitted to a secondary storage location and uses the RPO and the queue depth to calculate a bandwidth for transmitting data from a first storage location to the secondary storage location.

Claims

1. ) A method, comprising:

receiving a recovery point objective (RPO) for a disaster recovery (DR) system that uses asynchronous replication;

computing in the DR system a queue depth for queued data waiting to be transmitted to a secondary storage location; and

using the RPO and the queue depth to calculate a bandwidth for transmitting data from a first storage location to the secondary storage location.

2. ) The method of claim 1 further comprising, measuring historical write byte rates over a period of time for writing data from a primary storage location to the secondary storage location.

3. ) The method of claim 1 further comprising, computing a time required to drain a queue of data and transmit data to a secondary storage location.

4. ) The method of claim 1 further comprising, providing a graphical display that shows a visual correlation between different RPOs and different bandwidth transmission rates.

5. ) The method of claim 1 further comprising, outputting a recommendation for bandwidth size needed to transmit data from a first storage location to the secondary storage location in the DR system.

6. ) The method of claim 1 further comprising:

calculating a first achieved RPO based on an estimated bandwidth;

comparing the first achieved RPO with the RPO;

calculating a second achieved RPO when the first achieved RPO differs from the RPO.

7. ) The method of claim 1 further comprising, using the RPO, the queue depth, and a measured write byte rate to calculate the bandwidth.

8. ) A computer readable medium having instructions for causing a computer to execute a method, comprising:

receiving a recovery point objective (RPO) for a storage system that uses asynchronous replication;

receiving a write byte rate for the storage system; and

using the RPO and the write byte rate to calculate a bandwidth for transmitting data from a first storage location to a secondary storage location.

9. ) The computer readable medium of claim 8 further comprising:

analyzing historical write byte rates over a period of time to determine peak periods for writing data from the first storage location to the secondary storage location.

10. ) The computer readable medium of claim 8 further comprising:

receiving, from a user, an initial seed value that estimates a bandwidth needed to satisfy the RPO.

11. ) The computer readable medium of claim 8 further comprising:

calculating a running queue depth equal to a write byte rate minus available bandwidth over a period of time;

using the running queue depth to calculate the bandwidth.

12. ) The computer readable medium of claim 8 further comprising:

calculating a time required to empty a queue and transmit the data from the queue to the secondary storage location.

13. ) The computer readable medium of claim 8 further comprising:

iteratively calculating new bandwidths for transmitting data from the first storage location to the second storage location until a calculated bandwidth satisfies requirements specified in the RPO.

14. ) The computer readable medium of claim 8 further comprising:

receiving an estimated bandwidth to satisfy the RPO;

generating an achieved RPO for the estimated bandwidth;

comparing the achieved RPO with the RPO.

15. ) The computer readable medium of claim 8 further comprising:

providing a graphical output that shows a distribution between multiple different RPOs and multiple different bandwidths.

16. ) A method, comprising:

receiving a recovery point objective (RPO) for a system that uses asynchronous data replication;

receiving a write byte rate for the system;

receiving a queue depth for a queue that temporarily stores data in the system; and

calculating an achieved RPO based on the write byte rate and the queue depth to determine a bandwidth for transmitting data from a first storage location to a secondary storage location.

17. ) The method of claim 16 further comprising, calculating a time to drain the queue as being equal to a depth of the queue divided by a byte per second capacity to transmit data out of the queue.

18. ) The method of claim 16 further comprising, iteratively calculating new achieved RPOs and comparing the new achieved RPOs with the RPO.

19. ) The method of claim 16 further comprising:

comparing the achieved RPO to the RPO;

calculating a second achieved RPO when a difference between the achieved RPO and RPO is greater than a predetermined threshold.

20. ) The method of claim 16 further comprising, measuring historical write byte rates over a period of time for writing data from the first storage location to the secondary storage location.