Cluster Families for Cluster Selection and Cooperative Replication

• US 20110145497A1
• Filed: 12/11/2009
• Published: 06/16/2011
• Est. Priority Date: 12/11/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Nohta, Takeshi, Twito, Rufus-John Yeisuke, Bish, Thomas William, Swingler, Joseph M.
• Granted Patent: US 8,812,799 B2
• Time in Patent Office: Days
• US Class Current: 711/113
• CPC Class Codes: G06F 11/1464 for networked environments
• CPC Class Codes: G06F 11/2082 Data synchronisation
• CPC Class Codes: G06F 12/0802 Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
• CPC Class Codes: G06F 12/0815 Cache consistency protocols
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0617 in relation to availability
• 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 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• 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 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 3/0686 Libraries, e.g. tape libraries, jukebox
• 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]

Abstract

An apparatus, system, and method are disclosed to create cluster families for cluster selection and cooperative replication. The clusters are grouped into family members of a cluster family base on their relationships and roles. Members of the cluster family determine which family member is in the best position to obtain replicated information and become cumulatively consistent within their cluster family. Once the cluster family becomes cumulatively consistent, the data is shared within the cluster family so that all copies within the cluster family are consistent.

Claims

1. A method for cooperative replication of multiple clusters, the method comprising:

arranging at least one subset of the multiple clusters into family members of a cluster family;

negotiating between cluster family members to determine which cluster family member is in the best position to obtain at least one outside data object from at least one cluster outside of the family;

selecting one family member of the cluster family to obtain the outside data object; and

sharing the outside data objects among the cluster family so that each cluster within the cluster family is consistent with respect to outside data objects.

2. The method of claim 1, further comprises creating relationship among cluster families based on at least one of a cluster relationship and role.

3. The method of claim 1, wherein the family member with a consistent source maintains a volume in cache in order to make the volume readily available to other family members for peer replication.

4. The method of claim 3, wherein the family member maintaining the volume in cache for the other family members relieves the outside cluster from maintaining a copy in the outside cluster cache.

5. The method of claim 1, wherein each family members in the family replicates 1/Nth volumes.

6. The method of claim 1, further comprises cooperatively serializing all replication into the cluster family.

7. The method of claim 1, wherein a first family member to replicate 1/Nth volumes informs the outside cluster that the first family member will maintain the volumes for the cluster family members and relieves the outside cluster from maintaining the volumes in the outside cluster cache.

8. The method of claim 1, further comprises achieving cumulative consistency within the cluster family of a plurality of outside data objects prior to sharing outside data objects among clusters within the cluster family.

9. The method of claim 1, further comprises favoring one of the family members in the cluster family for mount processing over clusters outside the cluster family.

10. The method of claim 1, further comprises a plurality of cluster families wherein at least one family member from each family replicates a volume.

11. The method of claim 1, further comprises a domain comprising a plurality of clusters wherein the clusters cooperate to make sure at least one family member from each family replicates a volume and the remaining clusters surrender replication requirements.

12. A system for cooperative replication of multiple clusters, the system comprising:

a network;

a plurality of sites in communication over the network, each site comprising at least one host and a storage system comprising a plurality of clusters, each cluster comprising at least one tape drive configured to access volumes stored on magnetic tape, at least one tape volume cache, and a cluster manager configured to execute computer readable programs using a processor and a memory, wherein the software readable programs comprising;

a creation module configured to setup and arrange a group of clusters into family members of a cluster family; and

a cooperative replication module configured to select a family member to cooperatively replicate data into the cluster family and achieve cumulative family consistency.

13. The system of claim 12, wherein the cooperative replication module is further configured to share replication among each family member.

14. The system of claim 13, wherein each family members in the family replicates 1/Nth volumes.

15. The system of claim 12, wherein the creation module is further configured to create cluster families based on at least one of a relationship and role between clusters.

16. The system of claim 12, wherein the cooperative replication module is further configured to achieve cumulative consistency within the cluster family of a plurality of outside data objects prior to sharing outside data objects among clusters within the cluster family.

17. A method for cooperative replication of multiple clusters, the method comprising:

receiving a copy request to copy a volume into a first cluster;

determining whether the first cluster is a family member of a cluster family;

operative, if the first cluster is a family member of the cluster family, determining whether a another family member already completed copying the volume;

operative, if another family member has not already copied the volume, designating the first cluster to inherit the copy request;

executing the copy request and cooperatively replicating the volume into the cluster family;

achieving cumulative consistency within the cluster family; and

sharing volume within the cluster family so that all copies of the volume within the cluster family are consistent.

18. The method of claim 17, further comprising:

determining whether a second family member is actively copying the volume; and

operative, if the second family member is actively copying the volume, designating the second family member to inherit the copy request.

19. The method of claim 17, further comprising:

determining whether a second family member is ready to copy but is not actively copying at this time;

operative, if the second family member is ready to copy and has not actively copying at this time, lowering copy priority of the second family member and deferring the copy request.

20. The method of claim 17, further comprising:

selecting the second family member to inherit the copy request; and

lowering copy priority of the first cluster family member and deferring the copy request.

21. The method of claim 17, further comprising:

designating the first family member to inherit the copy request as a source cluster for the cluster family;

completing the coping at the first family member;

clearing copy requested flag at the first family member;

setting copy requested flags for other family members at the first family member;

other family members inheriting the copy requested flag;

other family members complete copying; and

each family member resets copy required flags.

22. An apparatus for cooperative replication of multiple clusters, the apparatus comprising:

a creation module comprising a computer readable program executing on a processor and configured to create cluster family from a plurality of clusters, wherein the clusters are in communication over a network and each cluster comprises a cache; and

a cooperative replication module comprising a computer readable program executing on a processor and configured to cooperatively replicate data into the cluster family.

23. The apparatus of claim 22, wherein the creation module is further configured to setup and arrange a group of clusters into family members according to at least one of a cluster relationship and role.

24. The apparatus of claim 22, wherein the cooperative replication module is further configured to handle persistent replication source awareness by deferring replication.

25. The apparatus of claim 22, wherein each family members in the cluster family replicates 1/Nth volumes.

26. The apparatus of claim 22, wherein the cooperative replication module is further configured to select a family member of the cluster family to obtain outside data objects and be the source cluster for all family members within the cluster family and having the source cluster responsible for achieving cumulative consistent within the cluster family prior to sharing the outside data objects.

27. The apparatus of claim 22, further comprising:

a relationship module comprising a computer readable program executing on a processor and configured to maintain factors defining roles, rules, and relationships between cluster families and family members.

28. The apparatus of claim 22, further comprising:

a mount processing module comprising a computer readable program executing on a processor and configured to favor family members within the cluster family over other cluster families for production purposes.

29. A computer program product comprising a computer useable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

group a plurality of clusters into family members of a cluster family;

determine which family member is in the best position to obtain outside data objects from a source;

select one or more family members of the cluster family to obtain the outside data objects;

cooperatively replicate the outside data objects into the cluster family; and

share the outside data objects within the cluster family so that all copies of the outside data objects within the cluster family are consistent.

30. The computer program product of claim 29, wherein the computer readable program further causes the computer to cooperatively serializing all replication into the cluster family.

31. The computer program product of claim 29, wherein the computer readable program further causes the computer to select a family member with a consistent source, and to maintain a volume in cache in order to make the volume readily available to other family members for peer replication.

32. The computer program product of claim 29, wherein the computer readable program further causes the computer to achieve cumulative consistency within the cluster family of a plurality of outside data objects prior to sharing outside data objects among clusters within the cluster family.

33. The computer program product of claim 29, wherein the computer readable program further causes the computer to instruct each family members in the family to replicate 1/Nth volumes.

34. A method for cooperative replication of multiple clusters, the method comprising:

means for arranging a plurality of clusters into family members of a cluster family;

means for determining which family members are in the best position to copy incoming data;

means for selecting one or more family members of the cluster family to obtain the data;

means for cooperatively replicating the data into the cluster family;

means for achieving cumulative consistency within the cluster family; and

means for sharing data within the cluster family so that all copies of the data within the cluster family are consistent.