Traitement en cours

Veuillez attendre...

PATENTSCOPE sera indisponible durant quelques heures pour des raisons de maintenance le mardi 27.07.2021 à 12:00 PM CEST
Paramétrages

Paramétrages

Aller à Demande

1. WO2011051164 - PERMUTATION DE VOLUMES À RÉPLICATION DYNAMIQUE DANS UNE GRAPPE

Note: Texte fondé sur des processus automatiques de reconnaissance optique de caractères. Seule la version PDF a une valeur juridique

[ EN ]

CLAIMS

1. A reboot method comprising:

configuring each node in a cluster with a listing of two boot volumes;

storing the listing of the boot volumes for each node in flash memory of each node, including defining the boot volume list as comprising a first logical path between a node and a primary storage subsystem, and a second logical path between the node and a secondary storage subsystem, wherein the first logical path points to the preferred boot volume and the second logical path points to a non-preferred boot volume;

changing the roles of the first and second logical paths in response to a dynamic replica volume swap operation for each node participating in the dynamic replica volume swap operation, including directing the first logical path to the non-preferred boot volume on the secondary storage subsystem and directing the second logical path to the preferred boot volume in the primary storage subsystem; and

during reboot of a third node that was inactivate during the dynamic replica volume swap operation, changing the ordering of the first and second logical paths in the third node.

2. The method of claim 1, further comprising for the third node that was inactive during the dynamic replica volume swap operation, consulting the listing of boot volumes in local flash memory and booting the node from the first logical path identified in the flash memory.

3. The method of claim 2, further comprising consulting a management node for determining an identity of the logical path to the preferred boot volume as well as a location of data volumes, before accessing any data volumes.

4. The method of claim 3, further comprising modifying a list of logical paths to boot volumes in flash memory of the rebooted node to reflect an accurate ordering of the preferred logical paths.

5. The method of claim 4, further comprising in response to an incorrect listing of logical paths to boot volumes for a node, rebooting the node after correcting the listing of logical paths.

6. The method of claim 1, further comprising the step of changing the roles of the first and second logical paths for each active node in the cluster.

7. A computer system, comprising:

a computer cluster with at least two nodes, each node in communication with an associated processor and flash memory, and each node in communication with a

management node;

a list of least two boot volumes maintained in flash memory of each node;

the flash memory to store the list of boot volumes for each node, including a first logical path between a node and a primary storage subsystem, and a second logical path between the node and a secondary storage subsystem, wherein the first logical path points to the preferred boot volume and the second logical path points to a non-preferred boot volume; a manager to change the roles of the first and second logical paths responsive to a dynamic replica volume swap operation and for each participant node in the operation, including the manager to direct the first logical path to the non-preferred boot volume on the secondary storage subsystem, and to direct the second logical path to the preferred boot volume on the primary storage subsystem; and

during a reboot of the third node that was inactive during the dynamic replica volume swap operation, the manager to change the ordering of the first and second logical paths in a third node.

8. The system of claim 7, further comprising for the third node that was inactive during the dynamic replica volume swap operation, a node manager to consult the listing of boot volumes in local flash memory and boot the node from the first logical path identified in the flash memory.

9. The system of claim 8, further comprising the manager to consult a management node to determine an identity of the logical path to the preferred boot volume as well as a location of data volumes, before accessing any data volumes.

10. The system of claim 9, further comprising the manager to modify a list of logical paths to boot volumes in flash memory of the rebooted node to reflect an accurate order of the preferred logical paths.

11. The system of claim 10, further comprising in response to an incorrect listing of logical paths to boot volumes for a node, the node manager to reboot the node after correcting the listing of logical paths.

12. An article comprising:

a computer-readable carrier including computer program instructions configured to accommodate a dynamic replica volume swap operation in an open system, comprising: instructions to configure each node in a cluster with a listing of two boot volumes; instructions to store the listing of the boot volumes for each node in flash memory of each node, wherein the listing defines the boot volume list as comprising a first logical path between a node and a primary storage subsystem, and a second logical path between the node and a secondary storage subsystem, wherein the first logical path points to the preferred boot volume and the second logical path points to a non-preferred boot volume;

instructions to change the roles of the first and second logical paths in response to a dynamic replica volume swap operation for each node participating in the dynamic replica volume swap operation, including directing the first logical path to the non-preferred boot volume on the secondary storage subsystem and directing the second logical path to the preferred boot volume in the primary storage subsystem; and

during reboot of a third node that was inactivate during the dynamic replica volume swap operation, instructions to change the ordering of the first and second logical paths in the third node.

13. The article of claim 12, further comprising for the third node that was inactive during the dynamic replica volume swap operation, instructions to consult the listing of boot volumes in local flash memory and booting the node from the first logical path identified in the flash memory.

14. The article of claim 13, further comprising instructions to consult a management node to determine an identity of the logical path to the preferred boot volume as well as a location of data volumes, before accessing any data volumes.

15. The article of claim 14, further comprising instructions to modify a list of logical paths to boot volumes in flash memory of the rebooted node to reflect an accurate ordering of the preferred logical paths.

16. The article of claim 15, further comprising in response to an incorrect listing of logical paths to boot volumes for a node, instructions to reboot the node after correcting the listing of logical paths.

17. A method accommodating a dynamic replica volume swap operation in a cluster computer system, comprising:

storing a list of boot volumes for each node in flash memory local to each node; defining the boot volume list as comprising a first logical path between a node and a primary storage subsystem, and a second logical path between the node and a secondary storage subsystem, wherein the first logical path points to the preferred boot volume and the second logical path points to a non-preferred boot volume;

conducting a dynamic replica volume swap operation for changing the roles of the first and second logical paths;

during boot of a third node that was inactivate during the dynamic replica volume swap operation, communicating the ordering of the first and second logical paths in the third node; and

the third node booting from a boot volume assigned to the second logical path.