Load sharing cluster file systems
View Patent ↗Load sharing clusters in which each node is responsible for one or more non-overlapping subset(s) of the cluster namespace and will process only those requests that access file or directory objects in the partitioned namespace that the node controls while redirecting requests designated for other nodes. A non-overlapping subset may be migrated from a source node to a destination node, for example, for load sharing or hotspot mitigation. Migration typically includes maintaining a file virtualization link from the destination node to the source node to permit forwarding of requests by the destination node to the source node during migration of metadata and then migration of data from the source node. After migration is complete, the file virtualization link is broken and the destination node services requests for the non-overlapping subset from the migrated metadata and data.
1. A method for migrating a non-overlapping portion of data from a source file storage node to a destination file storage node selected from one of an existing file storage node in a cluster of file storage nodes and a new file storage node added to the cluster, wherein each file storage node includes a file virtualization link identifying another file storage node for each of a plurality of non-overlapping portions not owned by the file storage node, the method comprising:
updating a cluster resource to map the non-overlapping portion to the destination file storage node;
establishing metadata for the non-overlapping portion on the destination file storage node;
while establishing the metadata for the non-overlapping portion, servicing client requests received for the non-overlapping portion by the source file storage node based on a file virtualization link on the destination file storage node;
after establishing the metadata for the non-overlapping portion on the destination file storage node, copying data for the non-overlapping portion from the source file storage node to the destination file storage node;
while copying, servicing metadata requests received for the non-overlapping portion by the destination file storage node using the metadata and servicing data requests for the non-overlapping portion by the source file storage node based on the file virtualization link on the destination file storage node; and
after completion of the copying, designating the destination file storage node as the owner of the non-overlapping portion.
2. A method according to claim 1 , wherein the non-overlapping portion is migrated due to reconfiguration of the cluster.
3. A method according to claim 1 , wherein the non-overlapping portion is migrated based on loading of the source file storage node.
4. A method according to claim 1 , further comprising:
breaking the file virtualization link on the destination file storage node and establishing a file virtualization link to the destination file storage node for the non-overlapping portion on the source file storage node; and
after breaking the file virtualization link, servicing requests for the non-overlapping portion from the migrated metadata and data.
5. A non-transitory computer readable medium having stored thereon instructions for migrating a non-overlapping portion of data from a source file storage node to a destination file storage node selected from one of an existing file storage node in a cluster of file storage nodes and a new file storage node added to the cluster, wherein each file storage node includes a file virtualization link identifying another file storage node for each of a plurality of non-overlapping portions not owned by the file storage node, the medium comprising machine executable code which when executed by at least one processor, causes the processor to perform steps comprising:
updating a cluster resource to map the non-overlapping portion to the destination file storage node;
establishing metadata for the non-overlapping portion on the destination file storage node;
while establishing the metadata for the non-overlapping portion, servicing client requests received for the non-overlapping portion by the source file storage node based on a file virtualization link on the destination file storage node;
after establishing the metadata for the non-overlapping portion on the destination file storage node, copying data for the non-overlapping portion from the source file storage node to the destination file storage node;
while copying, servicing metadata requests received for the non-overlapping portion by the destination file storage node using the metadata and servicing data requests for the non-overlapping portion by the source file storage node based on the file virtualization link on the destination file storage node; and
after completion of the copying, designating the destination file storage node as the owner of the non-overlapping portion.
6. A medium according to claim 5 , wherein the non-overlapping portion is migrated due to reconfiguration of the cluster.
7. A medium according to claim 5 , wherein the non-overlapping portion is migrated based on loading of the source file storage node.
8. A medium according to claim 5 further having stored thereon instructions that when executed by the at least one processor cause the processor to perform steps further comprising:
breaking the file virtualization link on the destination file storage node and establishing a file virtualization link to the destination file storage node for the non-overlapping portion on the source file storage node; and
after breaking the file virtualization link, servicing requests for the non-overlapping portion from the migrated metadata and data.
9. An apparatus for migrating a non-overlapping portion of data from a source file storage node to a destination file storage node selected from one of an existing file storage node in a cluster of file storage nodes and a new file storage node added to the cluster, wherein each file storage node includes a file virtualization link identifying another file storage node for each of a plurality of non-overlapping portions not owned by the file storage node, the apparatus comprising:
a processor;
a memory coupled to the processor; and
a network interface unit coupled to the processor and the memory via a bus, the network interface unit configured to implement and the processor configured to execute programmed instructions stored in the memory comprising:
updating a cluster resource to map the non-overlapping portion to the destination file storage node;
establishing metadata for the non-overlapping portion on the destination file storage node;
while establishing the metadata for the non-overlapping portion, servicing client requests received for the non-overlapping portion by the source file storage node based on a file virtualization link on the destination file storage node;
after establishing the metadata for the non-overlapping portion on the destination file storage node, copying data for the non-overlapping portion from the source file storage node to the destination file storage node;
while copying, servicing metadata requests received for the non-overlapping portion by the destination file storage node using the metadata and servicing data requests for the non-overlapping portion by the source file storage node based on the file virtualization link on the destination file storage node; and
after completion of the copying, designating the destination file storage node as the owner of the non-overlapping portion.
10. An apparatus according to claim 9 wherein the non-overlapping portion is migrated due to reconfiguration of the cluster.
11. An apparatus according to claim 9 wherein the non-overlapping portion is migrated based on loading of the source file storage node.
12. An apparatus according to claim 9 wherein the processor is further configured to execute programmed instructions stored in the memory further comprising
breaking the file virtualization link on the destination file storage node and establishing a file virtualization link to the destination file storage node for the non-overlapping portion on the source file storage node; and
after breaking the file virtualization link, servicing requests for the non-overlapping portion from the migrated metadata and data.
13. A system for migrating a non-overlapping portion of data comprising:
a plurality of file storage nodes including at least a source file storage node and a destination file storage node, wherein the destination file storage node is selected from one of an existing file storage node in a cluster of file storage nodes and a new file storage node added to the cluster, wherein each file storage node includes a file virtualization link identifying another file storage node for each of a plurality of non-overlapping portion not owned by the file storage node; and
a file virtualization apparatus comprising:
a processor;
a memory coupled to the processor; and
a network interface unit coupled to the processor and the memory via a bus, the network interface unit configured to implement and the processor configured to execute programmed instructions stored in the memory comprising:
updating a cluster resource to map the non-overlapping portion to the destination file storage node;
establishing metadata for the non-overlapping portion on the destination file storage node;
while establishing the metadata for the non-overlapping portion, servicing client requests received for the non-overlapping portion by the source file storage node based on a file virtualization link on the destination file storage node;
after establishing the metadata for the non-overlapping portion on the destination file storage node, copying data for the non-overlapping portion from the source file storage node to the destination file storage node;
while copying, servicing metadata requests received for the non-overlapping portion by the destination file storage node using the metadata and servicing data requests for the non-overlapping portion by the source file storage node based on the file virtualization link on the destination file storage node; and
after completion of the copying, designating the destination file storage node as the owner of the non-overlapping portion.
14. A system according to claim 13 wherein the non-overlapping portion is migrated due to reconfiguration of the cluster.
15. A system according to claim 13 wherein the non-overlapping portion is migrated based on loading of the source file storage node.
16. A system according to claim 13 wherein the processor is further configured to execute programmed instructions stored in the memory further comprising
breaking the file virtualization link on the destination file storage node and establishing a file virtualization link to the destination file storage node for the non-overlapping portion on the source file storage node; and
after breaking the file virtualization link, servicing requests for the non-overlapping portion from the migrated metadata and data.