Propagation of updates for attributes of a storage object from an owner node of the storage object to other nodes

• US 7,991,822 B2
• Filed: 08/29/2007
• Issued: 08/02/2011
• Est. Priority Date: 08/29/2007
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Young, Michael Wayne, Reid, Mark Albert, Bish, Thomas William, Swingler, Joseph M.
• Primary Examiner(s): Chankong; Dohm
• Assistant Examiner(s): UTREJA, NEERAJ K
• Application Number:
  US11/847,214
• Publication Number:
  US 20090063411A1
• Time in Patent Office: 1,434 Days
• Field of Search: 709/200
• US Class Current: 709/200
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor

Abstract

Local versions of attributes of a storage object are maintained at a plurality of nodes, wherein a first attribute designates a first node of the plurality of nodes as an owner node for the storage object, and wherein a second attribute includes information to resolve validity of ownership of the storage object among the plurality of nodes. The owner node communicates changes to be made to the local versions of the attributes at other nodes of the plurality of nodes. A second node of the plurality of nodes requests ownership of the storage object. The first attribute is updated to designate the second node of the plurality of nodes as the owner node, in response to determining from the second attribute that the validity of ownership of the storage object allows the second node to inherit ownership of the storage object once the first node surrenders ownership of the storage object.

Claims

1. A method, comprising:

maintaining local versions of attributes of a storage object at a plurality of nodes, wherein a first attribute designates a first node of the plurality of nodes as an owner node for the storage object, and wherein a second attribute includes information to resolve validity of ownership of the storage object among the plurality of nodes via an ownership validity information data structure, wherein ownership validity level for each node of the plurality of nodes is provided by the ownership validity information data structure;

communicating, by the owner node, changes to be made to the local versions of the attributes at other nodes of the plurality of nodes;

requesting, by a second node of the plurality of nodes, ownership of the storage object;

updating the first attribute to designate the second node of the plurality of nodes as the owner node, in response to determining for the storage object that the ownership validity level corresponding to the second node is greater than the ownership validity level corresponding to the first node;

receiving, a request for an operation on the storage object, at the owner node from a third node of the plurality of nodes, wherein the third node is a peer node of the owner node, wherein the operation is capable of being performed in parallel on the storage object while the storage object is currently busy within the owner node, wherein the operation is not a protected operation, and wherein the protected operation on the storage object is performed only by the owner node of the storage object; and

executing, by the owner node, the operation on the storage object on behalf of the third node that is the peer node of the owner node , wherein the executing of the operation on the storage object by the owner node allows the operation to succeed without movement of ownership of the storage object, and wherein the executing of the operation on the storage object by the owner node serializes all parallel operations, wherein the attributes are properties of the storage object, and wherein;

the owner node receives a request for a query operation on the storage object or on properties of the storage object on behalf of the third node, and the owner node performs the query operation on the storage object without transfer of ownership of the storage object and without being required to lock down the storage object;

the owner node initiates equivalent updates against the storage object and corresponding properties of the storage object against one or more other nodes when the one or more other nodes are available;

the owner node tracks pending updates against the storage object and corresponding properties of the storage object against the one or more other nodes when the one or more other nodes become unavailable;

only the owner node can reconcile all pending updates against the storage object and the corresponding properties of the storage object to the one or more other nodes when the one or more other nodes become available;

the owner node initiates a transfer of ownership of the storage object to another node of the plurality of nodes when the owner node is to become unavailable;

the owner node performs a reconciliation process prior to surrendering ownership of the storage object to another node that is marked as down-level with respect to the storage object or to the corresponding properties of the storage object, wherein the another node requests the reconciliation process without ownership transfer; and

updates to properties of a storage object within another node initiated by the owner node only occurs after validating ownership level properties of the owner node with respect to ownership level properties of the another node.

2. The method of claim 1, further comprising:

reserving a lock on the storage object, by the owner node, in response to determining that the owner node needs to modify data of the storage object;

modifying the data of the storage object, by the owner node, in response to reserving the lock; and

releasing the lock on the storage object, by the owner node, in response to modifying the data on the storage object, wherein the releasing of the lock permits a node that is different from the owner node in the plurality of nodes to request ownership of the storage object.

3. The method of claim 1, wherein each node of the plurality of nodes comprises a cluster of a plurality of clusters, wherein the plurality of clusters comprise a domain, wherein the storage object is a shared object for the plurality of clusters of the domain, wherein a stored object is a logical object that is physically stored on a device included in the domain, the method further comprising:

receiving, a request at the owner node from the third node, for transfer of ownership of the storage object;

determining, whether a lock on the storage object is reserved by the owner node; and

transferring, the ownership to the third node, in response to determining that the lock on the storage object is not reserved by the owner node.

4. A system, comprising:

a memory; and

a processor coupled to the memory, wherein the processor executes operations, the operations comprising;

maintaining local versions of attributes of a storage object at a plurality of nodes, wherein a first attribute designates a first node of the plurality of nodes as an owner node for the storage object, and wherein a second attribute includes information to resolve validity of ownership of the storage object among the plurality of nodes via an ownership validity information data structure, wherein ownership validity level for each node of the plurality of nodes is provided by the ownership validity information data structure;

communicating, by the owner node, changes to be made to the local versions of the attributes at other nodes of the plurality of nodes;

requesting, by a second node of the plurality of nodes, ownership of the storage object;

updating the first attribute to designate the second node of the plurality of nodes as the owner node, in response to determining for the storage object that the ownership validity level corresponding to the second node is greater than the ownership validity level corresponding to the first node;

receiving, a request for an operation on the storage object, at the owner node from a third node of the plurality of nodes, wherein the third node is a peer node of the owner node, wherein the operation is capable of being performed in parallel on the storage object while the storage object is currently busy within the owner node, wherein the operation is not a protected operation, and wherein the protected operation on the storage object is performed only by the owner node of the storage object; and

executing, by the owner node, the operation on the storage object on behalf of the third node that is the peer node of the owner node, wherein the executing of the operation on the storage object by the owner node allows the operation to succeed without movement of ownership of the storage object, and wherein the executing of the operation on the storage object by the owner node serializes all parallel operations, wherein the attributes are properties of the storage object, and wherein;

the owner node receives a request for a query operation on the storage object or on properties of the storage object on behalf of the third node, and the owner node performs the query operation on the storage object without transfer of ownership of the storage object and without being required to lock down the storage object;

the owner node initiates equivalent updates against the storage object and corresponding properties of the storage object against one or more other nodes when the one or more other nodes are available;

the owner node tracks pending updates against the storage object and corresponding properties of the storage object against the one or more other nodes when the one or more other nodes become unavailable;

only the owner node can reconcile all pending updates against the storage object and the corresponding properties of the storage object to the one or more other nodes when the one or more other nodes become available;

the owner node initiates a transfer of ownership of the storage object to another node of the plurality of nodes when the owner node is to become unavailable;

the owner node performs a reconciliation process prior to surrendering ownership of the storage object to another node that is marked as down-level with respect to the storage object or to the corresponding properties of the storage object, wherein the another node requests the reconciliation process without ownership transfer; and

updates to properties of a storage object within another node initiated by the owner node only occurs after validating ownership level properties of the owner node with respect to ownership level properties of the another node.

5. The system of claim 4, the operations further comprising:

reserving a lock on the storage object, by the owner node, in response to determining that the owner node needs to modify data of the storage object;

modifying the data of the storage object, by the owner node, in response to reserving the lock; and

releasing the lock on the storage object, by the owner node, in response to modifying the data on the storage object, wherein the releasing of the lock permits a node that is different from the owner node in the plurality of nodes to request ownership of the storage object.

6. The system of claim 4, wherein each node of the plurality of nodes comprises a cluster of a plurality of clusters, wherein the plurality of clusters comprise a domain, wherein the storage object is a shared object for the plurality of clusters of the domain, wherein a stored object is a logical object that is physically stored on a device included in the domain, the operations further comprising:

receiving, a request at the owner node from the third node, for transfer of ownership of the storage object;

determining, whether a lock on the storage object is reserved by the owner node; and

transferring, the ownership to the third node, in response to determining that the lock on the storage object is not reserved by the owner node.

7. A computer readable storage device, wherein code stored in the computer readable storage device when executed by a computer causes operations, the operations comprising:

maintaining local versions of attributes of a storage object at a plurality of nodes, wherein a first attribute designates a first node of the plurality of nodes as an owner node for the storage object, and wherein a second attribute includes information to resolve validity of ownership of the storage object among the plurality of nodes via an ownership validity information data structure, wherein ownership validity level for each node of the plurality of nodes is provided by the ownership validity information data structure;

communicating, by the owner node, changes to be made to the local versions of the attributes at other nodes of the plurality of nodes;

requesting, by a second node of the plurality of nodes, ownership of the storage object;

updating the first attribute to designate the second node of the plurality of nodes as the owner node, in response to determining for the storage object that the ownership validity level corresponding to the second node is greater than the ownership validity level corresponding to the first node;

receiving, a request for an operation on the storage object, at the owner node from a third node of the plurality of nodes, wherein the third node is a peer node of the owner node, wherein the operation is capable of being performed in parallel on the storage object while the storage object is currently busy within the owner node, wherein the operation is not a protected operation, and wherein the protected operation on the storage object is performed only by the owner node of the storage object; and

executing, by the owner node, the operation on the storage object on behalf of the third node that is the peer node of the owner node, wherein the executing of the operation on the storage object by the owner node allows the operation to succeed without movement of ownership of the storage object, and wherein the executing of the operation on the storage object by the owner node serializes all parallel operations, wherein the attributes are properties of the storage object, and wherein;

the owner node receives a request for a query operation on the storage object or on properties of the storage object on behalf of the third node, and the owner node performs the query operation on the storage object without transfer of ownership of the storage object and without being required to lock down the storage object;

the owner node initiates equivalent updates against the storage object and corresponding properties of the storage object against one or more other nodes when the one or more other nodes are available;

the owner node tracks pending updates against the storage object and corresponding properties of the storage object against the one or more other nodes when the one or more other nodes become unavailable;

only the owner node can reconcile all pending updates against the storage object and the corresponding properties of the storage object to the one or more other nodes when the one or more other nodes become available;

the owner node initiates a transfer of ownership of the storage object to another node of the plurality of nodes when the owner node is to become unavailable;

the owner node performs a reconciliation process prior to surrendering ownership of the storage object to another node that is marked as down-level with respect to the storage object or to the corresponding properties of the storage object, wherein the another node requests the reconciliation process without ownership transfer; and

updates to properties of a storage object within another node initiated by the owner node only occurs after validating ownership level properties of the owner node with respect to ownership level properties of the another node.

8. The computer readable storage device of claim 7, the operations further comprising:

reserving a lock on the storage object, by the owner node, in response to determining that the owner node needs to modify data of the storage object;

modifying the data of the storage object, by the owner node, in response to reserving the lock; and

releasing the lock on the storage object, by the owner node, in response to modifying the data on the storage object, wherein the releasing of the lock permits a node that is different from the owner node in the plurality of nodes to request ownership of the storage object.

9. The computer readable storage device of claim 7, wherein each node of the plurality of nodes comprises a cluster of a plurality of clusters, wherein the plurality of clusters comprise a domain, wherein the storage object is a shared object for the plurality of clusters of the domain, wherein a stored object is a logical object that is physically stored on a device included in the domain, the operations further comprising:

receiving, a request at the owner node from the third node, for transfer of ownership of the storage object;

determining, whether a lock on the storage object is reserved by the owner node; and

transferring, the ownership to the third node, in response to determining that the lock on the storage object is not reserved by the owner node.

10. A method for deploying computing infrastructure, comprising integrating computer-readable code into a computing system, wherein the code in combination with the computing system is capable of performing:

maintaining local versions of attributes of a storage object at a plurality of nodes, wherein a first attribute designates a first node of the plurality of nodes as an owner node for the storage object, and wherein a second attribute includes information to resolve validity of ownership of the storage object among the plurality of nodes via an ownership validity information data structure, wherein ownership validity level for each node of the plurality of nodes is provided by the ownership validity information data structure;

communicating, by the owner node, changes to be made to the local versions of the attributes at other nodes of the plurality of nodes;

requesting, by a second node of the plurality of nodes, ownership of the storage object;

updating the first attribute to designate the second node of the plurality of nodes as the owner node, in response to determining for the storage object that the ownership validity level corresponding to the second node is greater than the ownership validity level corresponding to the first node;

receiving, a request for an operation on the storage object, at the owner node from a third node of the plurality of nodes, wherein the third node is a peer node of the owner node, wherein the operation is capable of being performed in parallel on the storage object while the storage object is currently busy within the owner node, wherein the operation is not a protected operation, and wherein the protected operation on the storage object is performed only by the owner node of the storage object; and

executing, by the owner node, the operation on the storage object on behalf of the third node that is the peer node of the owner node, wherein the executing of the operation on the storage object by the owner node allows the operation to succeed without movement of ownership of the storage object, and wherein the executing of the operation on the storage object by the owner node serializes all parallel operations, wherein the attributes are properties of the storage object, and wherein;

the owner node receives a request for a query operation on the storage object or on properties of the storage object on behalf of the third node, and the owner node performs the query operation on the storage object without transfer of ownership of the storage object and without being required to lock down the storage object;

the owner node initiates equivalent updates against the storage object and corresponding properties of the storage object against one or more other nodes when the one or more other nodes are available;

the owner node tracks pending updates against the storage object and corresponding properties of the storage object against the one or more other nodes when the one or more other nodes become unavailable;

only the owner node can reconcile all pending updates against the storage object and the corresponding properties of the storage object to the one or more other nodes when the one or more other nodes become available;

the owner node initiates a transfer of ownership of the storage object to another node of the plurality of nodes when the owner node is to become unavailable;

the owner node performs a reconciliation process prior to surrendering ownership of the storage object to another node that is marked as down-level with respect to the storage object or to the corresponding properties of the storage object, wherein the another node requests the reconciliation process without ownership transfer; and

updates to properties of a storage object within another node initiated by the owner node only occurs after validating ownership level properties of the owner node with respect to ownership level properties of the another node.

11. The method for deploying computing infrastructure of claim 10, wherein the code in combination with the computing system is further capable of performing:

reserving a lock on the storage object, by the owner node, in response to determining that the owner node needs to modify data of the storage object;

modifying the data of the storage object, by the owner node, in response to reserving the lock; and

releasing the lock on the storage object, by the owner node, in response to modifying the data on the storage object, wherein the releasing of the lock permits a node that is different from the owner node in the plurality of nodes to request ownership of the storage object.

12. The method for deploying computing infrastructure of claim 10, wherein each node of the plurality of nodes comprises a cluster of a plurality of clusters, wherein the plurality of clusters comprise a domain, wherein the storage object is a shared object for the plurality of clusters of the domain, wherein a stored object is a logical object that is physically stored on a device included in the domain, wherein the code in combination with the computing system is further capable of performing:

receiving, a request at the owner node from the third node, for transfer of ownership of the storage object;

determining, whether a lock on the storage object is reserved by the owner node; and

transferring, the ownership to the third node, in response to determining that the lock on the storage object is not reserved by the owner node.