System, method and mechanism to efficiently coordinate cache sharing between cluster nodes operating on the same regions of a file or the file system blocks shared among multiple files
Various systems, methods and apparatuses for coordinating the sharing of cache data between cluster nodes operating on the same data objects. One embodiment involves a first node in a cluster receiving a request for a data object, querying a global lock manager to determine if a second node in the cluster is the lock owner of the data object, receiving an indication identifying the second node as the lock owner and indicating that the data object is available in the second node's local cache, requesting the data object from the second node, and then receiving the data object from the second node's local cache. Other embodiments include determining whether the lock is a shared lock or an exclusive lock, and either pulling the data object from the local node of the second cache or receiving the data object that is pushed from the second node, as appropriate.
1. A method, comprising:
receiving a request for a data object, wherein the request is received by a first node of a cluster of nodes;
querying a global lock manager to determine if a second node is a lock owner of the data object, wherein
the cluster of nodes comprises the second node,
the second node comprises a local cache, and
the first node and the second node are separate computing devices;
determining that the second node is the lock owner and that the data object is available in the local cache of the second node;
determining that a third node has a shared lock on the data object;
waiting for a third node to complete a pending operation on the data object pursuant to the shared lock;
after the third node has completed the pending operation, requesting the data object from the local cache of the second node;
in response to requesting the data object from the local cache of the second node, the data object is pushed to the first node from the local cache of the second node, wherein
the data object is pushed to the first node, from the local cache of the second node, after the second node completes one or more pending operations on the data object; and
subsequent to the second node receiving an acknowledgement from the first node, exclusively transferring an exclusive lock to the first node, wherein
the exclusive lock is transferred exclusively to the first node subsequent to the second node receiving the acknowledgement from the first node indicating that the first node has received the data object.
2. The method of claim 1 , further comprising:
prior to requesting the data object from the second node, determining whether the second node has an exclusive lock or a shared lock on the data object.
3. The method of claim 2 , further comprising:
sending the acknowledgment to the second node, wherein
the acknowledgment is sent in response to receiving the data object.
4. The method of claim 1 , further comprising:
receiving the exclusive lock associated with the data object, wherein
the receiving the exclusive lock is performed subsequent to the receiving the data object.
5. The method of claim 1 , further comprising:
subsequent to the requesting, receiving the data object from the local cache of the second node.
6. The method of claim 1 , further comprising:
a storage area network (“SAN”), wherein
the SAN is communicatively coupled the cluster via one or more networks,
the SAN comprises a plurality of storage devices,
a network storage device comprises a copy of the data object, and
the receiving the data object from the second node is more efficient than receiving the copy from the network storage device.
7. The method of claim 1 , where
the acknowledgement further indicates that the first node has received the data object without any errors.
8. A computer system comprising:
a processor; and
a memory coupled to the processor and configured to store instructions executable by the processor, the instructions configured to
receive a request for a data object, wherein
the request is received by a first node of a cluster of nodes;
query a global lock manager to determine if a second node is a lock owner of the data object, wherein
the cluster of nodes comprises the second node,
the second node comprises a local cache, and
the first node and the second node are separate computing devices;
determine that the second node is the lock owner and that the data object is available in the local cache of the second node;
determine that a third node has a shared lock on the data object;
wait for a third node to complete a pending operation on the data object pursuant to the shared lock;
after the third node has completed the pending operation, request the data object from the local cache of the second node;
in response to requesting the data object from the local cache of the second node, the data object is pushed to the first node from the local cache of the second node, wherein
the data object is pushed to the first node, from the local cache of the second node, after the second node completes one or more pending operations; and
subsequent to the second node receiving an acknowledgement from the first node, exclusively transferring an exclusive lock to the first node, wherein
the exclusive lock is transferred exclusively to the first node subsequent to the second node receiving the acknowledgement from the first node indicating that the first node has received the data object.
9. The computer system of claim 8 , wherein the instructions are further configured to:
prior to requesting the data object from the second node, determine whether the second node has an exclusive lock or a shared lock on the data object.
10. The computer system of claim 9 , wherein the instructions are further configured to:
send the acknowledgment to the second node, wherein
the acknowledgment is sent in response to receiving the data object.
11. The computer system of claim 8 , wherein the instructions are further configured to:
receive the exclusive lock associated with the data object, wherein
the receiving the exclusive lock is performed subsequent to receiving the data object.
12. The computer system of claim 8 , wherein the instructions are further configured to:
subsequent to requesting the data object from the local cache of the second node, receive the data object from the local cache of the second node.
13. The computer system of claim 8 , further comprising:
a storage area network (“SAN”), wherein
the SAN is communicatively coupled the cluster via one or more networks,
the SAN comprises a plurality of storage devices,
a network storage device comprises a copy of the data object, and
receiving the data object from the second node is more efficient than receiving the copy from the network storage device.
14. A non-transitory computer-readable storage medium configured to store program instructions that, when executed on a processor, are configured to cause the processor to perform a method comprising:
receiving a request for a data object, wherein
the request is received by a first node of a cluster of nodes;
querying a global lock manager to determine if a second node is a lock owner of the data object, wherein
the cluster of nodes comprises the second node,
the second node comprises a local cache, and
the first node and the second node are separate computing devices;
determining that the second node is the lock owner and that the data object is available in the local cache of the second node;
determining that a third node has a shared lock on the data object;
waiting for a third node to complete a pending operation on the data object pursuant to the shared lock;
after the third node has completed the pending operation, requesting the data object from the local cache of the second node;
in response to requesting the data object from the local cache of the second node, the data object is pushed to the first node from the local cache of the second node, wherein
the data object is pushed to the first node, from the local cache of the second node, after the second node completes one or more pending operations on the data object; and
subsequent to the second node receiving an acknowledgement from the first node, exclusively transferring an exclusive lock to the first node, wherein
the exclusive lock is transferred exclusively to the first node subsequent to the second node receiving the acknowledgement from the first node indicating that the first node has received the data object.
15. The non-transitory computer-readable storage medium of claim 14 , wherein the method further comprises:
prior to requesting the data object from the second node, determining whether the second node has an exclusive lock or a shared lock on the data object.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the method further comprises:
sending the acknowledgment to the second node, wherein
the acknowledgment is sent in response to receiving the data object.
17. The non-transitory computer-readable storage medium of claim 14 , wherein the method further comprises:
receiving the exclusive lock associated with the data object, wherein
the receiving the exclusive lock is performed subsequent to the receiving the data object.
18. The non-transitory computer-readable storage medium of claim 14 , wherein the method further comprises:
subsequent to the requesting, receiving the data object from the local cache of the second node.