Methods and systems for maintaining cache coherency between nodes in a clustered environment by performing a bitmap lookup in response to a read request from one of the nodes
Disclosed herein are methods, systems, and processes to provide coherency across disjoint caches in clustered environments. It is determined whether a data object is owned by an owner node, where the owner node is one of multiple nodes of a cluster. If the owner node for the data object is identified by the determining, a request is sent to the owner node for the data object. However, if the owner node for the data object is not identified by the determining, selects a node in the cluster is selected as the owner node, and the request for the data object is sent to the owner node.
1. A computer-implemented method implemented in a computer system, comprising:
broadcasting an availability of a cache of a node of a plurality of nodes of a cluster, wherein
the availability of the cache is broadcast to one or more other nodes of the plurality of nodes;
receiving a lookup request at the node, wherein
the computer system implements the node,
the lookup request is received from a reader node,
the reader node is a one of the one or more other nodes, and
the lookup request is for a bitmap stored at the node;
performing a bitmap lookup on the bitmap;
determining an availability of a data object in the cache, wherein
the availability of the data object is determined based, at least in part, on a result of the bitmap lookup, and
the cache is maintained in a local storage device of the node; and
in response to the data object being available in the cache, permitting the reader node to access the data object from the cache.
2. The computer-implemented method of claim 1 , wherein
the permitting the reader node to access the data object comprises at least one of permitting the reader node to read the data object from the cache, or permitting the reader node to retrieve the data object from the cache.
3. The computer-implemented method of claim 1 , further comprising:
selecting the node as an owner node, wherein
the selecting is performed by the reader node.
4. The computer-implemented method of claim 3 , wherein
the node is selected based on at least one of
a random selection method,
a circular selection method,
a cache characteristic selection method, or
node priority.
5. The computer-implemented method of claim 1 , further comprising:
attempting to acquire a lock for the data object, wherein
the lock is managed by a global lock manager that implements a distributed locking mechanism in the cluster.
6. The computer-implemented method of claim 5 , further comprising:
in response to the lock being acquired,
performing the permitting, wherein
the permitting comprises
receiving a query for the data object, wherein
the query is received from the reader node, and
in response to a result of the query indicating that the data object is available,
receiving a request to read the data object, and
in response to the request to read the data object,
providing the reader node with read access to the data object.
7. The computer-implemented method of claim 5 , further comprising:
in response to the lock not being acquired,
selecting another node of the plurality of nodes, wherein
the selecting is performed by the reader node, and
the another node is one of the plurality of nodes other than then node.
8. The computer-implemented method of claim 5 , further comprising:
granting the lock, wherein
the lock is granted by the global lock manager.
9. The computer-implemented method of claim 8 , wherein
the lock comprises lock information regarding the data object, and
the lock information is maintained by the global lock manager.
10. The computer-implemented method of claim 1 , further comprising:
determining whether the data object is in a cache of the reader node;
in response to the data object being in the cache of the reader node, serving the data object from the cache of the reader node; and
in response to the data object not being in the cache of the reader node, sending the lookup request to the node.
11. The computer-implemented method of claim 10 , further comprising:
reading another data object from a shared storage device, wherein
the shared storage device is accessible by the plurality of nodes, and
the reading the another data object from the shared storage device is performed by the reader node;
storing the another data object in the cache of the reader node; and
serving the another data object from the cache of the reader node.
12. The computer-implemented method of claim 11 , wherein
the permitting the reader node to access the data object from the cache and the reading the another data object from the shared storage device are performed substantially simultaneously.
13. The computer-implemented method of claim 1 , further comprising:
receiving an instruction to store the data object in the cache, wherein
the data object is read from a shared storage device, and
the shared storage device is accessible by the plurality of nodes.
14. The computer-implemented method of claim 1 , further comprising:
sending a request to read the data object, wherein
the request to read the data object is sent to the node;
sending another lookup request with regard to another data object, wherein
the another lookup request is sent to another node of the plurality of nodes; and
in response to the another data object being available on the another node, sending another request to read the another data object, wherein
the another request to read the another data object is sent to the another node in parallel with the sending the request to read the data object.
15. The computer-implemented method of claim 1 , wherein
the broadcasting is performed contemporaneously with at least one of
the node being brought online,
the cache being available for sharing, or
the cache no longer being available for sharing.
16. The computer-implemented method of claim 1 , wherein
The broadcasting broadcasts cache availability information, and
the cache availability information comprises information regarding the cache that comprises at least one of
a size of a cache,
an amount of used cache space, or
an amount of free cache space.
17. The computer-implemented method of claim 1 , wherein
The broadcasting broadcasts cache availability information, and
the cache availability information is
maintained in a specific bitmap, on a per-file system basis, on a number of nodes of the plurality of nodes, or
a consistent copy of the bitmap that is maintained, on a per-file system basis.
18. The computer-implemented method of claim 1 , wherein
the broadcasting broadcasts cached data information, and
the cached data information comprises metadata that identifies one or more data objects that are cached tin the cache.
19. A non-transitory computer-readable storage medium, comprising program instructions, which, when executed by one or more processors of a computing system, perform a method comprising:
broadcasting an availability of a cache of a node of a plurality of nodes of a cluster, wherein
the availability of the cache is broadcast to one or more other nodes of the plurality of nodes;
receiving a lookup request at the node, wherein
the computer system implements the node,
the lookup request is received from a reader node,
the reader node is a one of the one or more other nodes, and
the lookup request is for a bitmap stored at the node;
performing a bitmap lookup on the bitmap;
determining an availability of a data object in the cache, wherein
the availability of the data object is determined based, at least in part, on a result of the bitmap lookup, and
the cache is maintained in a local storage device of the node; and
in response to the data object being available in the cache, permitting the reader node to access the data object from the cache.
20. The non-transitory computer-readable storage medium of claim 19 , wherein
the permitting the reader node to access the data object comprises at least one of
permitting the reader node to read the data object from the cache, or
permitting the reader node to retrieve the data object from the cache.
21. The non-transitory computer-readable storage medium of claim 19 , wherein the method further comprises:
attempting to acquire a lock for the data object, wherein
the lock is managed by a global lock manager that implements a distributed locking mechanism in the cluster.
22. The non-transitory computer-readable storage medium of claim 21 , wherein the method further comprises:
in response to the lock being acquired,
performing the permitting, wherein
the permitting comprises
receiving a query for the data object, wherein
the query is received from the reader node, and
in response to a result of the query indicating that the data object is available,
receiving a request to read the data object, and
in response to the request to read the data object,
providing the reader node with read access to the data object.
23. The non-transitory computer-readable storage medium of claim 21 , wherein the method further comprises:
in response to the lock not being acquired,
selecting another node of the plurality of nodes, wherein
the selecting is performed by the reader node, and
the another node is one of the plurality of nodes other than then node.
24. A computing system comprising:
one or more processors; and
a computer-readable storage medium coupled to the one or more processors,
comprising program instructions, which, when executed by the one or more processors, perform a method comprising
broadcasting an availability of a cache of a node of a plurality of nodes of
a cluster, wherein
the availability of the cache is broadcast to one or more other nodes of the plurality of nodes,
receiving a lookup request at the node, wherein
the computing system implements the node,
the lookup request is received from a reader node,
the reader node is a one of the one or more other nodes, and
the lookup request is for a bitmap stored at the node,
performing a bitmap lookup on the bitmap,
determining an availability of a data object in the cache,
wherein
the availability of the data object is determined based, at least in part, on a result of the bitmap lookup, and
the cache is maintained in a local storage device of the node, and
in response to the data object being available in the cache, permitting the reader node to access the data object from the cache.