Systems and methods for application-state, distributed replication table cache poisoning

Patent metadata

Field	Value
Publication number	US-9621668-B2
Application number	US-201414245299-A
Country	US
Kind code	B2
Filing date	Apr 4, 2014
Priority date	Apr 6, 2013
Publication date	Apr 11, 2017
Grant date	Apr 11, 2017

Abstract

The present application is directed towards invalidating (also referred to as poisoning) ASDR table entries that are determined to be inaccurate because of changes to a multi-node system. For example, when a node leaves or enters a multi-node system, the ownership of the entries in the ASDR table can change thus invalidating cached and replica entries. More specifically, the system and methods disclosed herein include searching an ASDR table for cached entries responsive to the system determining the multi-node system has changed. After finding a cached entry, the system may determine if the entry should be poisoned. The decision to poison the entry may be responsive to the creation time of the entry, the time when the change to the multi-node system occurred, and in the case of a replica, the owner of the replica's position in a replication chain relative to source of the replica.

First claim

What is claimed is:

1. A method for invalidating a cached entry in an application-state, distributed replication table to track resources of applications across a cluster of nodes, the method comprising:
maintaining, across each node in a cluster of nodes an application-state, distributed replication table comprising entries to track resources of applications across the cluster of nodes, each of the nodes in the cluster of nodes owning one or more partitions of the application-state, distributed replication table;
determining, by a first node in the cluster of nodes, that a second node exited the cluster;
identifying, by the first node in the cluster of nodes, a plurality of entries assigned to the second node and stored in cache by the first node;
determining, by the first node in the cluster of nodes, that a third node in the cluster of nodes is within a replication chain of the second node and contains a valid copy of the plurality of entries assigned to the second node, wherein the replication chain identifies a plurality of nodes in the cluster of nodes to which the second node in the cluster of nodes replicated the entries in the one or more partitions owned by the second node;
marking, by the first node in the cluster of nodes, the identified entries as belonging to the third node in the cluster of nodes; and
obtaining, by the first node in the cluster of nodes, each of the marked entries from the third node.

2. The method of claim 1 , wherein marking further comprises setting the identified entries to an unusable value.

3. The method of claim 1 , further comprising purging the identified entries from the application-state, distributed replication table.

4. The method of claim 1 , further comprising determining, by the first node in the cluster of nodes, a last time the identified entries were accessed or updated.

5. The method of claim 4 , wherein obtaining each of the marked entries from the third node is responsive to the last time the identified entries were accessed or updated being greater than a predetermined amount of time.

6. The method of claim 1 , further comprising marking, by the first node, each of the identified plurality of entries as a replica copy.

7. The method of claim 1 , wherein obtaining each of the marked entries from the third node is responsive to receiving a request for one of the identified plurality of entries assigned to the second node and stored in cache by the first node.

8. The method of claim 1 , wherein the third node is a new owner node of the identified plurality of entries previously assigned to the second node.

9. The method of claim 1 , wherein the third node stores a replica of each of the identified plurality of entries previously assigned to the second node.

10. A system for invalidating a cached entry in an application-state, distributed replication table to track resources of applications across a cluster of nodes, the system comprising:
a cluster of nodes,
each of the cluster of nodes configured to maintain an application-state, distributed replication table comprising entries to track resources of applications across the cluster of nodes, each of the nodes in the cluster of nodes owning one or more partitions of the application-state, distributed replication table,
wherein a first node is configured to:
determine that a second node exited the cluster;
identify a plurality of entries assigned to the second node and stored in cache by the first node;
determine that a third node in the cluster of nodes is within a replication chain of the second node and contains a valid copy of the plurality of entries assigned to the second node, wherein the replication chain identifies a plurality of nodes in the cluster of nodes to which the second node in the cluster of nodes replicated the entries in the one or more partitions owned by the second node;
mark the identified entries as belonging to third node in the cluster of nodes; and
obtain each of the marked entries from the third node.

11. The system of claim 10 , wherein the first node is further configured to mark the identified entries to an unusable value.

12. The system of claim 10 , wherein the first node is further configured to purge the identified entries from the application-state, distributed replication table.

13. The system of claim 10 , wherein the first node is further configured to determine a last time the identified entries were accessed or updated.

14. The system of claim 13 , wherein the first node is further configured to obtain each of the marked entries from the third node responsive to the last time the identified entries were accessed or updated being greater than a predetermined amount of time.

15. The system of claim 10 , wherein the first node is further configured to mark each of the identified plurality of entries as a replica copy.

16. The system of claim 10 , wherein the first node is further configured to obtain each of the marked entries from the third node responsive to receiving a request for one of the identified plurality of entries assigned to the second node and stored in cache by the first node.

17. The system of claim 10 , wherein the third node is a new owner node of the identified plurality of entries previously assigned to the second node.

18. The system of claim 10 , wherein the third node stores a replica of each of the identified plurality of entries previously assigned to the second node.

Assignees

• Citrix Systems Inc

Inventors

• Kamath Sandeep
• Arumugam Mahesh
• Shetty Anil
• Sikha Gopinath
• Sridhar Jaidev

Classifications

• H04L43/0852

  Delays · CPC title

• H04L67/1097 Primary

  for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] · CPC title

• H04L67/2842 Primary

  Electricity · mapped topic

• G06F17/3033

  Physics · mapped topic

• H04L67/2852

  Electricity · mapped topic