Environmental aware witness for active-active storage cluster nodes
The system, devices, and methods disclosed herein relate to a dynamic, robust method for choosing a “winner” in an active-active data storage network. In the systems and methods disclosed herein, two or more intelligent nodes within an active-active data storage network periodically exchange operational parameters in an ongoing negotiation regarding who should be the winner in the event of a communication failure within the network. The winner is chosen dynamically based on the operational parameters. A witness is kept apprised of the winner. In the event of a communication failure between the two nodes, the winner is chosen by the witness based on the most recently negotiated lock file reported by one or both of the nodes.
1. A method for dynamically assigning a winning node in an active-active data storage network comprising the steps of:
a. periodically exchanging operational parameters between two nodes in an active-active data storage network;
b. negotiating between the two nodes which would be the winner in the event a quality measurement of a communication link between the two nodes falls below a threshold value, wherein the negotiation includes evaluating at least two operational parameters of each individual node;
c. choosing a winner based on the at least two operational parameters of each individual node;
d. recording a winner in a lock file; and
e. transmitting the lock file to a witness.
2. The method of claim 1 wherein the two or more operational parameters are accorded differing priorities.
3. The method of claim 1 wherein the two or more operational parameters are one or more of a synchronous communication connection to a third storage node, an asynchronous communication connection to a third storage node, a bias role, a non-bias role, a data replication pathway, a memory board state, or a faulted hardware state.
4. The method of claim 1 wherein the quality measurement is a split-brain state.
5. The method of claim 1 further comprising communicating the winner to at least one of the nodes after the quality threshold of the communication link has fallen below a threshold.
6. The method of claim 1 wherein the lock file further contains at least two operational parameters for at least one node.
7. A system for managing an active-active distributed data processing network, comprising:
a. A first intelligent storage node and a second intelligent storage node in an active-active network configuration connected via a communication link, wherein the first intelligent storage node and the second intelligent storage node are configured to monitor a quality measurement of the communication link;
b. a witness node communicatively coupled to the first intelligent storage node and the second intelligent storage node; and
c. a processor having logic stored thereon configured to:
i. periodically exchange operational parameters between two nodes in an active-active data storage network;
ii. negotiate between the two nodes which would be the winner in the event a quality measurement of a communication link between the two nodes falls below a threshold value, wherein the negotiation includes evaluating at least two operational parameters of each individual node;
iii. choose a winner based on the at least two operational parameters of each individual node;
iv. record at least the two operational parameters for each individual node and a winner in a lock file; and
v. transmit the lock file to a witness.
8. The system of claim 7 wherein the two or more operational parameters are accorded differing priorities.
9. The system of claim 7 wherein the two or more operational parameters are one or more of a synchronous communication connection to a third storage node, an asynchronous communication connection to a third storage node, a bias role, a non-bias role, a data replication pathway, a memory board state, or a faulted hardware state.
10. The system of claim 7 wherein the quality measurement is a split-brain state.
11. The system of claim 7 wherein the processor is further configured to communicate the winner to at least one of the nodes after the quality threshold of the communication link has fallen below a threshold.
12. The system of claim 7 wherein the lock file further contains at least two operational parameters for at least one node.
13. A non-transitory computer readable storage medium containing software for dynamically assigning a winning node in an active-active data storage network comprising performing the steps of:
a. periodically exchanging operational parameters between two nodes in an active-active data storage network;
b. negotiating between the two nodes which would be the winner in the event a quality measurement of a communication link between the two nodes falls below a threshold value, wherein the negotiation includes evaluating at least two operational parameters of each individual node;
c. choosing a winner based on the at least two operational parameters of each individual node;
d. recording at least the two operational parameters for each individual node and a winner in a lock file; and
e. transmitting the lock file to a witness.
14. The non-transitory computer readable storage medium of claim 13 wherein the two or more operational parameters are accorded differing priorities.
15. The non-transitory computer readable storage medium of claim 13 wherein the two or more operational parameters are one or more of a synchronous communication connection to a third storage node, an asynchronous communication connection to a third storage node, a bias role, a non-bias role, a data replication pathway, a memory board state, or a faulted hardware state.
16. The non-transitory computer readable storage medium of claim 13 wherein the quality measurement is a split-brain state.
17. The non-transitory computer readable storage medium of claim 13 further comprising communicating the winner to at least one of the nodes after the quality threshold of the communication link has fallen below a threshold.
18. The non-transitory computer readable storage medium of claim 13 wherein the lock file further contains at least two operational parameters for at least one node.