High-availability cluster with proactive maintenance
AssigneeHewlett-Packard Development Company, L.P.
InventorsKen Pomaranski, Andrew Barr
Life of this patent
Estimating the term…
Abstract
One embodiment disclosed relates to a method of preventative maintenance of a high-availability cluster. A least-recently-tested active node is determined. The least-recently-tested active node is swapped out from the HA cluster, and a stand-by node is swapped into the HA cluster. Other embodiments are also disclosed.
Claims29
A high-availability cluster apparatus, the apparatus comprising:
- a plurality of computing nodes of said cluster;
- a cluster master communicatively connected to each of the nodes;
- and
- non-volatile memory associated with the cluster master,
- wherein the non-volatile memory is configured to store data keeping track of quality measures of the nodes.
A method of pro-actively maintaining a high-availability (HA) cluster having a plurality of nodes, the method comprising:
- keeping track of status variables for the nodes;
- keeping track of quality measures for the nodes;
- and
- keeping track of freshness measures for the nodes.
A method of preventative maintenance of a high-availability (HA) cluster, the method comprising:
- determining a least-recently-tested active node;
- swapping out the least-recently-tested active node from the HA cluster;
- and
- swapping in a stand-by node into the HA cluster.
A method of moving a node of a high-availability cluster to a resource pool after the node has been repaired, the method comprising:
- changing a status of the node from an under repair status to a ready-to-be-tested status;
- executing functional tests on the node;
- setting a quality measure for the node based on results of the functional tests;
- and
- moving the node to the resource pool by changing the status of the node to a stand-by status if the qualilty measure is sufficient.
A method of adding a new node of a high-availability cluster, the method comprising:
- setting a status of the node to a ready-to-be-tested status;
- executing functional tests on the node;
- setting a quality measure for the node based on results of the functional tests;
- and
- placing the node in a resource pool by changing the status of the node to a stand-by status if the quality measure is sufficient.
Dependencies are inferred from the claim text.