Site asymmetric topology reconciliation in a computer cluster
AssigneeInternational Business Machines Corporation
InventorsMyung M. Bae, Esdras E. Cruz-Aguilar, Perinkulam I. Ganesh, Savitri Hunasheekatti, Dimpu K. Nath
Life of this patent
Estimating the term…
Abstract
A site asymmetric topology reconciliation module (SATRM) provides a stable topology for nodes located at different sites of the cluster during loss and reconnection of communication links between the sites. The SATRM monitors the cluster topology for changes in communication links between nodes. When there is an unstable cluster topology due to a loss in the communication links, the SATRM severs links to one or more sites to create a stable topology. When a communication links recovers, the SATRM merges sites to create a stable topology with the sites connected with the recovered communication links.
Claims14
An article of manufacture comprising software residing on a physical computer readable storage medium, the software comprising:
- a site asymmetric topology reconciliation module (SATRM) that monitors communication links of a computer cluster and determines if there are sites in the computer cluster with an asymmetric view of other sites, wherein the SATRM severs at least one communication links to form a stable topology when there is a site with an asymmetric view of the cluster;
- and
- wherein the SATRM severs one or more communication links to form a stable topology by making the communication link a restricted link and by discarding any message over the communication link other than health messages.
A computer-implemented method executed by at least one processor for site asymmetric topology reconciliation in a computer cluster comprising:
- monitoring communication links in the computer cluster;
- determining if there are sites in the computer cluster with an asymmetric view of other sites in the computer cluster;
- when there is a site with an asymmetric view of the cluster, severing at least one communication link to form a stable topology;
- and
- wherein the step of severing one or more communication links to form a stable topology further comprises making the communication link a restricted link and by discarding any message over the communication link other than health messages.
A computer-implemented method executed by at least one processor for site asymmetric topology reconciliation in a computer cluster comprising:
- monitoring communication links in the computer cluster;
- determining if there are sites in the computer cluster with an asymmetric view of other sites in the computer cluster, wherein the step of severing one or more communication links to form a stable topology further comprises making the communication link a restricted link and by discarding any message over the communication link other than health messages;
- when there is a site with an asymmetric view of the cluster, severing at least one communication link to form a stable topology;
- determining the cluster does not have sites with an asymmetric view and attempting to merge sites with healed links to form a larger cluster topology;
- and
- determining the cluster has a stable topology when nodes on all sites of the computer cluster see the same total count of the upbeat state and the downbeat state.
Dependencies are inferred from the claim text.