Distribution of workloads in cluster environment using server warranty information
Systems and methods take into account the criticality of workloads, the warranty needs of workloads, the warranty available time, and the lifetime of a workload to provide an optimal solution that ensures servers are used to highest extent. The warranty health of servers is computed and categorized as critical, warning, or healthy based on the number of days remaining in warranty. Workloads are tagged as short-term or long-term workloads. Workloads are also classified based on criticality. The quarantine mode for proactive high availability of servers is divided into multiple modes, including a long-time, critical-workload quarantine mode, a critical-workload quarantine mode, and a standard quarantine mode. Servers that are in quarantine mode are assigned new workloads based upon the warranty health, workload term, and workload criticality.
1. A method for managing workloads assigned to nodes in a data center, comprising:
assigning a primary node among a cluster of nodes, wherein each of the nodes are Information Handling Systems (IHS) hosting a plurality of virtual machines (VM), and wherein each workload is assigned to run on a selected VM in the cluster, the primary node monitoring a status of the nodes in the cluster;
identifying, by the primary node, nodes within the cluster that are in a quarantine mode, wherein a node is placed in quarantine mode when a potential node failure is detected but the node is still operating;
determining a remaining warranty time for the nodes in quarantine status by retrieving warranty information for each component in the node from a database within a vendor warranty system;
determining an expected duration for a selected workload;
determining a criticality of the selected workload by retrieving a workload tag assigned to the workload by a user of the cluster;
assigning, by the primary node, the selected workload to a node in the cluster based upon the remaining warranty time, the expected workload duration, and the workload criticality to ensure that the selected workload is completed within an assigned node's expected lifetime; and
executing the selected workload on the assigned node in the cluster.
2. The method of claim 1 , wherein the remaining warranty time is classified into two or more categories based upon a length of time before a warranty ends.
3. The method of claim 2 , wherein the categories comprise of at least one of: healthy, warning, and critical categories, and wherein each of the categories corresponds to a particular range of warranty days remaining.
4. The method of claim 3 , wherein the selected workload is blocked from quarantined nodes having a healthy warranty time remaining.
5. The method of claim 3 , wherein the selected workload is permitted to be assigned to quarantined nodes having an expired warranty if the workload criticality is noncritical.
6. The method of claim 3 , wherein the selected workload is permitted to be assigned to quarantined nodes having a warning warranty time remaining if the workload criticality is not critical.
7. The method of claim 1 , wherein the expected duration is classified into two or more categories.
8. The method of claim 7 , wherein the categories comprise of at least one of: short-term, seasonal, and long-term categories, and wherein each of the categories corresponds to a particular range of days associated with that the expected workload duration.
9. The method of claim 1 , wherein the criticality of the selected workload is determined based upon a criticality assigned by a user.
10. The method of claim 1 , wherein the selected workload is assigned to nonquarantined nodes without considering warranty restrictions.
11. The method of claim 1 , wherein the selected workload is assigned to a quarantined node.