Methods, systems, and computer readable mediums for workload clustering
Methods, systems, and computer readable mediums for optimizing a system configuration are disclosed. In some examples, a method includes determining whether a system configuration for executing a workload using a distributed computer system is optimizable and in response to determining that the system configuration is optimizable, modifying the system configuration such that at least one storage resource for storing workload data is located at a server node that is executing the workload in the distributed computer system.
1. A method comprising:
identifying at least one workload cluster using a machine-learning algorithm, wherein the machine-learning algorithm uses characteristics of a plurality of workloads for identifying the at least one workload cluster, wherein each of the plurality of workloads includes a virtual machine (VM), wherein the machine-learning algorithm uses a k-means clustering algorithm, wherein the k-means clustering algorithm analyzes the workloads by representing the workloads in Euclidean space, wherein each of the workloads is represented by two or three Euclidean space coordinates, wherein the two or three Euclidean space coordinates include at least two of a number of processing cores utilized, an amount of random access memory utilized, or an operating system (OS) type utilized;
providing a customized user interface that includes relevant workload operations based on the at least one workload cluster; and
managing workloads of the at least one workload cluster, wherein managing the workloads of the at least one workload cluster includes initiating an action that is to be performed with regard to each workload in the at least one workload cluster.
2. The method of claim 1 wherein the k-means clustering algorithm uses the characteristics of the plurality of workloads to identify k number of workload clusters.
3. The method of claim 2 wherein the k-means clustering algorithm is executed multiple times using different values for k.
4. The method of claim 1 wherein the characteristics of the plurality of workloads includes at least one of a group comprising information about a number of processing cores utilized, information about memory utilized, and information about an operating system utilized.
5. The method of claim 1 wherein managing the at least one workload cluster includes at least one of a group comprising starting a virtual machine (VM), stopping a VM, pausing a VM, and moving a VM.
6. The method of claim 1 wherein the machine-learning algorithm uses a predictive data model based on historical workload information, wherein the historical workload information includes characteristics of a workload and an appropriate workload cluster assignment for the workload.
7. A system comprising: at least one physical computer; and
a cluster manager implemented using the at least one physical computer for performing operations comprising:
identifying at least one workload cluster using a machine-learning algorithm, wherein the machine-learning algorithm uses characteristics of a plurality of workloads for identifying the at least one workload cluster, wherein each of the plurality of workloads includes a virtual machine (VM), wherein the machine-learning algorithm uses a k-means clustering algorithm, wherein the k-means clustering algorithm analyzes the workloads by representing the workloads in Euclidean space, wherein each of the workloads is represented by two or three Euclidean space coordinates, wherein the two or three Euclidean space coordinates include at least two of a number of processing cores utilized, an amount of random access memory utilized, or an operating system (OS) type utilized;
providing a customized user interface that includes relevant workload operations based on the at least one workload cluster; and
managing workloads of the at least one workload cluster, wherein managing the workloads of the at least one workload cluster includes initiating an action that is to be performed with regard to each workload in the at least one workload cluster.
8. The system of claim 7 wherein the k-means clustering algorithm uses the characteristics of the plurality of workloads to identify k number of workload clusters.
9. The system of claim 8 wherein the k-means clustering algorithm is executed multiple times using different values for k.
10. The system of claim 7 wherein the characteristics of the plurality of workloads includes at least one of a group comprising information about a number of processing cores utilized, information about memory utilized, and information about an operating system utilized.
11. The system of claim 7 wherein managing the at least one workload cluster includes at least one of a group comprising starting a virtual machine (VM), stopping a VM, pausing a VM, and moving a VM.
12. The system of claim 7 wherein the machine-learning algorithm uses a predictive data model based on historical workload information, wherein the historical workload information includes characteristics of a workload and an appropriate workload cluster assignment for the workload.
13. A non-transitory computer readable medium having stored thereon executable instructions which, when executed by at least one physical computer, cause the at least one physical computer to perform operations comprising:
identifying at least one workload cluster using a machine-learning algorithm, wherein the machine-learning algorithm uses characteristics of a plurality of workloads for identifying the at least one workload cluster, wherein each of the plurality of workloads includes a virtual machine (VM), wherein the machine-learning algorithm uses a k-means clustering algorithm, wherein the k-means clustering algorithm analyzes the workloads by representing the workloads in Euclidean space, wherein each of the workloads is represented by two or three Euclidean space coordinates, wherein the two or three Euclidean space coordinates include at least two of a number of processing cores utilized, an amount of random access memory utilized, or an operating system (OS) type utilized;
providing a customized user interface that includes relevant workload operations based on the at least one workload cluster; and
managing workloads of the at least one workload cluster, wherein managing the workloads of the at least one workload cluster includes initiating an action that is to be performed with regard to each workload in the at least one workload cluster.
14. The non-transitory computer readable medium of claim 13 wherein the k-means clustering algorithm uses the characteristics of the plurality of workloads to identify k number of workload clusters.
15. The non-transitory computer readable medium of claim 14 wherein the k-means clustering algorithm is executed multiple times using different values for k.
16. The non-transitory computer readable medium of claim 13 wherein the characteristics of the plurality of workloads includes at least one of a group comprising information about a number of processing cores utilized, information about memory utilized, and information about an operating system utilized.
17. The non-transitory computer readable medium of claim 13 wherein managing the at least one workload cluster includes at least one of a group comprising starting a virtual machine (VM), stopping a VM, pausing a VM, and moving a VM.
18. The non-transitory computer readable medium of claim 13 wherein the machine-learning algorithm uses a predictive data model based on historical workload information, wherein the historical workload information includes characteristics of a workload and an appropriate workload cluster assignment for the workload.