Management of multiple scale out workloads

Patent metadata

Field	Value
Publication number	US-9515905-B1
Application number	US-28967808-A
Country	US
Kind code	B1
Filing date	Oct 31, 2008
Priority date	Oct 31, 2008
Publication date	Dec 6, 2016
Grant date	Dec 6, 2016

Abstract

A scale out workload management system executing on a computer system controls simultaneous execution of multiple workloads. The computer system includes multiple nodes, where each node defines computer resources consumable by a workload. The scale out workload management system includes an application manager coupled to the nodes. The application manager controls start up and shut down of the nodes based on demands placed on the workloads. The scale out workload management system further includes a workload manager coupled to the application manager. The workload manager includes a monitor module that collects performance information from nodes on which the workloads are executing, an aggregator module that collects the performance information and aggregates the performance information from all nodes supporting the workloads, and a comparator module that compares aggregated performance information for the workloads to a performance target and determines if an allocation of nodes to the workloads should be changed.

First claim

What is claimed is:

1. A computer-implemented process comprising:
monitoring nodes executing instances of workloads to gather respective performance metrics, said workloads including plural scale-out workloads each having plural scale-out instances,
for each of said scale-out workloads, aggregating by a computer the performance metrics across instances of the scale-out workload to obtain an aggregate performance metric representative of an aggregate performance of the scale-out workload so as to obtain respective aggregate performance metrics for said scale-out workloads; and
based at least in part on said aggregate performance metrics, allocating by a computer an additional node to at least one scale-out workload by selecting a node on which a logical-server template for said scale-out workload has been instantiated or by instantiating a logical-server template said additional node, said additional node being a physical server, a hard or soft partition of a physical server, or a virtual machine.

2. A process as recited in claim 1 further requiring making a request specifying said logical-server template or a node on which said logical-server template has been instantiated additional node and either.

3. A process as recited in claim 2 wherein said logical-server template specifies resource requirements for said scale-out workload.

4. A process as recited in claim 2 wherein said request specifies resource requirements for said workload and a network address to be adopted by said node when said logical-server template is instantiated on said node so as to define a logical-server instance of said logical-server template.

5. A process as recited in claim 2 wherein said logical-server template is selected from plural logical-server templates respectively specifying different resource requirements for said scale-out workload.

6. A system comprising non-transitory computer-readable storage media encoded with code defining:
a workload manager to, when executed by a processor,
monitor nodes executing instances of workloads to gather respective performance metrics, said workloads including plural scale-out workloads each having plural active scale-out instances,
aggregate the performance metrics across the active scale-out instances for each of said plural scale-out workloads to obtain respective aggregate performance metrics representative of an aggregate performance of said scale-out workloads, and
based at least in part on said aggregate performance metrics, request an additional node be allocated to at least one scale-out workload, the request specifying the additional node and
a logical-server template; and

an application manager to, when executed by said processor, fulfill said request by selecting a node on which a logical-server template for the scale-out workload has been instantiated or by instantiating such a logical server template on a node, said node being a physical server, a hard or soft partition of a physical server, or a virtual machine.

7. A system as recited in claim 6 further comprising said processor.

8. A system as recited in claim 6 wherein said request specifies said logical-server template and said logical-server template specifies resource requirements for said scale-out workload.

9. A system as recited in claim 6 wherein said request specifies a network address to be adopted by said node when said logical-server template is instantiated on said node.

10. A system as recited in claim 6 wherein said code further defines plural logical-server templates respectively specifying different resource requirements for said scale-out workload.

Assignees

• Blanding William H
• Backer Bryan L
• Harrow Jr Jerry J
• Herington Dan
• Hewlett Packard Entpr Dev Lp

Inventors

• Blanding William H
• Backer Bryan L
• Harrow Jr Jerry J
• Herington Dan

Classifications

• H04L43/08 Primary

  Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters · CPC title

• H04L43/0876

  Network utilisation, e.g. volume of load or congestion level · CPC title

• H04L43/16

  Threshold monitoring · CPC title

• H04L43/04

  Processing captured monitoring data, e.g. for logfile generation · CPC title