HP-UX Workload Manager overview

9
SLOs that ensure a specified amount of CPU resources for workloads
The solutions in this section illustrate shares-based SLOs. They grant a workload a specified amount of
CPU shares.
Reserving CPU resources all of the time
In this first example, the SLO requests a fixed allocation of CPU shares for the Marketing workload,
reserving a portion of the CPU resources available. The 300 CPU shares being reserved equate to
three cores (when managing SLOs for partitions, WLM equates each core to 100 shares). This SLO is
priority 1 and is in effect at all times.
Workload: Marketing
Priority: 1
CPU shares: 300
Reserving CPU resources at specified times
This SLO also requests a fixed allocation, in this case, reserving 800 CPU shares. However, the
associated workload contains a payroll application that runs only twice a month. Consequently, the
SLO is enabled only twice a month, on the 15
th
and 28
th
.
Workload: Payroll
Priority: 1
CPU shares: 800
Condition: 15
th
and 28
th
Reserving CPU resources based on an event or condition
The following SLO is enabled only part time when a specific condition is met (rather than at a
specified date or time). The SLO is enabled only when a system accounting program is running, as
indicated by some metric (a condition to be met). When the SLO is active, it works to enable the
accounting program to complete quickly by reserving 600 CPU shares for the associated workload.
When the program is completed, the SLO is disabled.
Workload: SysAcct
Priority: 1
CPU shares: 600
Condition: System accounting program is running
Reserving CPU resources in an HP Serviceguard failover
The following SLO is also enabled based on a metric. This example illustrates an SLO that is only
active if the Serviceguard package pkgA is active on the current server. WLM provides a utility that
generates a metric indicating whether a package is active. When the metric has value 1, the package
is active, thus enabling the SLO. The SLO then causes WLM to attempt to allocate 300 CPU shares to
the associated workload.
Workload: Failover_pkgA
Priority: 1
CPU shares: 300
Condition: pkgA is active on the current server
SLOs that dynamically allocate resources based on usage goals
The solutions in this section illustrate SLOs based on usage goals. They allocate resources
dynamically, based on current demand or utilization. When the demand is high enough, more
resources are allocated for the workload. When the demand falls below a certain level, unused
resources can be made available for other workloads.