PowerScale OneFS 9.8.0.0 Web Administration Guide

PDF

Job performance impact

The Job Engine service uses impact policies to monitor the impact of maintenance jobs on system performance. You can manage the impact policies to determine when a job can run and the system resources that it consumes.

Job Engine monitors maintenance jobs to ensure that they do not interfere with regular cluster I/O activity or system administration tasks. Job Engine provides default impact policies that you can use but not modify, as shown in the following table.

Table 1. Job Performance ImpactThe following table displays the specifications for each impact policy.
Impact policy	Allowed to run	Resource consumption
LOW	Any time of day.	Low
MEDIUM	Any time of day.	Medium
HIGH	Any time of day.	High
OFF_HOURS	Outside of business hours. Business hours are defined as 9AM to 5PM, Monday through Friday. OFF_HOURS is paused during business hours.	Low

If your workflow requires an impact policy different from the defaults, you can create a custom policy with new settings.

Jobs with a low impact policy have the least impact on available CPU and disk I/O resources. Jobs with a high impact policy have a significant impact. Job Engine limits the number of tasks that can process in parallel according to the impact policy. However, if the impact of a job is under the impact limits, Job Engine can increase the number of tasks that are in process.

CAUTION:Job Engine can use more CPU and I/O even if doing so delays other system activities. Requesting a HIGH impact for a job can be disruptive to the cluster and can affect the client connection.