Sometimes it’s not enough to measure resource consumption at machine/system level. It’s often necessary to understand which processes are using resources. Linux allows this to be done via the –ps switch on the vmstat command.
However the results may not be what you expect. It is reasonable to assume that one would be delivered CPU and consumption per process per time interval but be careful. In SUSE Linux version 10 the results are the CPU and memory utilisation per process averaged since the process was started. This may or may not (probably not) be useful but is unlikely to be what was intended.
An alternative is to use the top command (and if you want all processes then ensure that there are no restrictions on the number of tasks/processes that are captured). This command will give the resource consumption per process per time interval.
About the author
Team Capacitas
FinOps and AI: Financial Discipline for Enterprise AI
Learn how FinOps extends to enterprise AI, connecting financial, technical and product decisions to manage spending and measure returns. blogs-(new)-post
Confidence Under Load: How We Verified AKS Readiness for Peak
How Capacitas verified AKS readiness for peak demand by validating workload performance, autoscaling, cluster capacity, monitoring, and incident response. blogs-(new)-post
Building Cloud Resilience: Lessons from the AWS Outage
Learning from the Latest Outage. Events like this week’s AWS disruption highlight one clear truth: resilience must be designed, not assumed. blogs-(new)-post
Bringing Order to Chaos: A Practical Guide to Chaos Testing in the Cloud
Build a structured approach to cloud chaos testing with the right tools, realistic failure scenarios, clear hypotheses and focused analysis of results. blogs-(new)-post