Yandex Cloud
Search
Discuss with expertTry it for free
  • Customer Stories
  • Documentation
  • Blog
  • All Services
  • System Status
  • Marketplace
    • Featured
    • Infrastructure & Network
    • Data Platform
    • AI for business
    • Security
    • DevOps tools
    • Serverless
    • Monitoring & Resources
  • All Solutions
    • By industry
    • By use case
    • Economics and Pricing
    • Security
    • Technical Support
    • Start testing with double trial credits
    • Cloud credits to scale your IT product
    • Gateway to Russia
    • Cloud for Startups
    • Center for Technologies and Society
    • Yandex Cloud Partner program
    • Price calculator
    • Pricing plans
  • Customer Stories
  • Documentation
  • Blog
© 2026 Direct Cursus Technology L.L.C.
Yandex Compute Cloud
  • Yandex Container Solution
  • Access management
  • Pricing policy
  • Terraform reference
  • Monitoring metrics
  • Audit Trails events
  • Release notes
    • General questions
    • Virtual machines
    • _Not enough resources_ error
    • Connection
    • Disks, snapshots, and images
    • Instance groups
    • Graphics processing units (GPUs)
    • Monitoring
    • Licensing
    • Troubleshooting
    • All questions on one page
  1. FAQ
  2. Monitoring

Monitoring resource utilization

Written by
Yandex Cloud
Updated at May 14, 2026
  • Why does vCPU utilization displayed on the chart exceed 100%?

  • How do I track vRAM use through monitoring?

Why does vCPU utilization displayed on the chart exceed 100%?Why does vCPU utilization displayed on the chart exceed 100%?

If your vCPUs feature guaranteed performance, e.g., 5%, the monitoring system treats the guaranteed 5% vCPU as the 100% expected utilization. With no other VMs sharing the physical core, you can get up to 100% of vCPU performance, which is 20 times the maximum expected utilization (20 times the 5%). Thus, the chart can show up to 2000%.

If you consistently observe vCPU utilization above 100% on the monitoring charts, we recommend increasing the guaranteed vCPU performance. Otherwise, if other VMs are allocated to the same physical core, your actual physical core utilization will drop to the guaranteed 5% (about 100 MHz). In such a scenario, the guest OS may fail to handle the workload and you could lose access to your VM.

How do I track vRAM usage through monitoring?How do I track vRAM usage through monitoring?

Compute Cloud cannot measure vRAM usage within the guest OS. For Compute Cloud, a VM's memory usage is a fixed amount allocated at the moment the VM starts up.

To monitor the vRAM state, use Yandex Monitoring. It enables you to write custom metrics. For details, this guide. Just schedule a job to export the vRAM state data, and Monitoring will render it.

Was the article helpful?

Previous
Graphics processing units (GPUs)
Next
Licensing
© 2026 Direct Cursus Technology L.L.C.