Platform Aware Scheduling

Platform Aware Scheduling (PAS) is an archived Kubernetes scheduling toolkit no longer maintained by Intel that exposes platform-specific attributes to the…

  • Infrastructure
  • Monitoring & Logging
Platform Aware Scheduling (PAS) is an archived Kubernetes scheduling toolkit no longer maintained by Intel that exposes platform-specific attributes to the scheduler using a modular, policy-driven approach to help operators place workloads by telemetry and platform constraints.

Platform availability

Available on 0 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

31/100 Low

Maintained
0GitHub repository is archived
Popular
45176 GitHub stars
Easy to install
250 install platforms, install notes, Docker image
Light to run
No data
Security check
83no serious findings, 1 minor, CI, tests, OpenSSF Scorecard 6.7/10

Based on 4 of 5 factors.

GitHub stars
176
Open issues
6
Last commit
2025-01-29
License
Apache-2.0
Activity
stale

Checked 3 days ago - source: GitHub (intel/platform-aware-scheduling)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Add the telemetry helper libraries Add :telemetry_poller and :telemetry_metrics to your app’s dependency list (the list of helper libraries it loads). Without them, the telemetry code won’t start or report anything. source
  • Start the reporter with metrics Start the ConsoleReporter in your supervision tree (the process manager that keeps things running) and give it a metrics: list. It is the part that prints metric data, so without it or an empty list you’ll see no telemetry output. source
  • Schedule periodic measurements If you want automatic readings, add :telemetry_poller to the same process manager with the measurements to run and a period in milliseconds. Without it, those metrics won’t refresh on their own. source
  • Project no longer maintained Intel has ceased development and maintenance of this project; if you rely on it, create your own fork to continue patches, bug fixes, and updates. source
  • Project status Intel has ceased development and no longer accepts patches; if you need continued fixes, fork the repository and maintain your own patches. source
  • Forking for Continued Use Intel has ceased all development and no longer accepts patches. If you need ongoing support, create your own fork of the repository and maintain it independently. source

Fetched 3 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

How does Telemetry-Aware Scheduling integrate with Kubernetes scheduling?

It uses Kubernetes Scheduler Extenders so the default scheduler can make HTTP calls to an external service. That service can then modify scheduling decisions for the workload.

What port does the example scheduler configuration use for TAS?

The example configuration uses port 9001 for the TAS service endpoint.

What TLS settings are shown in the example extender configuration?

The example enables HTTPS and references client certificate and key files. It also sets insecure to false in the TLS configuration.

How does the TAS extender evaluate a workload?

It checks whether the workload has a telemetry policy. If one exists, it inspects the associated strategies and returns scheduling opinions.

Answers sourced from github.com, github.com

Community

Collected 48 days ago - public community threads