Comments (3)
kube-scheduler logs
I1027 19:48:52.759571 1 trace.go:205] Trace[1755174988]: "Scheduling" namespace:default,name:demo-app-55b7cffd5d-hn476 (27-Oct-2022 19:48:52.597) (total time: 161ms): Trace[1755174988]: ---"Computing predicates done" 91ms (19:48:52.689) Trace[1755174988]: ---"Prioritizing done" 68ms (19:48:52.757) Trace[1755174988]: [161.160364ms] [161.160364ms] END
from platform-aware-scheduling.
The prioritization is not guaranteed to result in the Pod ending up scheduled into the node which TAS finds best suited.
The kubernetes scheduler takes into account many factors while considering the best suited node, and the priority score from TAS can be characterized as weak. One can fiddle with the weight
in the scheduler configuration, to increase the impact of TAS.
You can trace the scoring decisions in the kube-scheduler by increasing the verbosity of kube-scheduler to at least 10 (-v=10 to the command line) . See: https://github.com/kubernetes/kubernetes/blob/5de293c425ec0cde9a2cf8917a69329bebcd0bbd/pkg/scheduler/schedule_one.go#L732
from platform-aware-scheduling.
Thank you for your answer.
from platform-aware-scheduling.
Related Issues (20)
- Metrics present on custom metrics endpoint but controller says metric not found HOT 2
- KubeSchedulerConfiguration v1beta2 is deprecated in v1.25 and will be removed in v1.26 HOT 4
- All pods in same node giving same power values. HOT 2
- Warning about critical-pod non-functional HOT 2
- configure-scheduler.sh script breaks Kubernetes config HOT 6
- Custom metric not registered HOT 4
- Pod stay pending even though node has become schedulable HOT 5
- GAS Schedules to cards on same node, ignores podantiaffinity HOT 1
- Renaming repo to Platform Aware Scheduling HOT 1
- Major repo structure change HOT 2
- Intermittent issue in TAS adding and deleting strategy HOT 3
- TAS policy update HOT 2
- Cant' schedule power hungry application HOT 7
- Community work related questions HOT 2
- should modify kubeadm config rather than edit the kube-scheduler static manifest HOT 4
- correct way to post resource telemetry/scheduling to nodes HOT 6
- Working with descheduler HOT 7
- Irrelevant TAS topic HOT 2
- 'make mock' fails for gpu aware scheduling
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from platform-aware-scheduling.