Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

k8s cluster environment & dataset #14

Open
CSWYF3634076 opened this issue May 8, 2023 · 2 comments
Open

k8s cluster environment & dataset #14

CSWYF3634076 opened this issue May 8, 2023 · 2 comments

Comments

@CSWYF3634076
Copy link

CSWYF3634076 commented May 8, 2023

Hi, May I ask if this system requires a real k8scluster environment, and where can I obtain the dataset used for anomaly detection in this project

@isala404
Copy link
Owner

isala404 commented May 9, 2023

Hi,

Yes, to deploy ebpf probes and run the Gazer project, you need a real Kubernetes cluster with real nodes. It's important that these nodes are running on a Linux kernel since the ebpf probes require access to the kernel. Nodes running on KVM also work.

Note that Kind or any other Docker-based Kubernetes distributions won't work since they don't provide access to the host kernel.

Unfortunately, the dataset used to train the models in the Gazer project is not available as it was based on emulated data and has been removed. However, you can recreate the dataset by using the MicroSim project to deploy a simulated microservices system, then deploying Gazer using the deployment.yaml file and running the scraper.py script.

If you encounter any issues during this process, feel free to contact the project's author for assistance.

@CSWYF3634076
Copy link
Author

Hi,

Yes, to deploy ebpf probes and run the Gazer project, you need a real Kubernetes cluster with real nodes. It's important that these nodes are running on a Linux kernel since the ebpf probes require access to the kernel. Nodes running on KVM also work.

Note that Kind or any other Docker-based Kubernetes distributions won't work since they don't provide access to the host kernel.

Unfortunately, the dataset used to train the models in the Gazer project is not available as it was based on emulated data and has been removed. However, you can recreate the dataset by using the MicroSim project to deploy a simulated microservices system, then deploying Gazer using the deployment.yaml file and running the scraper.py script.

If you encounter any issues during this process, feel free to contact the project's author for assistance.

Thank you for your reply. Indeed, when I deployed on Kind, I found that Gazer failed to run

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants