Jirka Kremser jkremser

# two clusters
k config get-contexts -oname

# eu@aws
k --context cluster-eu@aws get no
k --context cluster-eu@aws describe node | grep -A5 "System Info"
k --context cluster-eu@aws get svc -n ingress-nginx
dig +short a1f9cb3961e1a4d11af80365d0c5fa28-31f9021cb00929cd.elb.eu-west-2.amazonaws.com
curl -s http://ip-api.com/json/18.132.100.90  | jq

apiVersion: v1
kind: Service
metadata:
  annotations:
    cloud.google.com/neg: '{"ingress":true}'
  labels:
    k8s-app: nvidia-gpu-device-plugin
  name: gpu-metrics
 namespace: kube-system

Kedify AI use-cases

general areas

GPU scheduling (DRA or some better support for nvidia plugin)
AI related scalers (metrics)
Glue - for operating the auto-scaleable models
Adding and releasing GPU enabled nodes dynamically to k8s cluster
Multi-cluster (overflow to a cluster that have GPUs 'attached' say spotinstances that are cheaper)
Maybe introduce a new CRD on the KEDA level that will support heterogeneous settings across replicas (currently all replicas of a single deployment or statefulset are identical)

install metric server to kind

curl -sL https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml | sed '/- args:/a \ \ \ \ \ \ \ \ - --kubelet-insecure-tls' | k apply -f -

helm template --debug .

{{- . | mustToPrettyJson | printf "\nThe JSON output of the dumped var is: \n%s" | fail }}

comments:

export CLUSTER=hello-kubecon

Provision Cluster

cat vsphere/cluster-list.yaml | envsubst | k apply -f -


	1*
	curl -s https://raw.githubusercontent.com/zroubalik/test-data/main/resources/create_resources.sh \| \
	OTHER_DEPLOYMENTS=9 \
	OTHER_STATEFUL_SETS=1 \
	bash -s -- 6 1 0 t



	zaple vsechno to neleakovalo, dokad sem neudelal SOs (1*) - monitoring (1,1,1)

	k exec -ti deployments/psql -n kedify -c psql -- pg_dump --user dashboard-service-account@kedify-initial.iam --host 127.0.0.1 -d kedify --inserts > db.dump
	psql --user postgres --host 127.0.0.1 -f db.dump


	#docker cp db.dump 02a749fdba3a:.

	#docker exec -ti 02a749fdba3a bash
	#psql --user postgres --host 127.0.0.1 -f db.dump

	kind: ConfigMap
	metadata:
	labels:
	app-operator.giantswarm.io/watching: "true"
	name: $CLUSTER-user-values
	namespace: org-$ORG
	apiVersion: v1
	data:
	values: \|
	baseDomain: test.gigantic.io

	---
	# Source: cluster-vsphere/templates/cluster.yaml
	apiVersion: cluster.x-k8s.io/v1beta1
	kind: Cluster
	metadata:
	name: gjirk25
	namespace: default
	annotations:
	cluster.giantswarm.io/description: "test cluster"
	labels: