input stringclasses 1
value | output stringlengths 30 28.3k | text stringlengths 151 31.8k | instruction stringlengths 49 30.3k |
|---|---|---|---|
NodePort is used to access a service within the cluster scope.
You might create a firewall rule that allows TCP traffic on your node port. Create a firewall rule that allows TCP traffic on port 32004.
On Ubuntu you can do something like:
sudo ufw allow 32004/tcp
And check port status with:
sudo ufw status
Once you ... | ###Instruction: I have created 2 pods within the same cluster. One service is initialized as
kubectl create deployment my-web --image=nginx --port=80
kubectl expose deployment my-web --target-port=80 --type=NodePort
to my understanding, this creates a deployment with one pod my-web-<string> and exposes a port. With ku... | I have created 2 pods within the same cluster. One service is initialized as
kubectl create deployment my-web --image=nginx --port=80
kubectl expose deployment my-web --target-port=80 --type=NodePort
to my understanding, this creates a deployment with one pod my-web-<string> and exposes a port. With kubectl describe s... | |
Sara's answer above pointed me to the right direction. Copying the files works but this requires a restart of the tomcat service which reverts the changes. I had to use 'cp -r' on the deployment yaml as per below:
spec:
containers:
- name: tomcat
image: tomcat
ports:
- containerPor... | ###Instruction: Hello I am trying to deploy a simple tomcat service. Below are the details:
1.minikube version: v1.8.1
2.OS: mac
3.The deployment.yaml file (I am in the directory of the yaml file)
apiVersion: apps/v1
kind: Deployment
metadata:
name: tomcat-deployment
spec:
selector:
matchLabels:
app: tomc... | Hello I am trying to deploy a simple tomcat service. Below are the details:
1.minikube version: v1.8.1
2.OS: mac
3.The deployment.yaml file (I am in the directory of the yaml file)
apiVersion: apps/v1
kind: Deployment
metadata:
name: tomcat-deployment
spec:
selector:
matchLabels:
app: tomcat
replicas: 1... | |
In principle, a go get sigs.k8s.io/cluster-api@v1.4.2 (done in the folder where your go.mod is) should be enough to:
update your go.mod,
add the library in your $GOPATH and
enable VSCode auto-import to work.
That means, when you start typing the name of a struct, like KubeadmControlPlane, the VSCode Go extension shou... | ###Instruction: Imagine you want to get kind/struct called KubeadmControlPlane from the kubernetes API server.
This means you need to import the related struct into your code.
A matching import statement for KubeadmControlPlane would be:
kubeadm "sigs.k8s.io/cluster-api/controlplane/kubeadm/api/v1beta1"
Up to now I n... | Imagine you want to get kind/struct called KubeadmControlPlane from the kubernetes API server.
This means you need to import the related struct into your code.
A matching import statement for KubeadmControlPlane would be:
kubeadm "sigs.k8s.io/cluster-api/controlplane/kubeadm/api/v1beta1"
Up to now I need to much time... | |
Answering to myself after having determined the root cause of the issue.
Regarding Linkerd, everything was correctly setup. The main precaution that one needs to take is adding the linkerd-await binary to the Flink image and making sure to override the entrypoint for the jobmanager since otherwise you will run into iss... | ###Instruction: I am deploying some Flink jobs which require access to some services under a service mesh implemented via Linkerd and I'm running into this error:
java.lang.NoClassDefFoundError: Could not initialize class foo.bar.Job
I can confirm that the jar file contains the class that cannot be found apparently, ... | I am deploying some Flink jobs which require access to some services under a service mesh implemented via Linkerd and I'm running into this error:
java.lang.NoClassDefFoundError: Could not initialize class foo.bar.Job
I can confirm that the jar file contains the class that cannot be found apparently, so it's not a pr... | |
Your use case is essentially autoscaling based on RabbitMQ queue length, which is a bit challenging due to the limitations of the native Kubernetes HPA controller, as it "typically" autoscale based on CPU and memory usage.
Alternatively, you may consider utilizing KEDA (Kubernetes Event-Driven Autoscaling):
KEDA is a K... | ###Instruction: I have this use case:
When there is much load on a specific queue in RabbitMQ, i want to start more replicas. Let's say, my app can handle 5 messages ( = tasks) simultaneously and they all take 1 min to complete. When there are more than 10 "ready" messages in the rabbitmq Queue, i want the HPA to star... | I have this use case:
When there is much load on a specific queue in RabbitMQ, i want to start more replicas. Let's say, my app can handle 5 messages ( = tasks) simultaneously and they all take 1 min to complete. When there are more than 10 "ready" messages in the rabbitmq Queue, i want the HPA to start a new replica.... | |
Try:
kubectl get pods \
--output=custom-columns=\
"POD_PORT":.spec.containers[*].ports[*].containerPort
You can include .metadata.name too to aid clarity:
kubectl get pods \
--output=custom-columns=\
"NAME":.metadata.name,\
"POD_PORT":.spec.containers[*].ports[*].containerPort
It's not clearly (!?) documented but I s... | ###Instruction: I am getting the IP address assigned to the pod using kubectl get pods -o custom-columns="POD_IP":.status.podIPs command.
And based on same approach, I am using kubectl get pods -o custom-columns="POD_PORT":.spec.containers.ports.containerPort command to get the port number but it is coming as blank.
cl... | I am getting the IP address assigned to the pod using kubectl get pods -o custom-columns="POD_IP":.status.podIPs command.
And based on same approach, I am using kubectl get pods -o custom-columns="POD_PORT":.spec.containers.ports.containerPort command to get the port number but it is coming as blank.
cloudshell:~$ kube... | |
Using Azure Application Insights there are two [private monitoring options] (https://learn.microsoft.com/en-us/azure/azure-monitor/app/availability-private-test) described.
Allowing limited inbound connectivity
Using Azure Functions, as you have described in your Option 2.
Personally I prefer endpoint monitoring to b... | ###Instruction: I have a deployment with multiple pods in Azure Kubernetes Service.
There is a K8s service that is used to connect deployment pods.
The service has a private IP accessible in Azure Virtual Network. The service type is LoadBalancer.
I want to monitor and see if the service is up. If it is not up, trigger... | I have a deployment with multiple pods in Azure Kubernetes Service.
There is a K8s service that is used to connect deployment pods.
The service has a private IP accessible in Azure Virtual Network. The service type is LoadBalancer.
I want to monitor and see if the service is up. If it is not up, trigger an email alert.... | |
I can confirm what Michael said. Kafka is atm not supported and not part of Red Hats otel distro. Here you see what otel components will be productized in the next release. To bypass your issue, you can create your own distro. The easiest way would be to extend Red Hats manifest.yaml with the Kafka exporter. For testin... | ###Instruction: I'm having kafka cluster deployed in openshift in different namespace also opentelemetry is delpoyed in another namespace.
This is my yaml file for opentelemetry
apiVersion: opentelemetry.io/v1alpha1
kind: OpenTelemetryCollector
metadata:
name: demo-otlcol-otlp
namespace: otlcol-demo
spec:
config:... | I'm having kafka cluster deployed in openshift in different namespace also opentelemetry is delpoyed in another namespace.
This is my yaml file for opentelemetry
apiVersion: opentelemetry.io/v1alpha1
kind: OpenTelemetryCollector
metadata:
name: demo-otlcol-otlp
namespace: otlcol-demo
spec:
config: |
receivers... | |
Sadly, Azure profiler just does not support dotnet 6. There might be other solutions for Azure witr this dotnet version
| ###Instruction: I got a .net6 service hosted in an AKS cluster with app insight and profiler enabled. Logs appear in app insight and live metrics are working and I can see every action in app insight.
When I click the "Profile now" button in the performance tab, it says a profiling session is in progress and I fire a f... | I got a .net6 service hosted in an AKS cluster with app insight and profiler enabled. Logs appear in app insight and live metrics are working and I can see every action in app insight.
When I click the "Profile now" button in the performance tab, it says a profiling session is in progress and I fire a few requests. Eve... | |
If you're running PostgreSQL, and you're using EKS 1.23 or higher, you'll need to install a CSI driver, e.g. the EBS CSI driver. Starting with 1.23, EKS no longer ships with a storage driver (the in-tree driver was deprecated). After installing the CSI driver, create a default storage class. Your pods should start shor... | ###Instruction: I have created an EKS cluster with ALB setup. I tried installing superset by following the steps provided in https://superset.apache.org/docs/installation/running-on-kubernetes/
my-values.yaml
ingress:
enabled: true
ingressClassName: ~
annotations:
kubernetes.io/ingress.class: alb
alb.ingr... | I have created an EKS cluster with ALB setup. I tried installing superset by following the steps provided in https://superset.apache.org/docs/installation/running-on-kubernetes/
my-values.yaml
ingress:
enabled: true
ingressClassName: ~
annotations:
kubernetes.io/ingress.class: alb
alb.ingress.kubernetes.i... | |
In the query editor of the graph panel, enter the PromQL query to retrieve the maximum number of running pods throughout the day. The query should use the max_over_time function to find the highest value over a time range.
This one worked for me - max_over_time(kube_pod_status_phase{phase="Running"}[1d])
I also found t... | ###Instruction: I have deploy my kubernetes cluster in AWS EKS. I have setup prometheus and grafana to monitor the EKS cluster. How to find Max no of running pods throughout the day ??
### Response: In the query editor of the graph panel, enter the PromQL query to retrieve the maximum number of running pods throughout... | I have deploy my kubernetes cluster in AWS EKS. I have setup prometheus and grafana to monitor the EKS cluster. How to find Max no of running pods throughout the day ??
| |
To your questions:
This is the first time that I use status and conditions, is it right way or do I miss something?
Your approach to managing the status and conditions of Kubernetes resources is generally fine. The status subresource in a Kubernetes API object is typically used to represent the current state of the sy... | ###Instruction: Im having k8s controller which needs to install some resources and update the status and condition accordantly
The flow in the reconcile is like following:
Install the resource and don’t wait
Call to the function checkAvailability and update the status accordantly if ready/ pending install/ error
I’v... | Im having k8s controller which needs to install some resources and update the status and condition accordantly
The flow in the reconcile is like following:
Install the resource and don’t wait
Call to the function checkAvailability and update the status accordantly if ready/ pending install/ error
I’ve two main quest... | |
Figured it out. The kubernetes retention policy of the volume was set to retain. I tried setting it to delete but the data was still persisting. I ended up logging on to the instance and blowing away everything where I mounted the PV. This forced the pod to restart, and when it did it actually went through the correct ... | ###Instruction: I think I'm going crazy. I had kubernetes setup to deploy a postgres database. Worked fine. I wanted to add an init script so I made a custom image, deployed to private docker hub repo, and then updated the deployment to pull new image. But no matter what I do kubernetes keeps deploying the old database... | I think I'm going crazy. I had kubernetes setup to deploy a postgres database. Worked fine. I wanted to add an init script so I made a custom image, deployed to private docker hub repo, and then updated the deployment to pull new image. But no matter what I do kubernetes keeps deploying the old database.... I updated t... | |
Previous answers didn't work to me, the regex seems wrong and the field with the actual creationTimestamp is the sixth as per today, so :
kubectl get pods -A --sort-by=.metadata.creationTimestamp | awk 'match($6,/^[0-9]+[sm]{1}|^[0-5][0-9]m|^[1-9]h|^1[0-9]*h|^2[0-4]h/) {print $0}'
It may be also useful to append |grep... | ###Instruction: I would like to list pods created within 24 hours. I didn't find any kubectl commands or anything to get those. Could anyone please help me with the kubectl command to get only the pods created in last 24 hours.
### Response: Previous answers didn't work to me, the regex seems wrong and the field with ... | I would like to list pods created within 24 hours. I didn't find any kubectl commands or anything to get those. Could anyone please help me with the kubectl command to get only the pods created in last 24 hours.
| |
In the Argo CD ApplicationSet controller, you are using {{ index .Clusters.values "nameOverride" }} to access the nameOverride value. However, Clusters is an array in your clusters.yaml file, not a dictionary. So, you should not be trying to directly index it as if it is a dictionary. (In YAML, an array (or list) is de... | ###Instruction: I just started working with ArgoCD and I have an issue I can't find the answer for.
I have a file called clusters.yaml in my Git repo:
clusters:
- name: cluster1-eu-k8s-002
url: https://cluster1.hcp.northeurope.azmk8s.io:443
values:
nameOverride: ReplaceWithThis
And I am using the following Ap... | I just started working with ArgoCD and I have an issue I can't find the answer for.
I have a file called clusters.yaml in my Git repo:
clusters:
- name: cluster1-eu-k8s-002
url: https://cluster1.hcp.northeurope.azmk8s.io:443
values:
nameOverride: ReplaceWithThis
And I am using the following ApplicationSet in ... | |
It's actually not related to WordPress, it's general purpose only you can use similar way Docker mounts the secret content at /run/secrets/connection_string
Your code can read the variable and it will get path from there which is /run/secrets/connection_string now your code can read that file runtime and get the conten... | ###Instruction: I have a docker-compose file that connects an app with a database.
I'm using docker secrets to hide sensitive data, such as in this case DB credentials, while I can do so with the database service, I'm not able to do the same within the app service, specifically the ConnectionString.
I couldn't find muc... | I have a docker-compose file that connects an app with a database.
I'm using docker secrets to hide sensitive data, such as in this case DB credentials, while I can do so with the database service, I'm not able to do the same within the app service, specifically the ConnectionString.
I couldn't find much in the documen... | |
As suggested by @Harsh Manver you can set up a multi cluster mesh outside Google Cloud to achieve internal service to service communication in Anthos multiple clusters.
As mentioned in the document:
The cluster's Kubernetes control plane address and the gateway address
need to be reachable from every cluster in the me... | ###Instruction: How to achieve internal service to service communication in Anthos multiple clusters Example
service A deployed in GKE cluster and service B deployed in AKS cluster, here how we can call service A from service B (internally) ?
### Response: As suggested by @Harsh Manver you can set up a multi cluster m... | How to achieve internal service to service communication in Anthos multiple clusters Example
service A deployed in GKE cluster and service B deployed in AKS cluster, here how we can call service A from service B (internally) ?
| |
The Answer is kubectl patch (docs).
For example, Given a deployment you can for example update the .spec.template.spec.containers[].image field using the following command:
kubectl patch deployment my-deploy \
--patch '{"spec": {"template": {"spec": {"containers": [{"image": "nginx:1.12.5"}]}}}}'
This way, you only ... | ###Instruction: Is it possible to modify a live Kubernetes manifest, on-the-fly and non-interactively? I know kubectl edit allows for this behavior, but this requires user interaction in an editor that is opened when the command is invoked. I need to be able to do this without user interaction (for example in a script,... | Is it possible to modify a live Kubernetes manifest, on-the-fly and non-interactively? I know kubectl edit allows for this behavior, but this requires user interaction in an editor that is opened when the command is invoked. I need to be able to do this without user interaction (for example in a script, etc.). Is this ... | |
We have faced the same issue and the problem was related to the fact, that the Ingress generated by the certificate manger contained the Ingress Controller reference using the deprecated Annotation kubernetes.io/ingress.class.
What we wanted:
spec:
ingressClassName: my-traefik-controller
What we got:
annotations:
... | ###Instruction: I've been trying to get the http-01 challenge method working with traefik v2 and cert-manager, both installed through their current helm charts. The LB endpoint can be requested through the ip and hostname, and I've tested that the http host passes on letsdebug (No issues were found with <domain>).
Trae... | I've been trying to get the http-01 challenge method working with traefik v2 and cert-manager, both installed through their current helm charts. The LB endpoint can be requested through the ip and hostname, and I've tested that the http host passes on letsdebug (No issues were found with <domain>).
Traefik lives in the... | |
Can you try this
#!/bin/bash
pod_name="devopslk"
namespace="devops"
# Get the pod status
pod_status=$(kubectl get pod "$pod_name" -n "$namespace" -o jsonpath='{.status.phase}')
# Check if any matching pod is running
if [[ -n "$pod_status" ]]; then
echo "Pod running"
else
echo "Pod not running, Current status: ... | ###Instruction: In my k8 cluster I have pods running that the pod name contains the word "inventory" (actually 2pods with this name)
I need to write a shell script to delete deployment and re-deploy and then it should check the specific pod is running or not and then display a message.
Here is what I tried.
#!/bin/bash... | In my k8 cluster I have pods running that the pod name contains the word "inventory" (actually 2pods with this name)
I need to write a shell script to delete deployment and re-deploy and then it should check the specific pod is running or not and then display a message.
Here is what I tried.
#!/bin/bash
cd /apps/applic... | |
I need a Listener in the second microservice in order to receive the message from Queue.
Why polling, when you can be notified through the KubeMQ Pub/Sub pattern?
In the context of message queues, "polling" refers to a process where your application continually checks the queue to see if a new message has arrived. T... | ###Instruction: Currently, I have two microservices. I want to send message to KubeMQ Queue from first microservice and want it to be received by Second microservice. I am able to send message to a KubeMQ Queue using below code:
Queue queue = new Queue("QueueName", "ClientID", "localhost:50000");
SendMessageResult re... | Currently, I have two microservices. I want to send message to KubeMQ Queue from first microservice and want it to be received by Second microservice. I am able to send message to a KubeMQ Queue using below code:
Queue queue = new Queue("QueueName", "ClientID", "localhost:50000");
SendMessageResult resSend = queue.Se... | |
My advice: don't do it! You don't want to have to deal with certs inside your pods. Get the TLS done on your load balancers, managed by your cloud provider, or managed in your cluster by cert-manager and a proper cert provider (like Let's Encrypt)
If you really want to terminate TLS in your pod, then use TCP as the pro... | ###Instruction: I am trying to do tls termination at pod level.
ingress(nlb) -->service(clusterip) --> pod
I have set ingress with ssl passthrough by adding the following annotations,
annotations:
nginx.ingress.kubernetes.io/backend-protocol: "HTTPS"
nginx.ingress.kubernetes.io/ssl-passthrough: "true"
nginx.ingre... | I am trying to do tls termination at pod level.
ingress(nlb) -->service(clusterip) --> pod
I have set ingress with ssl passthrough by adding the following annotations,
annotations:
nginx.ingress.kubernetes.io/backend-protocol: "HTTPS"
nginx.ingress.kubernetes.io/ssl-passthrough: "true"
nginx.ingress.kubernetes.io... | |
With certbot there is type of verification method DNS and HTTP
DNS method verify the record in DNS while HTTP check for 200 response from your Endpoint.
In CI/CD you can go with the HTTP method which checks for the Domain status
Refer repo for more : Auth script
certbot certonly $CERTBOT_DEBUG --non-interactive --manua... | ###Instruction: Im using nginx as a reverse proxy to serve an Express.js backend and a Vue.js frontend. The whole application runs in two Docker Compose images, one for development, and one for production. I'd like to be able to test the production image locally with HTTPS (especially because Vue's PWA framework depend... | Im using nginx as a reverse proxy to serve an Express.js backend and a Vue.js frontend. The whole application runs in two Docker Compose images, one for development, and one for production. I'd like to be able to test the production image locally with HTTPS (especially because Vue's PWA framework depends on HTTPS to pr... | |
JMESPath does have a to_string function.
So, you can use a JMESPath query in the path field and do:
path = "to_string(port)"
| ###Instruction: I am trying to mount a Kubernetes secret via a kubernetes_manifest like this, however, port is a number 5342
resource "kubernetes_manifest" "test" {
manifest = {
"apiVersion" = "secrets-store.csi.x-k8s.io/v1alpha1"
"kind" = "SecretProviderClass"
"metadata" = {
namespace = "test... | I am trying to mount a Kubernetes secret via a kubernetes_manifest like this, however, port is a number 5342
resource "kubernetes_manifest" "test" {
manifest = {
"apiVersion" = "secrets-store.csi.x-k8s.io/v1alpha1"
"kind" = "SecretProviderClass"
"metadata" = {
namespace = "test-namespace"
... | |
your type field on BackendConfig is TCP, docs say only http/https allowed https://cloud.google.com/kubernetes-engine/docs/how-to/ingress-configuration#direct_health
| ###Instruction: I have a deployment. The pod container's have no readinessProbe(s), because the healtcheck will be configured using a BackendConfig.
The service is as follows:
---
apiVersion: v1
kind: Service
metadata:
name: my-app-service
namespace: my-namespace
annotations:
cloud.google.com/neg: '{"ingress"... | I have a deployment. The pod container's have no readinessProbe(s), because the healtcheck will be configured using a BackendConfig.
The service is as follows:
---
apiVersion: v1
kind: Service
metadata:
name: my-app-service
namespace: my-namespace
annotations:
cloud.google.com/neg: '{"ingress": true}'
clo... | |
As per this doc by Platform9.
Restoring ETCD Backup to Recover Cluster From Loss of Quorum:
Master nodes going offline or a lack of connectivity between the master nodes leading to an unhealthy cluster state could cause a loss of quorum.
The idea behind Etcd restore is to restore Etcd from a backup using
etcdctl and r... | ###Instruction: In a scenario where a zone/dc dropped and 2 master nodes out of 5 are now offline, I would like to restore etcd on the remaining 3 master nodes.
So far the best I could manage was restoring from etcd backup, but I found myself needing to destroy the remaining 2 and recreating them. Otherwise, I got a sp... | In a scenario where a zone/dc dropped and 2 master nodes out of 5 are now offline, I would like to restore etcd on the remaining 3 master nodes.
So far the best I could manage was restoring from etcd backup, but I found myself needing to destroy the remaining 2 and recreating them. Otherwise, I got a split brain issue.... | |
Update your script with the Postgress User and database name to pass to the psql script as environmental variables.
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ .Values.postgres.configmap.name }}
namespace: {{ .Release.Namespace }}
data:
init_script.sh: |+
#!/bin/bash
set -e
psql -v ON_ERROR_STOP... | ###Instruction: I've setup a PostgreSQL database with Helm Chart using this ConfigMap, that contains the initial script which allows to create the databases and schemas I need:
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ .Values.postgres.configmap }}
namespace: {{ .Release.Namespace }}
data:
init_script.sh:... | I've setup a PostgreSQL database with Helm Chart using this ConfigMap, that contains the initial script which allows to create the databases and schemas I need:
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ .Values.postgres.configmap }}
namespace: {{ .Release.Namespace }}
data:
init_script.sh: |+
#!/bin/b... | |
The issue you're encountering is related to the way you're accessing the nameOverride value from clusters.yaml in the value field of your ArgoCD ApplicationSet.
In your current configuration, you're using the following expression to access the value:
value: '{{ index .Clusters.values "nameOverride" }}'
However, the pr... | ###Instruction: I just started working with ArgoCD and I have an issue I can't find the answer for.
I have a file called clusters.yaml in my Git repo:
clusters:
- name: cluster1-eu-k8s-002
url: https://cluster1.hcp.northeurope.azmk8s.io:443
values:
nameOverride: ReplaceWithThis
And I am using the following Ap... | I just started working with ArgoCD and I have an issue I can't find the answer for.
I have a file called clusters.yaml in my Git repo:
clusters:
- name: cluster1-eu-k8s-002
url: https://cluster1.hcp.northeurope.azmk8s.io:443
values:
nameOverride: ReplaceWithThis
And I am using the following ApplicationSet in ... | |
If you are using the standard Docker Hub postgres image and you are just trying to create a database, the easiest thing to do is to use its environment-variable settings
image: postgres:15
env:
- name: POSTGRES_USER
value: <user>
- name: POSTGRES_DB
value: my-db
For these settings you do not need a separat... | ###Instruction: I've setup a PostgreSQL database with Helm Chart using this ConfigMap, that contains the initial script which allows to create the databases and schemas I need:
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ .Values.postgres.configmap }}
namespace: {{ .Release.Namespace }}
data:
init_script.sh:... | I've setup a PostgreSQL database with Helm Chart using this ConfigMap, that contains the initial script which allows to create the databases and schemas I need:
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ .Values.postgres.configmap }}
namespace: {{ .Release.Namespace }}
data:
init_script.sh: |+
#!/bin/b... | |
I'm pretty sure that you create a cluster by default. If you did that, you used the Compute Engine default parameter that you can see here
Default service account and access scope. If you did that, it's normal you have no access: the minimal scope does not allow the Cloud SQL access.
To solve that, you have to select... | ###Instruction: I am following this tutorial: Connect to Cloud SQL for MySQL from Google Kubernetes Engine.
I have created a cluster. I have created a docker image in the repository. I have created a database. I am able to run my application outside of Kubernetes and it connects to the database. But after deploying app... | I am following this tutorial: Connect to Cloud SQL for MySQL from Google Kubernetes Engine.
I have created a cluster. I have created a docker image in the repository. I have created a database. I am able to run my application outside of Kubernetes and it connects to the database. But after deploying application, pods a... | |
If the servers are independent - You don't want to expose your production systems private key on a development machine - , you want different certificates and the question becomes "How do you use TLS on your development / testing infrastructure". This is a widely discussed question. E.g.:
https://web.dev/how-to-use-loc... | ###Instruction: Im using nginx as a reverse proxy to serve an Express.js backend and a Vue.js frontend. The whole application runs in two Docker Compose images, one for development, and one for production. I'd like to be able to test the production image locally with HTTPS (especially because Vue's PWA framework depend... | Im using nginx as a reverse proxy to serve an Express.js backend and a Vue.js frontend. The whole application runs in two Docker Compose images, one for development, and one for production. I'd like to be able to test the production image locally with HTTPS (especially because Vue's PWA framework depends on HTTPS to pr... | |
Experiencing the same issue while using kube-hetzner as you, I looked at the configuration file and found the culprit: by default, outbound traffic is filtered, except for a few popular ports like HTTP or HTTPS.
There are at least 2 solutions:
you set the variable restrict_outbound_traffic to false:
https://github.com... | ###Instruction: I set up a Kubernetes Cluster on Hetzner following theses steps: https://github.com/kube-hetzner/terraform-hcloud-kube-hetzner
Client Version: v1.26.3
Kustomize Version: v4.5.7
Server Version: v1.26.4+k3s1
Mongosh Version: 1.8.1
I am unable to connect to either my own mongodb server (docker deployment)... | I set up a Kubernetes Cluster on Hetzner following theses steps: https://github.com/kube-hetzner/terraform-hcloud-kube-hetzner
Client Version: v1.26.3
Kustomize Version: v4.5.7
Server Version: v1.26.4+k3s1
Mongosh Version: 1.8.1
I am unable to connect to either my own mongodb server (docker deployment) or a hosted one... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.