Versions Compared

Old Version 99

changes.mady.by.user Michael O'Brien

Saved on

compared with

New Version Current

changes.mady.by.user Michael O'Brien

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Committing Code

Code Block
themeMidnight
# clone
git clone ssh://michaelobrien@gerrit.onap.org:29418/logging-analytics
# modify files
# stage your changes
git add .
git commit -m "your commit message"
# commit your staged changes with sign-off
git commit -s --amend
# add Issue-ID after Change-ID
# Submit your commit to ONAP Gerrit for review
git review
# goto https://gerrit.onap.org/r/#/dashboard/self

...

Workstation configuration

Ubuntu 16.04 on VMware Workstation

...

15 or Fusion 8 or AWS/Azure VM

Note: do not use the gui upgrade (will cause the vm to periodically lock) - do individual apt-get 's

Code Block
languagebash
themeMidnight
# start with clean VM, I use root, you can use the recommended non-root account
sudo vi /etc/hosts
# add your hostname to ::1 and 127.0.0.1 or each sudo command will hang for up to 10 sec on DNS resolution especially on ubuntu 18.04
sudo apt-get update
sudo apt-get install openjdk-8-jdk
# not in headless vm
sudo apt-get install ubuntu-desktop
#sudo apt-get install git
sudo apt-get install maven
#or
sudo wget http://apache.mirror.gtcomm.net/maven/maven-3/3.5.4/binaries/apache-maven-3.5.4-bin.tar.gz
sudo cp ap(tab) /opt
cd /opt
tar -xvf apache-maven-3.5.4-bin.tar.gz
sudo vi /etc/environment
   MAVEN_OPTS="-Xms8192 -Djava.net.preferIPv4Stack=true"
# restart the terminal
ubuntu@ip-172-31-78-76:~$ mvn -version
Apache Maven 3.5.4 (1edded0938998edf8bf061f1ceb3cfdeccf443fe; 2018-06-17T18:33:14Z)
Maven home: /opt/apache-maven-3.5.4

Java version: 1.8.0_171, vendor: Oracle Corporation, runtime: /usr/lib/jvm/java-8-openjdk-amd64/jre
sudo vi ~/.ssh/config
Host *
   StrictHostKeyChecking no
   UserKnownHostsFile=/dev/null

 # scp onap gerrit cert into VM # a couple options on copying the ssh key
 # from hostanother macbookmachine
obrien:obrienlabs amdocs$ scp root@ubuntu:~/_dev# cat ~/.ssh/onapid_rsa amdocs@192.168.211.129:~/
move to root
sudo su -
 root@obriensystemsu0:~# cp /home/amdocs| ssh -i ~/.ssh/onap_rsa .
ls /home/amdocs/.m2
cp onap_rsa ~/ubuntu@ons.onap.info 'cat >> .ssh/idonap_rsa chmod&& 400 ~/.ssh/id_rsa 
# test your gerrit access
sudo git config --global --add gitreview.username michaelobrien
sudo git config --global user.email frank.obrien@amdocs.com 
sudo git config --global user.name "Michael OBrien"  
sudo git config --global gitreview.remote origin
sudo mkdir log-326-rancher-ver
cd log-326-rancher-ver/
sudo git clone ssh://michaelobrien@gerrit.onap.org:29418/logging-analytics
cd logging-analytics/
sudo vi deploy/rancher/oom_rancher_setup.sh 
sudo git add deploy/rancher/oom_rancher_setup.sh .
# setup git-review
sudo apt-get install git-review
sudo echo "Key copied"'
Key copied
sudo chown ubuntu:ubuntu ~/.ssh/onap_rsa

 # or
 # scp onap gerrit cert into VM from host macbook
obrien:obrienlabs amdocs$ scp ~/.ssh/onap_rsa amdocs@192.168.211.129:~/
move to root
sudo su -
 root@obriensystemsu0:~# cp /home/amdocs/onap_rsa .
ls /home/amdocs/.m2
cp onap_rsa ~/.ssh/id_rsa
chmod 400 ~/.ssh/id_rsa
# move from root to ubuntu - if using non-root user
sudo chown ubuntu:ubuntu ~/.ssh/onap_rsa 

# test your gerrit access
sudo git config --global --add gitreview.remote origin
# upload a patch
username michaelobrien
sudo git commitconfig -am "update rancher version to 1.6.18"
# 2nd line should be "Issue-ID: LOG-326"
sudo git commit -s --amend
sudo git review
Your change was committed before the commit hook was installed.
Amending the commit to add a gerrit change id.
remote: Processing changes: new: 1, refs: 1, done            
remote: New Changes:        
remote:   -global user.email frank.obrien@amdocs.com 
sudo git config --global user.name "Michael OBrien"  
sudo git config --global gitreview.remote origin
sudo mkdir log-326-rancher-ver
cd log-326-rancher-ver/
sudo git clone ssh://michaelobrien@gerrit.onap.org:29418/logging-analytics
cd logging-analytics/
sudo vi deploy/rancher/oom_rancher_setup.sh 
sudo git add deploy/rancher/oom_rancher_setup.sh .
# setup git-review
sudo apt-get install git-review
sudo  git config --global gitreview.remote origin
# upload a patch
sudo git commit -am "update rancher version to 1.6.18"
# 2nd line should be "Issue-ID: LOG-326"
sudo git commit -s --amend
sudo git review
Your change was committed before the commit hook was installed.
Amending the commit to add a gerrit change id.
remote: Processing changes: new: 1, refs: 1, done            
remote: New Changes:        
remote:   https://gerrit.onap.org/r/55299 update rancher version to 1.6.18        
remote: 
To ssh://michaelobrien@gerrit.onap.org:29418/logging-analytics
 * [new branch]      HEAD -> refs/publish/master
# see
https://gerrit.onap.org/r/#/c/55299/


if you get a corrupted FS type "fsck -y /dev/sda1"

...

https://kubernetes.io/docs/reference/generated/kubectl/kubectl-commands

...

Use a

...

different kubectl context

bash
Code Block
language
themeMidnightRDark
#kubectl automatically via cd.sh in LOG-326
# get the dev.yaml and set any pods you want up to true as well as fill out the openstack parameters
sudo wget https://git.onap.org/oom/plain/kubernetes/onap/resources/environments/dev.yaml
sudo cp logging-analytics/deploy/cd.sh .

# or
# manually
cd oom/kubernetes/
sudo make clean
sudo make all
sudo make onap
sudo helm install local/onap -n onap --namespace onap -f onap/resources/environments/disable-allcharts.yaml --set log.enabled=true
# adding another (so)
sudo helm upgrade local/onap --namespace onap -f onap/resources/environments/disable-allcharts.yaml --set so.enabled=true --set log.enabled=true

Get the nodeport of a particular service

https://kubernetes.io/docs/reference/kubectl/jsonpath/

Code Block
themeMidnight
# human readable list
kubectl get services --all-namespaces | grep robot
# machine readable number - via JSONPath
kubectl get --namespace onap -o jsonpath="{.spec.ports[0].nodePort}" services robot)

Test DNS URLS in the kubernetes ONAP namespace

Code Block
themeMidnight
test urls in the robot container
wget http://pomba-sdcctxbuilder.onap:9530/sdccontextbuilder/health
wget http://pomba-networkdiscoveryctxbuilder.onap:9530/ndcontextbuilder/health

...

Code Block
languagebash
themeMidnight
# override global docker pull policy for a single component
# set in oom/kubernetes/onap/values.yaml
# use global.pullPolicy in your -f yaml or a --set

Exec into a container of a pod with multiple containers

Code Block
themeMidnight
# for
onap          logdemonode-logdemonode-5c8bffb468-dhzcc   2/2       Running   0          1m
# use
kubectl exec -it logdemonode-logdemonode-5c8bffb468-dhzcc -n onap -c logdemonode bash

Push a file into a Kubernetes container/pod

Code Block
themeMidnight
opy files from the vm to the robot container - to avoid buiding a new robot image
root@ubuntu:~/_dev/62405_logback/testsuite/robot/testsuites# kubectl cp health-check.robot onap-robot-7c84f54558-f8mw7: -n onap 
root@ubuntu:~/_dev/62405_logback/testsuite/robot/testsuites# kubectl cp ../resources/pomba_interface.robot onap-robot-7c84f54558-f8mw7: -n onap

move the files in the robot container to the proper dir
root@onap-robot-7c84f54558-f8mw7:/# cp health-check.robot /var/opt/OpenECOMP_ETE/robot/testsuites/
root@onap-robot-7c84f54558-f8mw7:/# ls
bin  boot  dev  etc  health-check.robot  home  lib  lib64  media  mnt  opt  pomba_interface.robot  proc  root  run  sbin  share  srv  sys  tmp  usr  var
root@onap-robot-7c84f54558-f8mw7:/# cp pomba_interface.robot /var/opt/OpenECOMP_ETE/robot/resources/ 

retest health
root@ubuntu:~/_dev/62405_logback/oom/kubernetes/robot# ./ete-k8s.sh onap health


and directly in the robot container
wget http://pomba-sdcctxbuilder.onap:9530/sdccontextbuilder/health
wget http://pomba-networkdiscoveryctxbuilder.onap:9530/ndcontextbuilder/health

Restarting a container

Restarting a pod

If you change configuration like the logback.xml in a pod or would like restart an entire pod like the log and portal pods

Code Block
languagebash
themeMidnight
cd oom/kubernetes
# do a make if anything is modified in your charts
sudo make all
#sudo make onap
ubuntu@ip-172-31-19-23:~/oom/kubernetes$ sudo helm upgrade -i onap local/onap --namespace onap --set log.enabled=false
# wait and check in another terminal for all containers to terminate
ubuntu@ip-172-31-19-23:~$ --kubeconfig ~/.kube/config2  get pods --all-namespaces


Adding user kubectl accounts

Normally you don't use the admin account directly when working with particular namespaces.  Details on how to create a user token and the appropriate role bindings.

Code Block
themeRDark
# TODO: create a script out of this
# create a namespace
# https://kubernetes.io/docs/tasks/administer-cluster/namespaces-walkthrough/#create-new-namespaces
vi mobrien_namespace.yaml
{
  "kind": "Namespace",
  "apiVersion": "v1",
  "metadata": {
    "name": "mobrien",
    "labels": {
      "name": "mobrien"
    }
  }
}
kubectl create -f mobrien_namespace.yaml
# or
kubectl --kubeconfig ~/.kube/admin create ns mobrien
namespace "mobrien" created

# service account
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create sa mobrien
serviceaccount "mobrien" created

# rolebinding mobrien
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create rolebinding mobrien-mobrien-privilegedpsp --clusterrole=privilegedpsp --serviceaccount=mobrien:mobrien
rolebinding "mobrien-mobrien-privilegedpsp" created

# rolebinding default
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create rolebinding mobrien-default-privilegedpsp --clusterrole=privilegedpsp --serviceaccount=mobrien:default
rolebinding "mobrien-default-privilegedpsp" created

# rolebinding admin
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create rolebinding mobrien-mobrien-admin --clusterrole=admin --serviceaccount=mobrien:mobrien
rolebinding "mobrien-mobrien-admin" created

# rolebinding persistent-volume-role
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create clusterrolebinding mobrien-mobrien-persistent-volume-role --clusterrole=persistent-volume-role --serviceaccount=mobrien:mobrien
clusterrolebinding "mobrien-mobrien-persistent-volume-role" created

# rolebinding default-persistent-volume-role
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create clusterrolebinding mobrien-default-persistent-volume-role --clusterrole=persistent-volume-role --serviceaccount=mobrien:default
clusterrolebinding "mobrien-default-persistent-volume-role" created

# rolebinding helm-pod-list
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create clusterrolebinding mobrien-mobrien-helm-pod-list --clusterrole=helm-pod-list --serviceaccount=mobrien:mobrien
clusterrolebinding "mobrien-mobrien-helm-pod-list" created

# rolebinding default-helm-pod-list
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien create clusterrolebinding mobrien-default-helm-pod-list --clusterrole=helm-pod-list --serviceaccount=mobrien:default
clusterrolebinding "mobrien-default-helm-pod-list" created


# get the serviceAccount and extract the token to place into a config yaml
kubectl --kubeconfig ~/.kube/admin --namespace=mobrien get sa
NAME      SECRETS   AGE
default   1         20m
mobrien   1         18m

kubectl --kubeconfig ~/.kube/admin --namespace=mobrien describe serviceaccount mobrien
Name:		mobrien
Namespace:	mobrien
Labels:		<none>
Annotations:	<none>
Image pull secrets:	<none>
Mountable secrets: 	mobrien-token-v9z5j
Tokens:            	mobrien-token-v9z5j
TOKEN=$(kubectl --kubeconfig ~/.kube/admin --namespace=mobrien describe secrets "$(kubectl --kubeconfig ~/.kube/admin --namespace=mobrien describe serviceaccount mobrien | grep -i Tokens | awk '{print $2}')" | grep token: | awk '{print $2}')

echo $TOKEN
eyJO....b3VudC


# put this in your ~/.kube/config and edit the namespace

see also https://stackoverflow.com/questions/44948483/create-user-in-kubernetes-for-kubectl

Helm on Rancher unauthorized

Cycle the RBAC to Github off/on if you get any security issue running helm commands

Code Block
themeMidnight
ubuntu@a-ons1-master:~$ watch kubectl get pods --all-namespaces
| grep onap-log
onap          onap-log-elasticsearch-7557486bc4-5mng9    ubuntu@a-ons1-master:~$ sudo helm list
Error: Unauthorized
ubuntu@a-ons1-master:~$ sudo helm list
NAME       	REVISION	UPDATED      0/1       CrashLoopBackOff   9 	STATUS  	CHART       29m	NAMESPACE
onap       	4   onap-log-kibana-fc88b6b79-nt7sd    	Thu Mar  7 13:03:29 2019	DEPLOYED	onap-3.0.0  	onap     
onap-dmaap 1/	1       Running	Thu Mar       7 13:03:32 2019	DEPLOYED	dmaap-3.0.0 	onap    0          35m
onap          onap-log-logstash-c5z4d


Working with JSONPath 

https://kubernetes.io/docs/reference/kubectl/jsonpath/

Fortunately we can script most of what we can query from the state of our kubernetes deployment using JSONPath.  We can then use jq to do additional processing to get values as an option.

Get the full json output to design JSONPath queries

Jira Legacy
serverSystem Jira
serverId4733707d-2057-3a0f-ae5e-4fd8aff50176
keyLOG-914

Code Block
themeRDark
kubectl get pods --all-namespaces -o json
# we are looking to shutdown a rogue pod that is not responding to the normal deletion commands - but it contains a generated name
onap          onap-portal-portal-sdk-7c49c97955-smbws     10/12       Terminating   0     0     2d
ubuntu@onap-oom-obrien-rancher-e0:~$ kubectl get  4h
onap pods --field-selector=status.phase!=Running --all-namespaces
NAMESPACE   NAME      onap-log-logstash-ftxfz                          1/1      READY Terminating     STATUS   0     RESTARTS     4hAGE
onap          onap-portal-portal-logsdk-logstash7c49c97955-gl59msmbws   0/2       Terminating   0          2d
#"spec":  1/1       Terminating        0          4h
onap          onap-log-logstash-nxsf8                          1/1       Terminating        0          4h
onap          onap-log-logstash-w8q8m                          1/1       Terminating        0          4h
sudo helm upgrade -i onap local/onap --namespace onap --set portal.enabled=false
sudo vi portal/charts/portal-sdk/resources/config/deliveries/properties/ONAPPORTALSDK/logback.xml
sudo make portal
sudo make onap
ubuntu@ip-172-31-19-23:~$ kubectl get pods{"containers": [{},"name": "portal-sdk",
kubectl get pods --namespace onap -o jsonpath="{.items[*].spec.containers[0].name}"
portal-sdk
# so combining the two queries
kubectl get pods --field-selector=status.phase!=Running --all-namespaces -o jsonpath="{.items[*].metadata.name}"
onap-portal-portal-sdk-7c49c97955-smbws
# and wrapping it with a delete command

export POD_NAME=$(kubectl get pods --field-selector=status.phase!=Running --all-namespaces -o jsonpath="{.items[*].metadata.name}")
echo "$POD_NAME"
kubectl delete pods $POD_NAME --grace-period=0 --force -n onap

ubuntu@onap-oom-obrien-rancher-e0:~$ sudo ./term.sh 
onap-portal-portal-sdk-7c49c97955-smbws
warning: Immediate deletion does not wait for confirmation that the running resource has been terminated. The resource may continue to run on the cluster indefinitely.
pod "onap-portal-portal-sdk-7c49c97955-smbws" force deleted


Installing a pod

Code Block
languagebash
themeMidnight
# automatically via cd.sh in LOG-326
# get the dev.yaml and set any pods you want up to true as well as fill out the openstack parameters
sudo wget https://git.onap.org/oom/plain/kubernetes/onap/resources/environments/dev.yaml
sudo cp logging-analytics/deploy/cd.sh .

# or
# manually
cd oom/kubernetes/
sudo make clean
sudo make all
sudo make onap
sudo helm install local/onap -n onap --namespace onap -f onap/resources/environments/disable-allcharts.yaml --set log.enabled=true
# adding another (so)
sudo helm upgrade local/onap --namespace onap -f onap/resources/environments/disable-allcharts.yaml --set so.enabled=true --set log.enabled=true

Get the nodeport of a particular service

Code Block
themeMidnight
# human readable list
kubectl get services --all-namespaces | grep onap-log
sudo helm upgrade -i onap local/onaprobot
# machine readable number - via JSONPath
kubectl get --namespace onap --set log.enabled=true
sudo helm upgrade -i onap local/onap --namespace onap --set portal.enabled=true
ubuntu@ip-172-31-19-23:~$ kubectl get pods --all-namespaces | grep onap-log
onap          onap-log-elasticsearch-7557486bc4-2jd65          0/1o jsonpath="{.spec.ports[0].nodePort}" services robot)


Test DNS URLS in the kubernetes ONAP namespace

Code Block
themeMidnight
test urls in the robot container
wget http://pomba-sdcctxbuilder.onap:9530/sdccontextbuilder/health
wget http://pomba-networkdiscoveryctxbuilder.onap:9530/ndcontextbuilder/health


Override global policy

Code Block
languagebash
themeMidnight
# override global docker pull policy for a single component
# set in oom/kubernetes/onap/values.yaml
# use global.pullPolicy in your -f yaml or a --set

Exec into a container of a pod with multiple containers

Code Block
themeMidnight
# for
onap         Init:0/1  logdemonode-logdemonode-5c8bffb468-dhzcc   2/2       0Running   0       31s onap  1m
# use
kubectl exec -it   onaplogdemonode-loglogdemonode-kibana5c8bffb468-fc88b6b79dhzcc -5xqg4n onap -c logdemonode bash

Push a file into a Kubernetes container/pod

Code Block
themeMidnight
opy files from the vm to the robot container - to avoid buiding a 0/1new robot image
root@ubuntu:~/_dev/62405_logback/testsuite/robot/testsuites# kubectl cp  Init:0/1           0          31s
onap          onap-log-logstash-5vq82                          0/1       Init:0/1           0          31s
onap          onap-log-logstash-gvr9z                          0/1       Init:0/1           0          31shealth-check.robot onap-robot-7c84f54558-f8mw7: -n onap 
root@ubuntu:~/_dev/62405_logback/testsuite/robot/testsuites# kubectl cp ../resources/pomba_interface.robot onap-robot-7c84f54558-f8mw7: -n onap

move the files in the robot container to the proper dir
root@onap-robot-7c84f54558-f8mw7:/# cp health-check.robot /var/opt/OpenECOMP_ETE/robot/testsuites/
root@onap-robot-7c84f54558-f8mw7:/# ls
bin  boot  dev  etc  health-check.robot  home  lib  lib64  media  mnt  opt  pomba_interface.robot  proc  root  run  sbin  share  srv  sys  tmp  usr  var
root@onap-robot-7c84f54558-f8mw7:/# cp pomba_interface.robot /var/opt/OpenECOMP_ETE/robot/resources/ 

retest health
root@ubuntu:~/_dev/62405_logback/oom/kubernetes/robot# ./ete-k8s.sh onap health


and directly in the robot container
wget http://pomba-sdcctxbuilder.onap:9530/sdccontextbuilder/health
wget http://pomba-networkdiscoveryctxbuilder.onap:9530/ndcontextbuilder/health

Restarting a container

Restarting a pod

If you change configuration like the logback.xml in a pod or would like restart an entire pod like the log and portal pods

Code Block
languagebash
themeMidnight
cd oom/kubernetes
# do a make if anything is modified in your charts
sudo make all
#sudo make onap
ubuntu@ip-172-31-19-23:~/oom/kubernetes$ sudo helm upgrade -i onap local/onap --namespace onap --set log.enabled=false
# wait and check in another terminal for all containers to terminate
ubuntu@ip-172-31-19-23:~$ kubectl get pods --all-namespaces | grep onap-log
onap          onap-log-logstash-qqzq5elasticsearch-7557486bc4-5mng9          0/1       CrashLoopBackOff   9          29m
onap          onap-log-kibana-fc88b6b79-nt7sd                 0 1/1       Init:0/1Running            0          31s35m
onap          onap-log-logstash-vbp2xc5z4d                          01/1       Init:0/1   Terminating        0          31s4h
onap          onap-log-logstash-wr9rdftxfz                          01/1       Init:0/1Terminating        0     0     4h
onap    31s  ubuntu@ip-172-31-19-23:~$ kubectl get pods onap-log-alllogstash-namespacesgl59m | grep onap-portal
onap               onap-portal-app-8486dc7ff8-nbps7         1/1       Terminating 0/2       Init:0/1          4h
0onap          9m
onaponap-log-logstash-nxsf8           onap-portal-cassandra-8588fbd698-4wthv           1/1    1/1   Running    Terminating        0          9m4h
onap          onap-portallog-dblogstash-7d6b95cd94-9x4kfw8q8m                  0/1       Running 1/1       Terminating    0    0      9m onap   4h
sudo helm upgrade -i onap local/onap onap-portal-dbnamespace onap -config-dpqkqset portal.enabled=false
sudo vi portal/charts/portal-sdk/resources/config/deliveries/properties/ONAPPORTALSDK/logback.xml
sudo make portal
sudo make onap
ubuntu@ip-172-31-19-23:~$ kubectl get pods --all-namespaces | grep onap-log
sudo helm upgrade 0/2-i onap local/onap --namespace onap --set  Init:0/1           0          9m
log.enabled=true
sudo helm upgrade -i onap local/onap --namespace onap --set portal.enabled=true
ubuntu@ip-172-31-19-23:~$ kubectl get pods --all-namespaces | grep onap-log
onap          onap-portallog-sdkelasticsearch-77cd558c987557486bc4-5255r2jd65                 0/21       Init:0/1           0          9m31s
onap          onap-portallog-widgetkibana-6469f4bc56-g8s62fc88b6b79-5xqg4                  0/1       Init:0/1           0          9m31s
onap          onap-portallog-zookeeper-5d8c598c4c-czpnzlogstash-5vq82                          0/1       Init:0/1       Running    0        0  31s
onap       9m

downgrade docker if required

Code Block
sudo apt-get autoremove onap-y docker-engine

Change max-pods from default 110 pod limit

Rancher ships with a 110 pod limit - you can override this on the kubernetes template for 1.10

https://lists.onap.org/g/onap-discuss/topic/oom_110_kubernetes_pod/25213556?p=,,,20,0,0,0::recentpostdate%2Fsticky,,,20,2,0,25213556

Manual procedure: change the kubernetes template (1pt2) before using it to create an environment (1a7)

add --max-pods=500 to the "Additional Kubelet Flags" box on the v1.10.13 version of the kubernetes template from the "Manage Environments" dropdown on the left of the 8880 rancher console.

View file
name20180905_rancher_increase_110_pod_limit.mp4
height250

Jira Legacy
serverSystem Jira
serverId4733707d-2057-3a0f-ae5e-4fd8aff50176
keyOOM-1137

Image Removed

Image Removed

Or capture the output of the REST PUT call - and add around line 111 of the script https://git.onap.org/logging-analytics/tree/deploy/rancher/oom_rancher_setup.sh#n111

Image Removed

Automated - ongoing

Code Block
themeMidnight
ubuntu@ip-172-31-27-183:~$ curl 'http://127.0.0.1:8880/v2-beta/projecttemplates/1pt2' --data-binary '{"id":"1pt2","type":"projectTemplate","baseType":"projectTemplate","name":"Kubernetes","state":"active","accountId":null,"created":"2018-09-05T14:12:24Z","createdTS":1536156744000,"data":{"fields":{"stacks":[{"name":"healthcheck","templateId":"library:infra*healthcheck"},{"answers":{"CONSTRAINT_TYPE":"none","CLOUD_PROVIDER":"rancher","AZURE_CLOUD":"AzurePublicCloud","AZURE_TENANT_ID":"","AZURE_CLIENT_ID":"","AZURE_CLIENT_SECRET":"","AZURE_SEC_GROUP":"","RBAC":false,"REGISTRY":"","BASE_IMAGE_NAMESPACE":"","POD_INFRA_CONTAINER_IMAGE":"rancher/pause-amd64:3.0","HTTP_PROXY":"","NO_PROXY":"rancher.internal,cluster.local,rancher-metadata,rancher-kubernetes-auth,kubernetes,169.254.169.254,169.254.169.250,10.42.0.0/16,10.43.0.0/16","ENABLE_ADDONS":true,"ENABLE_RANCHER_INGRESS_CONTROLLER":true,"RANCHER_LB_SEPARATOR":"rancherlb","DNS_REPLICAS":"1","ADDITIONAL_KUBELET_FLAGS":"","FAIL_ON_SWAP":"false","ADDONS_LOG_VERBOSITY_LEVEL":"2","AUDIT_LOGS":false,"ADMISSION_CONTROLLERS":"NamespaceLifecycle,LimitRanger,ServiceAccount,PersistentVolumeLabel,DefaultStorageClass,DefaultTolerationSeconds,ResourceQuota","SERVICE_CLUSTER_CIDR":"10.43.0.0/16","DNS_CLUSTER_IP":"10.43.0.10","KUBEAPI_CLUSTER_IP":"10.43.0.1","KUBERNETES_CIPHER_SUITES":"TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305","DASHBOARD_CPU_LIMIT":"100m","DASHBOARD_MEMORY_LIMIT":"300Mi","INFLUXDB_HOST_PATH":"","EMBEDDED_BACKUPS":true,"BACKUP_PERIOD":"15m0s","BACKUP_RETENTION":"24h","ETCD_HEARTBEAT_INTERVAL":"500","ETCD_ELECTION_TIMEOUT":"5000"},"name":"kubernetes","templateVersionId":"library:infra*k8s:47"},{"name":"network-services","templateId":"library:infra*network-services"},{"name":"ipsec","templateId":"library:infra*ipsec"}]}},"description":"Default Kubernetes template","externalId":"catalog://library:project*kubernetes:0","isPublic":true,"kind":"projectTemplate","removeTime":null,"removed":null,"stacks":[{"type":"catalogTemplate","name":"healthcheck","templateId":"library:infra*healthcheck"},{"type":"catalogTemplate","answers":{"CONSTRAINT_TYPE":"none","CLOUD_PROVIDER":"rancher","AZURE_CLOUD":"AzurePublicCloud","AZURE_TENANT_ID":"","AZURE_CLIENT_ID":"","AZURE_CLIENT_SECRET":"","AZURE_SEC_GROUP":"","RBAC":false,"REGISTRY":"","BASE_IMAGE_NAMESPACE":"","POD_INFRA_CONTAINER_IMAGE":"rancher/pause-amd64:3.0","HTTP_PROXY":"","NO_PROXY":"rancher.internal,cluster.local,rancher-metadata,rancher-kubernetes-auth,kubernetes,169.254.169.254,169.254.169.250,10.42.0.0/16,10.43.0.0/16","ENABLE_ADDONS":true,"ENABLE_RANCHER_INGRESS_CONTROLLER":true,"RANCHER_LB_SEPARATOR":"rancherlb","DNS_REPLICAS":"1","ADDITIONAL_KUBELET_FLAGS":"--max-pods=600","FAIL_ON_SWAP":"false","ADDONS_LOG_VERBOSITY_LEVEL":"2","AUDIT_LOGS":false,"ADMISSION_CONTROLLERS":"NamespaceLifecycle,LimitRanger,ServiceAccount,PersistentVolumeLabel,DefaultStorageClass,DefaultTolerationSeconds,ResourceQuota","SERVICE_CLUSTER_CIDR":"10.43.0.0/16","DNS_CLUSTER_IP":"10.43.0.10","KUBEAPI_CLUSTER_IP":"10.43.0.1","KUBERNETES_CIPHER_SUITES":"TLS_ECDHE_log-logstash-gvr9z                          0/1       Init:0/1           0          31s
onap          onap-log-logstash-qqzq5                          0/1       Init:0/1           0          31s
onap          onap-log-logstash-vbp2x                          0/1       Init:0/1           0          31s
onap          onap-log-logstash-wr9rd                          0/1       Init:0/1           0          31s

ubuntu@ip-172-31-19-23:~$ kubectl get pods --all-namespaces | grep onap-portal
onap          onap-portal-app-8486dc7ff8-nbps7                 0/2       Init:0/1           0          9m
onap          onap-portal-cassandra-8588fbd698-4wthv           1/1       Running            0          9m
onap          onap-portal-db-7d6b95cd94-9x4kf                  0/1       Running            0          9m
onap          onap-portal-db-config-dpqkq                      0/2       Init:0/1           0          9m
onap          onap-portal-sdk-77cd558c98-5255r                 0/2       Init:0/1           0          9m
onap          onap-portal-widget-6469f4bc56-g8s62              0/1       Init:0/1           0          9m
onap          onap-portal-zookeeper-5d8c598c4c-czpnz           1/1       Running            0          9m

Kubernetes inter pod communication - using DNS service addresses

Try to use the service name (with or without the namespace) - not the service IP address for inter namespace communication (nodeports or ingress is only required outside the namespace)

For example log-ls:5044 or log-ls.onap:5044

Code Block
themeMidnight
# example curl call between AAI and SDC
amdocs@obriensystemsu0:~$ kubectl exec -it -n onap    onap-aai-aai-graphadmin-7bd5fc9bd-l4v4z bash
Defaulting container name to aai-graphadmin.
root@aai-graphadmin:/opt/app/aai-graphadmin# curl http://sdc-fe:8181
<HTML><HEAD><TITLE>Error 404 - Not Found</TITLE><BODY><H2>Error 404 - Not Found.</H2>
</ul><hr><a href="http://eclipse.org/jetty"><img border=0 src="/favicon.ico"/></a>&nbsp;<a href="http://eclipse.org/jetty">Powered by Jetty:// 9.4.12.v20180830</a><hr/>


docker if required

Code Block
sudo apt-get autoremove -y docker-engine

Change max-pods from default 110 pod limit

Rancher ships with a 110 pod limit - you can override this on the kubernetes template for 1.10

https://lists.onap.org/g/onap-discuss/topic/oom_110_kubernetes_pod/25213556?p=,,,20,0,0,0::recentpostdate%2Fsticky,,,20,2,0,25213556

Manual procedure: change the kubernetes template (1pt2) before using it to create an environment (1a7)

add --max-pods=500 to the "Additional Kubelet Flags" box on the v1.10.13 version of the kubernetes template from the "Manage Environments" dropdown on the left of the 8880 rancher console.

View file
name20180905_rancher_increase_110_pod_limit.mp4
height250

Jira Legacy
serverSystem Jira
serverId4733707d-2057-3a0f-ae5e-4fd8aff50176
keyOOM-1137

Image Added

Image Added

Or capture the output of the REST PUT call - and add around line 111 of the script https://git.onap.org/logging-analytics/tree/deploy/rancher/oom_rancher_setup.sh#n111

Image Added

Automated - ongoing

Code Block
themeMidnight
ubuntu@ip-172-31-27-183:~$ curl 'http://127.0.0.1:8880/v2-beta/projecttemplates/1pt2' --data-binary '{"id":"1pt2","type":"projectTemplate","baseType":"projectTemplate","name":"Kubernetes","state":"active","accountId":null,"created":"2018-09-05T14:12:24Z","createdTS":1536156744000,"data":{"fields":{"stacks":[{"name":"healthcheck","templateId":"library:infra*healthcheck"},{"answers":{"CONSTRAINT_TYPE":"none","CLOUD_PROVIDER":"rancher","AZURE_CLOUD":"AzurePublicCloud","AZURE_TENANT_ID":"","AZURE_CLIENT_ID":"","AZURE_CLIENT_SECRET":"","AZURE_SEC_GROUP":"","RBAC":false,"REGISTRY":"","BASE_IMAGE_NAMESPACE":"","POD_INFRA_CONTAINER_IMAGE":"rancher/pause-amd64:3.0","HTTP_PROXY":"","NO_PROXY":"rancher.internal,cluster.local,rancher-metadata,rancher-kubernetes-auth,kubernetes,169.254.169.254,169.254.169.250,10.42.0.0/16,10.43.0.0/16","ENABLE_ADDONS":true,"ENABLE_RANCHER_INGRESS_CONTROLLER":true,"RANCHER_LB_SEPARATOR":"rancherlb","DNS_REPLICAS":"1","ADDITIONAL_KUBELET_FLAGS":"","FAIL_ON_SWAP":"false","ADDONS_LOG_VERBOSITY_LEVEL":"2","AUDIT_LOGS":false,"ADMISSION_CONTROLLERS":"NamespaceLifecycle,LimitRanger,ServiceAccount,PersistentVolumeLabel,DefaultStorageClass,DefaultTolerationSeconds,ResourceQuota","SERVICE_CLUSTER_CIDR":"10.43.0.0/16","DNS_CLUSTER_IP":"10.43.0.10","KUBEAPI_CLUSTER_IP":"10.43.0.1","KUBERNETES_CIPHER_SUITES":"TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305","DASHBOARD_CPU_LIMIT":"100m","DASHBOARD_MEMORY_LIMIT":"300Mi","INFLUXDB_HOST_PATH":"","EMBEDDED_BACKUPS":true,"BACKUP_PERIOD":"15m0s","BACKUP_RETENTION":"24h","ETCD_HEARTBEAT_INTERVAL":"500","ETCD_ELECTION_TIMEOUT":"5000"},"name":"kubernetes","templateVersionId":"library:infra*k8s:47"},{"type":"catalogTemplate","name":"network-services","templateId":"library:infra*network-services"},{"type":"catalogTemplate","name":"ipsec","templateId":"library:infra*ipsec"}],"transitioning":"no","transitioningMessage":null,"transitioningProgress":null,"uuid":null}' --compressed

{"id":"9107b9ce-0b61-4c22-bc52-f147babb0ba7","type":"error","links":{},"actions":{},"status":405,"code":"Method not allowed","message":"Method not allowed","detail":null,"baseType":"error"}

Results

Single AWS 244G 32vCore VM with 110 pod limit workaround - 164 pods (including both secondary DCAEGEN2 orchestrations at 30 and 55 min) - most of the remaining 8 container failures are known/in-progress issues.

Code Block
themeMidnight
ubuntu@ip-172-31-20-218:~$ free
   k8s:47"},{"name":"network-services","templateId":"library:infra*network-services"},{"name":"ipsec","templateId":"library:infra*ipsec"}]}},"description":"Default Kubernetes template","externalId":"catalog://library:project*kubernetes:0","isPublic":true,"kind":"projectTemplate","removeTime":null,"removed":null,"stacks":[{"type":"catalogTemplate","name":"healthcheck","templateId":"library:infra*healthcheck"},{"type":"catalogTemplate","answers":{"CONSTRAINT_TYPE":"none","CLOUD_PROVIDER":"rancher","AZURE_CLOUD":"AzurePublicCloud","AZURE_TENANT_ID":"","AZURE_CLIENT_ID":"","AZURE_CLIENT_SECRET":"","AZURE_SEC_GROUP":"","RBAC":false,"REGISTRY":"","BASE_IMAGE_NAMESPACE":"","POD_INFRA_CONTAINER_IMAGE":"rancher/pause-amd64:3.0","HTTP_PROXY":"","NO_PROXY":"rancher.internal,cluster.local,rancher-metadata,rancher-kubernetes-auth,kubernetes,169.254.169.254,169.254.169.250,10.42.0.0/16,10.43.0.0/16","ENABLE_ADDONS":true,"ENABLE_RANCHER_INGRESS_CONTROLLER":true,"RANCHER_LB_SEPARATOR":"rancherlb","DNS_REPLICAS":"1","ADDITIONAL_KUBELET_FLAGS":"--max-pods=600","FAIL_ON_SWAP":"false","ADDONS_LOG_VERBOSITY_LEVEL":"2","AUDIT_LOGS":false,"ADMISSION_CONTROLLERS":"NamespaceLifecycle,LimitRanger,ServiceAccount,PersistentVolumeLabel,DefaultStorageClass,DefaultTolerationSeconds,ResourceQuota","SERVICE_CLUSTER_CIDR":"10.43.0.0/16","DNS_CLUSTER_IP":"10.43.0.10","KUBEAPI_CLUSTER_IP":"10.43.0.1","KUBERNETES_CIPHER_SUITES":"TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305","DASHBOARD_CPU_LIMIT":"100m","DASHBOARD_MEMORY_LIMIT":"300Mi","INFLUXDB_HOST_PATH":"","EMBEDDED_BACKUPS":true,"BACKUP_PERIOD":"15m0s","BACKUP_RETENTION":"24h","ETCD_HEARTBEAT_INTERVAL":"500","ETCD_ELECTION_TIMEOUT":"5000"},"name":"kubernetes","templateVersionId":"library:infra*k8s:47"},{"type":"catalogTemplate","name":"network-services","templateId":"library:infra*network-services"},{"type":"catalogTemplate","name":"ipsec","templateId":"library:infra*ipsec"}],"transitioning":"no","transitioningMessage":null,"transitioningProgress":null,"uuid":null}' --compressed

{"id":"9107b9ce-0b61-4c22-bc52-f147babb0ba7","type":"error","links":{},"actions":{},"status":405,"code":"Method not allowed","message":"Method not allowed","detail":null,"baseType":"error"}

Results

Single AWS 244G 32vCore VM with 110 pod limit workaround - 164 pods (including both secondary DCAEGEN2 orchestrations at 30 and 55 min) - most of the remaining 8 container failures are known/in-progress issues.


Code Block
themeMidnight
ubuntu@ip-172-31-20-218:~$ free
              total        used        free      shared  buff/cache   available
Mem:      251754696   111586672    45000724      193628    95167300   137158588
ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep onap | wc -l
164
ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep onap | grep -E '1/1|2/2' | wc -l
155
ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep -E '0/|1/2' | wc -l
8
ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep -E '0/|1/2'
onap          dep-dcae-ves-collector-59d4ff58f7-94rpq                 1/2       Running                 0          4m
onap          onap-aai-champ-68ff644d85-rv7tr                         0/1       Running                 0          59m
onap          onap-aai-gizmo-856f86d664-q5pvg                         1/2       CrashLoopBackOff        10         59m
onap          onap-oof-85864d6586-zcsz5                               0/1       ImagePullBackOff        0          59m
onap          onap-pomba-kibana-d76b6dd4c-sfbl6                       0/1       Init:CrashLoopBackOff   8          59m
onap          onap-pomba-networkdiscovery-85d76975b7-mfk92            1/2       CrashLoopBackOff        11         59m
onap          onap-pomba-networkdiscoveryctxbuilder-c89786dfc-qnlx9   1/2       CrashLoopBackOff        10         59m
onap          onap-vid-84c88db589-8cpgr                               1/2       CrashLoopBackOff        9          59m


Operations

Get failed/pending containers

Code Block
themeMidnight
linenumberstrue
kubectl get pods --all-namespaces | grep -E "0/|1/2" | wc -l


Code Block
kubectl cluster-info
# get pods/containers
kubectl get pods --all-namespaces
# get port mappings
kubectl get services --all-namespaces -o wide
NAMESPACE     NAME                                   READY     STATUS    RESTARTS   AGE
default       nginx-1389790254-lgkz3                 1/1       Running   1          5d
kube-system   heapster-4285517626-x080g              1/1       Running   1          6d
kube-system   kube-dns-638003847-tst97               3/3       Running   3          6d
kube-system   kubernetes-dashboard-716739405-fnn3g   1/1       Running   2          6d
kube-system   monitoring-grafana-2360823841-hr824    1/1       Running   1          6d
kube-system   monitoring-influxdb-2323019309-k7h1t   1/1       Running   1          6d
kube-system   tiller-deploy-737598192-x9wh5          1/1       Running   1          6d
# ssh into a pod
kubectl -n default exec -it  nginx-1389790254-lgkz3 /bin/bash
# get logs
kubectl -n default logs -f nginx-1389790254-lgkz3

Exec

kubectl -n onap-aai exec -it aai-resources-1039856271-d9bvq  bash

Bounce/Fix a failed container

Periodically one of the higher containers in a dependency tree will not get restarted in time to pick up running child containers - usually this is the kibana container

Fix this or "any" container by deleting the container in question and kubernetes will bring another one up.

Code Block
themeMidnight
root@a-onap-auto-20180412-ref:~# kubectl get services --all-namespaces | grep log
onap          dev-vfc-catalog               ClusterIP   10.43.210.8     <none>        8806/TCP                                                                     5d
onap          log-es                        NodePort    10.43.77.87     <none>        9200:30254/TCP                                                               5d
onap          log-es-tcp                    ClusterIP   10.43.159.93    <none>        9300/TCP                                                                     5d
onap          log-kibana                    NodePort    10.43.41.102    <none>        5601:30253/TCP                                                               5d
onap          log-ls                        NodePort    10.43.180.165   <none>        5044:30255/TCP                                                               5d
onap          log-ls-http                   ClusterIP   10.43.13.180    <none>        9600/TCP                                                                     5d
root@a-onap-auto-20180412-ref:~# kubectl get pods --all-namespaces | grep log
onap          dev-log-elasticsearch-66cdc4f855-wmpkz         1/1       Running                 0          5d
onap          dev-log-kibana-5b6f86bcb4-drpzq                0/1       Running                 1076       5d
onap          dev-log-logstash-6d9fdccdb6-ngq2f              1/1       Running                 0          5d
onap          dev-vfc-catalog-7d89bc8b9d-vxk74               2/2       Running                 0          5d
root@a-onap-auto-20180412-ref:~# kubectl delete pod dev-log-kibana-5b6f86bcb4-drpzq -n onap
pod "dev-log-kibana-5b6f86bcb4-drpzq" deleted
root@a-onap-auto-20180412-ref:~# kubectl get pods --all-namespaces | grep log
onap          dev-log-elasticsearch-66cdc4f855-wmpkz         1/1       Running                 0          5d
onap          dev-log-kibana-5b6f86bcb4-drpzq                0/1       Terminating             1076       5d
onap          dev-log-kibana-5b6f86bcb4-gpn2m                0/1       Pending                 0          12s
onap          dev-log-logstash-6d9fdccdb6-ngq2f              1/1       Running                 0          5d
onap          dev-vfc-catalog-7d89bc8b9d-vxk74               2/2       Running                 0          5d


Remove containers stuck in terminating

a helm namespace delete or a kubectl delete or a helm purge may not remove everything based on hanging PVs - use

Code Block
themeMidnight
#after a kubectl delete namespace onap
sudo helm delete --purge onap


melliott [12:11 PM]
kubectl delete pods <pod> --grace-period=0 --force -n onap

Reboot VMs hosting a Deployment

aka https://lists.onap.org/g/onap-discuss/topic/procedure_to_shut_down_and/29540879?p=,,,20,0,0,0::recentpostdate%2Fsticky,,,20,2,0,29540879

in progress

Code Block
themeMidnight
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces | wc -l
234
# master 20190125
ubuntu@a-ld0:~$ kubectl scale --replicas=0 deployments --all -n onap
deployment.extensions/onap-aaf-aaf-cm scaled
deployment.extensions/onap-aaf-aaf-cs scaled
deployment.extensions/onap-aaf-aaf-fs scaled
deployment.extensions/onap-aaf-aaf-gui scaled
deployment.extensions/onap-aaf-aaf-hello scaled
deployment.extensions/onap-aaf-aaf-locate scaled
deployment.extensions/onap-aaf-aaf-oauth scaled
deployment.extensions/onap-aaf-aaf-service scaled
deployment.extensions/onap-aaf-aaf-sms scaled
deployment.extensions/onap-aai-aai scaled
deployment.extensions/onap-aai-aai-babel scaled
deployment.extensions/onap-aai-aai-champ scaled
deployment.extensions/onap-aai-aai-data-router scaled
deployment.extensions/onap-aai-aai-elasticsearch scaled
deployment.extensions/onap-aai-aai-gizmo scaled
deployment.extensions/onap-aai-aai-graphadmin scaled
deployment.extensions/onap-aai-aai-modelloader scaled
deployment.extensions/onap-aai-aai-resources scaled
deployment.extensions/onap-aai-aai-search-data scaled
deployment.extensions/onap-aai-aai-sparky-be scaled
deployment.extensions/onap-aai-aai-spike scaled
deployment.extensions/onap-aai-aai-traversal scaled
deployment.extensions/onap-appc-appc-ansible-server scaled
deployment.extensions/onap-appc-appc-cdt scaled
deployment.extensions/onap-appc-appc-dgbuilder scaled
deployment.extensions/onap-clamp-clamp scaled
deployment.extensions/onap-clamp-clamp-dash-es scaled
deployment.extensions/onap-clamp-clamp-dash-kibana scaled
deployment.extensions/onap-clamp-clamp-dash-logstash scaled
deployment.extensions/onap-clamp-clampdb scaled
deployment.extensions/onap-cli-cli scaled
deployment.extensions/onap-consul-consul scaled
deployment.extensions/onap-contrib-netbox-app scaled
deployment.extensions/onap-contrib-netbox-nginx scaled
deployment.extensions/onap-contrib-netbox-postgres scaled
deployment.extensions/onap-dcaegen2-dcae-bootstrap scaled
deployment.extensions/onap-dcaegen2-dcae-cloudify-manager scaled
deployment.extensions/onap-dcaegen2-dcae-healthcheck scaled
deployment.extensions/onap-dcaegen2-dcae-pgpool scaled
deployment.extensions/onap-dmaap-dbc-pgpool scaled
deployment.extensions/onap-dmaap-dmaap-bus-controller scaled
deployment.extensions/onap-dmaap-dmaap-dr-db scaled
deployment.extensions/onap-dmaap-dmaap-dr-node scaled
deployment.extensions/onap-dmaap-dmaap-dr-prov scaled
deployment.extensions/onap-esr-esr-gui scaled
deployment.extensions/onap-esr-esr-server scaled
deployment.extensions/onap-log-log-elasticsearch scaled
deployment.extensions/onap-log-log-kibana scaled
deployment.extensions/onap-log-log-logstash scaled
deployment.extensions/onap-msb-kube2msb scaled
deployment.extensions/onap-msb-msb-consul scaled
deployment.extensions/onap-msb-msb-discovery scaled
deployment.extensions/onap-msb-msb-eag scaled
deployment.extensions/onap-msb-msb-iag scaled
deployment.extensions/onap-multicloud-multicloud scaled
deployment.extensions/onap-multicloud-multicloud-azure scaled
deployment.extensions/onap-multicloud-multicloud-ocata scaled
deployment.extensions/onap-multicloud-multicloud-pike scaled
deployment.extensions/onap-multicloud-multicloud-vio scaled
deployment.extensions/onap-multicloud-multicloud-windriver scaled
deployment.extensions/onap-oof-music-tomcat scaled
deployment.extensions/onap-oof-oof scaled
deployment.extensions/onap-oof-oof-cmso-service scaled
deployment.extensions/onap-oof-oof-has-api scaled
deployment.extensions/onap-oof-oof-has-controller scaled
deployment.extensions/onap-oof-oof-has-data scaled
deployment.extensions/onap-oof-oof-has-reservation scaled
deployment.extensions/onap-oof-oof-has-solver scaled
deployment.extensions/onap-policy-brmsgw scaled
deployment.extensions/onap-policy-nexus scaled
deployment.extensions/onap-policy-pap scaled
deployment.extensions/onap-policy-policy-distribution scaled
deployment.extensions/onap-policy-policydb scaled
deployment.extensions/onap-pomba-pomba-aaictxbuilder scaled
deployment.extensions/onap-pomba-pomba-contextaggregator scaled
deployment.extensions/onap-pomba-pomba-data-router scaled
deployment.extensions/onap-pomba-pomba-elasticsearch scaled
deployment.extensions/onap-pomba-pomba-kibana scaled
deployment.extensions/onap-pomba-pomba-networkdiscovery scaled
deployment.extensions/onap-pomba-pomba-networkdiscoveryctxbuilder scaled
deployment.extensions/onap-pomba-pomba-sdcctxbuilder scaled
deployment.extensions/onap-pomba-pomba-sdncctxbuilder scaled
deployment.extensions/onap-pomba-pomba-search-data scaled
deployment.extensions/onap-pomba-pomba-servicedecomposition scaled
deployment.extensions/onap-pomba-pomba-validation-service scaled
deployment.extensions/onap-portal-portal-app scaled
deployment.extensions/onap-portal-portal-cassandra scaled
deployment.extensions/onap-portal-portal-db scaled
deployment.extensions/onap-portal-portal-sdk scaled
deployment.extensions/onap-portal-portal-widget scaled
deployment.extensions/onap-portal-portal-zookeeper scaled
deployment.extensions/onap-robot-robot scaled
deployment.extensions/onap-sdc-sdc-be scaled
deployment.extensions/onap-sdc-sdc-cs scaled
deployment.extensions/onap-sdc-sdc-dcae-be scaled
deployment.extensions/onap-sdc-sdc-dcae-dt scaled
deployment.extensions/onap-sdc-sdc-dcae-fe scaled
deployment.extensions/onap-sdc-sdc-dcae-tosca-lab scaled
deployment.extensions/onap-sdc-sdc-es scaled
deployment.extensions/onap-sdc-sdc-fe scaled
deployment.extensions/onap-sdc-sdc-kb scaled
deployment.extensions/onap-sdc-sdc-onboarding-be scaled
deployment.extensions/onap-sdc-sdc-wfd-be scaled
deployment.extensions/onap-sdc-sdc-wfd-fe scaled
deployment.extensions/onap-sdnc-controller-blueprints scaled
deployment.extensions/onap-sdnc-network-name-gen scaled
deployment.extensions/onap-sdnc-sdnc-ansible-server scaled
deployment.extensions/onap-sdnc-sdnc-dgbuilder scaled
deployment.extensions/onap-sdnc-sdnc-dmaap-listener scaled
deployment.extensions/onap-sdnc-sdnc-portal scaled
deployment.extensions/onap-sdnc-sdnc-ueb-listener scaled
deployment.extensions/onap-sniro-emulator-sniro-emulator scaled
deployment.extensions/onap-so-so scaled
deployment.extensions/onap-so-so-bpmn-infra scaled
deployment.extensions/onap-so-so-catalog-db-adapter scaled
deployment.extensions/onap-so-so-mariadb scaled
deployment.extensions/onap-so-so-monitoring scaled
deployment.extensions/onap-so-so-openstack-adapter scaled
deployment.extensions/onap-so-so-request-db-adapter scaled
deployment.extensions/onap-so-so-sdc-controller scaled
deployment.extensions/onap-so-so-sdnc-adapter scaled
deployment.extensions/onap-so-so-vfc-adapter scaled
deployment.extensions/onap-uui-uui scaled
deployment.extensions/onap-uui-uui-server scaled
deployment.extensions/onap-vfc-vfc-catalog scaled
deployment.extensions/onap-vfc-vfc-db scaled
deployment.extensions/onap-vfc-vfc-ems-driver scaled
deployment.extensions/onap-vfc-vfc-generic-vnfm-driver scaled
deployment.extensions/onap-vfc-vfc-huawei-vnfm-driver scaled
deployment.extensions/onap-vfc-vfc-juju-vnfm-driver scaled
deployment.extensions/onap-vfc-vfc-multivim-proxy scaled
deployment.extensions/onap-vfc-vfc-nokia-v2vnfm-driver scaled
deployment.extensions/onap-vfc-vfc-nokia-vnfm-driver scaled
deployment.extensions/onap-vfc-vfc-nslcm scaled
deployment.extensions/onap-vfc-vfc-resmgr scaled
deployment.extensions/onap-vfc-vfc-vnflcm scaled
deployment.extensions/onap-vfc-vfc-vnfmgr scaled
deployment.extensions/onap-vfc-vfc-vnfres scaled
deployment.extensions/onap-vfc-vfc-workflow scaled
deployment.extensions/onap-vfc-vfc-workflow-engine scaled
deployment.extensions/onap-vfc-vfc-zte-sdnc-driver scaled
deployment.extensions/onap-vfc-vfc-zte-vnfm-driver scaled
deployment.extensions/onap-vid-vid scaled
deployment.extensions/onap-vnfsdk-vnfsdk scaled
deployment.extensions/onap-vnfsdk-vnfsdk-pgpool scaled
deployment.extensions/onap-vvp-vvp scaled
deployment.extensions/onap-vvp-vvp-ci-uwsgi scaled
deployment.extensions/onap-vvp-vvp-cms-uwsgi scaled
deployment.extensions/onap-vvp-vvp-em-uwsgi scaled
deployment.extensions/onap-vvp-vvp-ext-haproxy scaled
deployment.extensions/onap-vvp-vvp-gitlab scaled
deployment.extensions/onap-vvp-vvp-imagescanner scaled
deployment.extensions/onap-vvp-vvp-int-haproxy scaled
deployment.extensions/onap-vvp-vvp-jenkins scaled
deployment.extensions/onap-vvp-vvp-postgres scaled
deployment.extensions/onap-vvp-vvp-redis scaled
ubuntu@a-ld0:~$ kubectl scale --replicas=0 statefulsets --all -n onap
statefulset.apps/onap-aaf-aaf-sms-quorumclient scaled
statefulset.apps/onap-aaf-aaf-sms-vault scaled
statefulset.apps/onap-aai-aai-cassandra scaled
statefulset.apps/onap-appc-appc scaled
statefulset.apps/onap-appc-appc-db scaled
statefulset.apps/onap-consul-consul-server scaled
statefulset.apps/onap-dcaegen2-dcae-db scaled
statefulset.apps/onap-dcaegen2-dcae-redis scaled
statefulset.apps/onap-dmaap-dbc-pg scaled
statefulset.apps/onap-dmaap-message-router scaled
statefulset.apps/onap-dmaap-message-router-kafka scaled
statefulset.apps/onap-dmaap-message-router-zookeeper scaled
statefulset.apps/onap-oof-cmso-db scaled
statefulset.apps/onap-oof-music-cassandra scaled
statefulset.apps/onap-oof-zookeeper scaled
statefulset.apps/onap-policy-drools scaled
statefulset.apps/onap-policy-pdp scaled
statefulset.apps/onap-policy-policy-apex-pdp scaled
statefulset.apps/onap-sdnc-controller-blueprints-db scaled
statefulset.apps/onap-sdnc-nengdb scaled
statefulset.apps/onap-sdnc-sdnc scaled
statefulset.apps/onap-sdnc-sdnc-db scaled
statefulset.apps/onap-vid-vid-mariadb-galera scaled
statefulset.apps/onap-vnfsdk-vnfsdk-postgres scaled
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces | grep Terminating | wc -l
179
# 4 min later
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces | grep Terminating | wc -l
118
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces |  wc -l
135
# completed/failed jobs are left
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces |  wc -l
27
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces | grep Terminating | wc -l
0
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces 
NAMESPACE     NAME                                              READY     STATUS       RESTARTS   AGE
kube-system   heapster-7b48b696fc-99cd6                         1/1       Running      0          2d
kube-system   kube-dns-6655f78c68-k4dh4                         3/3       Running      0          2d
kube-system   kubernetes-dashboard-6f54f7c4b-fhqmf              1/1       Running      0          2d
kube-system   monitoring-grafana-7877679464-cscg4               1/1       Running      0          2d
kube-system   monitoring-influxdb-64664c6cf5-wmw8w              1/1       Running      0          2d
kube-system   tiller-deploy-78db58d887-9qlwh                    1/1       Running      0          2d
onap          onap-aaf-aaf-sms-preload-k7mx6                    0/1       Completed    0          2d
onap          onap-aaf-aaf-sshsm-distcenter-lk5st               0/1       Completed    0          2d
onap          onap-aaf-aaf-sshsm-testca-lg2g6                   0/1       Completed    0          2d
onap          onap-aai-aai-graphadmin-create-db-schema-7qhcr    0/1       Completed    0          2d
onap          onap-aai-aai-traversal-update-query-data-n6dt6    0/1       Init:0/1     289        2d
onap          onap-contrib-netbox-app-provisioning-7mb4f        0/1       Completed    0          2d
onap          onap-contrib-netbox-app-provisioning-wbvpv        0/1       Error        0          2d
onap          onap-oof-music-cassandra-job-config-wvwgv         0/1       Completed    0          2d
onap          onap-oof-oof-has-healthcheck-s44jv                0/1       Completed    0          2d
onap          onap-oof-oof-has-onboard-kcfb6                    0/1       Completed    0          2d
onap          onap-portal-portal-db-config-vt848                0/2       Completed    0          2d
totalonap        used  onap-sdc-sdc-be-config-backend-cktdp      free      shared  buff0/cache1    available Mem:  Completed    2517546960   111586672    45000724   2d
onap  193628    95167300   137158588 ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep onap | wc -l
164
ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep onap | grep -E '1/1|2/2' | wc -l
155
ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep -E '0/|1/2' | wc -l
8
ubuntu@ip-172-31-20-218:~$ kubectl get pods --all-namespaces | grep -E '0/|1/2'
onap          dep-dcae-ves-collector-59d4ff58f7-94rpq      onap-sdc-sdc-cs-config-cassandra-t5lt7            0/1       Completed    0          2d
onap          onap-sdc-sdc-dcae-be-tools-8pkqz                  0/1       Completed    0          2d
onap           1/2onap-sdc-sdc-dcae-be-tools-lrcwk        Running          0/1       Init:Error   0          4m2d
onap          onap-sdc-aaisdc-es-champconfig-68ff644d85-rv7trelasticsearch-9zrdw        0/1       Completed    0          2d
0/1onap       Running   onap-sdc-sdc-onboarding-be-cassandra-init-8klpv   0/1       Completed    0          59m2d
onap          onap-aaisdc-sdc-gizmowfd-856f86d664-q5pvg         be-workflow-init-b4j4v                1/20/1       CrashLoopBackOffCompleted    0    10         59m2d
onap          onap-vid-oofvid-galera-85864d6586-zcsz5     config-d4srr                          0/1       ImagePullBackOffCompleted        0          59m2d
onap          onap-pombavnfsdk-vnfsdk-kibanainit-d76b6dd4cpostgres-sfbl6bm668            0/1       Completed    0/1          2d
# Init:CrashLoopBackOffdeployments are still 8there
# reboot server
ubuntu@a-ld0:~$ sudo helm list
NAME  59m onap          onap-pomba-networkdiscovery-85d76975b7-mfk92  	REVISION	UPDATED          1/2       CrashLoopBackOff	STATUS  	CHART      11         59m	NAMESPACE
onap             onap-pomba-networkdiscoveryctxbuilder-c89786dfc-qnlx9  	28 1/2     	Thu Jan CrashLoopBackOff24 18:48:42 2019	DEPLOYED	onap-3.0.0      10    	onap     59m
onap-aaf          onap-vid-84c88db589-8cpgr  	23      	Thu Jan 24 18:48:45 2019	DEPLOYED	aaf-3.0.0           	onap     
onap-aai   1/2       CrashLoopBackOff 	21      	Thu 9Jan 24 18:48:51 2019	DEPLOYED	aai-3.0.0       59m

Operations

Get failed/pending containers

Code Block
themeMidnight
linenumberstrue
kubectl get pods --all-namespaces | grep -E "0/|1/2" | wc -l
Code Block
kubectl cluster-info
# get pods/containers
kubectl get pods --all-namespaces
# get port mappings
kubectl get services --all-namespaces -o wide
NAMESPACE	onap     
onap-appc          	7       	Thu Jan 24 18:49:02 2019	DEPLOYED	appc-3.0.0         NAME 	onap     
onap-clamp         	6       	Thu Jan 24 18:49:06 2019	DEPLOYED	clamp-3.0.0        READY 	onap    STATUS 
onap-cli  RESTARTS   AGE default     	5  nginx-1389790254-lgkz3     	Thu Jan 24 18:49:09 2019	DEPLOYED	cli-3.0.0        1/1   	onap    Running 
onap-consul 1       	27   5d kube-system   heapster-4285517626-x080g   	Thu Jan 24 18:49:11 2019	DEPLOYED	consul-3.0.0        	onap   1/1  
onap-contrib    Running   1	2       	Thu Jan 24 6d
kube-system18:49:14 2019	DEPLOYED	contrib-3.0.0    kube-dns-638003847-tst97   	onap     
onap-dcaegen2      3/3	24      	Thu RunningJan 24 18:49:18 2019	DEPLOYED	dcaegen2-3.0.0      	onap    6d 
kubeonap-systemdmaap   kubernetes-dashboard-716739405-fnn3g   1/1   	25    Running  	Thu 2Jan 24 18:49:22 2019	DEPLOYED	dmaap-3.0.0       6d kube-system 	onap  monitoring-grafana-2360823841-hr824   
1/1onap-esr       Running   1 	20      	Thu Jan 24 6d
kube-system18:49:27 2019	DEPLOYED	esr-3.0.0    monitoring-influxdb-2323019309-k7h1t   1/1    	onap   Running  
1onap-log          6d kube-system	11   tiller-deploy-737598192-x9wh5   	Thu Jan 24 18:49:31 2019	DEPLOYED	log-3.0.0   1/1       Running 	onap  1   
onap-msb      6d # ssh into a pod	26 kubectl -n default exec -it  nginx-1389790254-lgkz3 /bin/bash
# get logs
kubectl -n default logs -f nginx-1389790254-lgkz3

Exec

kubectl -n onap-aai exec -it aai-resources-1039856271-d9bvq  bash

Bounce/Fix a failed container

Periodically one of the higher containers in a dependency tree will not get restarted in time to pick up running child containers - usually this is the kibana container

Fix this or "any" container by deleting the container in question and kubernetes will bring another one up.

Code Block
themeMidnight
root@a-onap-auto-20180412-ref:~# kubectl get services --all-namespaces | grep log
onap          dev-vfc-catalog               ClusterIP   10.43.210.8     <none>        8806/TCP      	Thu Jan 24 18:49:34 2019	DEPLOYED	msb-3.0.0           	onap     
onap-multicloud    	19      	Thu Jan 24 18:49:37 2019	DEPLOYED	multicloud-3.0.0    	onap     
onap-oof           	18      	Thu Jan 24 18:49:44 2019	DEPLOYED	oof-3.0.0           	onap     
onap-policy        	13      	Thu Jan 24 18:49:52 2019	DEPLOYED	policy-3.0.0        	onap     
onap-pomba         	4     5d onap 	Thu Jan 24 18:49:56 2019	DEPLOYED	pomba-3.0.0     log-es    	onap     
onap-portal        	12      NodePort	Thu Jan 24  10.43.77.8718:50:03 2019	DEPLOYED	portal-3.0.0       <none> 	onap     
 9200:30254/TCPonap-robot         	22      	Thu Jan 24 18:50:08 2019	DEPLOYED	robot-3.0.0         	onap     
onap-sdc           	16      	Thu Jan 24 18:50:11 2019	DEPLOYED	sdc-3.0.0         5d  	onap     
onap-sdnc    log-es-tcp      	15      	Thu Jan 24 18:50:17 2019	DEPLOYED	sdnc-3.0.0    ClusterIP   10.43.159.93   	onap <none>    
onap-sniro-emulator	1     9300/TCP  	Thu Jan 24 18:50:21 2019	DEPLOYED	sniro-emulator-3.0.0	onap     
onap-so            	17      	Thu Jan 24 18:50:24 2019	DEPLOYED	so-3.0.0            	onap     
onap-uui           	9      5d onap	Thu Jan 24 18:50:30 2019	DEPLOYED	uui-3.0.0      log-kibana     	onap     
onap-vfc         NodePort    10.43.41.102	10    <none>  	Thu Jan     5601:30253/TCP 24 18:50:33 2019	DEPLOYED	vfc-3.0.0           	onap     
onap-vid           	14      	Thu Jan 24 18:50:38 2019	DEPLOYED	vid-3.0.0           	onap     
       5d
onaponap-vnfsdk        	8  log-ls     	Thu Jan 24 18:50:41 2019	DEPLOYED	vnfsdk-3.0.0        	onap     
onap-vvp NodePort    10.43.180.165   <none>        5044:30255/TCP	3       	Thu Jan 24 18:50:44 2019	DEPLOYED	vvp-3.0.0           	onap   


sudo reboot now
ubuntu@a-ld0:~$ sudo docker ps
CONTAINER ID        IMAGE                    5dCOMMAND onap          log-ls-http       CREATED            ClusterIP STATUS  10.43.13.180    <none>        9600/TCPPORTS                              NAMES
f61dc9902248        rancher/agent:v1.2.11    "/run.sh run"            2 days ago          Up 5d
root@a-onap-auto-20180412-ref:~# kubectl get pods --all-namespaces | grep log
onap30 seconds                  dev-log-elasticsearch-66cdc4f855-wmpkz         1/1       Running        rancher-agent
01f40fa3a4ed        0rancher/server:v1.6.25   "/usr/bin/entry /u..."   2 days ago 5d onap        Up  dev-log-kibana-5b6f86bcb4-drpzq30 seconds       3306/tcp, 0.0.0.0:8880->8080/tcp   rancher_server


# back  0/1       Runningup
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces
NAMESPACE     NAME              1076       5d onap          dev-log-logstash-6d9fdccdb6-ngq2f              1/1READY     STATUS  Running     RESTARTS   AGE
kube-system   heapster-7b48b696fc-99cd6     0          5d onap          dev-vfc-catalog-7d89bc8b9d-vxk740/1       Error        0 2/2       Running  2d
kube-system   kube-dns-6655f78c68-k4dh4           0          5d root@a-onap-auto-20180412-ref:~# kubectl delete pod dev-log-kibana-5b6f86bcb4-drpzq -n onap
pod "dev-log-kibana-5b6f86bcb4-drpzq" deleted
root@a-onap-auto-20180412-ref:~# kubectl get pods --all-namespaces | grep log
onap0/3       Error        0          2d
dev-log-elasticsearch-66cdc4f855-wmpkzkube-system   kubernetes-dashboard-6f54f7c4b-fhqmf              10/1       RunningError        0         0 2d
kube-system   monitoring-grafana-7877679464-cscg4     5d  onap        0/1  dev-log-kibana-5b6f86bcb4-drpzq     Completed    0       0/1   2d
kube-system   monitoring-influxdb-64664c6cf5-wmw8w Terminating             10760/1       5dCompleted onap   0       dev-log-kibana-5b6f86bcb4-gpn2m   2d
kube-system   tiller-deploy-78db58d887-9qlwh         0/1       Pending    1/1       Running      0          12s2d
onap          devonap-aaf-logaaf-logstashsms-6d9fdccdb6-ngq2fpreload-k7mx6                    10/1       RunningCompleted    0          2d
onap  0        onap-aaf-aaf-sshsm-distcenter-lk5st   5d onap          dev-vfc-catalog-7d89bc8b9d-vxk74  0/1       Completed    0   2/2       Running2d
....

# note not all replicas were actually 1 - some were 2,3,7
kubectl scale 0--replicas=1 deployments --all -n onap
kubectl scale --replicas=1 statefulsets  5d

...

a helm namespace delete or a kubectl delete or a helm purge may not remove everything based on hanging PVs - use

Code Block
themeMidnight
#after a kubectl delete namespace onap
sudo helm delete --purge onap


melliott [12:11 PM]
kubectl delete pods <pod> --grace-period=0 --force -n onap

Remove a Deployment

https://git.onap.org/logging-analytics/tree/deploy/cd.sh#n57

Code Block
themeMidnight
kubectl delete namespace onap
sudo helm delete --purge onap
kubectl delete pv --all
kubectl delete pvc --all
kubectl delete secrets --all
kubectl delete clusterrolebinding --all--all -n onap

# 6m
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces | grep -E '0/|1/2|1/3|2/3' | wc -l
199
# 20m
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces | grep -E '0/|1/2|1/3|2/3' | wc -l
180


# 60 min
ubuntu@a-ld0:~$ kubectl get pods --all-namespaces | grep -E '0/|1/2|1/3|2/3' | wc -l
42


Remove a Deployment

Cloud Native Deployment#RemoveaDeployment


Rotate Logs

find them

du --max-depth=1 | sort -nr

...

Make sure the robot container is deployed - you may run directly from the kubernetes folder outside of the container - see https://git.onap.org/logging-analytics/tree/deploy/cd.sh#n297

Code Block
themeMidnight
# make sure the robot container is up via --set robot.enabled=true
cd oom/kubernetes/robot
./ete-k8s.sh $ENVIRON health

...