Page History

# setup the master 
git clone https://gerrit.onap.org/r/logging-analytics
sudo logging-analytics/deploy/rancher/oom_rancher_setup.sh -b master -s <your domain/ip> -e onap
# manually delete the host that was installed on the master - in the rancher gui for now

# run without a client on the master
sudo logging-analytics/deploy/aws/oom_cluster_host_install.sh -n false -s <your domain/ip> -e fs-nnnnnn1b -r us-west-1 -t 371AEDC88zYAZdBXPM  -c true -v true
ls /dockerdata-nfs/
onap  test.sh

# run the script from git on each cluster node
git clone https://gerrit.onap.org/r/logging-analytics
sudo logging-analytics/deploy/aws/oom_cluster_host_install.sh -n true -s <your domain/ip> -e fs-nnnnnn1b -r us-west-1 -t 371AEDC88zYAZdBXPM  -c true -v true

# check a node
ls /dockerdata-nfs/
onap  test.sh
sudo docker ps
CONTAINER ID        IMAGE                             COMMAND                  CREATED             STATUS                  PORTS               NAMES
6e4a57e19c39        rancher/healthcheck:v0.3.3        "/.r/r /rancher-en..."   1 second ago        Up Less than a second                       r-healthcheck-healthcheck-5-f0a8f5e8
f9bffc6d9b3e        rancher/network-manager:v0.7.19   "/rancher-entrypoi..."   1 second ago        Up 1 second                                 r-network-services-network-manager-5-103f6104
460f31281e98        rancher/net:holder                "/.r/r /rancher-en..."   4 seconds ago       Up 4 seconds                                r-ipsec-ipsec-5-2e22f370
3e30b0cf91bb        rancher/agent:v1.2.9              "/run.sh run"            17 seconds ago      Up 16 seconds                               rancher-agent

# On the master - fix helm after adding nodes to the master
sudo helm init --upgrade
$HELM_HOME has been configured at /home/ubuntu/.helm.
Tiller (the Helm server-side component) has been upgraded to the current version.
sudo helm repo add local http://127.0.0.1:8879
# check the cluster on the master
kubectl top nodes
NAME                                          CPU(cores)   CPU%      MEMORY(bytes)   MEMORY%   
ip-172-31-16-85.us-west-1.compute.internal    129m         3%        1805Mi          5%        
ip-172-31-25-15.us-west-1.compute.internal    43m          1%        1065Mi          3%        
ip-172-31-28-145.us-west-1.compute.internal   40m          1%        1049Mi          3%        
ip-172-31-21-240.us-west-1.compute.internal   30m          0%        965Mi           3% 

# important: secure your rancher cluster by adding an oauth github account - to keep out crypto miners
http://cluster.onap.info:8880/admin/access/github
# now back to master to install onap
sudo cp logging-analytics/deploy/cd.sh .
sudo ./cd.sh -b master -e onap -c true -d true -w false -r false

136 pending > 0 at the 1th 15 sec interval
ubuntu@ip-172-31-28-152:~$ kubectl get pods -n onap | grep -E '1/1|2/2' | wc -l
20
120 pending > 0 at the 39th 15 sec interval
ubuntu@ip-172-31-28-152:~$ kubectl get pods -n onap | grep -E '1/1|2/2' | wc -l
47
99 pending > 0 at the 93th 15 sec interval


after an hour most of the 136 containers should be up
kubectl get pods --all-namespaces | grep -E '0/|1/2'
onap          onap-aaf-cs-59954bd86f-vdvhx                    0/1       CrashLoopBackOff   7          37m
onap          onap-aaf-oauth-57474c586c-f9tzc                 0/1       Init:1/2           2          37m
onap          onap-aai-champ-7d55cbb956-j5zvn                 0/1       Running            0          37m
onap          onap-drools-0                                   0/1       Init:0/1           0          1h
onap          onap-nexus-54ddfc9497-h74m2                     0/1       CrashLoopBackOff   17         1h
onap          onap-sdc-be-777759bcb9-ng7zw                    1/2       Running            0          1h
onap          onap-sdc-es-66ffbcd8fd-v8j7g                    0/1       Running            0          1h
onap          onap-sdc-fe-75fb4965bd-bfb4l                    0/2       Init:1/2           6          1h

# cpu bound - a small cluster has 4x4 cores - try to run with 4x16 cores
ubuntu@ip-172-31-28-152:~$ kubectl top nodes
NAME                                          CPU(cores)   CPU%      MEMORY(bytes)   MEMORY%   
ip-172-31-28-145.us-west-1.compute.internal   3699m        92%       26034Mi         85%       
ip-172-31-21-240.us-west-1.compute.internal   3741m        93%       3872Mi          12%       
ip-172-31-16-85.us-west-1.compute.internal    3997m        99%       23160Mi         75%       
ip-172-31-25-15.us-west-1.compute.internal    3998m        99%       27076Mi         88%     
       
# for reference 
register_node() {
    #constants
    DOCKERDATA_NFS=dockerdata-nfs
    DOCKER_VER=17.03
    USERNAME=ubuntu

    if [[ "$IS_NODE" != false ]]; then
        sudo curl https://releases.rancher.com/install-docker/$DOCKER_VER.sh | sh
        sudo usermod -aG docker $USERNAME
    fi
    sudo apt-get install nfs-common -y
    sudo mkdir /$DOCKERDATA_NFS
    sudo mount -t nfs4 -o nfsvers=4.1,rsize=1048576,wsize=1048576,hard,timeo=600,retrans=2 $AWS_EFS.efs.$AWS_REGION.amazonaws.com:/ /$DOCKERDATA_NFS
    if [[ "$IS_NODE" != false ]]; then
        echo "Running agent docker..."
        if [[ "$COMPUTEADDRESS" != false ]]; then
            echo "sudo docker run --rm --privileged -v /var/run/docker.sock:/var/run/docker.sock -v /var/lib/rancher:/var/lib/rancher rancher/agent:v1.2.9 http://$MASTER:8880/v1/scripts/$TOKEN"
            sudo docker run --rm --privileged -v /var/run/docker.sock:/var/run/docker.sock -v /var/lib/rancher:/var/lib/rancher rancher/agent:v1.2.9 http://$MASTER:8880/v1/scripts/$TOKEN
        else
            echo "sudo docker run -e CATTLE_AGENT_IP=\"$ADDRESS\" --rm --privileged -v /var/run/docker.sock:/var/run/docker.sock -v /var/lib/rancher:/var/lib/rancher rancher/agent:v1.2.9 http://$MASTER:8880/v1/scripts/$TOKEN"
            sudo docker run -e CATTLE_AGENT_IP="$ADDRESS" --rm --privileged -v /var/run/docker.sock:/var/run/docker.sock -v /var/lib/rancher:/var/lib/rancher rancher/agent:v1.2.9 http://$MASTER:8880/v1/scripts/$TOKEN
        fi
    fi
}

IS_NODE=false
MASTER=
TOKEN=
AWS_REGION=
AWS_EFS=
COMPUTEADDRESS=true
ADDRESS=
VALIDATE=
while getopts ":u:n:s:e:r:t:c:a:v" PARAM; do
  case $PARAM in
    u)
      usage
      exit 1
      ;;
    n)
      IS_NODE=${OPTARG}
      ;;
    s)
      MASTER=${OPTARG}
      ;;
    e)
      AWS_EFS=${OPTARG}
      ;;
    r)
      AWS_REGION=${OPTARG}
      ;;
    t)
      TOKEN=${OPTARG}
      ;;
    c)
      COMPUTEADDRESS=${OPTARG}
      ;;
    a)
      ADDRESS=${OPTARG}
      ;;
    v)
      VALIDATE=${OPTARG}
      ;;
    ?)
      usage
      exit
      ;;
  esac
done

if [ -z $MASTER ]; then
  usage
  exit 1
fi

register_node  $IS_NODE $MASTER $AWS_EFS $AWS_REGION $TOKEN $COMPUTEADDRESS $ADDRESS $VALIDATE