cluster loader config + ansible inventory for metrics issue

gistfile1.txt

clean up metrics for redeploy

oc delete --all rc
oc delete --all po
oc delete --all svc
oc delete --all route
oc delete --all pvc
oc delete sa heapster hawkular cassandra
oc delete secrets hawkular-cassandra-certs hawkular-metrics-account hawkular-metrics-certs heapster-certs heapster-secrets
# oc delete secret hawkular-cassandra-certificate hawkular-cassandra-secrets hawkular-metrics-certificate hawkular-metrics-secrets

run the deploy playbook again

metrics_ansible_inventory.txt

[OSEv3:children]
masters
nodes
etcd
lb

[OSEv3:vars]
ansible_ssh_user=root
debug_level=2
deployment_type=openshift-enterprise
openshift_install_examples=true
use_cluster_metrics=true
openshift_master_portal_net=172.24.0.0/14
osm_cluster_network_cidr=172.20.0.0/14
osm_host_subnet_length=9
openshift_docker_additional_registries=registry.ops.openshift.com
oreg_url=registry.ops.openshift.com/openshift3/ose-${component}:${version}
openshift_master_identity_providers=[{'name': 'htpasswd_auth', 'login': 'true', 'challenge': 'true', 'kind': 'HTPasswdPasswordIdentityProvider', 'filename': '/etc/origin/master/htpasswd'}]
 openshift_disable_check=disk_availability,memory_availability
openshift_master_cluster_method=native


openshift_master_cluster_hostname=ip-172-31-35-191
#changeme openshift_master_cluster_public_hostname=ec2-54-187-205-229.us-west-2.compute.amazonaws.com
#changeme openshift_master_default_subdomain=0718-lhs.qe.rhcloud.com
openshift_cloudprovider_kind=aws
openshift_cloudprovider_aws_access_key=
openshift_cloudprovider_aws_secret_key=


os_sdn_network_plugin_name='redhat/openshift-ovs-multitenant'
openshift_node_kubelet_args={'max-pods': ['512'], 'minimum-container-ttl-duration': ["10s"], 'maximum-dead-containers-per-container': ["1"], 'maximum-dead-containers': ["10"], 'image-gc-high-threshold': ["80"], 'image-gc-low-threshold': ["70"]}
#openshift_infra_nodes=["172.31.3.35"]
openshift_registry_selector='region=infra'
openshift_router_selector='region=infra'
osm_use_cockpit=false

# host group for masters
[lb]
[masters]
ip-172-31-35-191
[etcd]
ip-172-31-35-191

[nodes]
ip-172-31-35-191 openshift_scheduleable=False
ip-172-31-10-125.us-west-2.compute.internal openshift_node_labels="{'region': 'infra', 'zone': 'default'}"
ip-172-31-11-29.us-west-2.compute.internal openshift_node_labels="{'region': 'infra', 'zone': 'default'}"
ip-172-31-1-223.us-west-2.compute.internal openshift_node_labels="{'region': 'infra', 'zone': 'default'}"
ip-172-31-15-205.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-17-164.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-22-97.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-25-65.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-26-164.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-27-54.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-28-78.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-29-207.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-30-47.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-34-201.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-3-94.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-41-46.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-4-217.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"
ip-172-31-50-146.us-west-2.compute.internal openshift_node_labels="{'region': 'primary', 'zone': 'default'}"

metrics_cluster_loader.txt

projects:
  - num: 500
    basename: svt-c-
    tuning: default
    pods:
      - total: 20
      - num: 100
        image: gcr.io/google_containers/pause-amd64:3.0
        basename: pausepods
        file: content/pod-pause.json
        storage:
          - type: none

quotas:
  - name: default
    file: default

tuningsets:
  - name: default
    pods:
      stepping:
        stepsize: 40
        pause: 180 s
      rate_limit:
        delay: 0 ms

metrics_deploy_inventory.txt

# inventory for OSE  - playbook is byo/openshift-cluster/openshift-metrics.yaml
[oo_first_master]
172.31.47.236

[oo_first_master:vars]
openshift_deployment_type=openshift-enterprise
openshift_release=v3.6.0

openshift_metrics_install_metrics=true
openshift_metrics_hawkular_hostname=hawkular-metrics.0605-5ku.qe.rhcloud.com
openshift_metrics_project=openshift-infra
openshift_metrics_image_prefix=registry.ops.openshift.com/openshift3/
openshift_metrics_image_version=v3.6.140
openshift_metrics_cassandra_replicas=1
openshift_metrics_hawkular_replicas=1
openshift_metrics_cassandra_storage_type=dynamic
openshift_metrics_cassandra_pvc_size=100Gi
openshift_metrics_cassandra_limits_memory=4Gi
openshift_metrics_hawkular=4Gi



# inventory for origin
[oo_first_master]
172.31.12.246

[oo_first_master:vars]
openshift_deployment_type=openshift-enterprise
openshift_release=v3.6.0

openshift_metrics_install_metrics=true
openshift_metrics_hawkular_hostname=hawkular-metrics.0717-a2l.qe.rhcloud.com
openshift_metrics_project=openshift-infra
openshift_metrics_image_prefix=docker.io/openshift/origin-
openshift_metrics_image_version=latest
openshift_metrics_cassandra_replicas=1
openshift_metrics_hawkular_replicas=1
openshift_metrics_cassandra_storage_type=dynamic
openshift_metrics_cassandra_pvc_size=200Gi
openshift_metrics_cassandra_limits_memory=4Gi
openshift_metrics_hawkular=4Gi

Run cluster-loader with -p 3. The default -p 10 will overwhelm the nodes