Merge pull request 2i2c-org#3840 from sgibson91/new-cluster/bican

New AWS cluster: BICAN

.github/workflows/deploy-grafana-dashboards.yaml

@@ -15,6 +15,7 @@ jobs:
           - cluster_name: 2i2c-aws-us
           - cluster_name: 2i2c-uk
           - cluster_name: awi-ciroh
+          - cluster_name: bican
           - cluster_name: catalystproject-africa
           - cluster_name: catalystproject-latam
           - cluster_name: cloudbank

config/clusters/bican/cluster.yaml

@@ -0,0 +1,12 @@
+name: bican
+provider: aws # https://2i2c.awsapps.com/start#/
+aws:
+  key: enc-deployer-credentials.secret.json
+  clusterType: eks
+  clusterName: bican
+  region: us-east-2
+support:
+  helm_chart_values_files:
+    - support.values.yaml
+    - enc-support.secret.values.yaml
+hubs: []

config/clusters/bican/enc-deployer-credentials.secret.json

@@ -0,0 +1,25 @@
+{
+	"AccessKey": {
+		"AccessKeyId": "ENC[AES256_GCM,data:DeO+KCrRK5prA+MwdYH259ZoE30=,iv:wHbKxC+nj15O6Fk4W/RYxePl1ZIhN5IiTUotCCD8RU0=,tag:RW73gvM38ZVzM+uRxMNxeA==,type:str]",
+		"SecretAccessKey": "ENC[AES256_GCM,data:dWhFaB2jqM1/lN4T/vsLnUI4JZ2aEvKltHz1yELlHQYZocZwe9BuKQ==,iv:OaqLfhzgyJi+XlTxyNVwF7oofk2bxEL4w/vkqoIGBJw=,tag:4SUngOLKzXJKiU+RnvJB/A==,type:str]",
+		"UserName": "ENC[AES256_GCM,data:SWPTr2vK0g9duv/PJnGP6+yEhajuSHE=,iv:uzCudF/Jns0rkZeTFgF3TzfAdHj+uzIaRTddxjZkIQY=,tag:TicuD0Gy4DlS1cs3v+34eg==,type:str]"
+	},
+	"sops": {
+		"kms": null,
+		"gcp_kms": [
+			{
+				"resource_id": "projects/two-eye-two-see/locations/global/keyRings/sops-keys/cryptoKeys/similar-hubs",
+				"created_at": "2024-03-25T16:18:28Z",
+				"enc": "CiUA4OM7eI62pdzV0VlvcAweLwu3y+/mVg+D/IxPHr0JdwvDieADEkkAXoW3JvyeLJ3uoPtSm7/C3hjB9a+fehCUe/eA/2GgL4GCsWNWsCcIh8wftPsXPqVJn10DoUF/zjmiGaYTrxlsArVXBciGHip9"
+			}
+		],
+		"azure_kv": null,
+		"hc_vault": null,
+		"age": null,
+		"lastmodified": "2024-03-25T16:18:28Z",
+		"mac": "ENC[AES256_GCM,data:FE0dsSHtAjhgJjtUrHhax/zP7Rb6E50XjN25kFOFmDBos5He7R5F1ibIZ+iy/WAu3BRgs1IZIc+egfK1GHihvvmmAv1gPGf/KCjtxHmVm2AWRSzht76Z54Lp65z9yLwh7nvTgyI/KdeVgmfFQvbcZsdMugg+s5JnRZ1CKdcSLM4=,iv:xzSgeWcIqZJ+S1VvcX4V3Baeve3HbPL6YDClCn2UFPY=,tag:tfVCPiUb8Jg0yYZNqRejig==,type:str]",
+		"pgp": null,
+		"unencrypted_suffix": "_unencrypted",
+		"version": "3.8.1"
+	}
+}

config/clusters/bican/enc-grafana-token.secret.yaml

@@ -0,0 +1,15 @@
+grafana_token: ENC[AES256_GCM,data:ycdgNGt3VqcyJGKh4F51r1E9fn53GIHhOXwF5/mCoMeGgrWZg9qNcrgpUyAzmg==,iv:qZ8j+D2xJuEd2p+1pv7KYm1txAAiOB2RwqIP8ErCzM0=,tag:ujAmi9YozXMiux9yU20OHQ==,type:str]
+sops:
+    kms: []
+    gcp_kms:
+        - resource_id: projects/two-eye-two-see/locations/global/keyRings/sops-keys/cryptoKeys/similar-hubs
+          created_at: "2024-03-25T17:00:00Z"
+          enc: CiUA4OM7eOhriXoULTcORAf79SP0MiE+/8E7mpYi/Fld/7pHr/64EkkAXoW3JiccZbzRvAC1iWH3vgaunmsL7V8GS8bSYJpR7XoFSSyXB5aQijOObgcQGEIAAH7L3MIJrOxV4eW9f3t+fN9I1QWGy1+6
+    azure_kv: []
+    hc_vault: []
+    age: []
+    lastmodified: "2024-03-25T17:00:00Z"
+    mac: ENC[AES256_GCM,data:n7XUcuVcfgX37zg+ZLt5w8p9Ct5605laTBeaK809+UktFoUokByaFB5+x6/S+OZN08Q1A+fgF2E6TXNUavN+qgUNOiNal5FvQZr9HKPofgDPIWJi72851Fy1Q6rVYou7iSPC3f1oHMfh5ilPR0GmaHjQny4W+r3p88rLO6dtP/M=,iv:qSeOy1AKNAQt2hozBNGeeSCRW6JvXz2oB4IVd9uWfzo=,tag:7y8GOuq03ZI7LlTQdWpPqQ==,type:str]
+    pgp: []
+    unencrypted_suffix: _unencrypted
+    version: 3.8.1

config/clusters/bican/enc-support.secret.values.yaml

@@ -0,0 +1,22 @@
+prometheusIngressAuthSecret:
+    username: ENC[AES256_GCM,data:GzcSEBqXXvY2bxnAHq7NFM8T7OnkVdJqNdMHV6P57kjwpvQGhTBI0upMzYuWejD8OVpYgK+gywNUwrUIsIw+kw==,iv:coBbRSe2gdi8vqV5uaWDBm9oS16hEZR4Je3cSD/E7tE=,tag:4563alICoKwoXbok/h3/mQ==,type:str]
+    password: ENC[AES256_GCM,data:tp/AfO5x4oFV+9YiO42uyyAeJRGFPbJHB2Gtak7n77fWZuA+g1w2mpjG9UKoPcTmJXp6pv79+Clc03CeqNfXPQ==,iv:rzIYpQ4YI66CWDwm/Lc3EIxkJrz1mp+J/+SYtVZQK8k=,tag:Ho7pAmyS5fmDkqK22WvDOQ==,type:str]
+grafana:
+    grafana.ini:
+        auth.github:
+            client_id: ENC[AES256_GCM,data:r0girp4lkSsFJxT9RYkNqATagK0=,iv:rUF0925+HkU4d3xRbsgcq8az+aLSgW2kbNGg06ZR504=,tag:/kZxOX/ZNRrfA62vdAWIZg==,type:str]
+            client_secret: ENC[AES256_GCM,data:EysT8taieKuhc76qFFqUo9qxoeYxofRcOo1hLrDQ4aBsKH6zIOAH5Q==,iv:31LdaFhwg7Kkn1DvyFxnUFoWDRBYlchwMeFdm819uc0=,tag:aKt+2mdtcA4uO6yiJFsPXw==,type:str]
+sops:
+    kms: []
+    gcp_kms:
+        - resource_id: projects/two-eye-two-see/locations/global/keyRings/sops-keys/cryptoKeys/similar-hubs
+          created_at: "2024-03-25T16:58:36Z"
+          enc: CiUA4OM7eMjNppdOUODfRkFuLa6+B4w/pOw4QFFBwysbGYfDrxVhEkkAXoW3JnUAhPZeVwdvizCgUdBQpIH4O4V7SqdCmNYy+chPbvDkiyhOefoVVg7FrU4nHr9xSwhCsXVO16GOOdEukbrxL9YUiD7O
+    azure_kv: []
+    hc_vault: []
+    age: []
+    lastmodified: "2024-03-25T16:58:36Z"
+    mac: ENC[AES256_GCM,data:aLnsOYFwKqn97RsoHcbeoBdbQMV3djowqgaN1xWsPMhMEoyEFt4AyoFe8ZOrD2LFfPdCS7C9liGv93jkLY9HuIsoCtELxFUdTQzClBU7rzqspMDA+XQy4hGSJ+0mhg/JaxtBZ9NBuy19m2pBGM55V1nZPVzZNSTxWi/9EtGQDOY=,iv:jtdvEWfW3gqeLl/duh+vGIgFrCzWa+sBHwlcWRAmEJo=,tag:gVrCUxenY1REHnjepCY4lQ==,type:str]
+    pgp: []
+    unencrypted_suffix: _unencrypted
+    version: 3.8.1

config/clusters/bican/support.values.yaml

@@ -0,0 +1,34 @@
+prometheusIngressAuthSecret:
+  enabled: true
+
+prometheus:
+  server:
+    ingress:
+      enabled: true
+      hosts:
+        - prometheus.bican.2i2c.cloud
+      tls:
+        - secretName: prometheus-tls
+          hosts:
+            - prometheus.bican.2i2c.cloud
+
+grafana:
+  grafana.ini:
+    server:
+      root_url: https://grafana.bican.2i2c.cloud/
+  auth.github:
+    enabled: true
+    allowed_organizations: 2i2c-org
+  ingress:
+    hosts:
+      - grafana.bican.2i2c.cloud
+    tls:
+      - secretName: grafana-tls
+        hosts:
+          - grafana.bican.2i2c.cloud
+
+cluster-autoscaler:
+  enabled: true
+  autoDiscovery:
+    clusterName: bican
+  awsRegion: us-east-2

eksctl/bican.jsonnet

@@ -0,0 +1,149 @@
+/*
+    This file is a jsonnet template of a eksctl's cluster configuration file,
+    that is used with the eksctl CLI to both update and initialize an AWS EKS
+    based cluster.
+
+    This file has in turn been generated from eksctl/template.jsonnet which is
+    relevant to compare with for changes over time.
+
+    To use jsonnet to generate an eksctl configuration file from this, do:
+
+        jsonnet bican.jsonnet > bican.eksctl.yaml
+
+    References:
+    - https://eksctl.io/usage/schema/
+*/
+local ng = import "./libsonnet/nodegroup.jsonnet";
+
+// place all cluster nodes here
+local clusterRegion = "us-east-2";
+local masterAzs = ["us-east-2a", "us-east-2b", "us-east-2c"];
+local nodeAz = "us-east-2a";
+
+// Node definitions for notebook nodes. Config here is merged
+// with our notebook node definition.
+// A `node.kubernetes.io/instance-type label is added, so pods
+// can request a particular kind of node with a nodeSelector
+local notebookNodes = [
+    { instanceType: "r5.xlarge" },
+    { instanceType: "r5.4xlarge" },
+    { instanceType: "r5.16xlarge" },
+    {
+      instanceType: "g4dn.xlarge",
+      tags+: {
+        "k8s.io/cluster-autoscaler/node-template/resources/nvidia.com/gpu": "1"
+      },
+      // Allow provisioning GPUs across all AZs, to prevent situation where all
+      // GPUs in a single AZ are in use and no new nodes can be spawned
+      availabilityZones: masterAzs,
+    },
+];
+local daskNodes = [
+    // Node definitions for dask worker nodes. Config here is merged
+    // with our dask worker node definition, which uses spot instances.
+    // A `node.kubernetes.io/instance-type label is set to the name of the
+    // *first* item in instanceDistribution.instanceTypes, to match
+    // what we do with notebook nodes. Pods can request a particular
+    // kind of node with a nodeSelector
+    //
+    // A not yet fully established policy is being developed about using a single
+    // node pool, see https://github.com/2i2c-org/infrastructure/issues/2687.
+    //
+    { instancesDistribution+: { instanceTypes: ["r5.4xlarge"] }},
+];
+
+
+{
+    apiVersion: 'eksctl.io/v1alpha5',
+    kind: 'ClusterConfig',
+    metadata+: {
+        name: "bican",
+        region: clusterRegion,
+        version: "1.29",
+    },
+    availabilityZones: masterAzs,
+    iam: {
+        withOIDC: true,
+    },
+    // If you add an addon to this config, run the create addon command.
+    //
+    //    eksctl create addon --config-file=bican.eksctl.yaml
+    //
+    addons: [
+        {
+            // aws-ebs-csi-driver ensures that our PVCs are bound to PVs that
+            // couple to AWS EBS based storage, without it expect to see pods
+            // mounting a PVC failing to schedule and PVC resources that are
+            // unbound.
+            //
+            // Related docs: https://docs.aws.amazon.com/eks/latest/userguide/managing-ebs-csi.html
+            //
+            name: 'aws-ebs-csi-driver',
+            version: "latest",
+            wellKnownPolicies: {
+                ebsCSIController: true,
+            },
+        },
+    ],
+    nodeGroups: [
+        ng + {
+            namePrefix: 'core',
+            nameSuffix: 'a',
+            nameIncludeInstanceType: false,
+            availabilityZones: [nodeAz],
+            ssh: {
+                publicKeyPath: 'ssh-keys/bican.key.pub'
+            },
+            instanceType: "r5.xlarge",
+            minSize: 1,
+            maxSize: 6,
+            labels+: {
+                "hub.jupyter.org/node-purpose": "core",
+                "k8s.dask.org/node-purpose": "core"
+            },
+        },
+    ] + [
+        ng + {
+            namePrefix: 'nb',
+            availabilityZones: [nodeAz],
+            minSize: 0,
+            maxSize: 500,
+            instanceType: n.instanceType,
+            ssh: {
+                publicKeyPath: 'ssh-keys/bican.key.pub'
+            },
+            labels+: {
+                "hub.jupyter.org/node-purpose": "user",
+                "k8s.dask.org/node-purpose": "scheduler"
+            },
+            taints+: {
+                "hub.jupyter.org_dedicated": "user:NoSchedule",
+                "hub.jupyter.org/dedicated": "user:NoSchedule"
+            },
+        } + n for n in notebookNodes
+    ] + ( if daskNodes != null then
+        [
+        ng + {
+            namePrefix: 'dask',
+            availabilityZones: [nodeAz],
+            minSize: 0,
+            maxSize: 500,
+            ssh: {
+                publicKeyPath: 'ssh-keys/bican.key.pub'
+            },
+            labels+: {
+                "k8s.dask.org/node-purpose": "worker"
+            },
+            taints+: {
+                "k8s.dask.org_dedicated" : "worker:NoSchedule",
+                "k8s.dask.org/dedicated" : "worker:NoSchedule"
+            },
+            instancesDistribution+: {
+                onDemandBaseCapacity: 0,
+                onDemandPercentageAboveBaseCapacity: 0,
+                spotAllocationStrategy: "capacity-optimized",
+            },
+        } + n for n in daskNodes
+        ] else []
+    )
+}

eksctl/ssh-keys/bican.key.pub

@@ -0,0 +1 @@
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIAPuAmunoNk11Qr1WCfRulycEvQkbyfziEUXKxR3mUNU [email protected]

eksctl/ssh-keys/secret/bican.key

@@ -0,0 +1,21 @@
+{
+	"data": "ENC[AES256_GCM,data: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,iv:jORG54pmCYaxjkiJBvEdqDatv7jPc+3Y/y3EXtBuuOg=,tag:5FRS/BDxyNmBn5uCM3NRHQ==,type:str]",
+	"sops": {
+		"kms": null,
+		"gcp_kms": [
+			{
+				"resource_id": "projects/two-eye-two-see/locations/global/keyRings/sops-keys/cryptoKeys/similar-hubs",
+				"created_at": "2024-03-25T15:49:18Z",
+				"enc": "CiUA4OM7eDXDtAIuBO2G1PQUO/+z63OzqWASErrdn4hJXKUwOAoaEkkAXoW3Jrow6VFVyfdvrPtVgv13BIJ0lStrIiu4RjceEh/FHH8J2V9Bdx4uVEm2wxNArKjLEEmwIO+TcA9+9bTQmQNh6B5ZwFZ8"
+			}
+		],
+		"azure_kv": null,
+		"hc_vault": null,
+		"age": null,
+		"lastmodified": "2024-03-25T15:49:18Z",
+		"mac": "ENC[AES256_GCM,data:yu9fpvR48VhcnfODFTxeEqhqyJ9+fYF1sVFzED/Ej22XL1Lz2zIPHZtIu/sv5fwr82vWo5ku5/Ld+MMR3xrVL5M1+unRpPEVJRXpUcknssug0X+rHQ4/PcemamElIF77Ra82ezxkMEgGak2vsDn5v7UqMPeGDqjwhKlqtXxRnb0=,iv:AoXpaQhhuCOCDirK+yA8xL4VijcbmFPBtHClATGBh+A=,tag:KH6Czg6OBNQQuboqIaXUYw==,type:str]",
+		"pgp": null,
+		"unencrypted_suffix": "_unencrypted",
+		"version": "3.8.1"
+	}
+}

terraform/aws/projects/bican.tfvars

@@ -0,0 +1,26 @@
+region = "us-east-2"
+
+cluster_name = "bican"
+
+cluster_nodes_location = "us-east-2a"
+
+user_buckets = {
+  "scratch-staging" : {
+    "delete_after" : 7
+  },
+  "scratch" : {
+    "delete_after" : 7
+  },
+}
+
+
+hub_cloud_permissions = {
+  "staging" : {
+    bucket_admin_access : ["scratch-staging"],
+    extra_iam_policy : ""
+  },
+  "prod" : {
+    bucket_admin_access : ["scratch"],
+    extra_iam_policy : ""
+  },
+}