Backport of [QT-525] and [QT-530] into release/1.13.x (hashicorp#20158)

* [QT-525] enos: use spot instances for Vault targets (hashicorp#20037) The previous strategy for provisioning infrastructure targets was to use the cheapest instances that could reliably perform as Vault cluster nodes. With this change we introduce a new model for target node infrastructure. We've replaced on-demand instances for a spot fleet. While the spot price fluctuates based on dynamic pricing, capacity, region, instance type, and platform, cost savings for our most common combinations range between 20-70%. This change only includes spot fleet targets for Vault clusters. We'll be updating our Consul backend bidding in another PR. * Create a new `vault_cluster` module that handles installation, configuration, initializing, and unsealing Vault clusters. * Create a `target_ec2_instances` module that can provision a group of instances on-demand. * Create a `target_ec2_spot_fleet` module that can bid on a fleet of spot instances. * Extend every Enos scenario to utilize the spot fleet target acquisition strategy and the `vault_cluster` module. * Update our Enos CI modules to handle both the `aws-nuke` permissions and also the privileges to provision spot fleets. * Only use us-east-1 and us-west-2 in our scenario matrices as costs are lower than us-west-1. Signed-off-by: Ryan Cragun <me@ryan.ec> * [QT-530] enos: allow-list all public IP addresses (hashicorp#20304) The security groups that allow access to remote machines in Enos scenarios have been configured to only allow port 22 (SSH) from the public IP address of machine executing the Enos scenario. To achieve this we previously utilized the `enos_environment.public_ip_address` attribute. Sometime in mid March we started seeing sporadic SSH i/o timeout errors when attempting to execute Enos resources against SSH transport targets. We've only ever seen this when communicating from Azure hosted runners to AWS hosted machines. While testing we were able to confirm that in some cases the public IP address resolved using DNS over UDP4 to Google and OpenDNS name servers did not match what was resolved when using the HTTPS/TCP IP address service hosted by AWS. The Enos data source was implemented in a way that we'd attempt resolution of a single name server and only attempt resolving from the next if previous name server could not get a result. We'd then allow-list that single IP address. That's a problem if we can resolve two different public IP addresses depending our endpoint address. This change utlizes the new `enos_environment.public_ip_addresses` attribute and subsequent behavior change. Now the data source will attempt to resolve our public IP address via name servers hosted by Google, OpenDNS, Cloudflare, and AWS. We then return a unique set of these IP addresses and allow-list all of them in our security group. It is our hope that this resolves these i/o timeout errors that seem like they're caused by the security group black-holing our attempted access because the IP we resolved does not match what we're actually exiting with. Signed-off-by: Ryan Cragun <me@ryan.ec> --------- Signed-off-by: Ryan Cragun <me@ryan.ec> Co-authored-by: Ryan Cragun <me@ryan.ec>
fopina · Apr 23, 2023 · 05ca6d0 · 05ca6d0
1 parent 5b6b8fa
commit 05ca6d0
Show file tree

Hide file tree

Showing 25 changed files with 2,207 additions and 515 deletions.
diff --git a/.github/enos-run-matrices/build-github-oss-linux-amd64-zip.json b/.github/enos-run-matrices/build-github-oss-linux-amd64-zip.json
@@ -2,7 +2,7 @@
   "include": [
     {
       "scenario": "smoke backend:raft consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 3
     },
     {
@@ -12,7 +12,7 @@
     },
     {
       "scenario": "smoke backend:consul consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 1
     },
     {
@@ -22,7 +22,7 @@
     },
     {
       "scenario": "smoke backend:consul consul_version:1.12.7 distro:ubuntu seal:shamir arch:amd64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -32,7 +32,7 @@
     },
     {
       "scenario": "upgrade backend:raft consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 5
     },
     {
@@ -42,7 +42,7 @@
     },
     {
       "scenario": "upgrade backend:consul consul_version:1.13.4 distro:ubuntu seal:shamir arch:amd64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {

diff --git a/.github/enos-run-matrices/build-github-oss-linux-arm64-zip.json b/.github/enos-run-matrices/build-github-oss-linux-arm64-zip.json
@@ -7,7 +7,7 @@
     },
     {
       "scenario": "smoke backend:raft consul_version:1.14.2 distro:ubuntu seal:awskms arch:arm64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -17,7 +17,7 @@
     },
     {
       "scenario": "smoke backend:consul consul_version:1.14.2 distro:ubuntu seal:shamir arch:arm64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 4
     },
     {
@@ -27,7 +27,7 @@
     },
     {
       "scenario": "upgrade backend:raft consul_version:1.14.2 distro:ubuntu seal:shamir arch:arm64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 1
     },
     {
@@ -37,7 +37,7 @@
     },
     {
       "scenario": "upgrade backend:consul consul_version:1.12.7 distro:rhel seal:awskms arch:arm64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 3
     },
     {
@@ -47,7 +47,7 @@
     },
     {
       "scenario": "upgrade backend:consul consul_version:1.14.2 distro:rhel seal:awskms arch:arm64 artifact_source:crt edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 5
     }
   ]

diff --git a/.github/enos-run-matrices/enos_release_testing_oss-artifactory-oss-linux-amd64-zip.json b/.github/enos-run-matrices/enos_release_testing_oss-artifactory-oss-linux-amd64-zip.json
@@ -2,7 +2,7 @@
   "include": [
     {
       "scenario": "smoke backend:raft consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -12,7 +12,7 @@
     },
     {
       "scenario": "smoke backend:consul consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -22,7 +22,7 @@
     },
     {
       "scenario": "smoke backend:consul consul_version:1.12.7 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -32,7 +32,7 @@
     },
     {
       "scenario": "upgrade backend:raft consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -42,7 +42,7 @@
     },
     {
       "scenario": "upgrade backend:consul consul_version:1.13.4 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {

diff --git a/.github/enos-run-matrices/enos_release_testing_oss-artifactory-oss-linux-arm64-zip.json b/.github/enos-run-matrices/enos_release_testing_oss-artifactory-oss-linux-arm64-zip.json
@@ -7,17 +7,17 @@
     },
     {
       "scenario": "smoke backend:raft consul_version:1.14.2 distro:ubuntu seal:awskms arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
       "scenario": "smoke backend:consul consul_version:1.12.7 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 1
     },
     {
       "scenario": "smoke backend:consul consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -27,7 +27,7 @@
     },
     {
       "scenario": "upgrade backend:raft consul_version:1.14.2 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 2
     },
     {
@@ -42,7 +42,7 @@
     },
     {
       "scenario": "upgrade backend:consul consul_version:1.13.4 distro:ubuntu seal:shamir arch:amd64 artifact_source:artifactory edition:oss artifact_type:bundle",
-      "aws_region": "us-west-1",
+      "aws_region": "us-east-1",
       "test_group": 1
     },
     {

diff --git a/.gitignore b/.gitignore
@@ -67,6 +67,10 @@ enos/.terraform/*
 enos/.terraform.lock.hcl
 enos/*.tfstate
 enos/*.tfstate.*
+enos/**/.terraform/*
+enos/**/.terraform.lock.hcl
+enos/**/*.tfstate
+enos/**/*.tfstate.*
 
 .DS_Store
 .idea
@@ -127,4 +131,4 @@ website/components/node_modules
 .releaser/
 *.log
 
-tools/godoctests/.bin
+tools/godoctests/.bin
diff --git a/enos/ci/service-user-iam/main.tf b/enos/ci/service-user-iam/main.tf
@@ -28,6 +28,7 @@ resource "aws_iam_role" "role" {
 
 data "aws_iam_policy_document" "assume_role_policy_document" {
   provider = aws.us_east_1
+
   statement {
     effect  = "Allow"
     actions = ["sts:AssumeRole"]
@@ -43,31 +44,75 @@ resource "aws_iam_role_policy" "role_policy" {
   provider = aws.us_east_1
   role     = aws_iam_role.role.name
   name     = "${local.service_user}_policy"
-  policy   = data.aws_iam_policy_document.iam_policy_document.json
+  policy   = data.aws_iam_policy_document.role_policy.json
+}
+
+data "aws_iam_policy_document" "role_policy" {
+  source_policy_documents = [
+    data.aws_iam_policy_document.enos_scenario.json,
+    data.aws_iam_policy_document.aws_nuke.json,
+  ]
+}
+
+data "aws_iam_policy_document" "aws_nuke" {
+  provider = aws.us_east_1
+
+  statement {
+    effect = "Allow"
+    actions = [
+      "ec2:DescribeInternetGateways",
+      "ec2:DescribeNatGateways",
+      "ec2:DescribeRegions",
+      "ec2:DescribeVpnGateways",
+      "iam:DeleteAccessKey",
+      "iam:DeleteUser",
+      "iam:DeleteUserPolicy",
+      "iam:GetUser",
+      "iam:ListAccessKeys",
+      "iam:ListAccountAliases",
+      "iam:ListGroupsForUser",
+      "iam:ListUserPolicies",
+      "iam:ListUserTags",
+      "iam:ListUsers",
+      "iam:UntagUser",
+      "servicequotas:ListServiceQuotas"
+    ]
+
+    resources = ["*"]
+  }
 }
 
-data "aws_iam_policy_document" "iam_policy_document" {
+data "aws_iam_policy_document" "enos_scenario" {
   provider = aws.us_east_1
+
   statement {
     effect = "Allow"
     actions = [
       "ec2:AssociateRouteTable",
       "ec2:AttachInternetGateway",
       "ec2:AuthorizeSecurityGroupEgress",
       "ec2:AuthorizeSecurityGroupIngress",
+      "ec2:CancelSpotFleetRequests",
+      "ec2:CancelSpotInstanceRequests",
       "ec2:CreateInternetGateway",
       "ec2:CreateKeyPair",
+      "ec2:CreateLaunchTemplate",
+      "ec2:CreateLaunchTemplateVersion",
       "ec2:CreateRoute",
       "ec2:CreateRouteTable",
       "ec2:CreateSecurityGroup",
+      "ec2:CreateSpotDatafeedSubscription",
       "ec2:CreateSubnet",
       "ec2:CreateTags",
       "ec2:CreateVolume",
       "ec2:CreateVPC",
       "ec2:DeleteInternetGateway",
+      "ec2:DeleteLaunchTemplate",
+      "ec2:DeleteLaunchTemplateVersions",
       "ec2:DeleteKeyPair",
       "ec2:DeleteRouteTable",
       "ec2:DeleteSecurityGroup",
+      "ec2:DeleteSpotDatafeedSubscription",
       "ec2:DeleteSubnet",
       "ec2:DeleteTags",
       "ec2:DeleteVolume",
@@ -81,14 +126,22 @@ data "aws_iam_policy_document" "iam_policy_document" {
       "ec2:DescribeInstanceTypeOfferings",
       "ec2:DescribeInstanceTypes",
       "ec2:DescribeInternetGateways",
-      "ec2:DescribeInternetGateways",
       "ec2:DescribeKeyPairs",
+      "ec2:DescribeLaunchTemplates",
+      "ec2:DescribeLaunchTemplateVersions",
       "ec2:DescribeNatGateways",
       "ec2:DescribeNetworkAcls",
       "ec2:DescribeNetworkInterfaces",
       "ec2:DescribeRegions",
       "ec2:DescribeRouteTables",
       "ec2:DescribeSecurityGroups",
+      "ec2:DescribeSpotDatafeedSubscription",
+      "ec2:DescribeSpotFleetInstances",
+      "ec2:DescribeSpotFleetInstanceRequests",
+      "ec2:DescribeSpotFleetRequests",
+      "ec2:DescribeSpotFleetRequestHistory",
+      "ec2:DescribeSpotInstanceRequests",
+      "ec2:DescribeSpotPriceHistory",
       "ec2:DescribeSubnets",
       "ec2:DescribeTags",
       "ec2:DescribeVolumes",
@@ -99,14 +152,21 @@ data "aws_iam_policy_document" "iam_policy_document" {
       "ec2:DescribeVpnGateways",
       "ec2:DetachInternetGateway",
       "ec2:DisassociateRouteTable",
+      "ec2:GetLaunchTemplateData",
+      "ec2:GetSpotPlacementScores",
       "ec2:ImportKeyPair",
       "ec2:ModifyInstanceAttribute",
+      "ec2:ModifyLaunchTemplate",
+      "ec2:ModifySpotFleetRequest",
       "ec2:ModifySubnetAttribute",
       "ec2:ModifyVPCAttribute",
+      "ec2:RequestSpotInstances",
+      "ec2:RequestSpotFleet",
       "ec2:ResetInstanceAttribute",
       "ec2:RevokeSecurityGroupEgress",
       "ec2:RevokeSecurityGroupIngress",
       "ec2:RunInstances",
+      "ec2:SendSpotInstanceInterruptions",
       "ec2:TerminateInstances",
       "elasticloadbalancing:DescribeLoadBalancers",
       "elasticloadbalancing:DescribeTargetGroups",
@@ -115,11 +175,10 @@ data "aws_iam_policy_document" "iam_policy_document" {
       "iam:CreateInstanceProfile",
       "iam:CreatePolicy",
       "iam:CreateRole",
-      "iam:CreateRole",
+      "iam:CreateServiceLinkedRole",
       "iam:DeleteInstanceProfile",
       "iam:DeletePolicy",
       "iam:DeleteRole",
-      "iam:DeleteRole",
       "iam:DeleteRolePolicy",
       "iam:DetachRolePolicy",
       "iam:GetInstanceProfile",
@@ -132,7 +191,6 @@ data "aws_iam_policy_document" "iam_policy_document" {
       "iam:ListPolicies",
       "iam:ListRolePolicies",
       "iam:ListRoles",
-      "iam:ListRoles",
       "iam:PassRole",
       "iam:PutRolePolicy",
       "iam:RemoveRoleFromInstanceProfile",
@@ -150,6 +208,7 @@ data "aws_iam_policy_document" "iam_policy_document" {
       "kms:ScheduleKeyDeletion",
       "servicequotas:ListServiceQuotas"
     ]
+
     resources = ["*"]
   }
 }