open-vault/enos/enos-scenario-ui.hcl

296 lines
8.8 KiB
HCL
Raw Permalink Normal View History

# Copyright (c) HashiCorp, Inc.
# SPDX-License-Identifier: MPL-2.0
scenario "ui" {
matrix {
edition = ["ce", "ent"]
backend = ["consul", "raft"]
seal_ha_beta = ["true", "false"]
}
terraform_cli = terraform_cli.default
terraform = terraform.default
providers = [
provider.aws.default,
provider.enos.ubuntu
]
locals {
arch = "amd64"
artifact_type = "bundle"
backend_license_path = abspath(var.backend_license_path != null ? var.backend_license_path : joinpath(path.root, "./support/consul.hclic"))
backend_tag_key = "VaultStorage"
build_tags = {
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
"ce" = ["ui"]
"ent" = ["ui", "enterprise", "ent"]
}
bundle_path = abspath(var.vault_artifact_path)
distro = "ubuntu"
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
consul_version = "1.16.1"
seal = "awskms"
tags = merge({
"Project Name" : var.project_name
"Project" : "Enos",
"Environment" : "ci"
}, var.tags)
vault_install_dir_packages = {
rhel = "/bin"
ubuntu = "/usr/bin"
}
vault_install_dir = var.vault_install_dir
vault_license_path = abspath(var.vault_license_path != null ? var.vault_license_path : joinpath(path.root, "./support/vault.hclic"))
vault_tag_key = "Type" // enos_vault_start expects Type as the tag key
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
ui_test_filter = var.ui_test_filter != null && try(trimspace(var.ui_test_filter), "") != "" ? var.ui_test_filter : (matrix.edition == "ce") ? "!enterprise" : null
}
step "build_vault" {
module = module.build_local
variables {
build_tags = var.vault_local_build_tags != null ? var.vault_local_build_tags : local.build_tags[matrix.edition]
bundle_path = local.bundle_path
goarch = local.arch
goos = "linux"
product_version = var.vault_product_version
artifact_type = local.artifact_type
revision = var.vault_revision
}
}
step "ec2_info" {
module = module.ec2_info
}
step "create_vpc" {
module = module.create_vpc
variables {
common_tags = local.tags
}
}
step "create_seal_key" {
module = "seal_key_${local.seal}"
variables {
cluster_id = step.create_vpc.cluster_id
common_tags = global.tags
}
}
// This step reads the contents of the backend license if we're using a Consul backend and
// the edition is "ent".
step "read_backend_license" {
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
skip_step = matrix.backend == "raft" || var.backend_edition == "ce"
module = module.read_license
variables {
file_name = local.backend_license_path
}
}
step "read_vault_license" {
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
skip_step = matrix.edition == "ce"
module = module.read_license
variables {
file_name = local.vault_license_path
}
}
step "create_vault_cluster_targets" {
enos: use on-demand targets (#21459) (#21464) Add an updated `target_ec2_instances` module that is capable of dynamically splitting target instances over subnet/az's that are compatible with the AMI architecture and the associated instance type for the architecture. Use the `target_ec2_instances` module where necessary. Ensure that `raft` storage scenarios don't provision unnecessary infrastructure with a new `target_ec2_shim` module. After a lot of trial, the state of Ec2 spot instance capacity, their associated APIs, and current support for different fleet types in AWS Terraform provider, have proven to make using spot instances for scenario targets too unreliable. The current state of each method: * `target_ec2_fleet`: unusable due to the fact that the `instant` type does not guarantee fulfillment of either `spot` or `on-demand` instance request types. The module does support both `on-demand` and `spot` request types and is capable of bidding across a maximum of four availability zones, which makes it an attractive choice if the `instant` type would always fulfill requests. Perhaps a `request` type with `wait_for_fulfillment` option like `aws_spot_fleet_request` would make it more viable for future consideration. * `target_ec2_spot_fleet`: more reliable if bidding for target instances that have capacity in the chosen zone. Issues in the AWS provider prevent us from bidding across multiple zones succesfully. Over the last 2-3 months target capacity for the instance types we'd prefer to use has dropped dramatically and the price is near-or-at on-demand. The volatility for nearly no cost savings means we should put this option on the shelf for now. * `target_ec2_instances`: the most reliable method we've got. It is now capable of automatically determing which subnets and availability zones to provision targets in and has been updated to be usable for both Vault and Consul targets. By default we use the cheapest medium instance types that we've found are reliable to test vault. * Update .gitignore * enos/modules/create_vpc: create a subnet for every availability zone * enos/modules/target_ec2_fleet: bid across the maximum of four availability zones for targets * enos/modules/target_ec2_spot_fleet: attempt to make the spot fleet bid across more availability zones for targets * enos/modules/target_ec2_instances: create module to use ec2:RunInstances for scenario targets * enos/modules/target_ec2_shim: create shim module to satisfy the target module interface * enos/scenarios: use target_ec2_shim for backend targets on raft storage scenarios * enos/modules/az_finder: remove unsed module Signed-off-by: Ryan Cragun <me@ryan.ec> Co-authored-by: Ryan Cragun <me@ryan.ec>
2023-06-26 22:54:39 +00:00
module = module.target_ec2_instances
depends_on = [step.create_vpc]
providers = {
enos = provider.enos.ubuntu
}
variables {
ami_id = step.ec2_info.ami_ids[local.arch][local.distro][var.ubuntu_distro_version]
cluster_tag_key = local.vault_tag_key
common_tags = local.tags
seal_key_names = step.create_seal_key.resource_names
vpc_id = step.create_vpc.id
}
}
step "create_vault_cluster_backend_targets" {
enos: use on-demand targets (#21459) (#21464) Add an updated `target_ec2_instances` module that is capable of dynamically splitting target instances over subnet/az's that are compatible with the AMI architecture and the associated instance type for the architecture. Use the `target_ec2_instances` module where necessary. Ensure that `raft` storage scenarios don't provision unnecessary infrastructure with a new `target_ec2_shim` module. After a lot of trial, the state of Ec2 spot instance capacity, their associated APIs, and current support for different fleet types in AWS Terraform provider, have proven to make using spot instances for scenario targets too unreliable. The current state of each method: * `target_ec2_fleet`: unusable due to the fact that the `instant` type does not guarantee fulfillment of either `spot` or `on-demand` instance request types. The module does support both `on-demand` and `spot` request types and is capable of bidding across a maximum of four availability zones, which makes it an attractive choice if the `instant` type would always fulfill requests. Perhaps a `request` type with `wait_for_fulfillment` option like `aws_spot_fleet_request` would make it more viable for future consideration. * `target_ec2_spot_fleet`: more reliable if bidding for target instances that have capacity in the chosen zone. Issues in the AWS provider prevent us from bidding across multiple zones succesfully. Over the last 2-3 months target capacity for the instance types we'd prefer to use has dropped dramatically and the price is near-or-at on-demand. The volatility for nearly no cost savings means we should put this option on the shelf for now. * `target_ec2_instances`: the most reliable method we've got. It is now capable of automatically determing which subnets and availability zones to provision targets in and has been updated to be usable for both Vault and Consul targets. By default we use the cheapest medium instance types that we've found are reliable to test vault. * Update .gitignore * enos/modules/create_vpc: create a subnet for every availability zone * enos/modules/target_ec2_fleet: bid across the maximum of four availability zones for targets * enos/modules/target_ec2_spot_fleet: attempt to make the spot fleet bid across more availability zones for targets * enos/modules/target_ec2_instances: create module to use ec2:RunInstances for scenario targets * enos/modules/target_ec2_shim: create shim module to satisfy the target module interface * enos/scenarios: use target_ec2_shim for backend targets on raft storage scenarios * enos/modules/az_finder: remove unsed module Signed-off-by: Ryan Cragun <me@ryan.ec> Co-authored-by: Ryan Cragun <me@ryan.ec>
2023-06-26 22:54:39 +00:00
module = matrix.backend == "consul" ? module.target_ec2_instances : module.target_ec2_shim
depends_on = [step.create_vpc]
providers = {
enos = provider.enos.ubuntu
}
variables {
ami_id = step.ec2_info.ami_ids["arm64"]["ubuntu"]["22.04"]
cluster_tag_key = local.backend_tag_key
common_tags = local.tags
seal_key_names = step.create_seal_key.resource_names
vpc_id = step.create_vpc.id
}
}
step "create_backend_cluster" {
module = "backend_${matrix.backend}"
depends_on = [
step.create_vault_cluster_backend_targets,
]
providers = {
enos = provider.enos.ubuntu
}
variables {
cluster_name = step.create_vault_cluster_backend_targets.cluster_name
cluster_tag_key = local.backend_tag_key
license = (matrix.backend == "consul" && var.backend_edition == "ent") ? step.read_backend_license.license : null
release = {
edition = var.backend_edition
version = local.consul_version
}
target_hosts = step.create_vault_cluster_backend_targets.hosts
}
}
step "create_vault_cluster" {
module = module.vault_cluster
depends_on = [
step.create_backend_cluster,
step.build_vault,
step.create_vault_cluster_targets
]
providers = {
enos = provider.enos.ubuntu
}
variables {
backend_cluster_name = step.create_vault_cluster_backend_targets.cluster_name
backend_cluster_tag_key = local.backend_tag_key
cluster_name = step.create_vault_cluster_targets.cluster_name
consul_license = (matrix.backend == "consul" && var.backend_edition == "ent") ? step.read_backend_license.license : null
consul_release = matrix.backend == "consul" ? {
edition = var.backend_edition
version = local.consul_version
} : null
enable_audit_devices = var.vault_enable_audit_devices
install_dir = local.vault_install_dir
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
license = matrix.edition != "ce" ? step.read_vault_license.license : null
local_artifact_path = local.bundle_path
packages = global.distro_packages["ubuntu"]
seal_ha_beta = matrix.seal_ha_beta
seal_key_name = step.create_seal_key.resource_name
seal_type = local.seal
storage_backend = matrix.backend
target_hosts = step.create_vault_cluster_targets.hosts
}
}
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
// Wait for our cluster to elect a leader
step "wait_for_leader" {
module = module.vault_wait_for_leader
depends_on = [step.create_vault_cluster]
providers = {
enos = provider.enos.ubuntu
}
variables {
timeout = 120 # seconds
vault_hosts = step.create_vault_cluster_targets.hosts
vault_install_dir = local.vault_install_dir
vault_root_token = step.create_vault_cluster.root_token
}
}
step "test_ui" {
Backport [QT-602] Run `proxy` and `agent` test scenarios (#23176) into release/1.14.x (#23302) * [QT-602] Run `proxy` and `agent` test scenarios (#23176) Update our `proxy` and `agent` scenarios to support new variants and perform baseline verification and their scenario specific verification. We integrate these updated scenarios into the pipeline by adding them to artifact samples. We've also improved the reliability of the `autopilot` and `replication` scenarios by refactoring our IP address gathering. Previously, we'd ask vault for the primary IP address and use some Terraform logic to determine followers. The leader IP address gathering script was also implicitly responsible for ensuring that a found leader was within a given group of hosts, and thus waiting for a given cluster to have a leader, and also for doing some arithmetic and outputting `replication` specific output data. We've broken these responsibilities into individual modules, improved their error messages, and fixed various races and bugs, including: * Fix a race between creating the file audit device and installing and starting vault in the `replication` scenario. * Fix how we determine our leader and follower IP addresses. We now query vault instead of a prior implementation that inferred the followers and sometimes did not allow all nodes to be an expected leader. * Fix a bug where we'd always always fail on the first wrong condition in the `vault_verify_performance_replication` module. We also performed some maintenance tasks on Enos scenarios byupdating our references from `oss` to `ce` to handle the naming and license changes. We also enabled `shellcheck` linting for enos module scripts. * Rename `oss` to `ce` for license and naming changes. * Convert template enos scripts to scripts that take environment variables. * Add `shellcheck` linting for enos module scripts. * Add additional `backend` and `seal` support to `proxy` and `agent` scenarios. * Update scenarios to include all baseline verification. * Add `proxy` and `agent` scenarios to artifact samples. * Remove IP address verification from the `vault_get_cluster_ips` modules and implement a new `vault_wait_for_leader` module. * Determine follower IP addresses by querying vault in the `vault_get_cluster_ips` module. * Move replication specific behavior out of the `vault_get_cluster_ips` module and into it's own `replication_data` module. * Extend initial version support for the `upgrade` and `autopilot` scenarios. We also discovered an issue with undo_logs that has been described in the VAULT-20259. As such, we've disabled the undo_logs check until it has been fixed. * actions: fix actionlint error and linting logic (#23305) Signed-off-by: Ryan Cragun <me@ryan.ec>
2023-09-27 16:53:12 +00:00
module = module.vault_test_ui
depends_on = [step.wait_for_leader]
variables {
vault_addr = step.create_vault_cluster_targets.hosts[0].public_ip
vault_root_token = step.create_vault_cluster.root_token
vault_unseal_keys = step.create_vault_cluster.recovery_keys_b64
vault_recovery_threshold = step.create_vault_cluster.recovery_threshold
ui_test_filter = local.ui_test_filter
}
}
output "audit_device_file_path" {
description = "The file path for the file audit device, if enabled"
value = step.create_vault_cluster.audit_device_file_path
}
output "cluster_name" {
description = "The Vault cluster name"
value = step.create_vault_cluster.cluster_name
}
output "hosts" {
description = "The Vault cluster target hosts"
value = step.create_vault_cluster.target_hosts
}
output "private_ips" {
description = "The Vault cluster private IPs"
value = step.create_vault_cluster.private_ips
}
output "public_ips" {
description = "The Vault cluster public IPs"
value = step.create_vault_cluster.public_ips
}
output "recovery_key_shares" {
description = "The Vault cluster recovery key shares"
value = step.create_vault_cluster.recovery_key_shares
}
output "recovery_keys_b64" {
description = "The Vault cluster recovery keys b64"
value = step.create_vault_cluster.recovery_keys_b64
}
output "recovery_keys_hex" {
description = "The Vault cluster recovery keys hex"
value = step.create_vault_cluster.recovery_keys_hex
}
output "root_token" {
description = "The Vault cluster root token"
value = step.create_vault_cluster.root_token
}
output "seal_key_name" {
description = "The Vault cluster seal key name"
value = step.create_seal_key.resource_name
}
output "ui_test_environment" {
value = step.test_ui.ui_test_environment
description = "The environment variables that are required in order to run the test:enos yarn target"
}
output "ui_test_stderr" {
description = "The stderr of the ui tests that ran"
value = step.test_ui.ui_test_stderr
}
output "ui_test_stdout" {
description = "The stdout of the ui tests that ran"
value = step.test_ui.ui_test_stdout
}
output "unseal_keys_b64" {
description = "The Vault cluster unseal keys"
value = step.create_vault_cluster.unseal_keys_b64
}
output "unseal_keys_hex" {
description = "The Vault cluster unseal keys hex"
value = step.create_vault_cluster.unseal_keys_hex
}
}