Configure controller and worker node architecture separately

* On platforms that support ARM64 instances, configure controller and worker node host architectures separately * For example, you can run arm64 controllers and amd64 workers * Add `controller_arch` and `worker_arch` variables * Remove `arch` variable
poseidon · Aug 2, 2024 · af27661 · af27661
1 parent 516786d
commit af27661
Show file tree

Hide file tree

Showing 11 changed files with 71 additions and 24 deletions.
diff --git a/CHANGES.md b/CHANGES.md
@@ -4,6 +4,12 @@ Notable changes between versions.
 
 ## Latest
 
+### Azure
+
+* Allow controller and worker nodes to use different CPU architectures
+  * Add `controller_arch` and `worker_arch` variables
+  * Remove the `arch` variable
+
 ## v1.30.3
 
 * Kubernetes [v1.30.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.30.md#v1303)
@@ -19,17 +25,23 @@ Notable changes between versions.
   * Fix propagating settings to worker disks, previously ignored
 * Allow configuring CPU pricing model for burstable instance types ([#1482](https://github.com/poseidon/typhoon/pull/1482))
   * Add `controller_cpu_credits` and `worker_cpu_credits` variables (`standard` or `unlimited`)
+* Configure controller or worker instance architecture ([#1485](https://github.com/poseidon/typhoon/pull/1485))
+  * Add `controller_arch` and `worker_arch` variables (`amd64` or `arm64`)
+  * Remove `arch` variable
 
 ```diff
 module "cluster" {
   ...
+- arch      = "amd64"
 - disk_type = "gp3"
 - disk_size = 30
 - disk_iops = 3000
 
++ controller_arch        = "amd64"
 + controller_disk_size   = 15
-+ worker_disk_size       = 22
 + controller_cpu_credits = "standard"
++ worker_arch            = "amd64"
++ worker_disk_size       = 22
 + worker_cpu_credits     = "unlimited"
 }
 ```
@@ -53,6 +65,9 @@ module "cluster" {
   * Add `controller_disk_type` and `controller_disk_size` variables
   * Add `worker_disk_type`, `worker_disk_size`, and `worker_ephemeral_disk` variables
 * Reduce the number of public IPv4 addresses needed for the Azure load balancer ([#1470](https://github.com/poseidon/typhoon/pull/1470))
+* Configure controller or worker instance architecture for Flatcar Linux ([#1485](https://github.com/poseidon/typhoon/pull/1485))
+  * Add `controller_arch` and `worker_arch` variables (`amd64` or `arm64`)
+  * Remove `arch` variable
 
 ```diff
 module "cluster" {
@@ -65,7 +80,7 @@ module "cluster" {
 +   ipv4 = ["10.0.0.0/16"]
 + }
 
-  # optional
+  # instances
 + controller_disk_type = "StandardSSD_LRS"
 + worker_ephemeral_disk = true
 }

diff --git a/aws/fedora-coreos/kubernetes/ami.tf b/aws/fedora-coreos/kubernetes/ami.tf
@@ -19,7 +19,7 @@ data "aws_ami" "fedora-coreos" {
 }
 
 data "aws_ami" "fedora-coreos-arm" {
-  count = var.arch == "arm64" ? 1 : 0
+  count = var.controller_arch == "arm64" ? 1 : 0
 
   most_recent = true
   owners      = ["125523088429"]

diff --git a/aws/fedora-coreos/kubernetes/controllers.tf b/aws/fedora-coreos/kubernetes/controllers.tf
@@ -22,7 +22,7 @@ resource "aws_instance" "controllers" {
   }
 
   instance_type = var.controller_type
-  ami           = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
+  ami           = var.controller_arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
   user_data     = data.ct_config.controllers.*.rendered[count.index]
 
   # storage

diff --git a/aws/fedora-coreos/kubernetes/variables.tf b/aws/fedora-coreos/kubernetes/variables.tf
@@ -190,14 +190,25 @@ variable "cluster_domain_suffix" {
   default     = "cluster.local"
 }
 
-variable "arch" {
+# advanced
+
+variable "controller_arch" {
   type        = string
-  description = "Container architecture (amd64 or arm64)"
+  description = "Controller node(s) architecture (amd64 or arm64)"
   default     = "amd64"
+  validation {
+    condition     = contains(["amd64", "arm64"], var.controller_arch)
+    error_message = "The controller_arch must be amd64 or arm64."
+  }
+}
 
+variable "worker_arch" {
+  type        = string
+  description = "Worker node(s) architecture (amd64 or arm64)"
+  default     = "amd64"
   validation {
-    condition     = var.arch == "amd64" || var.arch == "arm64"
-    error_message = "The arch must be amd64 or arm64."
+    condition     = contains(["amd64", "arm64"], var.worker_arch)
+    error_message = "The worker_arch must be amd64 or arm64."
   }
 }
 

diff --git a/aws/fedora-coreos/kubernetes/workers.tf b/aws/fedora-coreos/kubernetes/workers.tf
@@ -9,7 +9,7 @@ module "workers" {
   worker_count    = var.worker_count
   instance_type   = var.worker_type
   os_stream       = var.os_stream
-  arch            = var.arch
+  arch            = var.worker_arch
   disk_type       = var.worker_disk_type
   disk_size       = var.worker_disk_size
   disk_iops       = var.worker_disk_iops

diff --git a/aws/flatcar-linux/kubernetes/ami.tf b/aws/flatcar-linux/kubernetes/ami.tf
@@ -1,7 +1,7 @@
 locals {
   # Pick a Flatcar Linux AMI
   # flatcar-stable -> Flatcar Linux AMI
-  ami_id  = var.arch == "arm64" ? data.aws_ami.flatcar-arm64[0].image_id : data.aws_ami.flatcar.image_id
+  ami_id  = var.controller_arch == "arm64" ? data.aws_ami.flatcar-arm64[0].image_id : data.aws_ami.flatcar.image_id
   channel = split("-", var.os_image)[1]
 }
 
@@ -26,7 +26,7 @@ data "aws_ami" "flatcar" {
 }
 
 data "aws_ami" "flatcar-arm64" {
-  count = var.arch == "arm64" ? 1 : 0
+  count = var.controller_arch == "arm64" ? 1 : 0
 
   most_recent = true
   owners      = ["075585003325"]

diff --git a/aws/flatcar-linux/kubernetes/variables.tf b/aws/flatcar-linux/kubernetes/variables.tf
@@ -190,17 +190,27 @@ variable "cluster_domain_suffix" {
   default     = "cluster.local"
 }
 
-variable "arch" {
+variable "controller_arch" {
   type        = string
-  description = "Container architecture (amd64 or arm64)"
+  description = "Controller node(s) architecture (amd64 or arm64)"
   default     = "amd64"
+  validation {
+    condition     = contains(["amd64", "arm64"], var.controller_arch)
+    error_message = "The controller_arch must be amd64 or arm64."
+  }
+}
 
+variable "worker_arch" {
+  type        = string
+  description = "Worker node(s) architecture (amd64 or arm64)"
+  default     = "amd64"
   validation {
-    condition     = var.arch == "amd64" || var.arch == "arm64"
-    error_message = "The arch must be amd64 or arm64."
+    condition     = contains(["amd64", "arm64"], var.worker_arch)
+    error_message = "The worker_arch must be amd64 or arm64."
   }
 }
 
+
 variable "daemonset_tolerations" {
   type        = list(string)
   description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"

diff --git a/aws/flatcar-linux/kubernetes/workers.tf b/aws/flatcar-linux/kubernetes/workers.tf
@@ -9,7 +9,7 @@ module "workers" {
   worker_count    = var.worker_count
   instance_type   = var.worker_type
   os_image        = var.os_image
-  arch            = var.arch
+  arch            = var.worker_arch
   disk_type       = var.worker_disk_type
   disk_size       = var.worker_disk_size
   disk_iops       = var.worker_disk_iops

diff --git a/azure/flatcar-linux/kubernetes/controllers.tf b/azure/flatcar-linux/kubernetes/controllers.tf
@@ -2,8 +2,8 @@ locals {
   # Container Linux derivative
   # flatcar-stable -> Flatcar Linux Stable
   channel      = split("-", var.os_image)[1]
-  offer_suffix = var.arch == "arm64" ? "corevm" : "free"
-  urn          = var.arch == "arm64" ? local.channel : "${local.channel}-gen2"
+  offer_suffix = var.controller_arch == "arm64" ? "corevm" : "free"
+  urn          = var.controller_arch == "arm64" ? local.channel : "${local.channel}-gen2"
 
   # Typhoon ssh_authorized_key supports RSA or a newer formats (e.g. ed25519).
   # However, Azure requires an older RSA key to pass validations. To use a
@@ -63,7 +63,7 @@ resource "azurerm_linux_virtual_machine" "controllers" {
   }
 
   dynamic "plan" {
-    for_each = var.arch == "arm64" ? [] : [1]
+    for_each = var.controller_arch == "arm64" ? [] : [1]
     content {
       publisher = "kinvolk"
       product   = "flatcar-container-linux-${local.offer_suffix}"

diff --git a/azure/flatcar-linux/kubernetes/variables.tf b/azure/flatcar-linux/kubernetes/variables.tf
@@ -168,14 +168,25 @@ variable "worker_node_labels" {
   default     = []
 }
 
-variable "arch" {
+# advanced
+
+variable "controller_arch" {
   type        = string
-  description = "Container architecture (amd64 or arm64)"
+  description = "Controller node(s) architecture (amd64 or arm64)"
   default     = "amd64"
+  validation {
+    condition     = contains(["amd64", "arm64"], var.controller_arch)
+    error_message = "The controller_arch must be amd64 or arm64."
+  }
+}
 
+variable "worker_arch" {
+  type        = string
+  description = "Worker node(s) architecture (amd64 or arm64)"
+  default     = "amd64"
   validation {
-    condition     = var.arch == "amd64" || var.arch == "arm64"
-    error_message = "The arch must be amd64 or arm64."
+    condition     = contains(["amd64", "arm64"], var.worker_arch)
+    error_message = "The worker_arch must be amd64 or arm64."
   }
 }
 

diff --git a/azure/flatcar-linux/kubernetes/workers.tf b/azure/flatcar-linux/kubernetes/workers.tf
@@ -25,5 +25,5 @@ module "workers" {
   cluster_domain_suffix = var.cluster_domain_suffix
   snippets              = var.worker_snippets
   node_labels           = var.worker_node_labels
-  arch                  = var.arch
+  arch                  = var.worker_arch
 }