Expose maxHealthyPercentage field

giantswarm · Oct 16, 2024 · bdb45af · bdb45af
1 parent 7b913b3
commit bdb45af
Show file tree

Hide file tree

Showing 4 changed files with 20 additions and 3 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+
+- Expose the `maxHealthyPercentage` property to allow setting the maximum percentage of healthy machines in the Auto Scaling Group during upgrades.
+
 ## [2.2.0] - 2024-09-23
 
 ### Added

diff --git a/helm/cluster-aws/README.md b/helm/cluster-aws/README.md
@@ -402,8 +402,9 @@ Node pools of the cluster. If not specified, this defaults to the value of `clus
 | `global.nodePools.PATTERN.instanceWarmup` | **Time interval, in seconds, between node replacement.**|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>|
 | `global.nodePools.PATTERN.libVolumeSizeGB` | **Lib volume size (GB)** - Size of the volume mounted at `/var/lib` on the worker nodes. This disk is shared between kubelet folder `/var/lib/kubelet` and containerd folder `/var/lib/containerd`s.|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>**Default:** `120`|
 | `global.nodePools.PATTERN.logVolumeSizeGB` | **Log volume size (GB)** - Size of the volume mounted at `/var/log` on the worker nodes.|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>**Default:** `30`|
+| `global.nodePools.PATTERN.maxHealthyPercentage` | **Minimum percentage of instances that must remain healthy during node replacement.** - The percentage of capacity in ASG that can be in service and healthy, or pending, to support your workload when replacing instances. A larger range increases the number of instances that can be replaced at the same time. The difference between minHealthyPercentage and maxnHealthyPercentage cannot be greater than 100.|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>**Default:** `100`|
 | `global.nodePools.PATTERN.maxSize` | **Maximum number of nodes**|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>|
-| `global.nodePools.PATTERN.minHealthyPercentage` | **Minimum percentage of instances that must remain healthy during node replacement.**|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>|
+| `global.nodePools.PATTERN.minHealthyPercentage` | **Minimum percentage of instances that must remain healthy during node replacement.**|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>**Default:** `90`|
 | `global.nodePools.PATTERN.minSize` | **Minimum number of nodes**|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>|
 | `global.nodePools.PATTERN.rootVolumeSizeGB` | **Root volume size (GB)**|**Type:** `integer`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>**Default:** `8`|
 | `global.nodePools.PATTERN.spotInstances` | **Spot instances** - Compared to on-demand instances, spot instances can help you save cost.|**Type:** `object`<br/>**Key pattern:**<br/>`PATTERN`=`^[a-z0-9][-a-z0-9]{3,18}[a-z0-9]$`<br/>|

diff --git a/helm/cluster-aws/templates/_machine_pools.tpl b/helm/cluster-aws/templates/_machine_pools.tpl
@@ -79,7 +79,8 @@ spec:
   {{- end }}
   refreshPreferences:
     instanceWarmup: {{ $value.instanceWarmup | default 600 }}
-    minHealthyPercentage: {{ $value.minHealthyPercentage | default 90 }}
+    minHealthyPercentage: {{ $value.minHealthyPercentage }}
+    maxHealthyPercentage: {{ $value.maxHealthyPercentage }}
   ignition:
     version: "3.4"
 ---

diff --git a/helm/cluster-aws/values.schema.json b/helm/cluster-aws/values.schema.json
@@ -196,13 +196,24 @@
                     "description": "Size of the volume mounted at `/var/log` on the worker nodes.",
                     "default": 30
                 },
+                "maxHealthyPercentage": {
+                    "type": "integer",
+                    "title": "Minimum percentage of instances that must remain healthy during node replacement.",
+                    "description": "The percentage of capacity in ASG that can be in service and healthy, or pending, to support your workload when replacing instances. A larger range increases the number of instances that can be replaced at the same time. The difference between minHealthyPercentage and maxnHealthyPercentage cannot be greater than 100.",
+                    "default": 100,
+                    "maximum": 200,
+                    "minimum": 100
+                },
                 "maxSize": {
                     "type": "integer",
                     "title": "Maximum number of nodes"
                 },
                 "minHealthyPercentage": {
                     "type": "integer",
-                    "title": "Minimum percentage of instances that must remain healthy during node replacement."
+                    "title": "Minimum percentage of instances that must remain healthy during node replacement.",
+                    "default": 90,
+                    "maximum": 100,
+                    "minimum": 0
                 },
                 "minSize": {
                     "type": "integer",