From 13cc09ff08797aacb9c8aabb747c101652843aaa Mon Sep 17 00:00:00 2001
From: David Porter <david@porter.me>
Date: Fri, 6 Nov 2020 01:32:55 +0000
Subject: [PATCH] Add graceful node shutdown feature gate

---
 .../en/docs/concepts/architecture/nodes.md    | 20 +++++++++++++++++++
 .../feature-gates.md                          |  2 ++
 2 files changed, 22 insertions(+)

diff --git a/content/en/docs/concepts/architecture/nodes.md b/content/en/docs/concepts/architecture/nodes.md
index 180b4ca9c4..d3ac8d6759 100644
--- a/content/en/docs/concepts/architecture/nodes.md
+++ b/content/en/docs/concepts/architecture/nodes.md
@@ -330,6 +330,26 @@ the kubelet can use topology hints when making resource assignment decisions.
 See [Control Topology Management Policies on a Node](/docs/tasks/administer-cluster/topology-manager/)
 for more information.
 
+## Graceful Node Shutdown {#graceful-node-shutdown}
+
+{{< feature-state state="alpha" for_k8s_version="v1.20" >}}
+
+If you have enabled the `GracefulNodeShutdown` [feature gate](/docs/reference/command-line-tools-reference/feature-gates/), then the kubelet attempts to detect the node system shutdown and terminates pods running on the node.
+Kubelet ensures that pods follow the normal [pod termination process](/docs/concepts/workloads/pods/pod-lifecycle/#pod-termination) during the node shutdown.
+
+When the `GracefulNodeShutdown` feature gate is enabled, kubelet uses [systemd inhibitor locks](https://www.freedesktop.org/wiki/Software/systemd/inhibit/) to delay the node shutdown with a given duration. During a shutdown kubelet terminates pods in two phases:
+
+1. Terminate regular pods running on the node.
+2. Terminate [critical pods](/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/#marking-pod-as-critical) running on the node.
+
+Graceful Node Shutdown feature is configured with two [`KubeletConfiguration`](/docs/tasks/administer-cluster/kubelet-config-file/) options:
+* `ShutdownGracePeriod`:
+  * Specifies the total duration that the node should delay the shutdown by. This is the total grace period for pod termination for both regular and [critical pods](/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/#marking-pod-as-critical).
+* `ShutdownGracePeriodCriticalPods`:
+  * Specifies the duration used to terminate [critical pods](/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/#marking-pod-as-critical) during a node shutdown. This should be less than `ShutdownGracePeriod`.
+
+For example, if `ShutdownGracePeriod=30s`, and `ShutdownGracePeriodCriticalPods=10s`, kubelet will delay the node shutdown by 30 seconds. During the shutdown, the first 20 (30-10) seconds would be reserved for gracefully terminating normal pods, and the last 10 seconds would be reserved for terminating [critical pods](/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/#marking-pod-as-critical).
+
 
 ## {{% heading "whatsnext" %}}
 
diff --git a/content/en/docs/reference/command-line-tools-reference/feature-gates.md b/content/en/docs/reference/command-line-tools-reference/feature-gates.md
index 303c90aae5..65cf2b0cc3 100644
--- a/content/en/docs/reference/command-line-tools-reference/feature-gates.md
+++ b/content/en/docs/reference/command-line-tools-reference/feature-gates.md
@@ -109,6 +109,7 @@ different Kubernetes components.
 | `ExpandPersistentVolumes` | `true` | Beta | 1.11 | |
 | `ExperimentalHostUserNamespaceDefaulting` | `false` | Beta | 1.5 | |
 | `GenericEphemeralVolume` | `false` | Alpha | 1.19 | |
+| `GracefulNodeShutdown` | `false` | Alpha | 1.20 | |
 | `HPAScaleToZero` | `false` | Alpha | 1.16 | |
 | `HugePageStorageMediumSize` | `false` | Alpha | 1.18 | 1.18 |
 | `HugePageStorageMediumSize` | `true` | Beta | 1.19 | |
@@ -471,6 +472,7 @@ Each feature gate is designed for enabling/disabling a specific feature:
    [Enabling Endpoint Slices](/docs/tasks/administer-cluster/enabling-endpointslices/).
 - `GCERegionalPersistentDisk`: Enable the regional PD feature on GCE.
 - `GenericEphemeralVolume`: Enables ephemeral, inline volumes that support all features of normal volumes (can be provided by third-party storage vendors, storage capacity tracking, restore from snapshot, etc.). See [Ephemeral Volumes](/docs/concepts/storage/ephemeral-volumes/).
+- `GracefulNodeShutdown`: Enables support for graceful shutdown in kubelet. During a system shutdown, kubelet will attempt to detect the shutdown event and gracefully terminate pods running on the node. See [Graceful Node Shutdown](/docs/concepts/architecture/nodes/#graceful-node-shutdown) for more details.
 - `HugePages`: Enable the allocation and consumption of pre-allocated [huge pages](/docs/tasks/manage-hugepages/scheduling-hugepages/).
 - `HugePageStorageMediumSize`: Enable support for multiple sizes pre-allocated [huge pages](/docs/tasks/manage-hugepages/scheduling-hugepages/).
 - `HyperVContainer`: Enable [Hyper-V isolation](https://docs.microsoft.com/en-us/virtualization/windowscontainers/manage-containers/hyperv-container) for Windows containers.