Irbe Krumina b406f209c3
cmd/{k8s-operator,containerboot},kube: ensure egress ProxyGroup proxies don't terminate while cluster traffic is still routed to them (#14436)
cmd/{containerboot,k8s-operator},kube: add preshutdown hook for egress PG proxies

This change is part of work towards minimizing downtime during update
rollouts of egress ProxyGroup replicas.
This change:
- updates the containerboot health check logic to return Pod IP in headers,
if set
- always runs the health check for egress PG proxies
- updates ClusterIP Services created for PG egress endpoints to include
the health check endpoint
- implements preshutdown endpoint in proxies. The preshutdown endpoint
logic waits till, for all currently configured egress services, the ClusterIP
Service health check endpoint is no longer returned by the shutting-down Pod
(by looking at the new Pod IP header).
- ensures that kubelet is configured to call the preshutdown endpoint

This reduces the possibility that, as replicas are terminated during an update,
a replica gets terminated to which cluster traffic is still being routed via
the ClusterIP Service because kube proxy has not yet updated routig rules.
This is not a perfect check as in practice, it only checks that the kube
proxy on the node on which the proxy runs has updated rules. However, overall
this might be good enough.

The preshutdown logic is disabled if users have configured a custom health check
port via TS_LOCAL_ADDR_PORT env var. This change throws a warnign if so and in
future setting of that env var for operator proxies might be disallowed (as users
shouldn't need to configure this for a Pod directly).
This is backwards compatible with earlier proxy versions.

Updates tailscale/tailscale#14326


Signed-off-by: Irbe Krumina <irbe@tailscale.com>
2025-01-29 07:35:50 +00:00

52 lines
2.8 KiB
Go

// Copyright (c) Tailscale Inc & AUTHORS
// SPDX-License-Identifier: BSD-3-Clause
package kubetypes
const (
// Hostinfo App values for the Tailscale Kubernetes Operator components.
AppOperator = "k8s-operator"
AppAPIServerProxy = "k8s-operator-proxy"
AppIngressProxy = "k8s-operator-ingress-proxy"
AppIngressResource = "k8s-operator-ingress-resource"
AppEgressProxy = "k8s-operator-egress-proxy"
AppConnector = "k8s-operator-connector-resource"
AppProxyGroupEgress = "k8s-operator-proxygroup-egress"
AppProxyGroupIngress = "k8s-operator-proxygroup-ingress"
// Clientmetrics for Tailscale Kubernetes Operator components
MetricIngressProxyCount = "k8s_ingress_proxies" // L3
MetricIngressResourceCount = "k8s_ingress_resources" // L7
MetricIngressPGResourceCount = "k8s_ingress_pg_resources" // L7 on ProxyGroup
MetricEgressProxyCount = "k8s_egress_proxies"
MetricConnectorResourceCount = "k8s_connector_resources"
MetricConnectorWithSubnetRouterCount = "k8s_connector_subnetrouter_resources"
MetricConnectorWithExitNodeCount = "k8s_connector_exitnode_resources"
MetricConnectorWithAppConnectorCount = "k8s_connector_appconnector_resources"
MetricNameserverCount = "k8s_nameserver_resources"
MetricRecorderCount = "k8s_recorder_resources"
MetricEgressServiceCount = "k8s_egress_service_resources"
MetricProxyGroupEgressCount = "k8s_proxygroup_egress_resources"
MetricProxyGroupIngressCount = "k8s_proxygroup_ingress_resources"
// Keys that containerboot writes to state file that can be used to determine its state.
// fields set in Tailscale state Secret. These are mostly used by the Tailscale Kubernetes operator to determine
// the state of this tailscale device.
KeyDeviceID string = "device_id" // node stable ID of the device
KeyDeviceFQDN string = "device_fqdn" // device's tailnet hostname
KeyDeviceIPs string = "device_ips" // device's tailnet IPs
KeyPodUID string = "pod_uid" // Pod UID
// KeyCapVer contains Tailscale capability version of this proxy instance.
KeyCapVer string = "tailscale_capver"
// KeyHTTPSEndpoint is a name of a field that can be set to the value of any HTTPS endpoint currently exposed by
// this device to the tailnet. This is used by the Kubernetes operator Ingress proxy to communicate to the operator
// that cluster workloads behind the Ingress can now be accessed via the given DNS name over HTTPS.
KeyHTTPSEndpoint string = "https_endpoint"
ValueNoHTTPS string = "no-https"
// Pod's IPv4 address header key as returned by containerboot health check endpoint.
PodIPv4Header string = "Pod-IPv4"
EgessServicesPreshutdownEP = "/internal-egress-services-preshutdown"
)