cmd/{containerboot,k8s-operator}: use state Secret for checking device auth (#16328)

Previously, the operator checked the ProxyGroup status fields for
information on how many of the proxies had successfully authed. Use
their state Secrets instead as a more reliable source of truth.

containerboot has written device_fqdn and device_ips keys to the
state Secret since inception, and pod_uid since 1.78.0, so there's
no need to use the API for that data. Read it from the state Secret
for consistency. However, to ensure we don't read data from a
previous run of containerboot, make sure we reset containerboot's
state keys on startup.

One other knock-on effect of that is ProxyGroups can briefly be
marked not Ready while a Pod is restarting. Introduce a new
ProxyGroupAvailable condition to more accurately reflect
when downstream controllers can implement flows that rely on a
ProxyGroup having at least 1 proxy Pod running.

Fixes #16327

Change-Id: I026c18e9d23e87109a471a87b8e4fb6271716a66

Signed-off-by: Tom Proctor <tomhjp@users.noreply.github.com>
This commit is contained in:
Tom Proctor
2025-06-27 18:10:04 +01:00
committed by GitHub
parent f81baa2d56
commit 711698f5a9
19 changed files with 373 additions and 202 deletions

View File

@@ -188,6 +188,14 @@ func run() error {
if err := cfg.setupKube(bootCtx, kc); err != nil {
return fmt.Errorf("error setting up for running on Kubernetes: %w", err)
}
// Clear out any state from previous runs of containerboot. Check
// hasKubeStateStore because although we know we're in kube, that
// doesn't guarantee the state store is properly configured.
if hasKubeStateStore(cfg) {
if err := kc.resetContainerbootState(bootCtx, cfg.PodUID); err != nil {
return fmt.Errorf("error clearing previous state from Secret: %w", err)
}
}
}
client, daemonProcess, err := startTailscaled(bootCtx, cfg)
@@ -367,11 +375,6 @@ authLoop:
if err := client.SetServeConfig(ctx, new(ipn.ServeConfig)); err != nil {
return fmt.Errorf("failed to unset serve config: %w", err)
}
if hasKubeStateStore(cfg) {
if err := kc.storeHTTPSEndpoint(ctx, ""); err != nil {
return fmt.Errorf("failed to update HTTPS endpoint in tailscale state: %w", err)
}
}
}
if hasKubeStateStore(cfg) && isTwoStepConfigAuthOnce(cfg) {
@@ -384,12 +387,6 @@ authLoop:
}
}
if hasKubeStateStore(cfg) {
if err := kc.storeCapVerUID(ctx, cfg.PodUID); err != nil {
return fmt.Errorf("storing capability version and UID: %w", err)
}
}
w, err = client.WatchIPNBus(ctx, ipn.NotifyInitialNetMap|ipn.NotifyInitialState)
if err != nil {
return fmt.Errorf("rewatching tailscaled for updates after auth: %w", err)