Files
kubesolo-os/update/cmd/healthcheck.go
Adolfo Delorenzo 9fb894c5af
Some checks failed
ARM64 Build / Build generic ARM64 disk image (push) Failing after 4s
CI / Go Tests (push) Successful in 1m29s
CI / Shellcheck (push) Successful in 48s
CI / Build Go Binaries (amd64, linux, linux-amd64) (push) Successful in 1m12s
CI / Build Go Binaries (arm64, linux, linux-arm64) (push) Has been cancelled
feat(update): pre-flight gates + deeper healthcheck + auto-rollback
Phase 8 of v0.3. Tightens the update lifecycle on both ends.

Pre-flight (apply.go, before any download):
- Free-space check on the passive partition: image size + 10% headroom must
  be available. Uses statfs(2) via the new pkg/partition.FreeBytes /
  HasFreeSpaceFor helpers (tests cover happy path, tiny request, huge
  request, missing path). Catches corrupted-FS and shrunk-partition cases
  before we destroy the existing slot data.
- Node-block-label check: refuses if the local K8s node carries the
  updates.kubesolo.io/block=true label. New pkg/health.CheckNodeBlocked
  shells out to kubectl per the project's zero-deps stance. Silently bypassed
  when no kubeconfig is reachable (air-gap case). Skipped by --force.

Healthcheck (extended via new pkg/health/extended.go + preflight.go):
- CheckKubeSystemReady waits until every kube-system pod has held the Running
  phase for >= N seconds (default 30). Catches "started ok, will crash-loop"
  bugs that a single-shot phase check misses.
- CheckProbeURL fetches an operator-supplied URL; 200 = pass. Wired through
  update.conf as healthcheck_url= and cloud-init updates.healthcheck_url.
- CheckDiskWritable writes/fsyncs/reads a 1-KiB probe under /var/lib/kubesolo.
  Always runs in healthcheck so a wedged data partition fails fast.
- pkg/health.Status grows KubeSystemReady, ProbeURL, DiskWritable booleans.
  Optional checks default to true in RunAll() so they don't block when
  unconfigured. health_test.go updated to the new 6-field shape.

Auto-rollback (healthcheck.go):
- state.UpdateState gains HealthCheckFailures (consecutive post-Activated
  failures). Reset on a clean pass.
- --auto-rollback-after N (also auto_rollback_after= in update.conf) triggers
  env.ForceRollback() when the failure count reaches the threshold. State
  transitions to RolledBack with a descriptive LastError. The command still
  exits with the healthcheck error; the operator/init is expected to reboot.
- Only fires while Phase == Activated. Doesn't second-guess a long-stable
  system that happens to fail one healthcheck.

config / opts / cloud-init plumbing:
- update.conf gains healthcheck_url= and auto_rollback_after= keys.
- New CLI flags: --healthcheck-url, --auto-rollback-after, --kube-system-settle.
- cloud-init full-config.yaml documents the new updates: subfields.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 19:08:30 -06:00

136 lines
4.7 KiB
Go

package cmd
import (
"fmt"
"log/slog"
"time"
"github.com/portainer/kubesolo-os/update/pkg/health"
"github.com/portainer/kubesolo-os/update/pkg/state"
)
// Healthcheck performs post-boot health verification.
// If all checks pass, it marks the boot as successful in GRUB.
// This should be run after every boot (typically via a systemd unit or
// init script) to confirm the system is healthy.
//
// State transition: Activated → Verifying → Success on pass, → Failed on fail.
// If state isn't in Activated (e.g. manual run on a long-stable system), the
// state file is left alone — healthcheck still does its job.
//
// When --auto-rollback-after N is set, consecutive post-Activated failures
// are counted in state.HealthCheckFailures. On the Nth failure, the agent
// calls Rollback() and the operator is expected to reboot (this command
// does not reboot the host — that's policy left to systemd/init).
func Healthcheck(args []string) error {
opts := parseOpts(args)
env := opts.NewBootEnv()
st, err := state.Load(opts.StatePath)
if err != nil {
slog.Warn("state file unreadable, starting fresh", "error", err)
st = state.New()
}
// Check if already marked successful
success, err := env.BootSuccess()
if err != nil {
slog.Warn("could not read boot_success", "error", err)
}
if success {
fmt.Println("Boot already marked successful")
return nil
}
// Only transition state if we're post-activation. Manual healthcheck on a
// long-stable system shouldn't reset Idle → Verifying.
postActivation := st.Phase == state.PhaseActivated
if postActivation {
if err := st.Transition(opts.StatePath, state.PhaseVerifying, "", ""); err != nil {
slog.Warn("state transition failed", "phase", state.PhaseVerifying, "error", err)
}
}
timeout := time.Duration(opts.TimeoutSecs) * time.Second
checker := health.NewChecker("", "", timeout)
checker.ProbeURL = opts.HealthcheckURL
if opts.KubeSystemSettle > 0 {
checker.KubeSystemSettle = time.Duration(opts.KubeSystemSettle) * time.Second
}
// Probe the data partition every healthcheck so a wedged disk fails fast.
checker.DataDir = "/var/lib/kubesolo"
slog.Info("running post-boot health checks",
"timeout", timeout,
"probe_url", checker.ProbeURL,
"kube_system_settle", checker.KubeSystemSettle)
status, err := checker.WaitForHealthy()
if err != nil {
fmt.Printf("Health check FAILED: %s\n", status.Message)
printStatusBreakdown(status)
fmt.Println("\nBoot NOT marked successful — system may roll back on next reboot")
if postActivation {
st.HealthCheckFailures++
_ = st.RecordError(opts.StatePath, fmt.Errorf("post-boot health check failed: %s", status.Message))
// Auto-rollback escalation. Only trigger when post-Activated;
// don't second-guess a healthy long-running system.
if opts.AutoRollbackAfter > 0 && st.HealthCheckFailures >= opts.AutoRollbackAfter {
slog.Warn("auto-rollback threshold reached",
"failures", st.HealthCheckFailures,
"threshold", opts.AutoRollbackAfter)
if rerr := env.ForceRollback(); rerr != nil {
slog.Error("auto-rollback failed", "error", rerr)
return err // return the original healthcheck error
}
if terr := st.Transition(opts.StatePath, state.PhaseRolledBack, "",
fmt.Sprintf("auto-rollback after %d healthcheck failures", st.HealthCheckFailures)); terr != nil {
slog.Warn("state transition failed", "phase", state.PhaseRolledBack, "error", terr)
}
fmt.Println("\nAuto-rollback triggered. Reboot to complete the rollback.")
}
}
return err
}
// Mark boot as successful
if err := env.MarkBootSuccess(); err != nil {
if postActivation {
_ = st.RecordError(opts.StatePath, fmt.Errorf("marking boot success: %w", err))
}
return fmt.Errorf("marking boot success: %w", err)
}
if postActivation {
// Reset failure counter on a clean pass.
st.HealthCheckFailures = 0
if err := st.Transition(opts.StatePath, state.PhaseSuccess, "", ""); err != nil {
slog.Warn("state transition failed", "phase", state.PhaseSuccess, "error", err)
}
}
fmt.Println("Health check PASSED — boot marked successful")
printStatusBreakdown(status)
return nil
}
// printStatusBreakdown emits a human-readable per-check summary. Only emits
// optional check lines when they actually ran.
func printStatusBreakdown(s *health.Status) {
fmt.Printf(" containerd: %v\n", s.Containerd)
fmt.Printf(" apiserver: %v\n", s.APIServer)
fmt.Printf(" node_ready: %v\n", s.NodeReady)
if !s.KubeSystemReady {
fmt.Printf(" kube-system pods: %v\n", s.KubeSystemReady)
}
if !s.ProbeURL {
fmt.Printf(" probe URL: %v\n", s.ProbeURL)
}
if !s.DiskWritable {
fmt.Printf(" disk writable: %v\n", s.DiskWritable)
}
}