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
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>
126 lines
3.5 KiB
Go
126 lines
3.5 KiB
Go
package health
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"net/http"
|
|
"os"
|
|
"os/exec"
|
|
"path/filepath"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// kubeSystemSettleSeconds is how long all kube-system pods must hold a
|
|
// Running phase before we consider the cluster genuinely up. Catches the
|
|
// "pod just started, will crash-loop in 5s" case.
|
|
const kubeSystemSettleSeconds = 30
|
|
|
|
// CheckKubeSystemReady verifies that every pod in the kube-system namespace
|
|
// is in Running phase and has been Running for at least settle. Returns
|
|
// (ready, error). settle defaults to 30s when zero.
|
|
func (c *Checker) CheckKubeSystemReady(settle time.Duration) bool {
|
|
if settle == 0 {
|
|
settle = kubeSystemSettleSeconds * time.Second
|
|
}
|
|
if _, err := os.Stat(c.kubeconfigPath); err != nil {
|
|
return false
|
|
}
|
|
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
|
defer cancel()
|
|
|
|
// jsonpath emits one line per pod: <phase>|<startTime>
|
|
cmd := exec.CommandContext(ctx, "kubectl",
|
|
"--kubeconfig", c.kubeconfigPath,
|
|
"get", "pods", "-n", "kube-system",
|
|
"-o", `jsonpath={range .items[*]}{.status.phase}|{.status.startTime}{"\n"}{end}`,
|
|
)
|
|
out, err := cmd.Output()
|
|
if err != nil {
|
|
return false
|
|
}
|
|
lines := strings.Split(strings.TrimSpace(string(out)), "\n")
|
|
if len(lines) == 0 || lines[0] == "" {
|
|
// No pods reported. Conservatively treat as not-ready: kube-system
|
|
// is expected to host at least CoreDNS + pause.
|
|
return false
|
|
}
|
|
now := time.Now()
|
|
for _, line := range lines {
|
|
parts := strings.SplitN(line, "|", 2)
|
|
phase := strings.TrimSpace(parts[0])
|
|
if phase != "Running" {
|
|
return false
|
|
}
|
|
if len(parts) < 2 {
|
|
return false
|
|
}
|
|
start, perr := time.Parse(time.RFC3339, strings.TrimSpace(parts[1]))
|
|
if perr != nil {
|
|
return false
|
|
}
|
|
if now.Sub(start) < settle {
|
|
return false
|
|
}
|
|
}
|
|
return true
|
|
}
|
|
|
|
// CheckProbeURL fetches the given URL and reports whether it returned 200.
|
|
// Empty url returns (true, nil) — the check is opt-in.
|
|
func CheckProbeURL(url string) (bool, error) {
|
|
if url == "" {
|
|
return true, nil
|
|
}
|
|
client := &http.Client{Timeout: 5 * time.Second}
|
|
resp, err := client.Get(url)
|
|
if err != nil {
|
|
return false, fmt.Errorf("probe URL %s: %w", url, err)
|
|
}
|
|
defer resp.Body.Close()
|
|
return resp.StatusCode == http.StatusOK, nil
|
|
}
|
|
|
|
// CheckDiskWritable writes a small file under dataDir, fsyncs, reads it back,
|
|
// and removes it. Confirms the data partition is mounted read-write and the
|
|
// underlying disk is responsive. Empty dataDir defaults to /var/lib/kubesolo.
|
|
func CheckDiskWritable(dataDir string) (bool, error) {
|
|
if dataDir == "" {
|
|
dataDir = "/var/lib/kubesolo"
|
|
}
|
|
if _, err := os.Stat(dataDir); err != nil {
|
|
// Data partition not mounted? That's catastrophic but we shouldn't
|
|
// claim the disk is fine.
|
|
return false, fmt.Errorf("dataDir %s: %w", dataDir, err)
|
|
}
|
|
probe := filepath.Join(dataDir, ".update-probe")
|
|
want := []byte("kubesolo-os healthcheck probe")
|
|
|
|
f, err := os.Create(probe)
|
|
if err != nil {
|
|
return false, fmt.Errorf("create probe: %w", err)
|
|
}
|
|
defer os.Remove(probe)
|
|
|
|
if _, err := f.Write(want); err != nil {
|
|
f.Close()
|
|
return false, fmt.Errorf("write probe: %w", err)
|
|
}
|
|
if err := f.Sync(); err != nil {
|
|
f.Close()
|
|
return false, fmt.Errorf("fsync probe: %w", err)
|
|
}
|
|
if err := f.Close(); err != nil {
|
|
return false, fmt.Errorf("close probe: %w", err)
|
|
}
|
|
|
|
got, err := os.ReadFile(probe)
|
|
if err != nil {
|
|
return false, fmt.Errorf("read probe: %w", err)
|
|
}
|
|
if string(got) != string(want) {
|
|
return false, fmt.Errorf("probe content mismatch: got %q", got)
|
|
}
|
|
return true, nil
|
|
}
|