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>
93 lines
2.4 KiB
Go
93 lines
2.4 KiB
Go
package health
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
func TestStatusIsHealthy(t *testing.T) {
|
|
// Helper for the new 6-field Status: all-true except the named one.
|
|
allBut := func(field string) Status {
|
|
s := Status{
|
|
Containerd: true, APIServer: true, NodeReady: true,
|
|
KubeSystemReady: true, ProbeURL: true, DiskWritable: true,
|
|
}
|
|
switch field {
|
|
case "Containerd":
|
|
s.Containerd = false
|
|
case "APIServer":
|
|
s.APIServer = false
|
|
case "NodeReady":
|
|
s.NodeReady = false
|
|
case "KubeSystemReady":
|
|
s.KubeSystemReady = false
|
|
case "ProbeURL":
|
|
s.ProbeURL = false
|
|
case "DiskWritable":
|
|
s.DiskWritable = false
|
|
}
|
|
return s
|
|
}
|
|
|
|
tests := []struct {
|
|
name string
|
|
status Status
|
|
wantHealth bool
|
|
}{
|
|
{"all healthy", allBut(""), true},
|
|
{"containerd down", allBut("Containerd"), false},
|
|
{"apiserver down", allBut("APIServer"), false},
|
|
{"node not ready", allBut("NodeReady"), false},
|
|
{"kube-system not ready", allBut("KubeSystemReady"), false},
|
|
{"probe URL failed", allBut("ProbeURL"), false},
|
|
{"disk not writable", allBut("DiskWritable"), false},
|
|
{"all down", Status{}, false},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
if got := tt.status.IsHealthy(); got != tt.wantHealth {
|
|
t.Errorf("IsHealthy() = %v, want %v", got, tt.wantHealth)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestNewChecker(t *testing.T) {
|
|
// Test defaults
|
|
c := NewChecker("", "", 0)
|
|
if c.kubeconfigPath != "/var/lib/kubesolo/pki/admin/admin.kubeconfig" {
|
|
t.Errorf("unexpected default kubeconfig: %s", c.kubeconfigPath)
|
|
}
|
|
if c.apiServerAddr != "127.0.0.1:6443" {
|
|
t.Errorf("unexpected default apiserver addr: %s", c.apiServerAddr)
|
|
}
|
|
if c.timeout != 120*time.Second {
|
|
t.Errorf("unexpected default timeout: %v", c.timeout)
|
|
}
|
|
|
|
// Test custom values
|
|
c = NewChecker("/custom/kubeconfig", "10.0.0.1:6443", 30*time.Second)
|
|
if c.kubeconfigPath != "/custom/kubeconfig" {
|
|
t.Errorf("expected custom kubeconfig, got %s", c.kubeconfigPath)
|
|
}
|
|
if c.apiServerAddr != "10.0.0.1:6443" {
|
|
t.Errorf("expected custom addr, got %s", c.apiServerAddr)
|
|
}
|
|
if c.timeout != 30*time.Second {
|
|
t.Errorf("expected 30s timeout, got %v", c.timeout)
|
|
}
|
|
}
|
|
|
|
func TestStatusMessage(t *testing.T) {
|
|
s := &Status{
|
|
Containerd: true,
|
|
APIServer: true,
|
|
NodeReady: true,
|
|
Message: "all checks passed",
|
|
}
|
|
if s.Message != "all checks passed" {
|
|
t.Errorf("unexpected message: %s", s.Message)
|
|
}
|
|
}
|