Files
oikos/internal/checkdefaults/build_test.go
dtoro 7160eee1e1
Some checks are pending
ci / build-test (push) Waiting to run
ci / docker-build (push) Waiting to run
ci / web (push) Waiting to run
Desktop App / Build Linux (amd64) (push) Waiting to run
Desktop App / Attach to Release (push) Blocked by required conditions
feat: add corosync quorum health check for proxmox-host entities
Adds pvecm_quorum_check.sh probe script and wires it into the
checkdefaults system as a new 'quorum' monitoring kind on proxmox-host
entities. Runs every 60s via ssh-script, surfaces unhealthy signal when
cluster loses quorum.

Closes the monitoring blind spot that let the 2026-08-12 3.5h corosync
flapping outage go undetected (ping passed, cluster was non-quorate).

Changes:
- seeds/ontology.yaml: proxmox-host declares monitoring: [quorum]
- internal/checkdefaults/defaults.go: KindQuorum builder
- internal/checkdefaults/build_test.go: 2 new test cases
- checks/pvecm_quorum_check.sh: new probe (deployed to hubris + strong)
- VERSION: 0.30.2 -> 0.31.0
2026-08-12 20:18:03 +02:00

203 lines
8.0 KiB
Go

package checkdefaults
import (
"reflect"
"strings"
"testing"
"github.com/dtoro/oikos/internal/ontology"
)
// Table-driven coverage of every implemented buildKind branch and the ssh()
// helper's user/port/args propagation. The previous tests exercised only
// ping/process/http/resource; updates, capacity, backup, cert-expiry,
// vm-status and dns were unverified.
func TestBuildKindAllImplementedKinds(t *testing.T) {
host := "10.0.0.5"
cases := []struct {
name string
kind string
target Target
attrs map[string]any
host string
wantSkip bool // true → expect a reason and zero defs
wantDefs int
wantKind string
wantKey string // a config key to assert
wantVal any // its expected value
wantReason string // substring when skipping
wantInterv int32 // expected interval on the (single) produced def
}{
{
name: "ping with host", kind: KindPing, host: host,
wantDefs: 1, wantKind: "ping", wantKey: "host", wantVal: host, wantInterv: 30,
},
{name: "ping no host skips", kind: KindPing, wantSkip: true, wantReason: "no address"},
{
name: "resource expands to four ssh scripts", kind: KindResource, host: host,
wantDefs: 4, wantKind: "ssh-script", wantKey: "host", wantVal: host, wantInterv: 60,
},
{name: "resource no host skips", kind: KindResource, wantSkip: true, wantReason: "no address"},
{
name: "updates is daily", kind: KindUpdates, host: host,
wantDefs: 1, wantKind: "ssh-script", wantKey: "script", wantVal: "updates_check.sh", wantInterv: 86400,
},
{name: "updates no host skips", kind: KindUpdates, wantSkip: true, wantReason: "no address"},
{
name: "capacity is one disk script", kind: KindCapacity, host: host,
wantDefs: 1, wantKind: "ssh-script", wantKey: "script", wantVal: "disk_usage_check.sh", wantInterv: 60,
},
{name: "capacity no host skips", kind: KindCapacity, wantSkip: true, wantReason: "no address"},
{
name: "backup needs path and host", kind: KindBackup, host: host,
attrs: map[string]any{"path": "/backups/db"},
wantDefs: 1, wantKind: "backup-freshness", wantKey: "path", wantVal: "/backups/db", wantInterv: 86400,
},
{name: "backup without path skips", kind: KindBackup, host: host, wantSkip: true, wantReason: "no path"},
{name: "backup without host skips", kind: KindBackup, attrs: map[string]any{"path": "/x"}, wantSkip: true, wantReason: "no address"},
{
name: "backup honors backup_max_age_s override", kind: KindBackup, host: host,
attrs: map[string]any{"path": "/x", "backup_max_age_s": float64(3600)},
wantDefs: 1, wantKey: "max_age_s", wantVal: 3600,
},
{
name: "cert-expiry from hostname attr", kind: KindCertExpiry,
attrs: map[string]any{"hostname": "media.hubris.network"},
wantDefs: 1, wantKind: "cert-expiry", wantKey: "host", wantVal: "media.hubris.network", wantInterv: 3600,
},
{
name: "cert-expiry from dotted name", kind: KindCertExpiry, target: Target{Name: "media.hubris.network"},
wantDefs: 1, wantKey: "host", wantVal: "media.hubris.network",
},
{
name: "cert-expiry propagates dial attr", kind: KindCertExpiry,
attrs: map[string]any{"hostname": "media.hubris.network", "dial": "10.0.0.2"},
wantDefs: 1, wantKey: "dial", wantVal: "10.0.0.2",
},
{name: "cert-expiry without a host name skips", kind: KindCertExpiry, target: Target{Name: "jellyfin"}, wantSkip: true, wantReason: "no hostname"},
{
name: "vm-status needs pve_id", kind: KindVMStatus, attrs: map[string]any{"pve_id": float64(101)},
wantDefs: 1, wantKind: "vm-status", wantInterv: 60,
},
{name: "vm-status without pve_id skips", kind: KindVMStatus, wantSkip: true, wantReason: "no pve_id"},
{
name: "dns resolves entity name", kind: KindDNS, target: Target{Name: "hubris.network"},
wantDefs: 1, wantKind: "dns", wantKey: "name", wantVal: "hubris.network", wantInterv: 300,
},
{name: "dns without a name skips", kind: KindDNS, target: Target{}, wantSkip: true, wantReason: "no name"},
{
name: "quorum runs pvecm script via ssh", kind: KindQuorum, host: host,
wantDefs: 1, wantKind: "ssh-script", wantKey: "script", wantVal: "pvecm_quorum_check.sh", wantInterv: 60,
},
{name: "quorum no host skips", kind: KindQuorum, wantSkip: true, wantReason: "no address"},
{name: "unknown kind skips", kind: "telepathy", host: host, wantSkip: true, wantReason: "no builder"},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
defs, reason := buildKind(c.kind, c.target, c.attrs, c.host, "root", 22)
if c.wantSkip {
if len(defs) != 0 {
t.Fatalf("expected zero defs, got %d", len(defs))
}
if c.wantReason != "" && !strings.Contains(reason, c.wantReason) {
t.Errorf("reason = %q, want substring %q", reason, c.wantReason)
}
return
}
if len(defs) != c.wantDefs {
t.Fatalf("got %d defs (%s), want %d", len(defs), reason, c.wantDefs)
}
if reason != "" {
t.Errorf("unexpected skip reason: %q", reason)
}
if c.wantKind != "" {
if got := defs[0].kind; got != c.wantKind {
t.Errorf("kind = %q, want %q", got, c.wantKind)
}
}
if c.wantKey != "" {
if got := defs[0].config[c.wantKey]; !reflect.DeepEqual(got, c.wantVal) {
t.Errorf("config[%q] = %v (%T), want %v (%T)", c.wantKey, got, got, c.wantVal, c.wantVal)
}
}
if c.wantInterv != 0 && defs[0].interval != c.wantInterv {
t.Errorf("interval = %d, want %d", defs[0].interval, c.wantInterv)
}
})
}
}
// ssh() must add user/port/args only when they differ from the root/22/empty
// defaults, so generated configs stay minimal and stable across re-seeds.
func TestBuildKindSSHOnlyEmitsNonDefaultUserPortArgs(t *testing.T) {
t.Run("default root 22 omits user and port", func(t *testing.T) {
defs, _ := buildKind(KindResource, Target{}, nil, "10.0.0.1", "root", 22)
for _, d := range defs {
if _, ok := d.config["user"]; ok {
t.Errorf("root should not emit user: %v", d.config)
}
if _, ok := d.config["port"]; ok {
t.Errorf("port 22 should not emit port: %v", d.config)
}
}
})
t.Run("non-root user and non-22 port are emitted", func(t *testing.T) {
defs, _ := buildKind(KindResource, Target{}, nil, "10.0.0.1", "oikos", 2222)
if defs[0].config["user"] != "oikos" {
t.Errorf("user = %v, want oikos", defs[0].config["user"])
}
if defs[0].config["port"] != 2222 {
t.Errorf("port = %v, want 2222", defs[0].config["port"])
}
})
t.Run("process unit name lands in args", func(t *testing.T) {
defs, _ := buildKind(KindProcess, Target{Name: "jellyfin"}, nil, "10.0.0.1", "root", 22)
if defs[0].config["args"] != "jellyfin" {
t.Errorf("args = %v, want jellyfin", defs[0].config["args"])
}
})
}
// resolveMonitoringAttr implements the entity-level `monitoring` override
// (project decision health_checks.monitoring_override): "none"/"" opts out,
// a kind-list replaces the type defaults, anything else falls back.
func TestResolveMonitoringAttr(t *testing.T) {
fallback := ontology.MonitoringResolution{Declared: true, Kinds: []string{"ping"}, Source: "type"}
cases := []struct {
name string
in any
want ontology.MonitoringResolution
}{
{"none opts out", "none", ontology.MonitoringResolution{Declared: true, Source: "attribute"}},
{"empty opts out", "", ontology.MonitoringResolution{Declared: true, Source: "attribute"}},
{
"kind list overrides",
[]any{"http", "process"},
ontology.MonitoringResolution{Declared: true, Kinds: []string{"http", "process"}, Source: "attribute"},
},
{"list drops empty and non-string entries", []any{"http", "", 7, "dns"}, ontology.MonitoringResolution{Declared: true, Kinds: []string{"http", "dns"}, Source: "attribute"}},
{"non-string scalar falls back to type default", float64(42), fallback},
{"nil falls back", nil, fallback},
{"unrecognized string falls back", "weird", fallback},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
got := resolveMonitoringAttr(c.in, fallback)
if !reflect.DeepEqual(got, c.want) {
t.Errorf("resolveMonitoringAttr(%v) = %+v, want %+v", c.in, got, c.want)
}
})
}
}