mesh-catalog/modules/zfs/cmd/zfs-tools/keeper_test.go

package main

import (
	"context"
	"encoding/json"
	"errors"
	"net"
	"os"
	"path/filepath"
	"strings"
	"testing"
)

// A-37: the keeper answers a closed list of calls: an event of the module (never scrub.requested), a key of its three
// states, and one of three invokes (the service manager only for the module's two units); anything else is refused.
func TestTheKeeperAnswersOnlyItsClosedListOfCalls(t *testing.T) {
	var emitted []string
	var called, said []string
	st := memStates{}
	k := &Keeper{
		Emit:   func(kind string, body any) error { emitted = append(emitted, kind); return nil },
		States: st,
		Call: func(key string, body any) (json.RawMessage, error) {
			called = append(called, key)
			return json.RawMessage(`{"ok":true}`), nil
		},
		Finding: func(event string, body json.RawMessage, id string) error {
			said = append(said, event+"/"+id)
			return nil
		},
	}
	req := func(op, kind, state, key, body string) KeeperRequest {
		return KeeperRequest{Op: op, Kind: kind, State: state, Key: key, Body: json.RawMessage(body)}
	}
	cases := []struct {
		name    string
		r       KeeperRequest
		refused string
	}{
		{"emit a kind", req(OpEmit, EventApplied, "", "", `{"key":"x"}`), ""},
		{"emit the scrub's kind", req(OpEmit, EventScrubRequested, "", "", `{}`), "not an event"},
		{"emit another module's kind", req(OpEmit, "package.changed", "", "", `{}`), "not an event"},
		{"put applied", req(OpPut, "", StateApplied, "hostid", `{"outcome":"applied"}`), ""},
		{"put schedule", req(OpPut, "", StateSchedule, "paused", `{}`), ""},
		{"put another state", req(OpPut, "", "holds", "x", `{}`), "not a state"},
		{"get findings", req(OpGet, "", StateFindings, "k", ``), ""},
		{"keys of another state", req(OpKeys, "", "mirrors", "", ``), "not a state"},
		{"delete schedule", req(OpDelete, "", StateSchedule, "paused", ``), ""},
		{"invoke record", req(OpInvoke, "", "", ToolRecord, `{}`), ""},
		{"invoke schedule", req(OpInvoke, "", "", ToolSchedule, `{}`), ""},
		{"start the run", req(OpInvoke, "", "", "seat:node-service-manager.start@ace", `{"scope":"system","unit":"zfs-mesh-run.service"}`), ""},
		{"start the apply", req(OpInvoke, "", "", "seat:node-service-manager.start@ace", `{"scope":"system","unit":"zfs-config-apply.service"}`), ""},
		{"start another unit", req(OpInvoke, "", "", "seat:node-service-manager.start@ace", `{"scope":"system","unit":"sshd.service"}`), "starts only"},
		{"stop a unit", req(OpInvoke, "", "", "seat:node-service-manager.stop@ace", `{"scope":"system","unit":"zfs-mesh-run.service"}`), "not one of the three"},
		{"invoke a tool of the module", req(OpInvoke, "", "", "zfs.zfs_snapshot", `{}`), "not one of the three"},
		{"another op", req("shell", "", "", "", ``), "not a call"},
		// A-339, A-340: the findings writer's three events, and no other, on the finding stream.
		{"say a finding written", KeeperRequest{Op: OpFinding, Kind: "finding-written", Body: json.RawMessage(`{}`), ID: "w1"}, ""},
		{"say the findings stated", KeeperRequest{Op: OpFinding, Kind: "findings-stated", Body: json.RawMessage(`{}`), ID: "s1"}, ""},
		{"say another event as a finding", KeeperRequest{Op: OpFinding, Kind: EventApplied, Body: json.RawMessage(`{}`)}, "not an event of the findings writer"},
	}
	for _, c := range cases {
		a := k.Do(c.r)
		if (c.refused == "") != (a.Error == "") || (c.refused != "" && !strings.Contains(a.Error, c.refused)) {
			t.Errorf("%s: %+v", c.name, a)
		}
	}
	if len(said) != 2 || said[0] != "finding-written/w1" {
		t.Errorf("said %v", said)
	}
	if len(emitted) != 1 || len(called) != 4 {
		t.Errorf("emitted %v, called %v", emitted, called)
	}
	if _, left := st["applied/hostid"]; !left {
		t.Errorf("the put was not kept")
	}
}

// shortTempDir is a directory in the test's temporary directory, or in /tmp when a socket in it (`k/k.sock`) would pass 100
// characters, the most a unix socket path takes, so a long TMPDIR cannot fail the bind.
func shortTempDir(prefix string) (string, error) {
	dir, err := os.MkdirTemp("", prefix)
	if err != nil || len(filepath.Join(dir, "k", "k.sock")) <= 100 {
		return dir, err
	}
	os.RemoveAll(dir)
	return os.MkdirTemp("/tmp", prefix)
}

// A-37: only root opens the socket; a root process says and reads through it as through a bus of its own, and with no
// keeper answering it acts as with the bus down, with a warning (A-8).
func TestOnlyRootOpensTheKeepersSocketAndANeedlessKeeperIsTheBusDown(t *testing.T) {
	st := memStates{}
	uid := 0
	k := &Keeper{Emit: func(string, any) error { return nil }, States: st,
		Call:   func(string, any) (json.RawMessage, error) { return nil, errors.New("down") },
		PeerOf: func(net.Conn) (int, error) { return uid, nil }}
	dir, err := shortTempDir("zk")
	if err != nil {
		t.Fatal(err)
	}
	defer os.RemoveAll(dir)
	sock := filepath.Join(dir, "k", "k.sock")
	l, err := Listen(sock)
	if err != nil {
		t.Fatal(err)
	}
	ctx, stop := context.WithCancel(context.Background())
	defer stop()
	go k.Serve(ctx, l)
	c := keeperClient{sock: sock}
	if err := c.Put(StateSchedule, "snapshots", map[string]string{"by": "x"}); err != nil {
		t.Fatal(err)
	}
	if keys, err := c.Keys(StateSchedule); err != nil || len(keys) != 1 || keys[0] != "snapshots" {
		t.Errorf("%v %v", keys, err)
	}
	if v, ok, err := c.Get(StateSchedule, "snapshots"); err != nil || !ok || !strings.Contains(string(v), `"by":"x"`) {
		t.Errorf("%s %v %v", v, ok, err)
	}
	if _, err := c.call(ToolSchedule, map[string]any{}); err == nil || !strings.Contains(err.Error(), "down") {
		t.Errorf("an invoke that failed: %v", err)
	}
	uid = 1000
	if err := c.Put(StateSchedule, "x", 1); err == nil || !strings.Contains(err.Error(), "only root") {
		t.Errorf("a peer that is not root: %v", err)
	}
	if _, left := st["schedule/x"]; left {
		t.Errorf("a refused peer's call was read")
	}
	// No socket variable: the machine keeps no bus and says so.
	t.Setenv(KeeperSocketEnv, "")
	m := newFake(t).machine()
	m.Emit = nil
	m.JoinBus()
	if m.Emit != nil || m.States != nil || len(m.Warnings) != 1 || !strings.Contains(m.Warnings[0], "bus is taken as down") {
		t.Errorf("no keeper: %+v", m.Warnings)
	}
	// A keeper not yet up: the process joins, its calls fail, and the same process uses the keeper once it is up.
	late := filepath.Join(dir, "late.sock")
	t.Setenv(KeeperSocketEnv, late)
	ml := newFake(t).machine()
	ml.JoinBus()
	if ml.States == nil {
		t.Fatalf("a keeper not up yet must not take the bus as down: %+v", ml.Warnings)
	}
	if _, err := ml.States.Keys(StateSchedule); err == nil {
		t.Errorf("no keeper up, yet a call answered")
	}
	ll, err := Listen(late)
	if err != nil {
		t.Fatal(err)
	}
	lctx, lcancel := context.WithCancel(context.Background())
	defer lcancel()
	go (&Keeper{Emit: func(string, any) error { return nil }, States: memStates{}, PeerOf: func(net.Conn) (int, error) { return 0, nil },
		Call: func(string, any) (json.RawMessage, error) { return nil, nil }}).Serve(lctx, ll)
	if _, err := ml.States.Keys(StateSchedule); err != nil {
		t.Errorf("a keeper that came up later is not used: %v", err)
	}
	t.Setenv(KeeperSocketEnv, sock)
	uid = 0
	m2 := newFake(t).machine()
	m2.JoinBus()
	if m2.Emit == nil || m2.States == nil || m2.Call == nil || m2.keeper == nil {
		t.Errorf("a keeper answering: the bus is up")
	}
}

// A-37: a root process whose keeper does not answer acts as with the bus down and says so, once, in a warning, for the
// hand acts, the forgetting of applied keys and the pause alike.
func TestAKeeperThatDoesNotAnswerIsWarnedOnce(t *testing.T) {
	dir, err := shortTempDir("kd")
	if err != nil {
		t.Fatal(err)
	}
	defer os.RemoveAll(dir)
	t.Setenv(KeeperSocketEnv, filepath.Join(dir, "none.sock"))
	m := newFake(t).machine()
	m.JoinBus()
	if got := m.handActs(); got != nil {
		t.Errorf("hand acts with no keeper: %v", got)
	}
	if len(m.Warnings) != 1 || !strings.Contains(m.Warnings[0], "bus is taken as down") {
		t.Fatalf("hand acts: %v", m.Warnings)
	}
	m.forget(&Config{})
	if m.Paused() {
		t.Errorf("paused with no keeper")
	}
	if len(m.Warnings) != 1 {
		t.Errorf("said more than once: %v", m.Warnings)
	}
}