Merge pull request #2661 from hashicorp/f-node-id

Adds basic support for node IDs.

api/agent_test.go

@@ -657,7 +657,7 @@ func TestAgent_Monitor(t *testing.T) {
 	// Wait for the first log message and validate it
 	select {
 	case log := <-logCh:
-		if !strings.Contains(log, "[INFO] raft: Initial configuration") {
+		if !strings.Contains(log, "[INFO]") {
 			t.Fatalf("bad: %q", log)
 		}
 	case <-time.After(10 * time.Second):

api/catalog.go

@@ -1,13 +1,15 @@
 package api
 
 type Node struct {
+	ID              string
 	Node            string
 	Address         string
 	TaggedAddresses map[string]string
 	Meta            map[string]string
 }
 
 type CatalogService struct {
+	ID                       string
 	Node                     string
 	Address                  string
 	TaggedAddresses          map[string]string
@@ -28,6 +30,7 @@ type CatalogNode struct {
 }
 
 type CatalogRegistration struct {
+	ID              string
 	Node            string
 	Address         string
 	TaggedAddresses map[string]string
@@ -39,7 +42,7 @@ type CatalogRegistration struct {
 
 type CatalogDeregistration struct {
 	Node       string
-	Address    string
+	Address    string // Obsolete.
 	Datacenter string
 	ServiceID  string
 	CheckID    string

command/agent/agent.go

@@ -224,7 +224,6 @@ func Create(config *Config, logOutput io.Writer, logWriter *logger.LogWriter,
 		shutdownCh:     make(chan struct{}),
 		endpoints:      make(map[string]string),
 	}
-
 	if err := agent.resolveTmplAddrs(); err != nil {
 		return nil, err
 	}
@@ -236,6 +235,12 @@ func Create(config *Config, logOutput io.Writer, logWriter *logger.LogWriter,
 	}
 	agent.acls = acls
 
+	// Retrieve or generate the node ID before setting up the rest of the
+	// agent, which depends on it.
+	if err := agent.setupNodeID(config); err != nil {
+		return nil, fmt.Errorf("Failed to setup node ID: %v", err)
+	}
+
 	// Initialize the local state.
 	agent.state.Init(config, agent.logger)
 
@@ -303,6 +308,9 @@ func (a *Agent) consulConfig() *consul.Config {
 		base = consul.DefaultConfig()
 	}
 
+	// This is set when the agent starts up
+	base.NodeID = a.config.NodeID
+
 	// Apply dev mode
 	base.DevMode = a.config.DevMode
 
@@ -600,6 +608,67 @@ func (a *Agent) setupClient() error {
 	return nil
 }
 
+// setupNodeID will pull the persisted node ID, if any, or create a random one
+// and persist it.
+func (a *Agent) setupNodeID(config *Config) error {
+	// If they've configured a node ID manually then just use that, as
+	// long as it's valid.
+	if config.NodeID != "" {
+		if _, err := uuid.ParseUUID(string(config.NodeID)); err != nil {
+			return err
+		}
+
+		return nil
+	}
+
+	// For dev mode we have no filesystem access so just make a GUID.
+	if a.config.DevMode {
+		id, err := uuid.GenerateUUID()
+		if err != nil {
+			return err
+		}
+
+		config.NodeID = types.NodeID(id)
+		a.logger.Printf("[INFO] agent: Generated unique node ID %q for this agent (will not be persisted in dev mode)", config.NodeID)
+		return nil
+	}
+
+	// Load saved state, if any. Since a user could edit this, we also
+	// validate it.
+	fileID := filepath.Join(config.DataDir, "node-id")
+	if _, err := os.Stat(fileID); err == nil {
+		rawID, err := ioutil.ReadFile(fileID)
+		if err != nil {
+			return err
+		}
+
+		nodeID := strings.TrimSpace(string(rawID))
+		if _, err := uuid.ParseUUID(nodeID); err != nil {
+			return err
+		}
+
+		config.NodeID = types.NodeID(nodeID)
+	}
+
+	// If we still don't have a valid node ID, make one.
+	if config.NodeID == "" {
+		id, err := uuid.GenerateUUID()
+		if err != nil {
+			return err
+		}
+		if err := lib.EnsurePath(fileID, false); err != nil {
+			return err
+		}
+		if err := ioutil.WriteFile(fileID, []byte(id), 0600); err != nil {
+			return err
+		}
+
+		config.NodeID = types.NodeID(id)
+		a.logger.Printf("[INFO] agent: Generated unique node ID %q for this agent (persisted)", config.NodeID)
+	}
+	return nil
+}
+
 // setupKeyrings is used to initialize and load keyrings during agent startup
 func (a *Agent) setupKeyrings(config *consul.Config) error {
 	fileLAN := filepath.Join(a.config.DataDir, serfLANKeyring)

command/agent/agent_test.go

@@ -18,6 +18,8 @@ import (
 	"github.com/hashicorp/consul/consul/structs"
 	"github.com/hashicorp/consul/logger"
 	"github.com/hashicorp/consul/testutil"
+	"github.com/hashicorp/consul/types"
+	"github.com/hashicorp/go-uuid"
 	"github.com/hashicorp/raft"
 	"strings"
 )
@@ -308,6 +310,71 @@ func TestAgent_ReconnectConfigSettings(t *testing.T) {
 	}()
 }
 
+func TestAgent_NodeID(t *testing.T) {
+	c := nextConfig()
+	dir, agent := makeAgent(t, c)
+	defer os.RemoveAll(dir)
+	defer agent.Shutdown()
+
+	// The auto-assigned ID should be valid.
+	id := agent.consulConfig().NodeID
+	if _, err := uuid.ParseUUID(string(id)); err != nil {
+		t.Fatalf("err: %v", err)
+	}
+
+	// Running again should get the same ID (persisted in the file).
+	c.NodeID = ""
+	if err := agent.setupNodeID(c); err != nil {
+		t.Fatalf("err: %v", err)
+	}
+	if newID := agent.consulConfig().NodeID; id != newID {
+		t.Fatalf("bad: %q vs %q", id, newID)
+	}
+
+	// Set an invalid ID via config.
+	c.NodeID = types.NodeID("nope")
+	err := agent.setupNodeID(c)
+	if err == nil || !strings.Contains(err.Error(), "uuid string is wrong length") {
+		t.Fatalf("err: %v", err)
+	}
+
+	// Set a valid ID via config.
+	newID, err := uuid.GenerateUUID()
+	if err != nil {
+		t.Fatalf("err: %v", err)
+	}
+	c.NodeID = types.NodeID(newID)
+	if err := agent.setupNodeID(c); err != nil {
+		t.Fatalf("err: %v", err)
+	}
+	if id := agent.consulConfig().NodeID; string(id) != newID {
+		t.Fatalf("bad: %q vs. %q", id, newID)
+	}
+
+	// Set an invalid ID via the file.
+	fileID := filepath.Join(c.DataDir, "node-id")
+	if err := ioutil.WriteFile(fileID, []byte("adf4238a!882b!9ddc!4a9d!5b6758e4159e"), 0600); err != nil {
+		t.Fatalf("err: %v", err)
+	}
+	c.NodeID = ""
+	err = agent.setupNodeID(c)
+	if err == nil || !strings.Contains(err.Error(), "uuid is improperly formatted") {
+		t.Fatalf("err: %v", err)
+	}
+
+	// Set a valid ID via the file.
+	if err := ioutil.WriteFile(fileID, []byte("adf4238a-882b-9ddc-4a9d-5b6758e4159e"), 0600); err != nil {
+		t.Fatalf("err: %v", err)
+	}
+	c.NodeID = ""
+	if err := agent.setupNodeID(c); err != nil {
+		t.Fatalf("err: %v", err)
+	}
+	if id := agent.consulConfig().NodeID; string(id) != "adf4238a-882b-9ddc-4a9d-5b6758e4159e" {
+		t.Fatalf("bad: %q vs. %q", id, newID)
+	}
+}
+
 func TestAgent_AddService(t *testing.T) {
 	dir, agent := makeAgent(t, nextConfig())
 	defer os.RemoveAll(dir)

command/agent/command.go

@@ -92,6 +92,7 @@ func (c *Command) readConfig() *Config {
 
 	cmdFlags.StringVar(&cmdConfig.LogLevel, "log-level", "", "log level")
 	cmdFlags.StringVar(&cmdConfig.NodeName, "node", "", "node name")
+	cmdFlags.StringVar((*string)(&cmdConfig.NodeID), "node-id", "", "node ID")
 	cmdFlags.StringVar(&dcDeprecated, "dc", "", "node datacenter (deprecated: use 'datacenter' instead)")
 	cmdFlags.StringVar(&cmdConfig.Datacenter, "datacenter", "", "node datacenter")
 	cmdFlags.StringVar(&cmdConfig.DataDir, "data-dir", "", "path to the data directory")
@@ -1115,6 +1116,7 @@ func (c *Command) Run(args []string) int {
 
 	c.Ui.Output("Consul agent running!")
 	c.Ui.Info(fmt.Sprintf("       Version: '%s'", c.HumanVersion))
+	c.Ui.Info(fmt.Sprintf("       Node ID: '%s'", config.NodeID))
 	c.Ui.Info(fmt.Sprintf("     Node name: '%s'", config.NodeName))
 	c.Ui.Info(fmt.Sprintf("    Datacenter: '%s'", config.Datacenter))
 	c.Ui.Info(fmt.Sprintf("        Server: %v (bootstrap: %v)", config.Server, config.Bootstrap))

command/agent/config.go

@@ -14,6 +14,7 @@ import (
 
 	"github.com/hashicorp/consul/consul"
 	"github.com/hashicorp/consul/lib"
+	"github.com/hashicorp/consul/types"
 	"github.com/hashicorp/consul/watch"
 	"github.com/mitchellh/mapstructure"
 )
@@ -312,6 +313,10 @@ type Config struct {
 	// LogLevel is the level of the logs to putout
 	LogLevel string `mapstructure:"log_level"`
 
+	// Node ID is a unique ID for this node across space and time. Defaults
+	// to a randomly-generated ID that persists in the data-dir.
+	NodeID types.NodeID `mapstructure:"node_id"`
+
 	// Node name is the name we use to advertise. Defaults to hostname.
 	NodeName string `mapstructure:"node_name"`
 
@@ -1273,6 +1278,9 @@ func MergeConfig(a, b *Config) *Config {
 	if b.Protocol > 0 {
 		result.Protocol = b.Protocol
 	}
+	if b.NodeID != "" {
+		result.NodeID = b.NodeID
+	}
 	if b.NodeName != "" {
 		result.NodeName = b.NodeName
 	}

command/agent/config_test.go

@@ -60,7 +60,7 @@ func TestDecodeConfig(t *testing.T) {
 	}
 
 	// Without a protocol
-	input = `{"node_name": "foo", "datacenter": "dc2"}`
+	input = `{"node_id": "bar", "node_name": "foo", "datacenter": "dc2"}`
 	config, err = DecodeConfig(bytes.NewReader([]byte(input)))
 	if err != nil {
 		t.Fatalf("err: %s", err)
@@ -70,6 +70,10 @@ func TestDecodeConfig(t *testing.T) {
 		t.Fatalf("bad: %#v", config)
 	}
 
+	if config.NodeID != "bar" {
+		t.Fatalf("bad: %#v", config)
+	}
+
 	if config.Datacenter != "dc2" {
 		t.Fatalf("bad: %#v", config)
 	}
@@ -1532,6 +1536,7 @@ func TestMergeConfig(t *testing.T) {
 		DataDir:                "/tmp/foo",
 		Domain:                 "basic",
 		LogLevel:               "debug",
+		NodeID:                 "bar",
 		NodeName:               "foo",
 		ClientAddr:             "127.0.0.1",
 		BindAddr:               "127.0.0.1",
@@ -1586,6 +1591,7 @@ func TestMergeConfig(t *testing.T) {
 		},
 		Domain:           "other",
 		LogLevel:         "info",
+		NodeID:           "bar",
 		NodeName:         "baz",
 		ClientAddr:       "127.0.0.2",
 		BindAddr:         "127.0.0.2",

command/agent/local.go

@@ -44,7 +44,7 @@ type localState struct {
 	iface consul.Interface
 
 	// nodeInfoInSync tracks whether the server has our correct top-level
-	// node information in sync (currently only used for tagged addresses)
+	// node information in sync
 	nodeInfoInSync bool
 
 	// Services tracks the local services
@@ -431,6 +431,7 @@ func (l *localState) setSyncState() error {
 
 	// Check the node info
 	if out1.NodeServices == nil || out1.NodeServices.Node == nil ||
+		out1.NodeServices.Node.ID != l.config.NodeID ||
 		!reflect.DeepEqual(out1.NodeServices.Node.TaggedAddresses, l.config.TaggedAddresses) ||
 		!reflect.DeepEqual(out1.NodeServices.Node.Meta, l.metadata) {
 		l.nodeInfoInSync = false
@@ -633,6 +634,7 @@ func (l *localState) deleteCheck(id types.CheckID) error {
 func (l *localState) syncService(id string) error {
 	req := structs.RegisterRequest{
 		Datacenter:      l.config.Datacenter,
+		ID:              l.config.NodeID,
 		Node:            l.config.NodeName,
 		Address:         l.config.AdvertiseAddr,
 		TaggedAddresses: l.config.TaggedAddresses,
@@ -695,6 +697,7 @@ func (l *localState) syncCheck(id types.CheckID) error {
 
 	req := structs.RegisterRequest{
 		Datacenter:      l.config.Datacenter,
+		ID:              l.config.NodeID,
 		Node:            l.config.NodeName,
 		Address:         l.config.AdvertiseAddr,
 		TaggedAddresses: l.config.TaggedAddresses,
@@ -722,6 +725,7 @@ func (l *localState) syncCheck(id types.CheckID) error {
 func (l *localState) syncNodeInfo() error {
 	req := structs.RegisterRequest{
 		Datacenter:      l.config.Datacenter,
+		ID:              l.config.NodeID,
 		Node:            l.config.NodeName,
 		Address:         l.config.AdvertiseAddr,
 		TaggedAddresses: l.config.TaggedAddresses,