Diagnostic client

- the client allows to talk to the diagnostic server and
decode the internal values of the overlay and service discovery

- the tool also allows to remediate in case of orphans entries

Signed-off-by: Flavio Crisciani <flavio.crisciani@docker.com>

Makefile

@@ -28,6 +28,7 @@ build-local:
 	@mkdir -p "bin"
 	go build -tags experimental -o "bin/dnet" ./cmd/dnet
 	go build -o "bin/docker-proxy" ./cmd/proxy
+	GOOS=linux go build -o "./cmd/diagnostic/diagnosticClient" ./cmd/diagnostic
 
 clean:
 	@echo "🐳 $@"

cmd/diagnostic/Dockerfile

@@ -0,0 +1,8 @@
+FROM docker:17.12-rc-dind
+
+RUN apk add --no-cache curl
+
+WORKDIR /tool
+
+COPY daemon.json /etc/docker/daemon.json
+COPY diagnosticClient /tool/diagnosticClient

cmd/diagnostic/daemon.json

@@ -0,0 +1,4 @@
+{
+  "debug": true,
+  "network-diagnostic-port": 2000
+}

cmd/diagnostic/main.go

@@ -0,0 +1,191 @@
+package main
+
+import (
+	"bufio"
+	"encoding/base64"
+	"encoding/json"
+	"flag"
+	"fmt"
+	"io"
+	"io/ioutil"
+	"net/http"
+	"os"
+	"strings"
+
+	"github.com/docker/libnetwork"
+	"github.com/docker/libnetwork/diagnose"
+	"github.com/docker/libnetwork/drivers/overlay"
+	"github.com/sirupsen/logrus"
+)
+
+const (
+	readyPath    = "http://%s:%d/ready"
+	joinNetwork  = "http://%s:%d/joinnetwork?nid=%s"
+	leaveNetwork = "http://%s:%d/leavenetwork?nid=%s"
+	clusterPeers = "http://%s:%d/clusterpeers?json"
+	networkPeers = "http://%s:%d/networkpeers?nid=%s&json"
+	dumpTable    = "http://%s:%d/gettable?nid=%s&tname=%s&json"
+	deleteEntry  = "http://%s:%d/deleteentry?nid=%s&tname=%s&key=%s&json"
+)
+
+func httpIsOk(body io.ReadCloser) {
+	b, err := ioutil.ReadAll(body)
+	if err != nil {
+		logrus.Fatalf("Failed the body parse %s", err)
+	}
+	if !strings.Contains(string(b), "OK") {
+		logrus.Fatalf("Server not ready %s", b)
+	}
+	body.Close()
+}
+
+func main() {
+	ipPtr := flag.String("ip", "127.0.0.1", "ip address")
+	portPtr := flag.Int("port", 2000, "port")
+	networkPtr := flag.String("net", "", "target network")
+	tablePtr := flag.String("t", "", "table to process <sd/overlay>")
+	remediatePtr := flag.Bool("r", false, "perform remediation deleting orphan entries")
+	verbosePtr := flag.Bool("v", false, "verbose output")
+
+	flag.Parse()
+
+	if *verbosePtr {
+		logrus.SetLevel(logrus.DebugLevel)
+	}
+
+	logrus.Infof("Connecting to %s:%d checking ready", *ipPtr, *portPtr)
+	resp, err := http.Get(fmt.Sprintf(readyPath, *ipPtr, *portPtr))
+	if err != nil {
+		logrus.WithError(err).Fatalf("The connection failed")
+	}
+	httpIsOk(resp.Body)
+
+	clusterPeers := fetchNodePeers(*ipPtr, *portPtr, "")
+	var networkPeers map[string]string
+	var joinedNetwork bool
+	if *networkPtr != "" {
+		logrus.Infof("Joining the network:%s", *networkPtr)
+		resp, err = http.Get(fmt.Sprintf(joinNetwork, *ipPtr, *portPtr, *networkPtr))
+		if err != nil {
+			logrus.WithError(err).Fatalf("Failed joining the network")
+		}
+		httpIsOk(resp.Body)
+		networkPeers = fetchNodePeers(*ipPtr, *portPtr, *networkPtr)
+		joinedNetwork = true
+	}
+
+	switch *tablePtr {
+	case "sd":
+		fetchTable(*ipPtr, *portPtr, *networkPtr, "endpoint_table", clusterPeers, networkPeers, *remediatePtr)
+	case "overlay":
+		fetchTable(*ipPtr, *portPtr, *networkPtr, "overlay_peer_table", clusterPeers, networkPeers, *remediatePtr)
+	}
+
+	if joinedNetwork {
+		resp, err = http.Get(fmt.Sprintf(leaveNetwork, *ipPtr, *portPtr, *networkPtr))
+		if err != nil {
+			logrus.WithError(err).Fatalf("Failed leaving the network")
+		}
+		httpIsOk(resp.Body)
+	}
+}
+
+func fetchNodePeers(ip string, port int, network string) map[string]string {
+	logrus.Infof("Fetch peers %s", network)
+	var path string
+	if network != "" {
+		path = fmt.Sprintf(networkPeers, ip, port, network)
+	} else {
+		path = fmt.Sprintf(clusterPeers, ip, port)
+	}
+
+	resp, err := http.Get(path)
+	if err != nil {
+		logrus.WithError(err).Fatalf("Failed fetching path")
+	}
+	defer resp.Body.Close()
+	body, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		logrus.WithError(err).Fatalf("Failed the body parse")
+	}
+
+	output := diagnose.HTTPResult{Details: &diagnose.TablePeersResult{}}
+	err = json.Unmarshal(body, &output)
+	if err != nil {
+		logrus.WithError(err).Fatalf("Failed the json unmarshalling")
+	}
+
+	logrus.Debugf("Parsing JSON response")
+	result := make(map[string]string, output.Details.(*diagnose.TablePeersResult).Length)
+	for _, v := range output.Details.(*diagnose.TablePeersResult).Elements {
+		logrus.Debugf("name:%s ip:%s", v.Name, v.IP)
+		result[v.Name] = v.IP
+	}
+	return result
+}
+
+func fetchTable(ip string, port int, network, tableName string, networkPeers, clusterPeers map[string]string, remediate bool) {
+	logrus.Infof("Fetch %s table and check owners", tableName)
+	resp, err := http.Get(fmt.Sprintf(dumpTable, ip, port, network, tableName))
+	if err != nil {
+		logrus.WithError(err).Fatalf("Failed fetching endpoint table")
+	}
+	defer resp.Body.Close()
+	body, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		logrus.WithError(err).Fatalf("Failed the body parse")
+	}
+
+	output := diagnose.HTTPResult{Details: &diagnose.TableEndpointsResult{}}
+	err = json.Unmarshal(body, &output)
+	if err != nil {
+		logrus.WithError(err).Fatalf("Failed the json unmarshalling")
+	}
+
+	logrus.Debug("Parsing data structures")
+	var orphanKeys []string
+	for _, v := range output.Details.(*diagnose.TableEndpointsResult).Elements {
+		decoded, err := base64.StdEncoding.DecodeString(v.Value)
+		if err != nil {
+			logrus.WithError(err).Errorf("Failed decoding entry")
+			continue
+		}
+		switch tableName {
+		case "endpoint_table":
+			var elem libnetwork.EndpointRecord
+			elem.Unmarshal(decoded)
+			logrus.Debugf("key:%s value:%+v owner:%s", v.Key, elem, v.Owner)
+		case "overlay_peer_table":
+			var elem overlay.PeerRecord
+			elem.Unmarshal(decoded)
+			logrus.Debugf("key:%s value:%+v owner:%s", v.Key, elem, v.Owner)
+		}
+
+		if _, ok := networkPeers[v.Owner]; !ok {
+			logrus.Warnf("The element with key:%s does not belong to any node on this network", v.Key)
+			orphanKeys = append(orphanKeys, v.Key)
+		}
+		if _, ok := clusterPeers[v.Owner]; !ok {
+			logrus.Warnf("The element with key:%s does not belong to any node on this cluster", v.Key)
+		}
+	}
+
+	if len(orphanKeys) > 0 && remediate {
+		logrus.Warnf("The following keys:%v results as orphan, do you want to proceed with the deletion (this operation is irreversible)? [Yes/No]", orphanKeys)
+		reader := bufio.NewReader(os.Stdin)
+		text, _ := reader.ReadString('\n')
+		text = strings.Replace(text, "\n", "", -1)
+		if strings.Compare(text, "Yes") == 0 {
+			for _, k := range orphanKeys {
+				resp, err := http.Get(fmt.Sprintf(deleteEntry, ip, port, network, tableName, k))
+				if err != nil {
+					logrus.WithError(err).Errorf("Failed deleting entry k:%s", k)
+					break
+				}
+				resp.Body.Close()
+			}
+		} else {
+			logrus.Infof("Deletion skipped")
+		}
+	}
+}