Improved error handling for support bundles and redactors for windows

examples/collect/host/all-collectors.yaml

@@ -1,7 +1,7 @@
 apiVersion: troubleshoot.sh/v1beta2
 kind: SupportBundle
 metadata:
-  name: all-collectors-test
+  name: all-host-collectors
 spec:
   hostCollectors:
     # System Info Collectors
@@ -46,25 +46,51 @@ spec:
         fileSize: 10Mi
         operationSizeBytes: 2300
 
-    # Certificate
+    # Certificate Collectors
     - certificate:
         collectorName: test-cert
         certificatePath: /etc/ssl/certs/ca-certificates.crt
+    - certificatesCollection:
+        collectorName: certs-collection
+        paths:
+          - /etc/ssl/certs
 
     # Network Tests
     - tcpPortStatus:
         collectorName: ssh-port
         port: 22
+    - udpPortStatus:
+        collectorName: dns-port
+        port: 53
     - tcpConnect:
         collectorName: localhost-ssh
         address: 127.0.0.1:22
+    - tcpLoadBalancer:
+        collectorName: lb-test
+        address: 127.0.0.1
+        port: 80
+    - httpLoadBalancer:
+        collectorName: http-lb-test
+        address: 127.0.0.1
+        port: 80
+        path: /healthz
     - http:
         collectorName: google
         get:
           url: https://www.google.com
     - dns:
         collectorName: dns-google
-        hostname: google.com
+        hostnames:
+          - google.com
+    - subnetAvailable:
+        collectorName: subnet-check
+        CIDRRangeAlloc: 10.0.0.0/16
+        desiredCIDR: 24
+    - networkNamespaceConnectivity:
+        collectorName: netns-connectivity
+        fromCIDR: 10.0.0.0/8
+        toCIDR: 192.168.0.0/16
+        port: 80
 
     # Custom Commands
     - run:

examples/collect/host/all-kubernetes-collectors.yaml

@@ -0,0 +1,170 @@
+apiVersion: troubleshoot.sh/v1beta2
+kind: SupportBundle
+metadata:
+  name: all-kubernetes-collectors
+spec:
+  collectors:
+    # Cluster Info Collectors (2)
+    - clusterInfo: {}
+    - clusterResources: {}
+
+    # Metrics Collectors (2)
+    - customMetrics:
+        collectorName: custom-metrics
+        metricRequests:
+          - resourceMetricName: example-metric
+    - nodeMetrics: {}
+
+    # ConfigMap and Secret Collectors (2)
+    - configMap:
+        collectorName: example-configmap
+        name: example-configmap
+        namespace: default
+        includeValue: false
+    - secret:
+        collectorName: example-secret
+        name: example-secret
+        namespace: default
+        includeValue: false
+
+    # Logs Collector (1)
+    - logs:
+        collectorName: example-logs
+        selector:
+          - app=example
+        namespace: default
+        limits:
+          maxAge: 720h
+          maxLines: 10000
+
+    # Pod Execution Collectors (4)
+    - run:
+        collectorName: run-example
+        name: run-example
+        namespace: default
+        image: busybox:latest
+        command: ["echo"]
+        args: ["hello from run"]
+    - runPod:
+        collectorName: run-pod-example
+        name: run-pod-example
+        namespace: default
+        podSpec:
+          containers:
+            - name: example
+              image: busybox:latest
+              command: ["echo", "hello from runPod"]
+    - runDaemonSet:
+        collectorName: run-daemonset-example
+        name: run-daemonset-example
+        namespace: default
+        podSpec:
+          containers:
+            - name: example
+              image: busybox:latest
+              command: ["echo", "hello from runDaemonSet"]
+    - exec:
+        collectorName: exec-example
+        name: exec-example
+        selector:
+          - app=example
+        namespace: default
+        command: ["echo"]
+        args: ["hello from exec"]
+
+    # Data Collector (1)
+    - data:
+        collectorName: static-data
+        name: static-data.txt
+        data: "This is static data"
+
+    # Copy Collectors (2)
+    - copy:
+        collectorName: copy-example
+        selector:
+          - app=example
+        namespace: default
+        containerPath: /tmp
+    - copyFromHost:
+        collectorName: copy-from-host-example
+        name: copy-from-host-example
+        namespace: default
+        image: busybox:latest
+        hostPath: /tmp/example
+
+    # HTTP Collector (1)
+    - http:
+        collectorName: http-get-example
+        get:
+          url: https://www.google.com
+          insecureSkipVerify: false
+
+    # Database Collectors (4)
+    - postgres:
+        collectorName: postgres-example
+        uri: postgresql://user:password@localhost:5432/dbname
+    - mysql:
+        collectorName: mysql-example
+        uri: user:password@tcp(localhost:3306)/dbname
+    - mssql:
+        collectorName: mssql-example
+        uri: sqlserver://user:password@localhost:1433?database=dbname
+    - redis:
+        collectorName: redis-example
+        uri: redis://localhost:6379
+
+    # Storage and System Collectors (3)
+    - collectd:
+        collectorName: collectd-example
+        namespace: default
+        image: busybox:latest
+        hostPath: /var/lib/collectd
+    - ceph:
+        collectorName: ceph-example
+        namespace: rook-ceph
+    - longhorn:
+        collectorName: longhorn-example
+        namespace: longhorn-system
+
+    # Registry and Image Collector (1)
+    - registryImages:
+        collectorName: registry-images-example
+        namespace: default
+        images:
+          - busybox:latest
+
+    # Sysctl Collector (1)
+    - sysctl:
+        collectorName: sysctl-example
+        name: sysctl-example
+        namespace: default
+        image: busybox:latest
+
+    # Certificate Collector (1)
+    - certificates:
+        collectorName: certificates-example
+        secrets:
+          - name: tls-secret
+            namespaces:
+              - default
+
+    # Application-Specific Collectors (3)
+    - helm:
+        collectorName: helm-example
+        namespace: default
+        releaseName: example-release
+        collectValues: false
+    - goldpinger:
+        collectorName: goldpinger-example
+        namespace: default
+    - sonobuoy:
+        collectorName: sonobuoy-example
+        namespace: sonobuoy
+
+    # DNS and Network Collectors (2)
+    - dns:
+        collectorName: dns-example
+        timeout: 10s
+    - etcd:
+        collectorName: etcd-example
+        image: quay.io/coreos/etcd:latest

pkg/collect/host_certificate.go

@@ -32,9 +32,11 @@ func (c *CollectHostCertificate) IsExcluded() (bool, error) {
 
 func (c *CollectHostCertificate) Collect(progressChan chan<- interface{}) (map[string][]byte, error) {
 	var result = KeyPairValid
+	var collectorErr error
 
 	_, err := tls.LoadX509KeyPair(c.hostCollector.CertificatePath, c.hostCollector.KeyPath)
 	if err != nil {
+		collectorErr = err
 		if strings.Contains(err.Error(), "no such file") {
 			result = KeyPairMissing
 		} else if strings.Contains(err.Error(), "PEM inputs may have been switched") {
@@ -67,7 +69,7 @@ func (c *CollectHostCertificate) Collect(progressChan chan<- interface{}) (map[s
 
 	return map[string][]byte{
 		name: b,
-	}, nil
+	}, collectorErr
 }
 
 func isEncryptedKey(filename string) (bool, error) {

pkg/collect/host_copy.go

@@ -48,11 +48,11 @@ func (c *CollectHostCopy) Collect(progressChan chan<- interface{}) (map[string][
 		klog.Errorf("Failed to copy files from %q to %q: %v", c.hostCollector.Path, "<bundle>/"+bundleRelPath, err)
 		fileName := fmt.Sprintf("%s/errors.json", c.relBundlePath(bundlePathDest))
 		output := NewResult()
-		err := output.SaveResult(c.BundlePath, fileName, marshalErrors([]string{err.Error()}))
-		if err != nil {
-			return nil, err
+		saveErr := output.SaveResult(c.BundlePath, fileName, marshalErrors([]string{err.Error()}))
+		if saveErr != nil {
+			return nil, saveErr
 		}
-		return output, nil
+		return output, err
 	}
 
 	return result, nil

pkg/collect/host_httploadbalancer.go

@@ -80,11 +80,15 @@ func (c *CollectHostHTTPLoadBalancer) Collect(progressChan chan<- interface{}) (
 	}()
 
 	var networkStatus NetworkStatus
+	var errorMessage string
+	var collectorErr error
 
 	stopAfter := time.Now().Add(timeout)
 	for {
 		if len(listenErr) > 0 {
 			err := <-listenErr
+			errorMessage = err.Error()
+			collectorErr = errors.Wrap(err, "failed to listen on HTTP port")
 			if strings.Contains(err.Error(), "address already in use") {
 				networkStatus = NetworkStatusAddressInUse
 				break
@@ -113,7 +117,8 @@ func (c *CollectHostHTTPLoadBalancer) Collect(progressChan chan<- interface{}) (
 	}
 
 	result := NetworkStatusResult{
-		Status: networkStatus,
+		Status:  networkStatus,
+		Message: errorMessage,
 	}
 
 	b, err := json.Marshal(result)
@@ -132,7 +137,7 @@ func (c *CollectHostHTTPLoadBalancer) Collect(progressChan chan<- interface{}) (
 
 	return map[string][]byte{
 		name: b,
-	}, nil
+	}, collectorErr
 }
 
 func attemptPOST(address string, request []byte, response []byte) NetworkStatus {

pkg/collect/host_network.go

@@ -2,6 +2,7 @@ package collect
 
 import (
 	"bytes"
+	"fmt"
 	"net"
 	"regexp"
 	"strconv"
@@ -70,19 +71,20 @@ func isValidLoadBalancerAddress(address string) bool {
 	return len(errs) == 0
 }
 
-func checkTCPConnection(progressChan chan<- interface{}, listenAddress string, dialAddress string, timeout time.Duration) (NetworkStatus, error) {
+func checkTCPConnection(progressChan chan<- interface{}, listenAddress string, dialAddress string, timeout time.Duration) (NetworkStatus, string, error) {
 
 	if !isValidLoadBalancerAddress(dialAddress) {
-		return NetworkStatusInvalidAddress, errors.Errorf("Invalid Load Balancer Address: %v", dialAddress)
+		errMsg := fmt.Sprintf("Invalid Load Balancer Address: %v", dialAddress)
+		return NetworkStatusInvalidAddress, errMsg, errors.New(errMsg)
 	}
 
 	lstn, err := net.Listen("tcp", listenAddress)
 	if err != nil {
 		if strings.Contains(err.Error(), "address already in use") {
-			return NetworkStatusAddressInUse, nil
+			return NetworkStatusAddressInUse, err.Error(), errors.Wrap(err, "failed to create listener")
 		}
 
-		return NetworkStatusErrorOther, errors.Wrap(err, "failed to create listener")
+		return NetworkStatusErrorOther, err.Error(), errors.Wrap(err, "failed to create listener")
 	}
 	defer lstn.Close()
 
@@ -110,7 +112,8 @@ func checkTCPConnection(progressChan chan<- interface{}, listenAddress string, d
 		if time.Now().After(stopAfter) {
 			debug.Printf("Timeout")
 
-			return NetworkStatusConnectionTimeout, nil
+			errMsg := "connection timeout"
+			return NetworkStatusConnectionTimeout, errMsg, errors.New(errMsg)
 		}
 
 		conn, err := net.DialTimeout("tcp", dialAddress, 50*time.Millisecond)
@@ -124,13 +127,13 @@ func checkTCPConnection(progressChan chan<- interface{}, listenAddress string, d
 				continue
 			}
 			if strings.Contains(err.Error(), "connection refused") {
-				return NetworkStatusConnectionRefused, nil
+				return NetworkStatusConnectionRefused, err.Error(), errors.Wrap(err, "failed to dial")
 			}
-			return NetworkStatusErrorOther, errors.Wrap(err, "failed to dial")
+			return NetworkStatusErrorOther, err.Error(), errors.Wrap(err, "failed to dial")
 		}
 
 		if verifyConnectionToServer(conn, requestToken, responseToken) {
-			return NetworkStatusConnected, nil
+			return NetworkStatusConnected, "", nil
 		}
 
 		progressChan <- errors.New("failed to verify connection to server")