Feat/traceroute (#113)

* feat: boilerplate * feat: register udptraceroute * chore: fix nits * fix: unit tests breaking * Merge from main * refactor: validation logic * review: implement changes requested by @lvlcn-t * review: implement changes requested by @puffitos * chore: add target to logger * chore: remove testcase type Signed-off-by: Niklas Treml <treml.niklas@gmail.com> * chore: rename shadowed variable Signed-off-by: Niklas Treml <treml.niklas@gmail.com> * fix: validate ip correctly Signed-off-by: Niklas Treml <treml.niklas@gmail.com> * docs: add docs for config Signed-off-by: Niklas Treml <treml.niklas@gmail.com> * chore: log error instead of err Signed-off-by: Niklas Treml <treml.niklas@gmail.com> * docs: update readme to include traceroute Signed-off-by: Niklas Treml <treml.niklas@gmail.com> * docs: capabilities Signed-off-by: Niklas Treml <treml.niklas@gmail.com> * docs: document target * chore: remove duplicate debug log Signed-off-by: Niklas Treml <treml.niklas@gmail.com> --------- Signed-off-by: Niklas Treml <treml.niklas@gmail.com>
caas-team · Mar 1, 2024 · ec1fc82 · ec1fc82
1 parent 1d5f0ed
commit ec1fc82
Show file tree

Hide file tree

Showing 10 changed files with 487 additions and 9 deletions.
diff --git a/.vscode/launch.json b/.vscode/launch.json
@@ -1,6 +1,15 @@
 {
   "version": "0.2.0",
   "configurations": [
+    {
+      "name": "Connect to server",
+      "type": "go",
+      "request": "attach",
+      "mode": "remote",
+      "remotePath": "${workspaceFolder}",
+      "port": 2345,
+      "host": "127.0.0.1"
+    },
     {
       "name": "Launch Package",
       "type": "go",

diff --git a/README.md b/README.md
@@ -53,6 +53,9 @@ The following checks are available:
 3. [DNS check](#check-dns) - `dns`: The `sparrow` is able to perform DNS resolution checks to monitor domain name system
    performance and reliability. The check has the ability to target specific domains or IPs for monitoring.
 
+4. [Traceroute Check](#check-traceroute) - `traceroute`: The `sparrow` is able to perform traceroute checks to monitor
+   the network path to a target. The check has the ability to target specific domains or IPs for monitoring.
+
 Each check is designed to provide comprehensive insights into the various aspects of network and service health,
 ensuring robust monitoring and quick detection of potential issues.
 
@@ -432,6 +435,41 @@ dns:
   - Description: Histogram of response times for DNS checks
   - Labelled with `target`
 
+### Check: Traceroute
+
+| Field             | Type              | Description                                                                                                                                               |
+| ----------------- | ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `interval`        | `duration`        | Interval to perform the Traceroute check.                                                                                                                 |
+| `timeout`         | `duration`        | Timeout for every hop.                                                                                                                                    |
+| `retries`         | `integer`         | Number of times to retry the traceroute for a target, if it fails.                                                                                        |
+| `maxHops`         | `integer`         | Maximum number of hops to try before giving up.                                                                                                           |
+| `targets`         | `list of objects` | List of targets to traceroute to.                                                                                                                         |
+| `targets[].addr`  | `string`          | The address of the target to traceroute to. Can be an IP address or DNS name                                                                              |
+| `targets[].port`  | `uint16`          | The port of the target to traceroute to. Default is 80                                                                                                    |
+
+#### Example configuration
+
+```yaml
+ traceroute:
+  interval: 5s
+  timeout: 3s
+  retries: 3
+  maxHops: 8
+  targets:
+    - addr: 8.8.8.8
+      port: 53
+    - addr: www.google.com
+      port: 80
+```
+
+#### Required Capabilities
+To use this check, sparrow needs to be run with the `CAP_NET_RAW` capability or elevated privileges to be able to send raw packets.
+Using the `CAP_NET_RAW` capability is recommended over running sparrow as sudo
+
+```bash
+sudo setcap 'cap_net_raw=ep' sparrow
+```
+
 ## API
 
 The `sparrow` exposes an API for accessing the results of various checks. Each check registers its own endpoint

diff --git a/go.mod b/go.mod
@@ -12,6 +12,13 @@ require (
 	gopkg.in/yaml.v3 v3.0.1
 )
 
+require (
+	github.com/aeden/traceroute v0.0.0-20210211061815-03f5f7cb7908
+	github.com/google/go-cmp v0.6.0
+)
+
+require github.com/mitchellh/mapstructure v1.5.0 // indirect
+
 require (
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.2.0 // indirect
@@ -28,7 +35,6 @@ require (
 	github.com/magiconair/properties v1.8.7 // indirect
 	github.com/mailru/easyjson v0.7.7 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
-	github.com/mitchellh/mapstructure v1.5.0 // indirect
 	github.com/mohae/deepcopy v0.0.0-20170929034955-c48cc78d4826 // indirect
 	github.com/pelletier/go-toml/v2 v2.1.0 // indirect
 	github.com/perimeterx/marshmallow v1.1.5 // indirect

diff --git a/go.sum b/go.sum
@@ -1,3 +1,5 @@
+github.com/aeden/traceroute v0.0.0-20210211061815-03f5f7cb7908 h1:6suDyKbvZ5r2G/gblQLV9Cdv7rdqNlUxsRXpLOF0rKM=
+github.com/aeden/traceroute v0.0.0-20210211061815-03f5f7cb7908/go.mod h1:HPBB/4vaPt7NcN9l72/+IwsmDVQsa6AWM6ZDKJCLB9U=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
@@ -27,8 +29,8 @@ github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaS
 github.com/golang/protobuf v1.5.3 h1:KhyjKVUg7Usr/dYsdSqoFveMYd5ko72D+zANwlG1mmg=
 github.com/golang/protobuf v1.5.3/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
-github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/hashicorp/hcl v1.0.0 h1:0Anlzjpi4vEasTeNFn2mLJgTSwt0+6sfsiTG8qcWGx4=
 github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=

diff --git a/pkg/checks/runtime/config.go b/pkg/checks/runtime/config.go
@@ -25,15 +25,17 @@ import (
 	"github.com/caas-team/sparrow/pkg/checks/dns"
 	"github.com/caas-team/sparrow/pkg/checks/health"
 	"github.com/caas-team/sparrow/pkg/checks/latency"
+	"github.com/caas-team/sparrow/pkg/checks/traceroute"
 )
 
 // Config holds the runtime configuration
 // for the various checks
 // the sparrow supports
 type Config struct {
-	Health  *health.Config  `yaml:"health" json:"health"`
-	Latency *latency.Config `yaml:"latency" json:"latency"`
-	Dns     *dns.Config     `yaml:"dns" json:"dns"`
+	Health     *health.Config     `yaml:"health" json:"health"`
+	Latency    *latency.Config    `yaml:"latency" json:"latency"`
+	Dns        *dns.Config        `yaml:"dns" json:"dns"`
+	Traceroute *traceroute.Config `yaml:"traceroute" json:"traceroute"`
 }
 
 // Empty returns true if no checks are configured
@@ -63,6 +65,9 @@ func (c Config) Iter() []checks.Runtime {
 	if c.Dns != nil {
 		configs = append(configs, c.Dns)
 	}
+	if c.Traceroute != nil {
+		configs = append(configs, c.Traceroute)
+	}
 	return configs
 }
 
@@ -78,6 +83,9 @@ func (c Config) size() int {
 	if c.HasDNSCheck() {
 		size++
 	}
+	if c.HasTracerouteCheck() {
+		size++
+	}
 	return size
 }
 
@@ -96,6 +104,11 @@ func (c Config) HasDNSCheck() bool {
 	return c.Dns != nil
 }
 
+// HasTracerouteCheck returns true if the check has a traceroute check configured
+func (c Config) HasTracerouteCheck() bool {
+	return c.Traceroute != nil
+}
+
 // HasCheck returns true if the check has a check with the given name configured
 func (c Config) HasCheck(name string) bool {
 	switch name {
@@ -105,6 +118,8 @@ func (c Config) HasCheck(name string) bool {
 		return c.HasLatencyCheck()
 	case dns.CheckName:
 		return c.HasDNSCheck()
+	case traceroute.CheckName:
+		return c.HasTracerouteCheck()
 	default:
 		return false
 	}
@@ -125,6 +140,10 @@ func (c Config) For(name string) checks.Runtime {
 		if c.HasDNSCheck() {
 			return c.Dns
 		}
+	case traceroute.CheckName:
+		if c.HasTracerouteCheck() {
+			return c.Traceroute
+		}
 	}
 	return nil
 }
diff --git a/pkg/checks/traceroute/config.go b/pkg/checks/traceroute/config.go
@@ -0,0 +1,51 @@
+package traceroute
+
+import (
+	"fmt"
+	"net"
+	"net/url"
+	"time"
+
+	"github.com/caas-team/sparrow/pkg/checks"
+)
+
+// Config is the configuration for the traceroute check
+type Config struct {
+	// Targets is a list of targets to traceroute to
+	Targets []Target `json:"targets" yaml:"targets" mapstructure:"targets"`
+	// Retries is the number of times to retry the traceroute for a target, if it fails
+	Retries int `json:"retries" yaml:"retries" mapstructure:"retries"`
+	// MaxHops is the maximum number of hops to try before giving up
+	MaxHops int `json:"maxHops" yaml:"maxHops" mapstructure:"maxHops"`
+	// Interval is the time to wait between check iterations
+	Interval time.Duration `json:"interval" yaml:"interval" mapstructure:"interval"`
+	// Timeout is the maximum time to wait for a response from a hop
+	Timeout time.Duration `json:"timeout" yaml:"timeout" mapstructure:"timeout"`
+}
+
+func (c *Config) For() string {
+	return CheckName
+}
+
+func (c *Config) Validate() error {
+	if c.Timeout <= 0 {
+		return checks.ErrInvalidConfig{CheckName: CheckName, Field: "traceroute.timeout", Reason: "must be greater than 0"}
+	}
+	if c.Interval <= 0 {
+		return checks.ErrInvalidConfig{CheckName: CheckName, Field: "traceroute.interval", Reason: "must be greater than 0"}
+	}
+
+	for i, t := range c.Targets {
+		ip := net.ParseIP(t.Addr)
+
+		if ip != nil {
+			continue
+		}
+
+		_, err := url.Parse(t.Addr)
+		if err != nil && ip == nil {
+			return checks.ErrInvalidConfig{CheckName: CheckName, Field: fmt.Sprintf("traceroute.targets[%d].addr", i), Reason: "invalid url or ip"}
+		}
+	}
+	return nil
+}