coolaj86
/
go-watchdog
1
0
Fork 0
Code Issues Pull Requests 1 Releases Wiki Activity

made useful, nay, usable!

This commit is contained in:
AJ ONeal 2019-06-08 03:11:42 -06:00
parent 65c7393253
commit 8248c33607
2 changed files with 238 additions and 143 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
README.md
View File

@ -19,15 +19,34 @@ go run ./watchdog.go -c dog.json
```json
{
"watches": [
{
"name": "Example Site",
"url": "https://example.com/",
"webhook": "twilio",
"keywords": "My Site",
"recover_script": "systemctl restart example-site"
}
],
"watches": [
{
"name": "Example Site",
"url": "https://example.com/",
"webhooks": ["twilio"],
"keywords": "My Site",
"recover_script": "systemctl restart example-site"
}
],
"webhooks": [
{
"name": "twilio",
"url": "https://api.twilio.com/2010-04-01/Accounts/AC00000000000000000000000000000000/Messages.json",
"auth": {
"user": "AC00000000000000000000000000000000",
"pass": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
},
"form": {
"To": "+1 801 555 1234",
"From": "+1 800 555 4321",
"Body": "[{{ .Name }}] The system is down. The system is down."
}
}
]
}
```
<!--
"webhooks": [
{
"name": "twilio",
@ -46,5 +65,4 @@ go run ./watchdog.go -c dog.json
}
}
]
}
```
-->

341
watchdog.go
View File

@ -9,8 +9,10 @@ import (
"log"
"net"
"net/http"
"net/url"
"os"
"os/exec"
"strings"
"time"
)
@ -54,17 +56,29 @@ func main() {
done := make(chan struct{}, 1)
allWebhooks := make(map[string]ConfigWebhook)
for i := range config.Webhooks {
h := config.Webhooks[i]
allWebhooks[h.Name] = h
}
logQueue := make(chan string, 10)
go logger(logQueue)
for i := range config.Watches {
c := config.Watches[i]
fmt.Printf("Watching '%s'", c.Name)
logQueue <- fmt.Sprintf("Watching '%s'", c.Name)
go func(c ConfigWatch) {
w := &Dog{
Name: c.Name,
CheckURL: c.URL,
Keywords: c.Keywords,
Recover: c.RecoverScript,
}
w.Watch()
d := New(&Dog{
Name: c.Name,
CheckURL: c.URL,
Keywords: c.Keywords,
Recover: c.RecoverScript,
Webhooks: c.Webhooks,
AllWebhooks: allWebhooks,
logger: logQueue,
})
d.Watch()
}(config.Watches[i])
}
@ -81,6 +95,9 @@ type Dog struct {
CheckURL string
Keywords string
Recover string
Webhooks []string
AllWebhooks map[string]ConfigWebhook
logger chan string
error error
failures int
passes int
@ -89,46 +106,24 @@ type Dog struct {
lastNotified time.Time
}
func (w *Dog) execRecover() {
if "" == w.Recover {
return
}
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
cmd := exec.CommandContext(ctx, "bash")
pipe, err := cmd.StdinPipe()
pipe.Write([]byte(w.Recover))
if nil != err {
fmt.Fprintf(os.Stderr, "Could not write to bash '%s': %s\n", w.Recover, err)
}
err = cmd.Start()
if nil != err {
fmt.Fprintf(os.Stderr, "Could not start '%s': %s\n", w.Recover, err)
}
err = pipe.Close()
if nil != err {
fmt.Fprintf(os.Stderr, "Could not close '%s': %s\n", w.Recover, err)
}
err = cmd.Wait()
cancel()
if nil != err {
fmt.Fprintf(os.Stderr, "'%s' failed: %s\n", w.Recover, err)
}
func New(d *Dog) *Dog {
d.lastPassed = time.Now().Add(-5 * time.Minute)
return d
}
func (w *Dog) Watch() {
w.watch()
func (d *Dog) Watch() {
d.watch()
for {
// TODO set cancellable callback ?
time.Sleep(5 * time.Minute)
w.watch()
d.watch()
}
}
func (w *Dog) watch() {
fmt.Println("Running a check")
func (d *Dog) watch() {
d.logger <- fmt.Sprintf("Check: '%s'", d.Name)
err := w.check()
err := d.check()
if nil == err {
return
}
@ -136,30 +131,193 @@ func (w *Dog) watch() {
failure := false
t := 10
for {
w.execRecover()
d.recover()
time.Sleep(time.Duration(t) * time.Second)
// backoff
t *= 2
err := w.check()
err := d.check()
if nil != err {
failure = true
}
// We should notify if
// * We've had success since the last notification
// * It's been at least 5 minutes since the last notification
if w.lastPassed.After(w.lastNotified) && w.lastNotified.Before(time.Now().Add(-5*time.Minute)) {
err := w.notify(failure)
if nil != err {
fmt.Println("Notify:", err)
}
fiveMinutesAgo := time.Now().Add(-5 * time.Minute)
if d.lastPassed.After(d.lastNotified) && d.lastNotified.Before(fiveMinutesAgo) {
d.notify(failure)
}
if w.failures >= 5 {
if d.failures >= 5 {
// go back to the main 5-minute loop
break
}
}
}
func (d *Dog) check() error {
var err error
defer func() {
if nil != err {
d.failures += 1
d.lastFailed = time.Now()
} else {
d.lastPassed = time.Now()
d.passes += 1
}
}()
client := NewHTTPClient()
response, err := client.Get(d.CheckURL)
if nil != err {
d.error = fmt.Errorf("Connection Failure: " + err.Error())
return err
}
b, err := ioutil.ReadAll(response.Body)
if nil != err {
d.error = fmt.Errorf("Network Failure: " + err.Error())
return err
}
if !bytes.Contains(b, []byte(d.Keywords)) {
err = fmt.Errorf("Down: '%s' Not Found for '%s'", d.Keywords, d.Name)
d.logger <- fmt.Sprintf("%s", err)
d.error = err
return err
} else {
d.logger <- fmt.Sprintf("Up: '%s'", d.Name)
}
return nil
}
func (d *Dog) recover() {
if "" == d.Recover {
return
}
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
cmd := exec.CommandContext(ctx, "bash")
pipe, err := cmd.StdinPipe()
pipe.Write([]byte(d.Recover))
if nil != err {
d.logger <- fmt.Sprintf("[Recover] Could not write to bash '%s': %s", d.Recover, err)
}
err = cmd.Start()
if nil != err {
d.logger <- fmt.Sprintf("[Recover] Could not start '%s': %s", d.Recover, err)
}
err = pipe.Close()
if nil != err {
d.logger <- fmt.Sprintf("[Recover] Could not close '%s': %s", d.Recover, err)
}
err = cmd.Wait()
cancel()
if nil != err {
d.logger <- fmt.Sprintf("[Recover] '%s' failed: %s", d.Recover, err)
}
}
func (d *Dog) notify(hardFail bool) {
d.logger <- fmt.Sprintf("Notifying the authorities of %s's failure", d.Name)
d.lastNotified = time.Now()
for i := range d.Webhooks {
name := d.Webhooks[i]
if "" == name {
continue
}
h, ok := d.AllWebhooks[name]
if !ok {
// TODO check in main when config is read
d.Webhooks[i] = ""
d.logger <- fmt.Sprintf("[Warning] Could not find webhook '%s' for '%s'", name, h.Name)
continue
}
// TODO do this in main on config init
if "" == h.Method {
h.Method = "POST"
}
var body *strings.Reader
if 0 != len(h.Form) {
form := url.Values{}
for k := range h.Form {
v := h.Form[k]
// TODO real templates
v = strings.Replace(v, "{{ .Name }}", d.Name, -1)
form.Set(k, v)
}
body = strings.NewReader(form.Encode())
}
client := NewHTTPClient()
req, err := http.NewRequest(h.Method, h.URL, body)
if nil != err {
log.Println("[Notify] HTTP Client Network Error:", err)
continue
}
if 0 != len(h.Form) {
req.Header.Add("Content-Type", "application/x-www-form-urlencoded")
}
if 0 != len(h.Auth) {
user := h.Auth["user"]
pass := h.Auth["pass"]
req.SetBasicAuth(user, pass)
}
resp, err := client.Do(req)
if nil != err {
d.logger <- fmt.Sprintf("[Notify] HTTP Client Error: %s", err)
continue
}
if !(resp.StatusCode >= 200 && resp.StatusCode < 300) {
d.logger <- fmt.Sprintf("[Notify] Response Error: %s", resp.Status)
continue
}
// TODO json vs xml vs txt
var data map[string]interface{}
req.Header.Add("Accept", "application/json")
decoder := json.NewDecoder(resp.Body)
err = decoder.Decode(&data)
if err != nil {
d.logger <- fmt.Sprintf("[Notify] Response Body Error: %s", resp.Status)
continue
}
// TODO some sort of way to determine if data is successful (keywords)
d.logger <- fmt.Sprintf("[Notify] Success? %#v", data)
}
}
type Config struct {
Watches []ConfigWatch `json:"watches"`
Webhooks []ConfigWebhook `json:"webhooks"`
}
type ConfigWatch struct {
Name string `json:"name"`
URL string `json:"url"`
Keywords string `json:"keywords"`
Webhooks []string `json:"webhooks"`
RecoverScript string `json:"recover_script"`
}
type ConfigWebhook struct {
Name string `json:"name"`
Method string `json:"method"`
URL string `json:"url"`
Auth map[string]string `json:"auth"`
Form map[string]string `json:"form"`
Config map[string]string `json:"config"`
Configs []map[string]string `json:"configs"`
}
func NewHTTPClient() *http.Client {
transport := &http.Transport{
Dial: (&net.Dialer{
@ -174,92 +332,11 @@ func NewHTTPClient() *http.Client {
return client
}
func (w *Dog) check() error {
var err error
defer func() {
if nil != err {
w.failures += 1
w.lastFailed = time.Now()
} else {
w.lastPassed = time.Now()
w.passes += 1
}
}()
client := NewHTTPClient()
response, err := client.Get(w.CheckURL)
if nil != err {
w.error = fmt.Errorf("Connection Failure: " + err.Error())
return err
func logger(msgs chan string) {
for {
msg := <-msgs
log.Println(msg)
}
b, err := ioutil.ReadAll(response.Body)
if nil != err {
w.error = fmt.Errorf("Network Failure: " + err.Error())
return err
}
if !bytes.Contains(b, []byte(w.Keywords)) {
err = fmt.Errorf("Keywords Not Found: " + w.Keywords)
fmt.Println(err)
w.error = err
return err
} else {
fmt.Println("Happy day!")
}
return nil
}
func (w *Dog) notify(hardFail bool) error {
w.lastNotified = time.Now()
fmt.Println("Notifying the authorities of a failure")
return nil
/*
urlStr := "https://api.twilio.com/2010-04-01/Accounts/" + accountSid + "/Messages.json"
msgData := url.Values{}
msgData.Set("To", "+1 555 555 5555")
msgData.Set("From", "+1 555 555 1234")
if hardFail {
msgData.Set("Body", fmt.Sprintf("[%s] The system is down. The system is down.", w.Name))
} else {
msgData.Set("Body", fmt.Sprintf("[%s] had a hiccup.", w.Name))
}
msgDataReader := *strings.NewReader(msgData.Encode())
client := NewHTTPClient()
req, err := http.NewRequest("POST", urlStr, &msgDataReader)
if nil != err {
fmt.Fprintf(os.Stderr, "Failed to text: %s\n", err)
}
req.SetBasicAuth(accountSid, authToken)
req.Header.Add("Accept", "application/json")
req.Header.Add("Content-Type", "application/x-www-form-urlencoded")
resp, _ := client.Do(req)
if resp.StatusCode >= 200 && resp.StatusCode < 300 {
var data map[string]interface{}
decoder := json.NewDecoder(resp.Body)
err := decoder.Decode(&data)
if err == nil {
fmt.Println(data["sid"])
}
} else {
fmt.Println("Error:", resp.Status)
}
return nil
*/
}
type Config struct {
Watches []ConfigWatch `json:"watches"`
}
type ConfigWatch struct {
Name string `json:"name"`
URL string `json:"url"`
Keywords string `json:"keywords"`
Webhook string `json:"webhook"`
RecoverScript string `json:"recover_script"`
}
/*