Merge branch 'duration-intervals'
All checks were successful
continuous-integration/drone/push Build is passing
All checks were successful
continuous-integration/drone/push Build is passing
This commit is contained in:
commit
31a4b484bf
17
README.md
17
README.md
@ -54,7 +54,7 @@ The global configurations are:
|
||||
|
||||
|key|value|
|
||||
|---|---|
|
||||
|`check_interval`|Maximum frequency to run checks for each monitor|
|
||||
|`check_interval`|Maximum frequency to run checks for each monitor as duration, eg. 1m2s.|
|
||||
|`monitors`|List of all monitors. Detailed description below|
|
||||
|`alerts`|List of all alerts. Detailed description below|
|
||||
|
||||
@ -111,7 +111,7 @@ minitor -metrics -metrics-port 3000
|
||||
|
||||
## Contributing
|
||||
|
||||
Whether you're looking to submit a patch or just tell me I broke something, you can contribute through the Github mirror and I can merge PRs back to the source repository.
|
||||
Whether you're looking to submit a patch or tell me I broke something, you can contribute through the Github mirror and I can merge PRs back to the source repository.
|
||||
|
||||
Primary Repo: https://git.iamthefij.com/iamthefij/minitor.git
|
||||
|
||||
@ -143,6 +143,18 @@ alerts:
|
||||
command: 'echo {{.MonitorName}}'
|
||||
```
|
||||
|
||||
Interval durations have changed from being an integer number of seconds to a duration string supported by Go, for example:
|
||||
|
||||
minitor-py:
|
||||
```yaml
|
||||
check_interval: 90
|
||||
```
|
||||
|
||||
minitor-go:
|
||||
```yaml
|
||||
check_interval: 1m30s
|
||||
```
|
||||
|
||||
For the time being, legacy configs for the Python version of Minitor should be compatible if you apply the `-py-compat` flag when running Minitor. Eventually, this flag will go away when later breaking changes are introduced.
|
||||
|
||||
## Future
|
||||
@ -153,4 +165,3 @@ Future, potentially breaking changes
|
||||
- [ ] Async checking
|
||||
- [ ] Revisit metrics and see if they all make sense
|
||||
- [ ] Consider dropping `alert_up` and `alert_down` in favor of using Go templates that offer more control of messaging (Breaking)
|
||||
- [ ] Use durations rather than seconds checked in event loop (Potentially breaking)
|
||||
|
31
config.go
31
config.go
@ -3,6 +3,7 @@ package main
|
||||
import (
|
||||
"errors"
|
||||
"io/ioutil"
|
||||
"time"
|
||||
|
||||
"git.iamthefij.com/iamthefij/slog"
|
||||
"gopkg.in/yaml.v2"
|
||||
@ -12,7 +13,7 @@ var errInvalidConfig = errors.New("Invalid configuration")
|
||||
|
||||
// Config type is contains all provided user configuration
|
||||
type Config struct {
|
||||
CheckInterval int64 `yaml:"check_interval"`
|
||||
CheckInterval SecondsOrDuration `yaml:"check_interval"`
|
||||
Monitors []*Monitor
|
||||
Alerts map[string]*Alert
|
||||
}
|
||||
@ -51,6 +52,34 @@ func (cos *CommandOrShell) UnmarshalYAML(unmarshal func(interface{}) error) erro
|
||||
return nil
|
||||
}
|
||||
|
||||
// SecondsOrDuration wraps a duration value for parsing a duration or seconds from YAML
|
||||
// NOTE: This should be removed in favor of only parsing durations once compatibility is broken
|
||||
type SecondsOrDuration struct {
|
||||
value time.Duration
|
||||
}
|
||||
|
||||
// Value returns a duration value
|
||||
func (sod SecondsOrDuration) Value() time.Duration {
|
||||
return sod.value
|
||||
}
|
||||
|
||||
// UnmarshalYAML allows unmarshalling a duration value or seconds if an int was provided
|
||||
func (sod *SecondsOrDuration) UnmarshalYAML(unmarshal func(interface{}) error) error {
|
||||
var seconds int64
|
||||
err := unmarshal(&seconds)
|
||||
|
||||
if err == nil {
|
||||
sod.value = time.Second * time.Duration(seconds)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// Error indicates that we don't have an int
|
||||
err = unmarshal(&sod.value)
|
||||
|
||||
return err
|
||||
}
|
||||
|
||||
// IsValid checks config validity and returns true if valid
|
||||
func (config Config) IsValid() (isValid bool) {
|
||||
isValid = true
|
||||
|
@ -3,6 +3,7 @@ package main
|
||||
import (
|
||||
"log"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
func TestLoadConfig(t *testing.T) {
|
||||
@ -35,11 +36,37 @@ func TestLoadConfig(t *testing.T) {
|
||||
|
||||
// Set PyCompat to default value
|
||||
PyCompat = false
|
||||
|
||||
log.Println("-----")
|
||||
}
|
||||
}
|
||||
|
||||
func TestIntervalParsing(t *testing.T) {
|
||||
log.Printf("Testing case TestIntervalParsing")
|
||||
|
||||
config, err := LoadConfig("./test/valid-config.yml")
|
||||
if err != nil {
|
||||
t.Errorf("Failed loading config: %v", err)
|
||||
}
|
||||
|
||||
oneSecond := time.Second
|
||||
tenSeconds := 10 * time.Second
|
||||
oneMinute := time.Minute
|
||||
|
||||
// validate top level interval seconds represented as an int
|
||||
if config.CheckInterval.Value() != oneSecond {
|
||||
t.Errorf("Incorrectly parsed int seconds. expected=%v actual=%v", oneSecond, config.CheckInterval)
|
||||
}
|
||||
|
||||
if config.Monitors[0].CheckInterval.Value() != tenSeconds {
|
||||
t.Errorf("Incorrectly parsed seconds duration. expected=%v actual=%v", oneSecond, config.CheckInterval)
|
||||
}
|
||||
|
||||
if config.Monitors[1].CheckInterval.Value() != oneMinute {
|
||||
t.Errorf("Incorrectly parsed seconds duration. expected=%v actual=%v", oneSecond, config.CheckInterval)
|
||||
}
|
||||
|
||||
log.Println("-----")
|
||||
}
|
||||
|
||||
// TestMultiLineConfig is a more complicated test stepping through the parsing
|
||||
// and execution of mutli-line strings presented in YAML
|
||||
func TestMultiLineConfig(t *testing.T) {
|
||||
|
3
main.go
3
main.go
@ -120,7 +120,6 @@ func main() {
|
||||
panic(err)
|
||||
}
|
||||
|
||||
sleepTime := time.Duration(config.CheckInterval) * time.Second
|
||||
time.Sleep(sleepTime)
|
||||
time.Sleep(config.CheckInterval.Value())
|
||||
}
|
||||
}
|
||||
|
10
monitor.go
10
monitor.go
@ -11,9 +11,9 @@ import (
|
||||
// Monitor represents a particular periodic check of a command
|
||||
type Monitor struct { //nolint:maligned
|
||||
// Config values
|
||||
AlertAfter int16 `yaml:"alert_after"`
|
||||
AlertEvery int16 `yaml:"alert_every"`
|
||||
CheckInterval float64 `yaml:"check_interval"`
|
||||
AlertAfter int16 `yaml:"alert_after"`
|
||||
AlertEvery int16 `yaml:"alert_every"`
|
||||
CheckInterval SecondsOrDuration `yaml:"check_interval"`
|
||||
Name string
|
||||
AlertDown []string `yaml:"alert_down"`
|
||||
AlertUp []string `yaml:"alert_up"`
|
||||
@ -43,9 +43,9 @@ func (monitor Monitor) ShouldCheck() bool {
|
||||
return true
|
||||
}
|
||||
|
||||
sinceLastCheck := time.Since(monitor.lastCheck).Seconds()
|
||||
sinceLastCheck := time.Since(monitor.lastCheck)
|
||||
|
||||
return sinceLastCheck >= monitor.CheckInterval
|
||||
return sinceLastCheck >= monitor.CheckInterval.Value()
|
||||
}
|
||||
|
||||
// Check will run the command configured by the Monitor and return a status
|
||||
|
@ -45,9 +45,9 @@ func TestMonitorShouldCheck(t *testing.T) {
|
||||
name string
|
||||
}{
|
||||
{Monitor{}, true, "Empty"},
|
||||
{Monitor{lastCheck: timeNow, CheckInterval: 15}, false, "Just checked"},
|
||||
{Monitor{lastCheck: timeTenSecAgo, CheckInterval: 15}, false, "-10s"},
|
||||
{Monitor{lastCheck: timeTwentySecAgo, CheckInterval: 15}, true, "-20s"},
|
||||
{Monitor{lastCheck: timeNow, CheckInterval: SecondsOrDuration{time.Second * 15}}, false, "Just checked"},
|
||||
{Monitor{lastCheck: timeTenSecAgo, CheckInterval: SecondsOrDuration{time.Second * 15}}, false, "-10s"},
|
||||
{Monitor{lastCheck: timeTwentySecAgo, CheckInterval: SecondsOrDuration{time.Second * 15}}, true, "-20s"},
|
||||
}
|
||||
|
||||
for _, c := range cases {
|
||||
|
@ -3,21 +3,23 @@ check_interval: 1
|
||||
|
||||
monitors:
|
||||
- name: Command
|
||||
command: ['echo', '$PATH']
|
||||
alert_down: ['log_command', 'log_shell']
|
||||
command: ["echo", "$PATH"]
|
||||
alert_down: ["log_command", "log_shell"]
|
||||
alert_every: 0
|
||||
check_interval: 10s
|
||||
- name: Shell
|
||||
command: >
|
||||
echo 'Some string with stuff';
|
||||
echo 'another line';
|
||||
echo $PATH;
|
||||
exit 1
|
||||
alert_down: ['log_command', 'log_shell']
|
||||
alert_down: ["log_command", "log_shell"]
|
||||
alert_after: 5
|
||||
alert_every: 0
|
||||
check_interval: 1m
|
||||
|
||||
alerts:
|
||||
log_command:
|
||||
command: ['echo', 'regular', '"command!!!"', "{{.MonitorName}}"]
|
||||
command: ["echo", "regular", '"command!!!"', "{{.MonitorName}}"]
|
||||
log_shell:
|
||||
command: echo "Failure on {{.MonitorName}} User is $USER"
|
||||
|
Loading…
Reference in New Issue
Block a user