Compare commits

..

1 Commits

Author SHA1 Message Date
Ian Fijolek
6c7c0a470f WIP: Begin adding prometheus metrics exporting 2019-11-15 11:25:21 -08:00
41 changed files with 854 additions and 2253 deletions
+6 -93
View File
@@ -1,100 +1,13 @@
---
kind: pipeline kind: pipeline
name: test name: test
steps: steps:
- name: build
image: golang:1.12
commands:
- make build
- name: test - name: test
image: golang:1.26 image: golang:1.12
environment:
VERSION: ${DRONE_TAG:-${DRONE_COMMIT}}
commands: commands:
- make test - make test
- name: check
image: iamthefij/drone-pre-commit:personal
---
kind: pipeline
name: publish
depends_on:
- test
trigger:
event:
- push
- tag
refs:
- refs/heads/master
- refs/tags/v*
steps:
- name: build all binaries
image: golang:1.26
environment:
VERSION: ${DRONE_TAG:-${DRONE_COMMIT}}
commands:
- make all
- name: compress binaries for release
image: ubuntu
commands:
- find ./dist -type f -executable -execdir tar -czvf {}.tar.gz {} \;
when:
event: tag
- name: upload gitea release
image: plugins/gitea-release
settings:
title: ${DRONE_TAG}
files: dist/*.tar.gz
checksum:
- md5
- sha1
- sha256
- sha512
base_url:
from_secret: gitea_base_url
api_key:
from_secret: gitea_token
when:
event: tag
- name: Build and publish docker images
image: thegeeklab/drone-docker-buildx
settings:
repo: iamthefij/minitor-go
auto_tag: true
platforms:
- linux/amd64
- linux/arm64
- linux/arm
username:
from_secret: docker_username
password:
from_secret: docker_password
---
kind: pipeline
name: notify
depends_on:
- test
- publish
trigger:
status:
- failure
steps:
- name: notify
image: drillster/drone-email
settings:
host:
from_secret: SMTP_HOST # pragma: whitelist secret
username:
from_secret: SMTP_USER # pragma: whitelist secret
password:
from_secret: SMTP_PASS # pragma: whitelist secret
from: drone@iamthefij.com
-112
View File
@@ -1,112 +0,0 @@
name: ci
on:
push:
branches:
- main
tags:
- "v*"
pull_request:
branches:
- main
jobs:
tests:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: go.mod
- name: Run tests
run: make test
lint:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: go.mod
- name: Set up Python
uses: actions/setup-python@v6
- name: Run pre-commit
uses: https://git.iamthefij.com/iamthefij/pre-commit-action@v3.1.0
release:
runs-on: ubuntu-latest
needs: test
if: "${{ github.event_name != 'pull_request' }}"
steps:
- uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: go.mod
- name: Build binaries
env:
VERSION: "${{ github.REF_NAME }}"
run: make all
# Package binaries and create release if this is a tagged build
- name: Compress binaries
if: "${{ github.ref_type == 'tag' }}"
run: find ./dist -type f -executable -execdir tar -czvf {}.tar.gz {} \;
- name: Upload release
uses: https://gitea.com/actions/gitea-release-action@v1
if: "${{ github.ref_type == 'tag' }}"
with:
files: |-
dist/*.tar.gz
md5sum: true
sha256sum: true
- name: Docker meta
id: meta
uses: docker/metadata-action@v6
with:
# list of Docker images to use as base name for tags
images: |
${{ github.REPOSITORY }}
# generate Docker tags based on the following events/attributes
tags: |
type=ref,event=branch
type=ref,event=pr
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
type=semver,pattern={{major}}
- name: Login to Docker Hub
uses: docker/login-action@v4
if: "${{ github.event_name != 'pull_request' }}"
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Set up QEMU
uses: docker/setup-qemu-action@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Build and push
uses: docker/build-push-action@v7
with:
# Use path context so we can access pre-compiled binaries
context: .
push: ${{ github.event_name != 'pull_request' }}
platforms: |
linux/amd64
linux/arm64
linux/arm/v7
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
Vendored
-3
View File
@@ -14,9 +14,6 @@
# User configuration # User configuration
config.yml config.yml
config.hcl
# Output binary # Output binary
minitor
minitor-go minitor-go
dist/
-34
View File
@@ -1,34 +0,0 @@
version: "2"
linters:
enable:
- errcheck
- errname
- errorlint
- exhaustive
- gosec
- govet
- ineffassign
- misspell
- mnd
- modernize
- staticcheck
- tagalign
- testpackage
- thelper
- tparallel
- unconvert
- unused
- wrapcheck
- wsl_v5
exclusions:
generated: lax
presets:
- common-false-positives
rules:
- linters:
- gosec
path: _test\.go
formatters:
enable:
- gofumpt
- goimports
-20
View File
@@ -1,20 +0,0 @@
---
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v6.0.0
hooks:
- id: check-added-large-files
- id: check-yaml
args:
- --allow-multiple-documents
- id: trailing-whitespace
- id: end-of-file-fixer
- id: check-merge-conflict
- repo: https://github.com/golangci/golangci-lint
rev: v2.10.1
hooks:
- id: golangci-lint
- repo: https://github.com/hadolint/hadolint
rev: refs/pull/1152/head
hooks:
- id: hadolint-github
+5 -22
View File
@@ -1,25 +1,8 @@
FROM alpine:3.23 ARG REPO=library
FROM ${REPO}/busybox:latest
WORKDIR /root/
RUN mkdir /app ARG ARCH=amd64
WORKDIR /app/ COPY ./minitor-go ./minitor
# Add common checking tools
# hadolint ignore=DL3018
RUN apk --no-cache add bash=~5 curl=~8 jq=~1 bind-tools=~9 tzdata
# Add minitor user for running as non-root
RUN addgroup -S minitor && adduser -S minitor -G minitor
# Copy scripts
COPY ./scripts /app/scripts
RUN chmod -R 755 /app/scripts
# Copy minitor in
ARG TARGETOS
ARG TARGETARCH
COPY ./dist/minitor-${TARGETOS}-${TARGETARCH} ./minitor
# Drop to non-root user
USER minitor
ENTRYPOINT [ "./minitor" ] ENTRYPOINT [ "./minitor" ]
+9 -25
View File
@@ -1,5 +1,9 @@
FROM golang:1.26 AS builder ARG REPO=library
FROM golang:1.12-alpine AS builder
RUN apk add --no-cache git
RUN mkdir /app
WORKDIR /app WORKDIR /app
COPY ./go.mod ./go.sum /app/ COPY ./go.mod ./go.sum /app/
@@ -7,33 +11,13 @@ RUN go mod download
COPY ./*.go /app/ COPY ./*.go /app/
ARG TARGETOS ARG ARCH=amd64
ARG TARGETARCH
ARG VERSION=dev ARG VERSION=dev
ENV CGO_ENABLED=0 GOOS=$TARGETOS GOARCH=${TARGETARCH} ENV CGO_ENABLED=0 GOOS=linux GOARCH=${ARCH}
RUN go build -ldflags "-X main.version=${VERSION}" -a -installsuffix nocgo -o minitor . RUN go build -ldflags "-X main.version=${VERSION}" -a -installsuffix nocgo -o minitor .
FROM alpine:3.23 FROM ${REPO}/busybox:latest
RUN mkdir /app WORKDIR /root/
WORKDIR /app/
# Copy minitor in
COPY --from=builder /app/minitor . COPY --from=builder /app/minitor .
# Add common checking tools
# hadolint ignore=DL3018
RUN apk --no-cache add bash=~5 curl=~8 jq=~1 bind-tools=~9 tzdata
# Add minitor user for running as non-root
RUN addgroup -S minitor && adduser -S minitor -G minitor
# Copy scripts
COPY ./scripts /app/scripts
RUN chmod -R 755 /app/scripts
# Drop to non-root user
USER minitor
ENTRYPOINT [ "./minitor" ] ENTRYPOINT [ "./minitor" ]
# vim: set filetype=dockerfile:
+15 -71
View File
@@ -1,95 +1,39 @@
DOCKER_TAG ?= minitor-go-${USER} DOCKER_TAG ?= minitor-go-${USER}
VERSION ?= $(shell git describe --tags --dirty)
GOFILES = *.go go.mod go.sum
# Multi-arch targets are generated from this
TARGET_ALIAS = minitor-linux-amd64 minitor-linux-arm minitor-linux-arm64 minitor-darwin-amd64
TARGETS = $(addprefix dist/,$(TARGET_ALIAS))
#
# Default make target will run tests
.DEFAULT_GOAL = test
# Build all static Minitor binaries .PHONY: test
.PHONY: all default: test
all: $(TARGETS)
# Build all static Linux Minitor binaries. Used in Docker images
.PHONY: all-linux
all-linux: $(filter dist/minitor-linux-%,$(TARGETS))
# Build minitor for the current machine
minitor: $(GOFILES)
@echo Version: $(VERSION)
go build -ldflags '-X "main.version=${VERSION}"' -o minitor
.PHONY: build .PHONY: build
build: minitor build:
go build
minitor-go:
go build
# Run minitor for the current machine
.PHONY: run .PHONY: run
run: minitor run: minitor-go build
./minitor -debug ./minitor-go -debug
.PHONY: run-metrics
run-metrics: minitor
./minitor -debug -metrics
# Run all tests
.PHONY: test .PHONY: test
test: test:
go test -coverprofile=coverage.out go test -coverprofile=coverage.out
@echo
go tool cover -func=coverage.out go tool cover -func=coverage.out
@echo
@# Check min coverage percentage
@go tool cover -func=coverage.out | awk -v target=80.0% \ @go tool cover -func=coverage.out | awk -v target=80.0% \
'/^total:/ { print "Total coverage: " $$3 " Minimum coverage: " target; if ($$3+0.0 >= target+0.0) print "ok"; else { print "fail"; exit 1; } }' '/^total:/ { print "Total coverage: " $$3 " Minimum coverage: " target; if ($$3+0.0 >= target+0.0) print "ok"; else { print "fail"; exit 1; } }'
# Installs pre-commit hooks
.PHONY: install-hooks
install-hooks:
pre-commit install --install-hooks
# Runs pre-commit checks on files
.PHONY: check
check:
pre-commit run --all-files
.PHONY: clean .PHONY: clean
clean: clean:
rm -f ./minitor rm -f ./minitor-go
rm -f ./coverage.out rm -f ./coverage.out
rm -fr ./dist
.PHONY: docker-build .PHONY: docker-build
docker-build: docker-build:
docker build -f ./Dockerfile.multi-stage -t $(DOCKER_TAG)-linux-amd64 . docker build -f ./Dockerfile.multi-stage -t $(DOCKER_TAG) .
.PHONY: docker-run .PHONY: docker-run
docker-run: docker-build docker-run: docker-build
docker run --rm -v $(shell pwd)/sample-config.hcl:/root/config.hcl $(DOCKER_TAG) docker run --rm -v $(shell pwd)/config.yml:/root/config.yml $(DOCKER_TAG)
## Multi-arch targets
$(TARGETS): $(GOFILES)
mkdir -p ./dist
GOOS=$(word 2, $(subst -, ,$(@))) GOARCH=$(word 3, $(subst -, ,$(@))) CGO_ENABLED=0 \
go build -ldflags '-X "main.version=${VERSION}"' -a -installsuffix nocgo \
-o $@
.PHONY: $(TARGET_ALIAS)
$(TARGET_ALIAS):
$(MAKE) $(addprefix dist/,$@)
# Arch specific docker build targets
.PHONY: docker-build-arm
docker-build-arm: dist/minitor-linux-arm
docker build --platform linux/arm . -t ${DOCKER_TAG}-linux-arm
.PHONY: docker-build-arm64
docker-build-arm64: dist/minitor-linux-arm64
docker build --platform linux/arm64 . -t ${DOCKER_TAG}-linux-arm64
# Cross run on host architechture
.PHONY: docker-run-arm
docker-run-arm: docker-build-arm
docker run --rm -v /var/run/docker.sock:/var/run/docker.sock --name $(DOCKER_TAG)-run ${DOCKER_TAG}-linux-arm
.PHONY: docker-run-arm64
docker-run-arm64: docker-build-arm64
docker run --rm -v /var/run/docker.sock:/var/run/docker.sock --name $(DOCKER_TAG)-run ${DOCKER_TAG}-linux-arm64
+79 -202
View File
@@ -1,220 +1,97 @@
# [minitor-go](https://git.iamthefij.com/iamthefij/minitor-go) # minitor-go
A minimal monitoring system A reimplementation of [Minitor](https://git.iamthefij/iamthefij/minitor) in Go
## What does it do? Minitor is already a very minimal monitoring tool. Python 3 was a quick way to get something live, but Python itself comes with a very large footprint.Thus Go feels like a better fit for the project, longer term.
Minitor accepts an HCL configuration file with a set of commands to run and a set of alerts to execute when those commands fail. Minitor has a narow feature set and instead follows a principle to outsource to other command line tools when possible. Thus, it relies on other command line tools to do checks and issue alerts. To make getting started a bit easier, Minitor includes a few scripts to help with common tasks. Initial target is meant to be roughly compatible requiring only minor changes to configuration. Future iterations may diverge to take advantage of Go specific features.
## But why? ## Differences from Python version
I'm running a few small services and found Sensu, Consul, Nagios, etc. to all be far too complicated for my usecase. There are a few key differences between the Python version and the v0.x Go version.
## So how do I use it? First, configuration keys cannot have multiple types in Go, so a different key must be used when specifying a Shell command as a string rather than a list of args. Instead of `command`, you must use `command_shell`. Eg:
### Running
Install and execute with:
```bash
go install github.com/iamthefij/minitor-go/v2@latest
minitor
```
If locally developing you can use:
```bash
make run
```
It will read the contents of `sample-config.hcl` and begin its loop. You could also run it directly and provide a new config file via the `-config` argument.
#### Docker
You can pull this repository directly from Docker:
```bash
docker pull iamthefij/minitor-go:latest
```
The Docker image uses a default `config.hcl` copied from `sample-config.hcl`. This won't really do anything for you, so when you run the Docker image, you should supply your own `config.hcl` file:
```bash
docker run -v $PWD/sample-config.hcl:/app/config.hcl iamthefij/minitor-go:latest
```
Images are provided for `amd64`, `arm`, and `arm64` architechtures.
You can configure the timezone for the container by passing a `TZ` env variable. Eg. `TZ=America/Los_Angeles`.
## Configuring
In this repo, you can explore the `sample-config.hcl` file for an example, but the general structure is as follows. If you are passing environment variables to your commands or alerts, you should be aware that `${VAR}` syntax is reserved for HCL variable interpolation. To avoid issues, you can use `$${VAR}` syntax to escape the `$` character, simply use `$VAR`.
```hcl
The global configurations are:
|key|value|
|---|---|
|`check_interval`|Maximum frequency to run checks for each monitor as duration, eg. 1m2s.|
|`default_alert_after`|A default value used as an `alert_after` value for a monitor if not specified. Defaults 1, which will alert immediately.|
|`default_alert_every`|A default value used as an `alert_every` value for a monitor if not specified. Defaults to -1, which will re-alert exponentially.|
|`default_alert_down`|Default down alerts to used by a monitor in case none are provided.|
|`default_alert_up`|Default up alerts to used by a monitor in case none are provided.|
|`monitor`|block listing monitors. Detailed description below|
|`alert`|List of all alerts. Detailed description below|
### Monitors
Represent your monitors as blocks with a label indicating the name of the monitor.
```hcl
monitor "example" {
command = ["echo", "Hello, World!"]
alert_down = ["log"]
alert_up = ["log"]
check_interval = "1m"
alert_after = 1
alert_every = -1
}
```
Each monitor allows the following configuration:
|key|value|
|---|---|
|`name`|Name of the monitor running. This will show up in messages and logs.|
|`command`|A list of strings representing a command to be executed. This command's exit value will determine whether the check is successful. This value is mutually exclusive to `shell_command`|
|`shell_command`|A single string that represents a shell command to be executed. This command's exit value will determine whether the check is successful. This value is mutually exclusive to `command`|
|`alert_down`|A list of Alerts to be triggered when the monitor is in a "down" state|
|`alert_up`|A list of Alerts to be triggered when the monitor moves to an "up" state|
|`check_interval`|The interval at which this monitor should be checked. This must be greater than the global `check_interval` value|
|`alert_after`|Allows specifying the number of failed checks before an alert should be triggered. A value of 1 will start sending alerts after the first failure.|
|`alert_every`|Allows specifying how often an alert should be retriggered. There are a few magic numbers here. Defaults to `-1` for an exponential backoff. Setting to `0` disables re-alerting. Positive values will allow retriggering after the specified number of checks|
### Alerts
Represent your alerts as blocks with a lable indicating the name of the alert. The name will be used in your monitor setup in `alert_down` and `alert_up`.
```hcl
monitor "example" {
command = ["false"]
alert_down = ["log"]
}
alert "log" {
shell_command = "echo '{{.MonitorName}} is down!'"
}
```
Each alert allows the following configuration:
|key|value|
|---|---|
|`command`|Specifies the command that should be executed in exec form. This is the command that will be run when the alert is executed. This can be templated with environment variables or the variables shown in the table below. This value is mutually exclusive to `shell_command`|
|`shell_command`|Specifies a shell command as a single string. This is the command that will be run when the alert is executed. This can be templated with environment variables or the variables shown in the table below. This value is mutually exclusive to `command`|
Also, when alerts are executed, they will be passed through Go's format function with arguments for some attributes of the Monitor. The following monitor specific variables can be referenced using Go formatting syntax:
|token|value|
|---|---|
|`{{.AlertCount}}`|Number of times this monitor has alerted|
|`{{.FailureCount}}`|The total number of sequential failed checks for this monitor|
|`{{.LastCheckOutput}}`|The last returned value from the check command to either stderr or stdout|
|`{{.LastSuccess}}`|The datetime of the last successful check as a go Time struct|
|`{{.MonitorName}}`|The name of the monitor that failed and triggered the alert|
|`{{.IsUp}}`|Indicates if the monitor that is alerting is up or not. Can be used in a conditional message template|
To provide flexible formatting, the following non-standard functions are available in templates:
|func|description|
|---|---|
|`ANSIC <Time>`|Formats provided time in ANSIC format|
|`UnixDate <Time>`|Formats provided time in UnixDate format|
|`RubyDate <Time>`|Formats provided time in RubyDate format|
|`RFC822Z <Time>`|Formats provided time in RFC822Z format|
|`RFC850 <Time>`|Formats provided time in RFC850 format|
|`RFC1123 <Time>`|Formats provided time in RFC1123 format|
|`RFC1123Z <Time>`|Formats provided time in RFC1123Z format|
|`RFC3339 <Time>`|Formats provided time in RFC3339 format|
|`RFC3339Nano <Time>`|Formats provided time in RFC3339Nano format|
|`FormatTime <Time> <string template>`|Formats provided time according to provided template|
|`InTZ <Time> <string timezone name>`|Converts provided time to parsed timezone from the provided name|
For more information, check out the [Go documentation for the time module](https://pkg.go.dev/time@go1.20.7#pkg-constants).
#### Running alerts on startup
It's not the best feeling to find out your alerts are broken when you're expecting to be alerted about another failure. To avoid this and provide early insight into broken alerts, it is possible to specify a list of alerts to run when Minitor starts up. This can be done using the command line flag `-startup-alerts`. This flag accepts a comma separated list of strings and will run a test of each of those alerts. Minitor will then respond as it typically does for any failed alert. This can be used to allow you time to correct when initially launching, and to allow schedulers to more easily detect a failed deployment of Minitor.
Eg.
```bash
minitor -startup-alerts=log_down,log_up -config ./config.hcl
```
### Metrics
Minitor supports exporting metrics for [Prometheus](https://prometheus.io/). Prometheus is an open source tool for reading and querying metrics from different sources. Combined with another tool, [Grafana](https://grafana.com/), it allows building of charts and dashboards. You could also opt to just use Minitor to log check results, and instead do your alerting with Grafana.
It is also possible to use the metrics endpoint for monitoring Minitor itself! This allows setting up multiple instances of Minitor on different servers and have them monitor each-other so that you can detect a minitor outage.
To run minitor with metrics, use the `-metrics` flag. The metrics will be served on port `8080` by default, though it can be overriden using `-metrics-port`. They will be accessible on the path `/metrics`. Eg. `localhost:8080/metrics`.
```bash
minitor -metrics
# or
minitor -metrics -metrics-port 3000
```
## Migrating from v1 to v2
Minitor v2 introduces some breaking changes from v1. The most notable changes are:
- The configuration file is now in HCL format instead of YAML.
- The the Python formatting backwards compatability is removed.
- The Command and ShellCommand fields are now mutually exclusive.
- The check_interval is now strictly a duration string value. Eg. "30s" rather than `30`.
- Default alert_every is now -1 (exponential backoff) rather than 0 (no re-alerting).
For the configuration, a confic that looked like this in v1:
minitor-py:
```yaml ```yaml
check_interval: 60
monitors: monitors:
- name: example - name: Exec command
command: "false" command: ['echo', 'test']
alert_down: ["log"] - name: Shell command
command: echo 'test'
```
minitor-go:
```yaml
monitors:
- name: Exec command
command: ['echo', 'test']
- name: Shell command
command_shell: echo 'test'
```
Second, templating for Alert messages has been updated. In the Python version, `str.format(...)` was used with certain keys passed in that could be used to format messages. In the Go version, we use a struct containing Alert info and the built in Go templating format. Eg.
minitor-py:
```yaml
alerts: alerts:
log: log_command:
command: ["echo", "Minitor up={{.IsUp}} for {{.MonitorName}}"] command: ['echo', '{monitor_name}']
log_shell:
command_shell: "echo {monitor_name}"
``` ```
Would now look like this in v2: minitor-go:
```yaml
```hcl alerts:
check_interval = "1m" log_command:
command: ['echo', '{{.MonitorName}}']
monitor "example" { log_shell:
# example showing string to shell command migration command_shell: "echo {{.MonitorName}}"
shell_command = "false"
alert_down = ["log"]
check_interval = "1m"
}
alert "log" {
# example showing list to exec command migration
command = ["echo", "Minitor up={{.IsUp}} for {{.MonitorName}}"]
}
``` ```
## Contributing Finally, newlines in a shell command don't terminate a particular command. Semicolons must be used and continuations should not.
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. minitor-py:
```yaml
alerts:
log_shell:
command_shell: >
echo "line 1"
echo "line 2"
echo "continued" \
"line"
```
Primary Repo: https://git.iamthefij.com/iamthefij/minitor.git minitor-go:
```yaml
alerts:
log_shell:
command_shell: >
echo "line 1";
echo "line 2";
echo "continued"
"line"
```
Github Mirror: https://github.com/IamTheFij/minitor.git ## To do
There are two sets of task lists. The first is to get rough parity on key features with the Python version. The second is to make some improvements to the framework.
Pairity:
- [x] Run monitor commands
- [x] Run monitor commands in a shell
- [x] Run alert commands
- [x] Run alert commands in a shell
- [x] Allow templating of alert commands
- [ ] Implement Prometheus client to export metrics
- [ ] Test coverage
Improvement:
- [ ] Implement leveled logging (maybe glog or logrus)
- [ ] Consider switching from YAML to TOML
- [ ] Consider value of templating vs injecting values into Env variables
- [ ] Consider dropping `alert_up` and `alert_down` in favor of using Go templates that offer more control of messaging
- [ ] Async checking
- [ ] Use durations rather than seconds checked in event loop
+32 -111
View File
@@ -2,161 +2,89 @@ package main
import ( import (
"bytes" "bytes"
"errors"
"fmt" "fmt"
"log"
"os/exec" "os/exec"
"text/template" "text/template"
"time" "time"
"git.iamthefij.com/iamthefij/slog/v2"
)
var (
errNoTemplate = errors.New("no template")
// ErrAlertFailed indicates that an alert failed to send
ErrAlertFailed = errors.New("alert failed")
) )
// Alert is a config driven mechanism for sending a notice // Alert is a config driven mechanism for sending a notice
type Alert struct { type Alert struct {
Name string `hcl:"name,label"` Name string
Command []string `hcl:"command,optional"` Command []string
ShellCommand string `hcl:"shell_command,optional"` CommandShell string `yaml:"command_shell"`
commandTemplate []*template.Template commandTemplate []*template.Template
commandShellTemplate *template.Template commandShellTemplate *template.Template
} }
// AlertNotice captures the context for an alert to be sent // AlertNotice captures the context for an alert to be sent
type AlertNotice struct { type AlertNotice struct {
AlertCount int
FailureCount int
IsUp bool
LastSuccess time.Time
MonitorName string MonitorName string
AlertCount int16
FailureCount int16
LastCheckOutput string LastCheckOutput string
LastSuccess time.Time
IsUp bool
} }
// Validate checks that the Alert is properly configured and returns errors if not // IsValid returns a boolean indicating if the Alert has been correctly
func (alert Alert) Validate() error { // configured
hasCommand := len(alert.Command) > 0 func (alert Alert) IsValid() bool {
hasShellCommand := alert.ShellCommand != "" atLeastOneCommand := (alert.CommandShell != "" || alert.Command != nil)
atMostOneCommand := (alert.CommandShell == "" || alert.Command == nil)
var err error return atLeastOneCommand && atMostOneCommand
hasAtLeastOneCommand := hasCommand || hasShellCommand
if !hasAtLeastOneCommand {
err = errors.Join(err, fmt.Errorf(
"%w: alert %s has no command or shell_command configured",
ErrInvalidAlert,
alert.Name,
))
}
hasAtMostOneCommand := !(hasCommand && hasShellCommand)
if !hasAtMostOneCommand {
err = errors.Join(err, fmt.Errorf(
"%w: alert %s has both command and shell_command configured",
ErrInvalidAlert,
alert.Name,
))
}
return err
} }
// BuildTemplates compiles command templates for the Alert // BuildTemplates compiles command templates for the Alert
func (alert *Alert) BuildTemplates() error { func (alert *Alert) BuildTemplates() error {
slog.Debugf("Building template for alert %s", alert.Name) if LogDebug {
log.Printf("DEBUG: Building template for alert %s", alert.Name)
// Time format func factory
tff := func(formatString string) func(time.Time) string {
return func(t time.Time) string {
return t.Format(formatString)
}
} }
if alert.commandTemplate == nil && alert.Command != nil {
// Create some functions for formatting datetimes in popular formats
timeFormatFuncs := template.FuncMap{
"ANSIC": tff(time.ANSIC),
"UnixDate": tff(time.UnixDate),
"RubyDate": tff(time.RubyDate),
"RFC822Z": tff(time.RFC822Z),
"RFC850": tff(time.RFC850),
"RFC1123": tff(time.RFC1123),
"RFC1123Z": tff(time.RFC1123Z),
"RFC3339": tff(time.RFC3339),
"RFC3339Nano": tff(time.RFC3339Nano),
"FormatTime": func(t time.Time, timeFormat string) string {
return t.Format(timeFormat)
},
"InTZ": func(t time.Time, tzName string) (time.Time, error) {
tz, err := time.LoadLocation(tzName)
if err != nil {
return t, fmt.Errorf("failed to convert time to specified tz: %w", err)
}
return t.In(tz), nil
},
}
switch {
case alert.Command != nil:
alert.commandTemplate = []*template.Template{} alert.commandTemplate = []*template.Template{}
for i, cmdPart := range alert.Command { for i, cmdPart := range alert.Command {
alert.commandTemplate = append(alert.commandTemplate, template.Must( alert.commandTemplate = append(alert.commandTemplate, template.Must(
template.New(alert.Name+fmt.Sprint(i)).Funcs(timeFormatFuncs).Parse(cmdPart), template.New(alert.Name+string(i)).Parse(cmdPart),
)) ))
} }
case alert.ShellCommand != "": } else if alert.commandShellTemplate == nil && alert.CommandShell != "" {
shellCmd := alert.ShellCommand
alert.commandShellTemplate = template.Must( alert.commandShellTemplate = template.Must(
template.New(alert.Name).Funcs(timeFormatFuncs).Parse(shellCmd), template.New(alert.Name).Parse(alert.CommandShell),
) )
default: } else {
return fmt.Errorf("No template provided for alert %s: %w", alert.Name, errNoTemplate) return fmt.Errorf("No template provided for alert %s", alert.Name)
} }
return nil return nil
} }
// Send will send an alert notice by executing the command template // Send will send an alert notice by executing the command template
func (alert Alert) Send(notice AlertNotice) (outputStr string, err error) { func (alert Alert) Send(notice AlertNotice) (output_str string, err error) {
slog.Infof("Sending alert %s for %s", alert.Name, notice.MonitorName) log.Printf("INFO: Sending alert %s for %s", alert.Name, notice.MonitorName)
var cmd *exec.Cmd var cmd *exec.Cmd
if alert.commandTemplate != nil {
switch {
case alert.commandTemplate != nil:
command := []string{} command := []string{}
for _, cmdTmp := range alert.commandTemplate { for _, cmdTmp := range alert.commandTemplate {
var commandBuffer bytes.Buffer var commandBuffer bytes.Buffer
err = cmdTmp.Execute(&commandBuffer, notice) err = cmdTmp.Execute(&commandBuffer, notice)
if err != nil { if err != nil {
return return
} }
command = append(command, commandBuffer.String()) command = append(command, commandBuffer.String())
} }
cmd = exec.Command(command[0], command[1:]...) cmd = exec.Command(command[0], command[1:]...)
case alert.commandShellTemplate != nil: } else if alert.commandShellTemplate != nil {
var commandBuffer bytes.Buffer var commandBuffer bytes.Buffer
err = alert.commandShellTemplate.Execute(&commandBuffer, notice) err = alert.commandShellTemplate.Execute(&commandBuffer, notice)
if err != nil { if err != nil {
return return
} }
shellCommand := commandBuffer.String() shellCommand := commandBuffer.String()
cmd = ShellCommand(shellCommand) cmd = ShellCommand(shellCommand)
default: } else {
err = fmt.Errorf("No templates compiled for alert %s: %w", alert.Name, errNoTemplate) err = fmt.Errorf("No templates compiled for alert %v", alert.Name)
return return
} }
@@ -167,17 +95,10 @@ func (alert Alert) Send(notice AlertNotice) (outputStr string, err error) {
var output []byte var output []byte
output, err = cmd.CombinedOutput() output, err = cmd.CombinedOutput()
outputStr = string(output) output_str = string(output)
slog.Debugf("Alert output for: %s\n---\n%s\n---", alert.Name, outputStr) if LogDebug {
log.Printf("DEBUG: Alert output for: %s\n---\n%s\n---", alert.Name, output_str)
if err != nil {
err = fmt.Errorf(
"Alert %s failed to send. Returned %w: %w",
alert.Name,
err,
ErrAlertFailed,
)
} }
return outputStr, err return output_str, err
} }
+58 -74
View File
@@ -1,74 +1,69 @@
package main_test package main
import ( import (
"errors" "log"
"testing" "testing"
m "git.iamthefij.com/iamthefij/minitor-go/v2"
) )
func TestAlertValidate(t *testing.T) { func TestAlertIsValid(t *testing.T) {
t.Parallel()
cases := []struct { cases := []struct {
alert m.Alert alert Alert
expected error expected bool
name string name string
}{ }{
{m.Alert{Command: []string{"echo", "test"}}, nil, "Command only"}, {Alert{Command: []string{"echo", "test"}}, true, "Command only"},
{m.Alert{ShellCommand: "echo test"}, nil, "CommandShell only"}, {Alert{CommandShell: "echo test"}, true, "CommandShell only"},
{m.Alert{Command: []string{"echo", "test"}, ShellCommand: "echo test"}, m.ErrInvalidAlert, "Both commands"}, {Alert{}, false, "No commands"},
{m.Alert{}, m.ErrInvalidAlert, "No commands"}, {
Alert{Command: []string{"echo", "test"}, CommandShell: "echo test"},
false,
"Both commands",
},
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { actual := c.alert.IsValid()
t.Parallel() if actual != c.expected {
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expected, actual)
actual := c.alert.Validate() log.Printf("Case failed: %s", c.name)
hasErr := (actual != nil) }
expectErr := (c.expected != nil) log.Println("-----")
if hasErr != expectErr || !errors.Is(actual, c.expected) {
t.Errorf("expected=%t actual=%t", c.expected, actual)
}
})
} }
} }
func TestAlertSend(t *testing.T) { func TestAlertSend(t *testing.T) {
cases := []struct { cases := []struct {
alert m.Alert alert Alert
notice m.AlertNotice notice AlertNotice
expectedOutput string expectedOutput string
expectErr bool expectErr bool
name string name string
}{ }{
{ {
m.Alert{Command: []string{"echo", "{{.MonitorName}}"}}, Alert{Command: []string{"echo", "{{.MonitorName}}"}},
m.AlertNotice{MonitorName: "test"}, AlertNotice{MonitorName: "test"},
"test\n", "test\n",
false, false,
"Command with template", "Command with template",
}, },
{ {
m.Alert{ShellCommand: "echo {{.MonitorName}}"}, Alert{CommandShell: "echo {{.MonitorName}}"},
m.AlertNotice{MonitorName: "test"}, AlertNotice{MonitorName: "test"},
"test\n", "test\n",
false, false,
"Command shell with template", "Command shell with template",
}, },
{ {
m.Alert{Command: []string{"echo", "{{.Bad}}"}}, Alert{Command: []string{"echo", "{{.Bad}}"}},
m.AlertNotice{MonitorName: "test"}, AlertNotice{MonitorName: "test"},
"", "",
true, true,
"Command with bad template", "Command with bad template",
}, },
{ {
m.Alert{ShellCommand: "echo {{.Bad}}"}, Alert{CommandShell: "echo {{.Bad}}"},
m.AlertNotice{MonitorName: "test"}, AlertNotice{MonitorName: "test"},
"", "",
true, true,
"Command shell with bad template", "Command shell with bad template",
@@ -76,62 +71,51 @@ func TestAlertSend(t *testing.T) {
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { c.alert.BuildTemplates()
t.Parallel() output, err := c.alert.Send(c.notice)
hasErr := (err != nil)
err := c.alert.BuildTemplates() if output != c.expectedOutput {
if err != nil { t.Errorf("Send(%v output), expected=%v actual=%v", c.name, c.expectedOutput, output)
t.Errorf("Send(%v output), error building templates: %v", c.name, err) log.Printf("Case failed: %s", c.name)
} }
if hasErr != c.expectErr {
output, err := c.alert.Send(c.notice) t.Errorf("Send(%v err), expected=%v actual=%v", c.name, "Err", err)
hasErr := (err != nil) log.Printf("Case failed: %s", c.name)
}
if output != c.expectedOutput { log.Println("-----")
t.Errorf("Send(%v output), expected=%v actual=%v", c.name, c.expectedOutput, output)
}
if hasErr != c.expectErr {
t.Errorf("Send(%v err), expected=%v actual=%v", c.name, "Err", err)
}
})
} }
} }
func TestAlertSendNoTemplates(t *testing.T) { func TestAlertSendNoTemplates(t *testing.T) {
alert := m.Alert{} alert := Alert{}
notice := m.AlertNotice{} notice := AlertNotice{}
output, err := alert.Send(notice) output, err := alert.Send(notice)
if err == nil { if err == nil {
t.Errorf("Send(no template), expected=%v actual=%v", "Err", output) t.Errorf("Send(no template), expected=%v actual=%v", "Err", output)
} }
log.Println("-----")
} }
func TestAlertBuildTemplate(t *testing.T) { func TestAlertBuildTemplate(t *testing.T) {
cases := []struct { cases := []struct {
alert m.Alert alert Alert
expectErr bool expectErr bool
name string name string
}{ }{
{m.Alert{Command: []string{"echo", "test"}}, false, "Command only"}, {Alert{Command: []string{"echo", "test"}}, false, "Command only"},
{m.Alert{ShellCommand: "echo test"}, false, "CommandShell only"}, {Alert{CommandShell: "echo test"}, false, "CommandShell only"},
{m.Alert{}, true, "No commands"}, {Alert{}, true, "No commands"},
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { err := c.alert.BuildTemplates()
t.Parallel() hasErr := (err != nil)
if hasErr != c.expectErr {
err := c.alert.BuildTemplates() t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expectErr, err)
hasErr := (err != nil) log.Printf("Case failed: %s", c.name)
}
if hasErr != c.expectErr { log.Println("-----")
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expectErr, err)
}
})
} }
} }
+54 -109
View File
@@ -2,126 +2,66 @@ package main
import ( import (
"errors" "errors"
"fmt" "gopkg.in/yaml.v2"
"time" "io/ioutil"
"log"
"git.iamthefij.com/iamthefij/slog/v2" "os"
"github.com/hashicorp/hcl/v2/hclsimple"
)
var (
ErrLoadingConfig = errors.New("Failed to load or parse configuration")
ErrConfigInit = errors.New("Failed to initialize configuration")
ErrInvalidConfig = errors.New("Invalid configuration")
ErrNoAlerts = errors.New("No alerts provided")
ErrInvalidAlert = errors.New("Invalid alert configuration")
ErrNoMonitors = errors.New("No monitors provided")
ErrInvalidMonitor = errors.New("Invalid monitor configuration")
ErrUnknownAlert = errors.New("Unknown alert")
) )
// Config type is contains all provided user configuration // Config type is contains all provided user configuration
type Config struct { type Config struct {
CheckIntervalStr string `hcl:"check_interval"` CheckInterval int64 `yaml:"check_interval"`
CheckInterval time.Duration Monitors []*Monitor
Alerts map[string]*Alert
DefaultAlertAfter int `hcl:"default_alert_after,optional"`
DefaultAlertEvery *int `hcl:"default_alert_every,optional"`
DefaultAlertDown []string `hcl:"default_alert_down,optional"`
DefaultAlertUp []string `hcl:"default_alert_up,optional"`
Monitors []*Monitor `hcl:"monitor,block"`
Alerts []*Alert `hcl:"alert,block"`
alertLookup map[string]*Alert
}
// Init performs extra initialization on top of loading the config from file
func (config *Config) Init() (err error) {
config.CheckInterval, err = time.ParseDuration(config.CheckIntervalStr)
if err != nil {
return fmt.Errorf("failed to parse top level check_interval duration: %w", err)
}
if config.DefaultAlertAfter == 0 {
minAlertAfter := 1
config.DefaultAlertAfter = minAlertAfter
}
if config.DefaultAlertEvery == nil {
defaultDefaultAlertEvery := -1
config.DefaultAlertEvery = &defaultDefaultAlertEvery
}
for _, monitor := range config.Monitors {
if err = monitor.Init(
config.DefaultAlertAfter,
config.DefaultAlertEvery,
config.DefaultAlertDown,
config.DefaultAlertUp,
); err != nil {
return
}
}
err = config.BuildAllTemplates()
return
} }
// IsValid checks config validity and returns true if valid // IsValid checks config validity and returns true if valid
func (config Config) IsValid() error { func (config Config) IsValid() (isValid bool) {
var err error isValid = true
// Validate alerts
if len(config.Alerts) == 0 {
err = errors.Join(err, ErrNoAlerts)
}
for _, alert := range config.Alerts {
err = errors.Join(err, alert.Validate())
}
// Validate monitors // Validate monitors
if len(config.Monitors) == 0 { if config.Monitors == nil || len(config.Monitors) == 0 {
err = errors.Join(err, ErrNoMonitors) log.Printf("ERROR: Invalid monitor configuration: Must provide at least one monitor")
isValid = false
} }
for _, monitor := range config.Monitors { for _, monitor := range config.Monitors {
err = errors.Join(err, monitor.Validate()) if !monitor.IsValid() {
log.Printf("ERROR: Invalid monitor configuration: %s", monitor.Name)
isValid = false
}
// Check that all Monitor alerts actually exist // Check that all Monitor alerts actually exist
for _, isUp := range []bool{true, false} { for _, isUp := range []bool{true, false} {
for _, alertName := range monitor.GetAlertNames(isUp) { for _, alertName := range monitor.GetAlertNames(isUp) {
if _, ok := config.GetAlert(alertName); !ok { if _, ok := config.Alerts[alertName]; !ok {
err = errors.Join( log.Printf(
err, "ERROR: Invalid monitor configuration: %s. Unknown alert %s",
fmt.Errorf("%w: %s. %w: %s", ErrInvalidMonitor, monitor.Name, ErrUnknownAlert, alertName), monitor.Name, alertName,
) )
isValid = false
} }
} }
} }
} }
return err // Validate alerts
} if config.Alerts == nil || len(config.Alerts) == 0 {
log.Printf("ERROR: Invalid alert configuration: Must provide at least one alert")
// GetAlert returns an alert by name isValid = false
func (c Config) GetAlert(name string) (*Alert, bool) { }
if c.alertLookup == nil { for _, alert := range config.Alerts {
c.alertLookup = map[string]*Alert{} if !alert.IsValid() {
for _, alert := range c.Alerts { log.Printf("ERROR: Invalid alert configuration: %s", alert.Name)
c.alertLookup[alert.Name] = alert isValid = false
} }
} }
v, ok := c.alertLookup[name] return
return v, ok
} }
// BuildAllTemplates builds all alert templates // Init performs extra initialization on top of loading the config from file
func (c *Config) BuildAllTemplates() (err error) { func (config *Config) Init() (err error) {
for _, alert := range c.Alerts { for name, alert := range config.Alerts {
alert.Name = name
if err = alert.BuildTemplates(); err != nil { if err = alert.BuildTemplates(); err != nil {
return return
} }
@@ -131,23 +71,28 @@ func (c *Config) BuildAllTemplates() (err error) {
} }
// LoadConfig will read config from the given path and parse it // LoadConfig will read config from the given path and parse it
func LoadConfig(filePath string) (Config, error) { func LoadConfig(filePath string) (config Config, err error) {
var config Config data, err := ioutil.ReadFile(filePath)
if err != nil {
if err := hclsimple.DecodeFile(filePath, nil, &config); err != nil { return
return config, errors.Join(ErrLoadingConfig, err)
} }
slog.Debugf("Config values:\n%v\n", config) // TODO: Decide if this is better expanded here, or only when executing
envExpanded := os.ExpandEnv(string(data))
err = yaml.Unmarshal([]byte(envExpanded), &config)
if err != nil {
return
}
log.Printf("config:\n%v\n", config)
if !config.IsValid() {
err = errors.New("Invalid configuration")
return
}
// Finish initializing configuration // Finish initializing configuration
if err := config.Init(); err != nil { err = config.Init()
return config, errors.Join(ErrConfigInit, err)
}
if err := config.IsValid(); err != nil { return
return config, errors.Join(ErrInvalidConfig, err)
}
return config, nil
} }
+18 -178
View File
@@ -1,191 +1,31 @@
package main_test package main
import ( import (
"errors" "log"
"testing" "testing"
"time"
m "git.iamthefij.com/iamthefij/minitor-go/v2"
) )
func TestLoadConfig(t *testing.T) { func TestLoadConfig(t *testing.T) {
cases := []struct { cases := []struct {
configPath string configPath string
expectedErr error expectErr bool
name string name string
}{ }{
{"./test/does-not-exist", m.ErrLoadingConfig, "Invalid config path"}, {"./test/valid-config.yml", false, "Valid config file"},
{"./test/invalid-config-wrong-hcl-type.hcl", m.ErrLoadingConfig, "Incorrect HCL type"}, {"./test/does-not-exist", true, "Invalid config path"},
{"./test/invalid-config-missing-alerts.hcl", m.ErrNoAlerts, "Invalid config missing alerts"}, {"./test/invalid-config-type.yml", true, "Invalid config type for key"},
{"./test/invalid-config-missing-alerts.hcl", m.ErrInvalidConfig, "Invalid config general"}, {"./test/invalid-config-missing-alerts.yml", true, "Invalid config missing alerts"},
{"./test/invalid-config-invalid-duration.hcl", m.ErrConfigInit, "Invalid config type for key"}, {"./test/invalid-config-unknown-alert.yml", true, "Invalid config unknown alert"},
{"./test/invalid-config-unknown-alert.hcl", m.ErrUnknownAlert, "Invalid config unknown alert"},
{"./test/valid-config-default-values.hcl", nil, "Valid config file with default values"},
{"./test/valid-config.hcl", nil, "Valid config file"},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
t.Parallel()
_, err := m.LoadConfig(c.configPath)
hasErr := (err != nil)
expectErr := (c.expectedErr != nil)
if hasErr != expectErr || !errors.Is(err, c.expectedErr) {
t.Errorf("LoadConfig(%v), expected_error=%v actual=%v", c.name, c.expectedErr, err)
}
})
}
}
func TestDefaultConfig(t *testing.T) {
cases := []struct {
configPath string
expectedResult m.Config
name string
}{
{
"./test/valid-config-default-values.hcl",
m.Config{
CheckInterval: 1 * time.Second,
DefaultAlertAfter: 2,
DefaultAlertEvery: new(0),
DefaultAlertDown: []string{"log_command"},
},
"override defaults",
},
{
"./test/valid-config.hcl",
m.Config{
CheckInterval: 30 * time.Second,
DefaultAlertAfter: 1,
DefaultAlertEvery: new(-1),
DefaultAlertDown: []string{},
},
"default defaults",
},
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { _, err := LoadConfig(c.configPath)
t.Parallel() hasErr := (err != nil)
if hasErr != c.expectErr {
config, err := m.LoadConfig(c.configPath) t.Errorf("LoadConfig(%v), expected=%v actual=%v", c.name, "Err", err)
if err != nil { log.Printf("Case failed: %s", c.name)
t.Errorf("Got error when loading config file %q: %s", c.configPath, err) }
} log.Println("-----")
// Test Config has default values
if config.DefaultAlertAfter != c.expectedResult.DefaultAlertAfter {
t.Errorf("Got unexpected DefaultAlertAfter from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertAfter, config.DefaultAlertAfter)
}
if *config.DefaultAlertEvery != *c.expectedResult.DefaultAlertEvery {
t.Errorf("Got unexpected DefaultAlertEvery from file %q: expected=%v actual=%v", c.configPath, *c.expectedResult.DefaultAlertEvery, *config.DefaultAlertEvery)
}
if !m.EqualSliceString(config.DefaultAlertUp, c.expectedResult.DefaultAlertUp) {
t.Errorf("Got unexpected DefaultAlertUp from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertUp, config.DefaultAlertUp)
}
if !m.EqualSliceString(config.DefaultAlertDown, c.expectedResult.DefaultAlertDown) {
t.Errorf("Got unexpected DefaultAlertDown from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertDown, config.DefaultAlertDown)
}
// Check that monitor defaults propagate
var defaultMonitor *m.Monitor
for _, monitor := range config.Monitors {
if monitor.Name == "Default" {
defaultMonitor = monitor
}
}
if defaultMonitor == nil {
t.Errorf("failed to find default monitor in %q", c.configPath)
}
if defaultMonitor.AlertAfter != c.expectedResult.DefaultAlertAfter {
t.Errorf("Got unexpected AlertAfter from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertAfter, defaultMonitor.AlertAfter)
}
if *defaultMonitor.AlertEvery != *c.expectedResult.DefaultAlertEvery {
t.Errorf("Got unexpected AlertEvery from file %q: expected=%v actual=%v", c.configPath, *c.expectedResult.DefaultAlertEvery, *defaultMonitor.AlertEvery)
}
if !m.EqualSliceString(defaultMonitor.AlertUp, c.expectedResult.DefaultAlertUp) {
t.Errorf("Got unexpected AlertUp from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertUp, defaultMonitor.AlertUp)
}
// NOTE: Can't compare AlertDown because default is empty and that is invalid
})
} }
} }
// TestMultiLineConfig is a more complicated test stepping through the parsing
// and execution of mutli-line strings presented in YAML
func TestMultiLineConfig(t *testing.T) {
t.Parallel()
config, err := m.LoadConfig("./test/valid-verify-multi-line.hcl")
if err != nil {
t.Fatalf("TestMultiLineConfig(load), expected=no_error actual=%v", err)
}
t.Run("Test Monitor with Indented Multi-Line String", func(t *testing.T) {
// Verify indented heredoc is as expected
expected := "echo 'Some string with stuff'\necho \"<angle brackets>\"\nexit 1\n"
actual := config.Monitors[0].ShellCommand
if expected != actual {
t.Error("Heredoc mismatch")
t.Errorf("string expected=`%v`", expected)
t.Errorf("string actual =`%v`", actual)
}
// Run the monitor and verify the output
_, notice := config.Monitors[0].Check()
if notice == nil {
t.Fatal("Did not receive an alert notice and should have")
}
// Verify the output of the monitor is as expected
expected = "Some string with stuff\n<angle brackets>\n"
actual = notice.LastCheckOutput
if expected != actual {
t.Error("Output mismatch")
t.Errorf("string expected=`%v`", expected)
t.Errorf("string actual =`%v`", actual)
}
})
t.Run("Test Alert with Multi-Line String", func(t *testing.T) {
alert, ok := config.GetAlert("log_shell")
if !ok {
t.Fatal("Could not find expected alert 'log_shell'")
}
expected := " echo 'Some string with stuff'\n echo '<angle brackets>'\n"
actual := alert.ShellCommand
if expected != actual {
t.Error("Heredoc mismatch")
t.Errorf("string expected=`%v`", expected)
t.Errorf("string actual =`%v`", actual)
}
actual, err = alert.Send(m.AlertNotice{})
if err != nil {
t.Fatal("Execution of alert failed")
}
expected = "Some string with stuff\n<angle brackets>\n"
if expected != actual {
t.Error("Output mismatch")
t.Errorf("string expected=`%v`", expected)
t.Errorf("string actual =`%v`", actual)
}
})
}
+4 -27
View File
@@ -1,31 +1,8 @@
module git.iamthefij.com/iamthefij/minitor-go/v2 module git.iamthefij.com/iamthefij/minitor-go
go 1.26.0 go 1.12
require ( require (
git.iamthefij.com/iamthefij/slog/v2 v2.0.1 github.com/prometheus/client_golang v1.2.1
github.com/hashicorp/hcl/v2 v2.24.0 gopkg.in/yaml.v2 v2.2.4
github.com/prometheus/client_golang v1.23.2
)
require (
github.com/agext/levenshtein v1.2.1 // indirect
github.com/apparentlymart/go-textseg/v13 v13.0.0 // indirect
github.com/apparentlymart/go-textseg/v15 v15.0.0 // indirect
github.com/beorn7/perks v1.0.1 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/google/go-cmp v0.7.0 // indirect
github.com/mitchellh/go-wordwrap v1.0.1 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
github.com/prometheus/client_model v0.6.2 // indirect
github.com/prometheus/common v0.66.1 // indirect
github.com/prometheus/procfs v0.16.1 // indirect
github.com/zclconf/go-cty v1.16.3 // indirect
go.yaml.in/yaml/v2 v2.4.2 // indirect
golang.org/x/mod v0.26.0 // indirect
golang.org/x/sync v0.16.0 // indirect
golang.org/x/sys v0.35.0 // indirect
golang.org/x/text v0.28.0 // indirect
golang.org/x/tools v0.35.0 // indirect
google.golang.org/protobuf v1.36.8 // indirect
) )
+68 -100
View File
@@ -1,110 +1,78 @@
git.iamthefij.com/iamthefij/slog/v2 v2.0.1 h1:eXf3ga0aMTkm0l6EMYOQpg34S+dQw7cN8o+W1Cg/0C0= github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
git.iamthefij.com/iamthefij/slog/v2 v2.0.1/go.mod h1:VFjX1e1tfHADyQr2wJBAz0JUQT+K/5FBjzSHgUKOuu8= github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
github.com/agext/levenshtein v1.2.1 h1:QmvMAjj2aEICytGiWzmxoE0x2KZvE0fvmqMOfy2tjT8= github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
github.com/agext/levenshtein v1.2.1/go.mod h1:JEDfjyjHDjOF/1e4FlBE/PkbqA9OfWu2ki2W0IB5558= github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
github.com/apparentlymart/go-dump v0.0.0-20180507223929-23540a00eaa3/go.mod h1:oL81AME2rN47vu18xqj1S1jPIPuN7afo62yKTNn3XMM= github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
github.com/apparentlymart/go-textseg v1.0.0/go.mod h1:z96Txxhf3xSFMPmb5X/1W05FF/Nj9VFpLOpjS5yuumk= github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
github.com/apparentlymart/go-textseg/v13 v13.0.0 h1:Y+KvPE1NYz0xl601PVImeQfFyEy6iT90AvPUL1NNfNw=
github.com/apparentlymart/go-textseg/v13 v13.0.0/go.mod h1:ZK2fH7c4NqDTLtiYLvIkEghdlcqw7yxLeM89kiTRPUo=
github.com/apparentlymart/go-textseg/v15 v15.0.0 h1:uYvfpb3DyLSCGWnctWKGj857c6ew1u1fNQOlOtuGxQY=
github.com/apparentlymart/go-textseg/v15 v15.0.0/go.mod h1:K8XmNZdhEBkdlyDdvbmmsvpAG721bKi0joRfFdHIWJ4=
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM= 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/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs= github.com/cespare/xxhash/v2 v2.1.0 h1:yTUvW7Vhb89inJ+8irsUqiWjh8iT6sQPZiQzI6ReGkA=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs= github.com/cespare/xxhash/v2 v2.1.0/go.mod h1:dgIUBU3pDso/gPgZ1osOZ0iQf77oPR28Tjxl5dIMyVM=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/go-test/deep v1.0.3 h1:ZrJSEWsXzPOxaZnFteGEfooLba+ju3FYIbOrS+rQd68= github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
github.com/go-test/deep v1.0.3/go.mod h1:wGDj63lr65AM2AQyKZd/NYHGb0R+1RLqB8NKt3aSFNA= github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
github.com/golang/protobuf v1.1.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9GBnD5lWE=
github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk=
github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/golang/protobuf v1.3.4/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw= github.com/golang/protobuf v1.3.2 h1:6nsPYzhq5kReh6QImI3k5qWzO4PEbvbIW2cwSfR/6xs=
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU= github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8= github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU= github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
github.com/hashicorp/hcl/v2 v2.11.1 h1:yTyWcXcm9XB0TEkyU/JCRU6rYy4K+mgLtzn2wlrJbcc= github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
github.com/hashicorp/hcl/v2 v2.11.1/go.mod h1:FwWsfWEjyV/CMj8s/gqAuiviY72rJ1/oayI9WftqcKg= github.com/json-iterator/go v1.1.7/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
github.com/hashicorp/hcl/v2 v2.24.0 h1:2QJdZ454DSsYGoaE6QheQZjtKZSUs9Nh2izTWiwQxvE= github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
github.com/hashicorp/hcl/v2 v2.24.0/go.mod h1:oGoO1FIQYfn/AgyOhlg9qLC6/nOJPX3qGbkZpYAcqfM= github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo= github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ= github.com/matttproud/golang_protobuf_extensions v1.0.1 h1:4hp9jkHxhMHkqkrB3Ix0jegS5sx/RkqARlsWZ6pIwiU=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE= github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE= github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
github.com/kylelemons/godebug v0.0.0-20170820004349-d65d576e9348/go.mod h1:B69LEHPfb2qLo0BaaOLcbitczOKLWTsrBG9LczfCD4k= github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc= github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
github.com/mitchellh/go-wordwrap v0.0.0-20150314170334-ad45545899c7 h1:DpOJ2HYzCv8LZP15IdmG+YdwD2luVPHITV96TkirNBM=
github.com/mitchellh/go-wordwrap v0.0.0-20150314170334-ad45545899c7/go.mod h1:ZXFpozHsX6DPmq2I0TCekCxypsnAUbP2oI0UX1GXzOo=
github.com/mitchellh/go-wordwrap v1.0.1 h1:TLuKupo69TCn6TQSyGxwI1EblZZEsQ0vMlAFQflz0v0=
github.com/mitchellh/go-wordwrap v1.0.1/go.mod h1:R62XHJLzvMFRBbcrT7m7WgmE1eOyTSsCt+hzestvNj0=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o= github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg= github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=
github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk= github.com/prometheus/client_golang v1.2.1 h1:JnMpQc6ppsNgw9QPAGF6Dod479itz7lvlsMzzNayLOI=
github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE= github.com/prometheus/client_golang v1.2.1/go.mod h1:XMU6Z2MjaRKVu/dC1qupJI9SiNkDYzz3xecMgSW/F+U=
github.com/prometheus/common v0.66.1 h1:h5E0h5/Y8niHc5DlaLlWLArTQI7tMrsfQjHV+d9ZoGs= github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
github.com/prometheus/common v0.66.1/go.mod h1:gcaUsgf3KfRSwHY4dIMXLPV0K/Wg1oZ8+SbZk/HH/dA= github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg= github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4 h1:gQz4mCbXsO+nc9n1hCxHcGA3Zx3Eo+UHZoInFGUIXNM=
github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is= github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ= github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y86RQel1bk4=
github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog= github.com/prometheus/common v0.7.0 h1:L+1lyG48J1zAQXA3RBX/nG/B3gjlHq0zTt2tlbJLyCY=
github.com/sergi/go-diff v1.0.0 h1:Kpca3qRNrduNnOQeazBd0ysaKrUJiIuISHxogkT9RPQ= github.com/prometheus/common v0.7.0/go.mod h1:DjGbpBbp5NYNiECxcL/VnbXCCaQpKd3tt26CguLLsqA=
github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo= github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
github.com/spf13/pflag v1.0.2/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4= github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
github.com/prometheus/procfs v0.0.5 h1:3+auTFlqw+ZaQYJARz6ArODtkaIwtvBTx3N2NehQlL8=
github.com/prometheus/procfs v0.0.5/go.mod h1:4A/X28fw3Fc593LaREMrKMqOKvUAntwMDaekg4FpcdQ=
github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs= github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U= golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
github.com/vmihailenco/msgpack v3.3.3+incompatible/go.mod h1:fy3FlTQTDXWkZ7Bh6AcGMlsjHatGryHQYUTf1ShIgkk=
github.com/vmihailenco/msgpack/v4 v4.3.12/go.mod h1:gborTTJjAo/GWTqqRjrLCn9pgNN+NXzzngzBKDPIqw4=
github.com/vmihailenco/tagparser v0.1.1/go.mod h1:OeAg3pn3UbLjkWt+rN9oFYB6u/cQgqMEUPoW2WPyhdI=
github.com/zclconf/go-cty v1.2.0/go.mod h1:hOPWgoHbaTUnI5k4D2ld+GRpFJSCe6bCM7m1q/N4PQ8=
github.com/zclconf/go-cty v1.8.0 h1:s4AvqaeQzJIu3ndv4gVIhplVD0krU+bgrcLSVUnaWuA=
github.com/zclconf/go-cty v1.8.0/go.mod h1:vVKLxnk3puL4qRAv72AO+W99LUD4da90g3uUAzyuvAk=
github.com/zclconf/go-cty v1.16.3 h1:osr++gw2T61A8KVYHoQiFbFd1Lh3JOCXc/jFLJXKTxk=
github.com/zclconf/go-cty v1.16.3/go.mod h1:VvMs5i0vgZdhYawQNq5kePSpLAoz8u1xvZgrPIxfnZE=
github.com/zclconf/go-cty-debug v0.0.0-20191215020915-b22d67c1ba0b/go.mod h1:ZRKQfBXbGkpdV6QMzT3rU1kSTAnfu1dO8dPKjYprgj8=
go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
go.yaml.in/yaml/v2 v2.4.2 h1:DzmwEr2rDGHl7lsFgAHxmNz/1NlQ7xLIrlN2h5d1eGI=
go.yaml.in/yaml/v2 v2.4.2/go.mod h1:081UH+NErpNdqlCXm3TtEran0rJZGxAYx9hb/ELlsPU=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20190426145343-a29dc8fdc734/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI= golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/mod v0.26.0 h1:EGMPT//Ezu+ylkCijjPc+f4Aih7sZvaAr+O3EHBxvZg= golang.org/x/net v0.0.0-20190613194153-d28f0bde5980/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/mod v0.26.0/go.mod h1:/j6NAhSk8iQ723BGAUyoAcn7SlD7s15Dp9Nd/SfeaFQ= golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/net v0.0.0-20180811021610-c39426892332/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks= golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/net v0.0.0-20200301022130-244492dfa37a/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.16.0 h1:ycBJEhp9p4vXvUZNszeOq0kGTPghopOL8q0fq3vstxw=
golang.org/x/sync v0.16.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20190502175342-a43fa875dd82/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20191010194322-b09406accb47/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.35.0 h1:vz1N37gP5bs89s7He8XuIYXpyY0+QlsKmzipCbUtyxI=
golang.org/x/sys v0.35.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk= gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.28.0 h1:rhazDwis8INMIwQ4tpjLDzUhx6RlXqZNPEM0huQojng=
golang.org/x/text v0.28.0/go.mod h1:U8nCwOR8jO/marOQ0QbDiOngZVEBB7MAiitBuMjXiNU=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.35.0 h1:mBffYraMEf7aa0sB+NuKnuCy8qI/9Bughn8dC2Gu5r0=
golang.org/x/tools v0.35.0/go.mod h1:NKdj5HkL/73byiZSJjqJgKn3ep7KjFkBOkR/Hps3VPw=
google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
google.golang.org/appengine v1.6.5/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
google.golang.org/protobuf v1.36.8 h1:xHScyCOEuuwZEc6UtSOvPbAT4zRh0xcNRYekJwfqyMc=
google.golang.org/protobuf v1.36.8/go.mod h1:fuxRtAxBytpl4zzqUh6/eyUujkJdNiuEkXntxiD/uRU=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= gopkg.in/yaml.v2 v2.2.4 h1:/eiJrUcujPVeJ3xlSWaiNi3uSVmDGBK1pDHUHAnao1I=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+61 -113
View File
@@ -1,86 +1,65 @@
package main package main
import ( import (
"errors"
"flag" "flag"
"fmt" "fmt"
"strings" "github.com/prometheus/client_golang/prometheus/promhttp"
"log"
"net/http"
"time" "time"
"git.iamthefij.com/iamthefij/slog/v2"
) )
var ( var (
// LogDebug will control whether debug messsages should be logged
LogDebug = false
// ExportMetrics will track whether or not we want to export metrics to prometheus // ExportMetrics will track whether or not we want to export metrics to prometheus
ExportMetrics = false ExportMetrics = false
// MetricsPort is the port to expose metrics on
MetricsPort = 8080
// Metrics contains all active metrics
Metrics = NewMetrics()
// version of minitor being run // version of minitor being run
version = "dev" version = "dev"
errUnknownAlert = errors.New("unknown alert")
) )
func SendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) error { func checkMonitors(config *Config) error {
slog.Debugf("Received an alert notice from %s", alertNotice.MonitorName)
alertNames := monitor.GetAlertNames(alertNotice.IsUp)
if alertNames == nil {
// This should only happen for a recovery alert. AlertDown is validated not empty
slog.Warningf(
"Received alert, but no alert mechanisms exist. MonitorName=%s IsUp=%t",
alertNotice.MonitorName, alertNotice.IsUp,
)
return nil
}
for _, alertName := range alertNames {
if alert, ok := config.GetAlert(alertName); ok {
output, err := alert.Send(*alertNotice)
if err != nil {
slog.Errorf(
"Alert '%s' failed. result=%v: output=%s",
alert.Name,
err,
output,
)
return err
}
// Count alert metrics
Metrics.CountAlert(monitor.Name, alert.Name)
} else {
// This case should never actually happen since we validate against it
slog.Errorf("Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
return fmt.Errorf("unknown alert for monitor %s: %s: %w", alertNotice.MonitorName, alertName, errUnknownAlert)
}
}
return nil
}
func CheckMonitors(config *Config) error {
// TODO: Run this in goroutines and capture exceptions
for _, monitor := range config.Monitors { for _, monitor := range config.Monitors {
if monitor.ShouldCheck() { if monitor.ShouldCheck() {
success, alertNotice := monitor.Check() _, alertNotice := monitor.Check()
hasAlert := alertNotice != nil
// Track status metrics
Metrics.SetMonitorStatus(monitor.Name, monitor.IsUp())
Metrics.CountCheck(monitor.Name, success, monitor.LastCheckMilliseconds(), hasAlert)
// Should probably consider refactoring everything below here
if alertNotice != nil { if alertNotice != nil {
err := SendAlerts(config, monitor, alertNotice) if LogDebug {
// If there was an error in sending an alert, exit early and bubble it up log.Printf("DEBUG: Recieved an alert notice from %s", alertNotice.MonitorName)
if err != nil { }
return err alertNames := monitor.GetAlertNames(alertNotice.IsUp)
if alertNames == nil {
// This should only happen for a recovery alert. AlertDown is validated not empty
log.Printf(
"WARNING: Recieved alert, but no alert mechanisms exist. MonitorName=%s IsUp=%t",
alertNotice.MonitorName, alertNotice.IsUp,
)
}
for _, alertName := range alertNames {
if alert, ok := config.Alerts[alertName]; ok {
output, err := alert.Send(*alertNotice)
if err != nil {
log.Printf(
"ERROR: Alert '%s' failed. result=%v: output=%s",
alert.Name,
err,
output,
)
return fmt.Errorf(
"Unsuccessfully triggered alert '%s'. "+
"Crashing to avoid false negatives: %v",
alert.Name,
err,
)
}
} else {
// This case should never actually happen since we validate against it
log.Printf("ERROR: Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
return fmt.Errorf("Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
}
} }
} }
} }
@@ -89,75 +68,44 @@ func CheckMonitors(config *Config) error {
return nil return nil
} }
func SendStartupAlerts(config *Config, alertNames []string) error { func serveMetrics() {
for _, alertName := range alertNames { http.Handle("/metrics", promhttp.Handler())
var err error _ = http.ListenAndServe(":8080", nil)
alert, ok := config.GetAlert(alertName)
if !ok {
err = fmt.Errorf("unknown alert %s: %w", alertName, errUnknownAlert)
}
if err == nil {
_, err = alert.Send(AlertNotice{
AlertCount: 0,
FailureCount: 0,
IsUp: true,
LastSuccess: time.Now(),
MonitorName: fmt.Sprintf("First Run Alert Test: %s", alert.Name),
LastCheckOutput: "",
})
}
if err != nil {
return err
}
}
return nil
} }
func main() { func main() {
showVersion := flag.Bool("version", false, "Display the version of minitor and exit") // Get debug flag
configPath := flag.String("config", "config.hcl", "Alternate configuration path (default: config.hcl)") flag.BoolVar(&LogDebug, "debug", false, "Enables debug logs (default: false)")
startupAlerts := flag.String("startup-alerts", "", "List of alerts to run on startup. This can help determine unhealthy alerts early on. (default \"\")")
flag.BoolVar(&slog.DebugLevel, "debug", false, "Enables debug logs (default: false)")
flag.BoolVar(&ExportMetrics, "metrics", false, "Enables prometheus metrics exporting (default: false)") flag.BoolVar(&ExportMetrics, "metrics", false, "Enables prometheus metrics exporting (default: false)")
flag.IntVar(&MetricsPort, "metrics-port", MetricsPort, "The port that Prometheus metrics should be exported on, if enabled. (default: 8080)") var showVersion = flag.Bool("version", false, "Display the version of minitor and exit")
flag.Parse() flag.Parse()
// Print version if flag is provided // Print version if flag is provided
if *showVersion { if *showVersion {
fmt.Println("Minitor version:", version) log.Println("Minitor version:", version)
return return
} }
// Load configuration // Load configuration
config, err := LoadConfig(*configPath) config, err := LoadConfig("config.yml")
slog.OnErrFatalf(err, "Error loading config") if err != nil {
log.Fatalf("Error loading config: %v", err)
}
// Serve metrics exporter, if specified // Serve metrics exporter, if specified
if ExportMetrics { if ExportMetrics {
slog.Infof("Exporting metrics to Prometheus on port %d", MetricsPort) log.Println("INFO: Exporting metrics to Prometheus")
go serveMetrics()
go ServeMetrics()
}
if *startupAlerts != "" {
alertNames := strings.Split(*startupAlerts, ",")
err = SendStartupAlerts(&config, alertNames)
slog.OnErrPanicf(err, "Error running startup alerts")
} }
// Start main loop // Start main loop
for { for {
err = CheckMonitors(&config) err = checkMonitors(&config)
slog.OnErrPanicf(err, "Error checking monitors") if err != nil {
panic(err)
}
time.Sleep(config.CheckInterval) sleepTime := time.Duration(config.CheckInterval) * time.Second
time.Sleep(sleepTime)
} }
} }
+89 -161
View File
@@ -1,186 +1,114 @@
package main_test package main
import ( import "testing"
"testing"
m "git.iamthefij.com/iamthefij/minitor-go/v2"
)
// TestCheckConfig tests the checkConfig function
// It also tests results for potentially invalid configuration. For example, no alerts
func TestCheckMonitors(t *testing.T) { func TestCheckMonitors(t *testing.T) {
cases := []struct { cases := []struct {
config m.Config config Config
expectFailureError bool expectErr bool
expectRecoverError bool name string
name string
}{ }{
{ {
config: m.Config{ config: Config{},
CheckIntervalStr: "1s", expectErr: false,
Monitors: []*m.Monitor{ name: "Empty",
{
Name: "Success",
},
},
},
expectFailureError: false,
expectRecoverError: false,
name: "No alerts",
}, },
{ {
config: m.Config{ config: Config{
CheckIntervalStr: "1s", Monitors: []*Monitor{
Monitors: []*m.Monitor{ &Monitor{
{ Name: "Success",
Name: "Failure",
AlertDown: []string{"unknown"},
AlertUp: []string{"unknown"},
AlertAfter: 1,
},
},
},
expectFailureError: true,
expectRecoverError: true,
name: "Unknown alerts",
},
{
config: m.Config{
CheckIntervalStr: "1s",
Monitors: []*m.Monitor{
{
Name: "Failure",
AlertDown: []string{"good"},
AlertUp: []string{"good"},
AlertAfter: 1,
},
},
Alerts: []*m.Alert{{
Name: "good",
Command: []string{"true"},
}},
},
expectFailureError: false,
expectRecoverError: false,
name: "Successful alert",
},
{
config: m.Config{
CheckIntervalStr: "1s",
Monitors: []*m.Monitor{
{
Name: "Failure",
AlertDown: []string{"bad"},
AlertUp: []string{"bad"},
AlertAfter: 1,
},
},
Alerts: []*m.Alert{{
Name: "bad",
Command: []string{"false"},
}},
},
expectFailureError: true,
expectRecoverError: true,
name: "Failing alert",
},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
t.Parallel()
err := c.config.Init()
if err != nil {
t.Errorf("checkMonitors(%s): unexpected error reading config: %v", c.name, err)
}
for _, check := range []struct {
shellCmd string
name string
expectErr bool
}{
{"false", "Failure", c.expectFailureError}, {"true", "Success", c.expectRecoverError},
} {
// Set the shell command for this check
c.config.Monitors[0].ShellCommand = check.shellCmd
// Run the check
err = m.CheckMonitors(&c.config)
// Check the results
if err == nil && check.expectErr {
t.Errorf("checkMonitors(%s:%s): Expected error, the code did not error", c.name, check.name)
} else if err != nil && !check.expectErr {
t.Errorf("checkMonitors(%s:%s): Did not expect an error, but we got one anyway: %v", c.name, check.name, err)
}
}
})
}
}
func TestFirstRunAlerts(t *testing.T) {
cases := []struct {
config m.Config
expectErr bool
startupAlerts []string
name string
}{
{
config: m.Config{
CheckIntervalStr: "1s",
},
expectErr: true,
startupAlerts: []string{"missing"},
name: "Unknown",
},
{
config: m.Config{
CheckIntervalStr: "1s",
Alerts: []*m.Alert{
{
Name: "good",
Command: []string{"true"}, Command: []string{"true"},
}, },
}, },
}, },
expectErr: false, expectErr: false,
startupAlerts: []string{"good"}, name: "Monitor success, no alerts",
name: "Successful alert",
}, },
{ {
config: m.Config{ config: Config{
CheckIntervalStr: "1s", Monitors: []*Monitor{
Alerts: []*m.Alert{ &Monitor{
{ Name: "Failure",
Command: []string{"false"},
AlertAfter: 1,
},
&Monitor{
Name: "Failure",
Command: []string{"false"},
AlertDown: []string{"unknown"},
AlertAfter: 1,
},
},
},
expectErr: false,
name: "Monitor failure, no and unknown alerts",
},
{
config: Config{
Monitors: []*Monitor{
&Monitor{
Name: "Success",
Command: []string{"ls"},
alertCount: 1,
},
&Monitor{
Name: "Success",
Command: []string{"true"},
AlertUp: []string{"unknown"},
alertCount: 1,
},
},
},
expectErr: false,
name: "Monitor recovery, no alerts",
},
{
config: Config{
Monitors: []*Monitor{
&Monitor{
Name: "Failure",
Command: []string{"false"},
AlertDown: []string{"good"},
AlertAfter: 1,
},
},
Alerts: map[string]*Alert{
"good": &Alert{
Command: []string{"true"},
},
},
},
expectErr: false,
name: "Monitor failure, successful alert",
},
{
config: Config{
Monitors: []*Monitor{
&Monitor{
Name: "Failure",
Command: []string{"false"},
AlertDown: []string{"bad"},
AlertAfter: 1,
},
},
Alerts: map[string]*Alert{
"bad": &Alert{
Name: "bad", Name: "bad",
Command: []string{"false"}, Command: []string{"false"},
}, },
}, },
}, },
expectErr: true, expectErr: true,
startupAlerts: []string{"bad"}, name: "Monitor failure, bad alert",
name: "Failed alert",
}, },
} }
for _, c := range cases { for _, c := range cases {
c.config.Init()
t.Run(c.name, func(t *testing.T) { err := checkMonitors(&c.config)
t.Parallel() if err == nil && c.expectErr {
t.Errorf("checkMonitors(%s): Expected panic, the code did not panic", c.name)
err := c.config.Init() }
if err != nil {
t.Errorf("sendFirstRunAlerts(%s): unexpected error reading config: %v", c.name, err)
}
err = m.SendStartupAlerts(&c.config, c.startupAlerts)
if err == nil && c.expectErr {
t.Errorf("sendFirstRunAlerts(%s): Expected error, the code did not error", c.name)
} else if err != nil && !c.expectErr {
t.Errorf("sendFirstRunAlerts(%s): Did not expect an error, but we got one anyway: %v", c.name, err)
}
})
} }
} }
-117
View File
@@ -1,117 +0,0 @@
package main
import (
"fmt"
"net/http"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promhttp"
)
// TODO: Not sure if this is the best way to handle. A global instance for
// metrics isn't bad, but it might be nice to curry versions of the metrics
// for each monitor. Especially since every monitor has it's own. Perhaps
// another new function that essentially curries each metric for a given
// monitor name would do. This could be run when validating monitors and
// initializing alert templates.
// MinitorMetrics contains all counters and metrics that Minitor will need to access
type MinitorMetrics struct {
alertCount *prometheus.CounterVec
checkCount *prometheus.CounterVec
checkTime *prometheus.GaugeVec
monitorStatus *prometheus.GaugeVec
}
// NewMetrics creates and initializes all metrics
func NewMetrics() *MinitorMetrics {
// Initialize all metrics
metrics := &MinitorMetrics{
alertCount: prometheus.NewCounterVec(
prometheus.CounterOpts{
Name: "minitor_alert_total",
Help: "Number of Minitor alerts",
},
[]string{"alert", "monitor"},
),
checkCount: prometheus.NewCounterVec(
prometheus.CounterOpts{
Name: "minitor_check_total",
Help: "Number of Minitor checks",
},
[]string{"monitor", "status", "is_alert"},
),
checkTime: prometheus.NewGaugeVec(
prometheus.GaugeOpts{
Name: "minitor_check_milliseconds",
Help: "Time in miliseconds that a check ran for",
},
[]string{"monitor", "status"},
),
monitorStatus: prometheus.NewGaugeVec(
prometheus.GaugeOpts{
Name: "minitor_monitor_up_count",
Help: "Status of currently responsive monitors",
},
[]string{"monitor"},
),
}
// Register newly created metrics
prometheus.MustRegister(metrics.alertCount)
prometheus.MustRegister(metrics.checkCount)
prometheus.MustRegister(metrics.checkTime)
prometheus.MustRegister(metrics.monitorStatus)
return metrics
}
// SetMonitorStatus sets the current status of Monitor
func (metrics *MinitorMetrics) SetMonitorStatus(monitor string, isUp bool) {
val := 0.0
if isUp {
val = 1.0
}
metrics.monitorStatus.With(prometheus.Labels{"monitor": monitor}).Set(val)
}
// CountCheck counts the result of a particular Monitor check
func (metrics *MinitorMetrics) CountCheck(monitor string, isSuccess bool, ms int64, isAlert bool) {
status := "failure"
if isSuccess {
status = "success"
}
alertVal := "false"
if isAlert {
alertVal = "true"
}
metrics.checkCount.With(
prometheus.Labels{"monitor": monitor, "status": status, "is_alert": alertVal},
).Inc()
metrics.checkTime.With(
prometheus.Labels{"monitor": monitor, "status": status},
).Set(float64(ms))
}
// CountAlert counts an alert
func (metrics *MinitorMetrics) CountAlert(monitor string, alert string) {
metrics.alertCount.With(
prometheus.Labels{
"alert": alert,
"monitor": monitor,
},
).Inc()
}
// ServeMetrics starts an http server with a Prometheus metrics handler
func ServeMetrics() {
http.Handle("/metrics", promhttp.Handler())
host := fmt.Sprintf(":%d", MetricsPort)
_ = http.ListenAndServe(host, nil)
}
+91 -167
View File
@@ -1,164 +1,86 @@
package main package main
import ( import (
"errors" "log"
"fmt"
"math" "math"
"os/exec" "os/exec"
"time" "time"
"git.iamthefij.com/iamthefij/slog/v2"
) )
// Monitor represents a particular periodic check of a command // Monitor represents a particular periodic check of a command
type Monitor struct { //nolint:maligned type Monitor struct {
// Config values // Config values
CheckIntervalStr *string `hcl:"check_interval,optional"` Name string
CheckInterval time.Duration Command []string
CommandShell string `yaml:"command_shell"`
Name string `hcl:"name,label"` AlertDown []string `yaml:"alert_down"`
AlertCount int AlertUp []string `yaml:"alert_up"`
AlertAfter int `hcl:"alert_after,optional"` CheckInterval float64 `yaml:"check_interval"`
AlertEvery *int `hcl:"alert_every,optional"` AlertAfter int16 `yaml:"alert_after"`
AlertDown []string `hcl:"alert_down,optional"` AlertEvery int16 `yaml:"alert_every"`
AlertUp []string `hcl:"alert_up,optional"`
Command []string `hcl:"command,optional"`
ShellCommand string `hcl:"shell_command,optional"`
// Other values // Other values
failureCount int lastCheck time.Time
lastCheck time.Time lastOutput string
lastSuccess time.Time alertCount int16
lastOutput string failureCount int16
lastCheckDuration time.Duration lastSuccess time.Time
} }
// Init initializes the Monitor with default values // IsValid returns a boolean indicating if the Monitor has been correctly
func (monitor *Monitor) Init(defaultAlertAfter int, defaultAlertEvery *int, defaultAlertDown []string, defaultAlertUp []string) error { // configured
// Parse the check_interval string into a time.Duration func (monitor Monitor) IsValid() bool {
if monitor.CheckIntervalStr != nil { atLeastOneCommand := (monitor.CommandShell != "" || monitor.Command != nil)
var err error atMostOneCommand := (monitor.CommandShell == "" || monitor.Command == nil)
return (atLeastOneCommand &&
monitor.CheckInterval, err = time.ParseDuration(*monitor.CheckIntervalStr) atMostOneCommand &&
if err != nil { monitor.getAlertAfter() > 0 &&
return fmt.Errorf("failed to parse check_interval duration for monitor %s: %w", monitor.Name, err) monitor.AlertDown != nil)
}
}
// Set default values for monitor alerts
if monitor.AlertAfter == 0 {
minAlertAfter := 1
monitor.AlertAfter = max(defaultAlertAfter, minAlertAfter)
}
if monitor.AlertEvery == nil {
monitor.AlertEvery = defaultAlertEvery
}
if len(monitor.AlertDown) == 0 {
monitor.AlertDown = defaultAlertDown
}
if len(monitor.AlertUp) == 0 {
monitor.AlertUp = defaultAlertUp
}
return nil
} }
// Validate checks that the Monitor is properly configured and returns errors if not // ShouldCheck returns a boolean indicating if the Monitor is ready to be
func (monitor Monitor) Validate() error { // be checked again
hasCommand := len(monitor.Command) > 0
hasShellCommand := monitor.ShellCommand != ""
hasValidAlertAfter := monitor.AlertAfter > 0
hasAlertDown := len(monitor.AlertDown) > 0
var err error
hasAtLeastOneCommand := hasCommand || hasShellCommand
if !hasAtLeastOneCommand {
err = errors.Join(err, fmt.Errorf(
"%w: monitor %s has no command or shell_command configured",
ErrInvalidMonitor,
monitor.Name,
))
}
hasAtMostOneCommand := !(hasCommand && hasShellCommand)
if !hasAtMostOneCommand {
err = errors.Join(err, fmt.Errorf(
"%w: monitor %s has both command and shell_command configured",
ErrInvalidMonitor,
monitor.Name,
))
}
if !hasValidAlertAfter {
err = errors.Join(err, fmt.Errorf(
"%w: monitor %s has invalid alert_after value %d. Must be greater than 0",
ErrInvalidMonitor,
monitor.Name,
monitor.AlertAfter,
))
}
if !hasAlertDown {
err = errors.Join(err, fmt.Errorf(
"%w: monitor %s has no alert_down configured. Configure one here or add a default_alert_down",
ErrInvalidMonitor,
monitor.Name,
))
}
return err
}
func (monitor Monitor) LastOutput() string {
return monitor.lastOutput
}
// ShouldCheck returns a boolean indicating if the Monitor is ready to be be checked again
func (monitor Monitor) ShouldCheck() bool { func (monitor Monitor) ShouldCheck() bool {
if monitor.lastCheck.IsZero() || monitor.CheckInterval == 0 { if monitor.lastCheck.IsZero() {
return true return true
} }
sinceLastCheck := time.Since(monitor.lastCheck) sinceLastCheck := time.Now().Sub(monitor.lastCheck).Seconds()
return sinceLastCheck >= monitor.CheckInterval return sinceLastCheck >= monitor.CheckInterval
} }
// Check will run the command configured by the Monitor and return a status and a possible AlertNotice // Check will run the command configured by the Monitor and return a status
// and a possible AlertNotice
func (monitor *Monitor) Check() (bool, *AlertNotice) { func (monitor *Monitor) Check() (bool, *AlertNotice) {
var cmd *exec.Cmd var cmd *exec.Cmd
if len(monitor.Command) > 0 { if monitor.Command != nil {
cmd = exec.Command(monitor.Command[0], monitor.Command[1:]...) cmd = exec.Command(monitor.Command[0], monitor.Command[1:]...)
} else if monitor.ShellCommand != "" {
cmd = ShellCommand(monitor.ShellCommand)
} else { } else {
slog.Fatalf("Monitor %s has no command configured", monitor.Name) cmd = ShellCommand(monitor.CommandShell)
} }
checkStartTime := time.Now()
output, err := cmd.CombinedOutput() output, err := cmd.CombinedOutput()
monitor.lastCheck = time.Now() monitor.lastCheck = time.Now()
monitor.lastOutput = string(output) monitor.lastOutput = string(output)
monitor.lastCheckDuration = monitor.lastCheck.Sub(checkStartTime)
var alertNotice *AlertNotice var alertNotice *AlertNotice
isSuccess := (err == nil) isSuccess := (err == nil)
if isSuccess { if isSuccess {
alertNotice = monitor.Success() alertNotice = monitor.success()
} else { } else {
alertNotice = monitor.Failure() alertNotice = monitor.failure()
} }
slog.Debugf("Command output: %s", monitor.lastOutput) if LogDebug {
slog.OnErrWarnf(err, "Command result: %v", err) log.Printf("DEBUG: Command output: %s", monitor.lastOutput)
}
if err != nil {
if LogDebug {
log.Printf("DEBUG: Command result: %v", err)
}
}
slog.Infof( log.Printf(
"%s success=%t, alert=%t", "INFO: %s success=%t, alert=%t",
monitor.Name, monitor.Name,
isSuccess, isSuccess,
alertNotice != nil, alertNotice != nil,
@@ -167,89 +89,91 @@ func (monitor *Monitor) Check() (bool, *AlertNotice) {
return isSuccess, alertNotice return isSuccess, alertNotice
} }
// GetAlertNames gives a list of alert names for a given monitor status func (monitor Monitor) isUp() bool {
func (monitor Monitor) GetAlertNames(up bool) []string { return monitor.alertCount == 0
if up {
return monitor.AlertUp
}
return monitor.AlertDown
} }
// IsUp returns the status of the current monitor func (monitor *Monitor) success() (notice *AlertNotice) {
func (monitor Monitor) IsUp() bool { if !monitor.isUp() {
return monitor.AlertCount == 0
}
// LastCheckMilliseconds gives number of miliseconds the last check ran for
func (monitor Monitor) LastCheckMilliseconds() int64 {
return monitor.lastCheckDuration.Milliseconds()
}
func (monitor *Monitor) Success() (notice *AlertNotice) {
if !monitor.IsUp() {
// Alert that we have recovered // Alert that we have recovered
notice = monitor.createAlertNotice(true) notice = monitor.createAlertNotice(true)
} }
monitor.failureCount = 0 monitor.failureCount = 0
monitor.AlertCount = 0 monitor.alertCount = 0
monitor.lastSuccess = time.Now() monitor.lastSuccess = time.Now()
return return
} }
func (monitor *Monitor) Failure() (notice *AlertNotice) { func (monitor *Monitor) failure() (notice *AlertNotice) {
monitor.failureCount++ monitor.failureCount++
// If we haven't hit the minimum failures, we can exit // If we haven't hit the minimum failures, we can exit
if monitor.failureCount < monitor.AlertAfter { if monitor.failureCount < monitor.getAlertAfter() {
slog.Debugf( if LogDebug {
"%s failed but did not hit minimum failures. "+ log.Printf(
"Count: %v alert after: %v", "DEBUG: %s failed but did not hit minimum failures. "+
monitor.Name, "Count: %v alert after: %v",
monitor.failureCount, monitor.Name,
monitor.AlertAfter, monitor.failureCount,
) monitor.getAlertAfter(),
)
}
return return
} }
// Take number of failures after minimum // Take number of failures after minimum
failureCount := (monitor.failureCount - monitor.AlertAfter) failureCount := (monitor.failureCount - monitor.getAlertAfter())
// Use alert cadence to determine if we should alert // Use alert cadence to determine if we should alert
switch { if monitor.AlertEvery > 0 {
case monitor.AlertEvery == nil, *monitor.AlertEvery == 0: // Handle integer number of failures before alerting
if failureCount%monitor.AlertEvery == 0 {
notice = monitor.createAlertNotice(false)
}
} else if monitor.AlertEvery == 0 {
// Handle alerting on first failure only // Handle alerting on first failure only
if failureCount == 0 { if failureCount == 0 {
notice = monitor.createAlertNotice(false) notice = monitor.createAlertNotice(false)
} }
case *monitor.AlertEvery > 0: } else {
// Handle integer number of failures before alerting
if failureCount%*monitor.AlertEvery == 0 {
notice = monitor.createAlertNotice(false)
}
default:
// Handle negative numbers indicating an exponential backoff // Handle negative numbers indicating an exponential backoff
if failureCount >= int(math.Pow(2, float64(monitor.AlertCount))-1) { //nolint:mnd if failureCount >= int16(math.Pow(2, float64(monitor.alertCount))-1) {
notice = monitor.createAlertNotice(false) notice = monitor.createAlertNotice(false)
} }
} }
// If we're going to alert, increment count // If we're going to alert, increment count
if notice != nil { if notice != nil {
monitor.AlertCount++ monitor.alertCount++
notice.AlertCount = monitor.AlertCount
} }
return notice return
}
func (monitor Monitor) getAlertAfter() int16 {
// TODO: Come up with a better way than this method
// Zero is one!
if monitor.AlertAfter == 0 {
return 1
} else {
return monitor.AlertAfter
}
}
// GetAlertNames gives a list of alert names for a given monitor status
func (monitor Monitor) GetAlertNames(up bool) []string {
if up {
return monitor.AlertUp
} else {
return monitor.AlertDown
}
} }
func (monitor Monitor) createAlertNotice(isUp bool) *AlertNotice { func (monitor Monitor) createAlertNotice(isUp bool) *AlertNotice {
// TODO: Maybe add something about recovery status here // TODO: Maybe add something about recovery status here
return &AlertNotice{ return &AlertNotice{
MonitorName: monitor.Name, MonitorName: monitor.Name,
AlertCount: monitor.AlertCount, AlertCount: monitor.alertCount,
FailureCount: monitor.failureCount, FailureCount: monitor.failureCount,
LastCheckOutput: monitor.lastOutput, LastCheckOutput: monitor.lastOutput,
LastSuccess: monitor.lastSuccess, LastSuccess: monitor.lastSuccess,
+161 -181
View File
@@ -1,193 +1,164 @@
package main_test package main
import ( import (
"errors" "log"
"reflect"
"testing" "testing"
"time" "time"
m "git.iamthefij.com/iamthefij/minitor-go/v2"
) )
func TestMonitorValidate(t *testing.T) { // TestMonitorIsValid tests the Monitor.IsValid()
t.Parallel() func TestMonitorIsValid(t *testing.T) {
cases := []struct { cases := []struct {
monitor m.Monitor monitor Monitor
expected error expected bool
name string name string
}{ }{
{m.Monitor{AlertAfter: 1, Command: []string{"echo", "test"}, AlertDown: []string{"log"}}, nil, "Command only"}, {Monitor{Command: []string{"echo", "test"}, AlertDown: []string{"log"}}, true, "Command only"},
{m.Monitor{AlertAfter: 1, ShellCommand: "echo test", AlertDown: []string{"log"}}, nil, "CommandShell only"}, {Monitor{CommandShell: "echo test", AlertDown: []string{"log"}}, true, "CommandShell only"},
{m.Monitor{AlertAfter: 1, Command: []string{"echo", "test"}}, m.ErrInvalidMonitor, "No AlertDown"}, {Monitor{Command: []string{"echo", "test"}}, false, "No AlertDown"},
{m.Monitor{AlertAfter: 1, AlertDown: []string{"log"}}, m.ErrInvalidMonitor, "No commands"}, {Monitor{AlertDown: []string{"log"}}, false, "No commands"},
{m.Monitor{AlertAfter: -1, Command: []string{"echo", "test"}, AlertDown: []string{"log"}}, m.ErrInvalidMonitor, "Invalid alert threshold, -1"}, {
Monitor{Command: []string{"echo", "test"}, CommandShell: "echo test", AlertDown: []string{"log"}},
false,
"Both commands",
},
{Monitor{Command: []string{"echo", "test"}, AlertDown: []string{"log"}, AlertAfter: -1}, false, "Invalid alert threshold, -1"},
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { actual := c.monitor.IsValid()
t.Parallel() if actual != c.expected {
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expected, actual)
actual := c.monitor.Validate() log.Printf("Case failed: %s", c.name)
hasErr := (actual != nil) }
expectErr := (c.expected != nil) log.Println("-----")
if hasErr != expectErr || !errors.Is(actual, c.expected) {
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expected, actual)
}
})
} }
} }
// TestMonitorShouldCheck tests the Monitor.ShouldCheck() // TestMonitorShouldCheck tests the Monitor.ShouldCheck()
func TestMonitorShouldCheck(t *testing.T) { func TestMonitorShouldCheck(t *testing.T) {
t.Parallel() timeNow := time.Now()
timeTenSecAgo := time.Now().Add(time.Second * -10)
timeTwentySecAgo := time.Now().Add(time.Second * -20)
// Create a monitor that should check every second and then verify it checks with some sleeps cases := []struct {
monitor := m.Monitor{ShellCommand: "true", CheckInterval: time.Second} monitor Monitor
expected bool
if !monitor.ShouldCheck() { name string
t.Errorf("New monitor should be ready to check") }{
{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.Check() for _, c := range cases {
actual := c.monitor.ShouldCheck()
if monitor.ShouldCheck() { if actual != c.expected {
t.Errorf("Monitor should not be ready to check after a check") t.Errorf("ShouldCheck(%v), expected=%t actual=%t", c.name, c.expected, actual)
} }
time.Sleep(time.Second)
if !monitor.ShouldCheck() {
t.Errorf("Monitor should be ready to check after a second")
} }
} }
// TestMonitorIsUp tests the Monitor.IsUp() // TestMonitorIsUp tests the Monitor.isUp()
func TestMonitorIsUp(t *testing.T) { func TestMonitorIsUp(t *testing.T) {
t.Parallel() cases := []struct {
monitor Monitor
// Creating a monitor that should alert after 2 failures. The monitor should be considered up until we reach two failed checks expected bool
monitor := m.Monitor{ShellCommand: "false", AlertAfter: 2} name string
if !monitor.IsUp() { }{
t.Errorf("New monitor should be considered up") {Monitor{}, true, "Empty"},
{Monitor{alertCount: 1}, false, "Has alert"},
{Monitor{alertCount: -1}, false, "Negative alerts"},
{Monitor{alertCount: 0}, true, "No alerts"},
} }
monitor.Check() for _, c := range cases {
log.Printf("Testing case %s", c.name)
if !monitor.IsUp() { actual := c.monitor.isUp()
t.Errorf("Monitor should be considered up with one failure and no alerts") if actual != c.expected {
} t.Errorf("isUp(%v), expected=%t actual=%t", c.name, c.expected, actual)
log.Printf("Case failed: %s", c.name)
monitor.Check() }
log.Println("-----")
if monitor.IsUp() {
t.Errorf("Monitor should be considered down with one alert")
} }
} }
// TestMonitorGetAlertNames tests that proper alert names are returned // TestMonitorGetAlertNames tests that proper alert names are returned
func TestMonitorGetAlertNames(t *testing.T) { func TestMonitorGetAlertNames(t *testing.T) {
cases := []struct { cases := []struct {
monitor m.Monitor monitor Monitor
up bool up bool
expected []string expected []string
name string name string
}{ }{
{m.Monitor{}, true, nil, "Empty up"}, {Monitor{}, true, nil, "Empty up"},
{m.Monitor{}, false, nil, "Empty down"}, {Monitor{}, false, nil, "Empty down"},
{m.Monitor{AlertUp: []string{"alert"}}, true, []string{"alert"}, "Return up"}, {Monitor{AlertUp: []string{"alert"}}, true, []string{"alert"}, "Return up"},
{m.Monitor{AlertDown: []string{"alert"}}, false, []string{"alert"}, "Return down"}, {Monitor{AlertDown: []string{"alert"}}, false, []string{"alert"}, "Return down"},
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { actual := c.monitor.GetAlertNames(c.up)
t.Parallel() if !EqualSliceString(actual, c.expected) {
t.Errorf("GetAlertNames(%v), expected=%v actual=%v", c.name, c.expected, actual)
actual := c.monitor.GetAlertNames(c.up) log.Printf("Case failed: %s", c.name)
if !reflect.DeepEqual(actual, c.expected) { }
t.Errorf("GetAlertNames(%v), expected=%v actual=%v", c.name, c.expected, actual) log.Println("-----")
}
})
} }
} }
func TestMonitorAlertCount(t *testing.T) { // TestMonitorSuccess tests the Monitor.success()
alertEvery := 1 func TestMonitorSuccess(t *testing.T) {
cases := []struct { cases := []struct {
checkSuccess bool monitor Monitor
alertCount int expectNotice bool
name string name string
}{ }{
{false, 1, "First failure and first alert"}, {Monitor{}, false, "Empty"},
{false, 2, "Second failure and first alert"}, {Monitor{alertCount: 0}, false, "No alerts"},
{true, 2, "Success should preserve past alert count"}, {Monitor{alertCount: 1}, true, "Has alert"},
{false, 1, "First failure and first alert after success"},
} }
// Unlike previous tests, this one requires a static Monitor with repeated
// calls to the failure method
monitor := m.Monitor{AlertAfter: 1, AlertEvery: &alertEvery}
for _, c := range cases { for _, c := range cases {
t.Logf("Testing case %s", c.name) log.Printf("Testing case %s", c.name)
notice := c.monitor.success()
var notice *m.AlertNotice hasNotice := (notice != nil)
if c.checkSuccess { if hasNotice != c.expectNotice {
notice = monitor.Success() t.Errorf("success(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
} else { log.Printf("Case failed: %s", c.name)
notice = monitor.Failure()
}
if notice == nil {
t.Fatalf("failure(%v) expected notice, got nil", c.name)
}
if notice.AlertCount != c.alertCount {
t.Errorf("failure(%v), expected=%v actual=%v", c.name, c.alertCount, notice.AlertCount)
t.Logf("Case failed: %s", c.name)
} }
log.Println("-----")
} }
} }
// TestMonitorFailureAlertAfter tests that alerts will not trigger until // TestMonitorFailureAlertAfter tests that alerts will not trigger until
// hitting the threshold provided by AlertAfter // hitting the threshold provided by AlertAfter
func TestMonitorFailureAlertAfter(t *testing.T) { func TestMonitorFailureAlertAfter(t *testing.T) {
var alertEveryOne int = 1
cases := []struct { cases := []struct {
monitor m.Monitor monitor Monitor
numChecks int
expectNotice bool expectNotice bool
name string name string
}{ }{
{m.Monitor{ShellCommand: "false", AlertAfter: 1}, 1, true, "Empty After 1"}, // Defaults to true because and AlertEvery default to 0 {Monitor{AlertAfter: 1}, true, "Empty"}, // Defaults to true because and AlertEvery default to 0
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryOne}, 1, true, "Alert after 1: first failure"}, {Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 1}, true, "Alert after 1: first failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryOne}, 2, true, "Alert after 1: second failure"}, {Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 1}, true, "Alert after 1: second failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 1, false, "Alert after 20: first failure"}, {Monitor{failureCount: 0, AlertAfter: 20, AlertEvery: 1}, false, "Alert after 20: first failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 20, true, "Alert after 20: 20th failure"}, {Monitor{failureCount: 19, AlertAfter: 20, AlertEvery: 1}, true, "Alert after 20: 20th failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 21, true, "Alert after 20: 21st failure"}, {Monitor{failureCount: 20, AlertAfter: 20, AlertEvery: 1}, true, "Alert after 20: 21st failure"},
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { notice := c.monitor.failure()
t.Parallel() hasNotice := (notice != nil)
if hasNotice != c.expectNotice {
hasNotice := false t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
log.Printf("Case failed: %s", c.name)
for i := 0; i < c.numChecks; i++ { }
_, notice := c.monitor.Check() log.Println("-----")
hasNotice = (notice != nil)
}
if hasNotice != c.expectNotice {
t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
}
})
} }
} }
@@ -195,41 +166,51 @@ func TestMonitorFailureAlertAfter(t *testing.T) {
// on the expected intervals // on the expected intervals
func TestMonitorFailureAlertEvery(t *testing.T) { func TestMonitorFailureAlertEvery(t *testing.T) {
cases := []struct { cases := []struct {
monitor m.Monitor monitor Monitor
expectedNotice []bool expectNotice bool
name string name string
}{ }{
{m.Monitor{ShellCommand: "false", AlertAfter: 1}, []bool{true}, "No AlertEvery set"}, // Defaults to true because AlertAfter and AlertEvery default to nil /*
TODO: Actually found a bug in original implementation. There is an inconsistency in the way AlertAfter is treated.
For "First alert only" (ie. AlertEvery=0), it is the number of failures to ignore before alerting, so AlertAfter=1
will ignore the first failure and alert on the second failure
For other intervals (ie. AlertEvery=1), it is essentially indexed on one. Essentially making AlertAfter=1 trigger
on the first failure.
For usabilty, this should be consistent. Consistent with what though? minitor-py? Or itself? Dun dun duuuunnnnn!
*/
{Monitor{AlertAfter: 1}, true, "Empty"}, // Defaults to true because AlertAfter and AlertEvery default to 0
// Alert first time only, after 1 // Alert first time only, after 1
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: new(0)}, []bool{true, false, false}, "Alert first time only after 1"}, {Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 0}, true, "Alert first time only after 1: first failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 0}, false, "Alert first time only after 1: second failure"},
{Monitor{failureCount: 2, AlertAfter: 1, AlertEvery: 0}, false, "Alert first time only after 1: third failure"},
// Alert every time, after 1 // Alert every time, after 1
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: new(1)}, []bool{true, true, true}, "Alert every time after 1"}, {Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 1}, true, "Alert every time after 1: first failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 1}, true, "Alert every time after 1: second failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 1}, true, "Alert every time after 1: third failure"},
// Alert every other time, after 1 // Alert every other time, after 1
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: new(2)}, []bool{true, false, true, false}, "Alert every other time after 1"}, {Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 2}, true, "Alert every other time after 1: first failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 2}, false, "Alert every other time after 1: second failure"},
{Monitor{failureCount: 2, AlertAfter: 1, AlertEvery: 2}, true, "Alert every other time after 1: third failure"},
{Monitor{failureCount: 3, AlertAfter: 1, AlertEvery: 2}, false, "Alert every other time after 1: fourth failure"},
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { notice := c.monitor.failure()
t.Parallel() hasNotice := (notice != nil)
if hasNotice != c.expectNotice {
for i, expectNotice := range c.expectedNotice { t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
_, notice := c.monitor.Check() log.Printf("Case failed: %s", c.name)
hasNotice := (notice != nil) }
log.Println("-----")
if hasNotice != expectNotice {
t.Errorf("failed %s check %d: expected=%t actual=%t", c.name, i, expectNotice, hasNotice)
}
}
})
} }
} }
// TestMonitorFailureExponential tests that alerts will trigger // TestMonitorFailureExponential tests that alerts will trigger
// with an exponential backoff after repeated failures // with an exponential backoff after repeated failures
func TestMonitorFailureExponential(t *testing.T) { func TestMonitorFailureExponential(t *testing.T) {
var alertEveryExp int = -1
cases := []struct { cases := []struct {
expectNotice bool expectNotice bool
name string name string
@@ -246,18 +227,17 @@ func TestMonitorFailureExponential(t *testing.T) {
// Unlike previous tests, this one requires a static Monitor with repeated // Unlike previous tests, this one requires a static Monitor with repeated
// calls to the failure method // calls to the failure method
monitor := m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryExp} monitor := Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: -1}
for _, c := range cases { for _, c := range cases {
t.Run(c.name, func(t *testing.T) { log.Printf("Testing case %s", c.name)
// NOTE: These tests are not parallel because they rely on the state of the Monitor
_, notice := monitor.Check()
hasNotice := (notice != nil)
if hasNotice != c.expectNotice { notice := monitor.failure()
t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice) hasNotice := (notice != nil)
} if hasNotice != c.expectNotice {
}) t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
log.Printf("Case failed: %s", c.name)
}
log.Println("-----")
} }
} }
@@ -268,53 +248,53 @@ func TestMonitorCheck(t *testing.T) {
hasNotice bool hasNotice bool
lastOutput string lastOutput string
} }
cases := []struct { cases := []struct {
monitor m.Monitor monitor Monitor
expect expected expect expected
name string name string
}{ }{
{ {
m.Monitor{AlertAfter: 1, Command: []string{"echo", "success"}}, Monitor{Command: []string{"echo", "success"}},
expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"}, expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"},
"Test successful command", "Test successful command",
}, },
{ {
m.Monitor{AlertAfter: 1, ShellCommand: "echo success"}, Monitor{CommandShell: "echo success"},
expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"}, expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"},
"Test successful command shell", "Test successful command shell",
}, },
{ {
m.Monitor{AlertAfter: 1, Command: []string{"total", "failure"}}, Monitor{Command: []string{"total", "failure"}},
expected{isSuccess: false, hasNotice: true, lastOutput: ""}, expected{isSuccess: false, hasNotice: true, lastOutput: ""},
"Test failed command", "Test failed command",
}, },
{ {
m.Monitor{AlertAfter: 1, ShellCommand: "false"}, Monitor{CommandShell: "false"},
expected{isSuccess: false, hasNotice: true, lastOutput: ""}, expected{isSuccess: false, hasNotice: true, lastOutput: ""},
"Test failed command shell", "Test failed command shell",
}, },
} }
for _, c := range cases { for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) { isSuccess, notice := c.monitor.Check()
t.Parallel() if isSuccess != c.expect.isSuccess {
t.Errorf("Check(%v) (success), expected=%t actual=%t", c.name, c.expect.isSuccess, isSuccess)
log.Printf("Case failed: %s", c.name)
}
isSuccess, notice := c.monitor.Check() hasNotice := (notice != nil)
if isSuccess != c.expect.isSuccess { if hasNotice != c.expect.hasNotice {
t.Errorf("Check(%v) (success), expected=%t actual=%t", c.name, c.expect.isSuccess, isSuccess) t.Errorf("Check(%v) (notice), expected=%t actual=%t", c.name, c.expect.hasNotice, hasNotice)
} log.Printf("Case failed: %s", c.name)
}
hasNotice := (notice != nil) lastOutput := c.monitor.lastOutput
if hasNotice != c.expect.hasNotice { if lastOutput != c.expect.lastOutput {
t.Errorf("Check(%v) (notice), expected=%t actual=%t", c.name, c.expect.hasNotice, hasNotice) t.Errorf("Check(%v) (output), expected=%v actual=%v", c.name, c.expect.lastOutput, lastOutput)
} log.Printf("Case failed: %s", c.name)
}
lastOutput := c.monitor.LastOutput() log.Println("-----")
if lastOutput != c.expect.lastOutput {
t.Errorf("Check(%v) (output), expected=%v actual=%v", c.name, c.expect.lastOutput, lastOutput)
}
})
} }
} }
-3
View File
@@ -1,3 +0,0 @@
{
"$schema": "https://docs.renovatebot.com/renovate-schema.json"
}
-52
View File
@@ -1,52 +0,0 @@
check_interval = "5s"
monitor "Fake Website" {
command = ["curl", "-s", "-o", "/dev/null", "https://minitor.mon"]
alert_down = ["log_down", "mailgun_down", "sms_down"]
alert_up = ["log_up", "email_up"]
check_interval = "10s" # Must be at minimum the global `check_interval`
alert_after = 3
alert_every = -1 # Defaults to -1 for exponential backoff. 0 to disable repeating
}
monitor "Real Website" {
command = ["curl", "-s", "-o", "/dev/null", "https://google.com"]
alert_down = ["log_down", "mailgun_down", "sms_down"]
alert_up = ["log_up", "email_up"]
check_interval = "5s"
alert_after = 3
alert_every = -1
}
alert "log_down" {
command = ["echo", "Minitor failure for {{.MonitorName}}"]
}
alert "log_up" {
command = ["echo", "Minitor recovery for {{.MonitorName}}"]
}
alert "email_up" {
command = ["sendmail", "me@minitor.mon", "Recovered: {monitor_name}", "We're back!"]
}
alert "mailgun_down" {
shell_command = <<-EOF
curl -s -X POST \
-F subject="Alert! {{.MonitorName}} failed" \
-F from="Minitor <minitor@minitor.mon>" \
-F to=me@minitor.mon \
-F text="Our monitor failed" \
https://api.mailgun.net/v3/minitor.mon/messages \
-u "api:$${MAILGUN_API_KEY}"
EOF
}
alert "sms_down" {
shell_command = <<-EOF
curl -s -X POST -F "Body=Failure! {{.MonitorName}} has failed" \
-F "From=$${AVAILABLE_NUMBER}" -F "To=$${MY_PHONE}" \
"https://api.twilio.com/2010-04-01/Accounts/$${ACCOUNT_SID}/Messages" \
-u "$${ACCOUNT_SID}:$${AUTH_TOKEN}"
EOF
}
+29
View File
@@ -0,0 +1,29 @@
check_interval: 30
monitors:
- name: My Website
command: [ 'curl', '-s', '-o', '/dev/null', 'https://minitor.mon' ]
alert_down: [ log, mailgun_down, sms_down ]
alert_up: [ log, email_up ]
check_interval: 30 # Must be at minimum the global `check_interval`
alert_after: 3
alert_every: -1 # Defaults to -1 for exponential backoff. 0 to disable repeating
alerts:
email_up:
command: [ sendmail, "me@minitor.mon", "Recovered: {monitor_name}", "We're back!" ]
mailgun_down:
command: >
curl -s -X POST
-F subject="Alert! {monitor_name} failed"
-F from="Minitor <minitor@minitor.mon>"
-F to=me@minitor.mon
-F text="Our monitor failed"
https://api.mailgun.net/v3/minitor.mon/messages
-u "api:${MAILGUN_API_KEY}"
sms_down:
command: >
curl -s -X POST -F "Body=Failure! {monitor_name} has failed"
-F "From=${AVAILABLE_NUMBER}" -F "To=${MY_PHONE}"
"https://api.twilio.com/2010-04-01/Accounts/${ACCOUNT_SID}/Messages"
-u "${ACCOUNT_SID}:${AUTH_TOKEN}"
-5
View File
@@ -1,5 +0,0 @@
# Minitor Scripts
A collection of some handy scripts to use with Minitor
These are not included with the Python package, but they are included in the Docker image in `/app/scripts`.
-6
View File
@@ -1,6 +0,0 @@
#! /bin/sh
# Used for a basic HTTP health check
# Avoids output from non-errors and will fail if the HTTP response is unsuccessful
curl --silent --show-error --fail -o /dev/null "$@"
-63
View File
@@ -1,63 +0,0 @@
#! /bin/bash
set -e
#################
# docker_check.sh
#
# Checks the most recent state exit code of a Docker container
#################
# Docker host will default to a socket
# To override, export DOCKER_HOST to a new hostname
DOCKER_HOST="${DOCKER_HOST:=socket}"
container_name="$1"
num_log_lines="$2"
# Curls Docker either using a socket or URL
function curl_docker {
local path="$1"
if [ "$DOCKER_HOST" == "socket" ]; then
curl --unix-socket /var/run/docker.sock "http://localhost/$path" 2>/dev/null
else
curl "http://${DOCKER_HOST}/$path" 2>/dev/null
fi
}
# Returns caintainer ID for a given container name
function get_container_id {
local container_name="$1"
curl_docker 'containers/json?all=1' \
| jq -r ".[] | {Id, Name: .Names[]} | select(.Name == \"/${container_name}\") | .Id"
}
# Returns container JSON
function inspect_container {
local container_id="$1"
curl_docker "containers/$container_id/json"
}
# Gets some lines from docker log
function get_logs {
container_id="$1"
num_lines="$2"
curl_docker "containers/$container_id/logs?stdout=1&stderr=1" | tail -n "$num_lines"
}
if [ -z "$container_name" ]; then
echo "Usage: $0 container_name [num_log_lines]"
echo "Will exit with the last status code of continer with provided name"
exit 1
fi
container_id=$(get_container_id "$container_name")
if [ -z "$container_id" ]; then
echo "ERROR: Could not find container with name: $container_name"
exit 1
fi
exit_code=$(inspect_container "$container_id" | jq -r .State.ExitCode)
if [ -n "$num_log_lines" ]; then
get_logs "$container_id" "$num_log_lines"
fi
exit "$exit_code"
-73
View File
@@ -1,73 +0,0 @@
#! /bin/bash
set -e
#################
# docker_healthcheck.sh
#
# Returns the results of a Docker Healthcheck for a container
#################
# Docker host will default to a socket
# To override, export DOCKER_HOST to a new hostname
DOCKER_HOST="${DOCKER_HOST:=socket}"
container_name="$1"
num_log_lines="$2"
# Curls Docker either using a socket or URL
function curl_docker {
local path="$1"
if [ "$DOCKER_HOST" == "socket" ]; then
curl --unix-socket /var/run/docker.sock "http://localhost/$path" 2>/dev/null
else
curl "http://${DOCKER_HOST}/$path" 2>/dev/null
fi
}
# Returns caintainer ID for a given container name
function get_container_id {
local container_name="$1"
curl_docker 'containers/json?all=1' \
| jq -r ".[] | {Id, Name: .Names[]} | select(.Name == \"/${container_name}\") | .Id"
}
# Returns container JSON
function inspect_container {
local container_id="$1"
curl_docker "containers/$container_id/json"
}
# Gets some lines from docker log
function get_logs {
container_id="$1"
num_lines="$2"
curl_docker "containers/$container_id/logs?stdout=1&stderr=1" | tail -n "$num_lines"
}
if [ -z "$container_name" ]; then
echo "Usage: $0 container_name [num_log_lines]"
echo "Will return results of healthcheck for continer with provided name"
exit 1
fi
container_id=$(get_container_id "$container_name")
if [ -z "$container_id" ]; then
echo "ERROR: Could not find container with name: $container_name"
exit 1
fi
health=$(inspect_container "$container_id" | jq -r '.State.Health.Status')
if [ -n "$num_log_lines" ]; then
get_logs "$container_id" "$num_log_lines"
fi
case "$health" in
null)
echo "No healthcheck results"
;;
starting|healthy)
echo "Status: '$health'"
;;
*)
echo "Status: '$health'"
exit 1
esac
-1
View File
@@ -1 +0,0 @@
check_interval = "woops, I'm not an int!"
-7
View File
@@ -1,7 +0,0 @@
check_interval = "1s"
monitor "Command" {
command = ["echo", "$PATH"]
alert_down = [ "alert_down", "log_shell", "log_command" ]
alert_every = 0
}
+9
View File
@@ -0,0 +1,9 @@
check_interval: 1
monitors:
- name: Command
command: ['echo', '$PATH']
alert_down: [ 'alert_down', 'log_shell', 'log_command' ]
# alert_every: -1
alert_every: 0
+1
View File
@@ -0,0 +1 @@
check_interval: woops, I'm not an int!
-12
View File
@@ -1,12 +0,0 @@
check_interval = "1s"
monitor "Command" {
command = ["echo", "$PATH"]
alert_down = ["not_log"]
alert_every = 0
}
alert "log" {
command = ["true"]
}
+13
View File
@@ -0,0 +1,13 @@
check_interval: 1
monitors:
- name: Command
command: ['echo', '$PATH']
alert_down: [ 'not_log']
# alert_every: -1
alert_every: 0
alerts:
log:
command: ['true']
-12
View File
@@ -1,12 +0,0 @@
check_interval = "1s"
alert "log_command" {
command = "should be a list"
}
monitor "Command" {
command = ["echo", "$PATH"]
alert_down = ["log_command"]
alert_every = 2
check_interval = "10s"
}
-16
View File
@@ -1,16 +0,0 @@
check_interval = "1s"
default_alert_down = ["log_command"]
default_alert_every = 0
default_alert_after = 2
monitor "Default" {
command = ["echo"]
}
monitor "Command" {
command = ["echo", "$PATH"]
}
alert "log_command" {
command = ["echo", "default", "'command!!!'", "{{.MonitorName}}"]
}
-34
View File
@@ -1,34 +0,0 @@
check_interval = "1s"
alert "log_command" {
command = ["echo", "regular", "'command!!!'", "{{.MonitorName}}"]
}
alert "log_shell" {
shell_command = "echo \"Failure on {{.MonitorName}} User is $USER\""
}
monitor "Default" {
command = ["echo"]
alert_down = ["log_command"]
}
monitor "Command" {
command = ["echo", "$PATH"]
alert_down = ["log_command", "log_shell"]
alert_every = 2
check_interval = "10s"
}
monitor "Shell" {
shell_command = <<-EOF
echo 'Some string with stuff'
echo 'another line'
echo $PATH
exit 1
EOF
alert_down = ["log_command", "log_shell"]
alert_after = 5
alert_every = 0
check_interval = "1m"
}
+22
View File
@@ -0,0 +1,22 @@
check_interval: 1
monitors:
- name: Command
command: ['echo', '$PATH']
alert_down: [ 'log_command', 'log_shell' ]
alert_every: 0
- name: Shell
command_shell: >
echo 'Some string with stuff';
echo 'another line';
echo $PATH;
exit 1
alert_down: [ 'log_command', 'log_shell' ]
alert_after: 5
alert_every: 0
alerts:
log_command:
command: [ 'echo', 'regular', '"command!!!"', "{{.MonitorName}}" ]
log_shell:
command_shell: echo "Failure on {{.MonitorName}} User is $USER"
-19
View File
@@ -1,19 +0,0 @@
check_interval = "1s"
monitor "Shell" {
shell_command = <<-EOF
echo 'Some string with stuff'
echo "<angle brackets>"
exit 1
EOF
alert_down = ["log_shell"]
alert_after = 1
alert_every = 0
}
alert "log_shell" {
shell_command = <<EOF
echo 'Some string with stuff'
echo '<angle brackets>'
EOF
}
+12 -4
View File
@@ -5,10 +5,20 @@ import (
"strings" "strings"
) )
// escapeCommandShell accepts a command to be executed by a shell and escapes it
func escapeCommandShell(command string) string {
// Remove extra spaces and newlines from ends
command = strings.TrimSpace(command)
// TODO: Not sure if this part is actually needed. Should verify
// Escape double quotes since this will be passed in as an argument
command = strings.Replace(command, `"`, `\"`, -1)
return command
}
// ShellCommand takes a string and executes it as a command using `sh` // ShellCommand takes a string and executes it as a command using `sh`
func ShellCommand(command string) *exec.Cmd { func ShellCommand(command string) *exec.Cmd {
shellCommand := []string{"sh", "-c", strings.TrimSpace(command)} shellCommand := []string{"sh", "-c", escapeCommandShell(command)}
//log.Printf("Shell command: %v", shellCommand)
return exec.Command(shellCommand[0], shellCommand[1:]...) return exec.Command(shellCommand[0], shellCommand[1:]...)
} }
@@ -17,12 +27,10 @@ func EqualSliceString(a, b []string) bool {
if len(a) != len(b) { if len(a) != len(b) {
return false return false
} }
for i, val := range a { for i, val := range a {
if val != b[i] { if val != b[i] {
return false return false
} }
} }
return true return true
} }
+8 -16
View File
@@ -1,9 +1,6 @@
package main package main
import ( import "testing"
"fmt"
"testing"
)
func TestUtilEqualSliceString(t *testing.T) { func TestUtilEqualSliceString(t *testing.T) {
cases := []struct { cases := []struct {
@@ -24,17 +21,12 @@ func TestUtilEqualSliceString(t *testing.T) {
} }
for _, c := range cases { for _, c := range cases {
actual := EqualSliceString(c.a, c.b)
t.Run(fmt.Sprintf("%v %v", c.a, c.b), func(t *testing.T) { if actual != c.expected {
t.Parallel() t.Errorf(
"EqualSliceString(%v, %v), expected=%v actual=%v",
actual := EqualSliceString(c.a, c.b) c.a, c.b, c.expected, actual,
if actual != c.expected { )
t.Errorf( }
"EqualSliceString(%v, %v), expected=%v actual=%v",
c.a, c.b, c.expected, actual,
)
}
})
} }
} }