Compare commits

..

72 Commits

Author SHA1 Message Date
IamTheFij
5f6c924089 Merge pull request 'golang-1-26' (#27) from golang-1-26 into main
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/27
2026-02-18 17:39:24 +00:00
Ian Fijolek
e614fb35b5 Clean up golangci-lint config 2026-02-18 17:39:24 +00:00
Ian Fijolek
3323a562c9 Run go fix 2026-02-18 17:39:24 +00:00
Ian Fijolek
c40841ef61 Bump go to 1.26 2026-02-18 17:39:24 +00:00
IamTheFij
59ce31c35f Merge pull request 'Update https://git.iamthefij.com/iamthefij/pre-commit-action action to v3.1.0' (#26) from renovate/https-git.iamthefij.com-iamthefij-pre-commit-action-3.x into main
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/26
2026-02-15 01:19:36 +00:00
Renovate Bot
39359ffb1e Update https://git.iamthefij.com/iamthefij/pre-commit-action action to v3.1.0 2026-02-13 00:03:15 +00:00
Renovate Bot
7d92458a7a Update golang Docker tag to v1.26 2026-02-12 22:37:59 +00:00
Ian Fijolek
723cf7d127 Add armv7 docker build 2026-01-16 10:36:49 -08:00
Ian Fijolek
fd8e81cb1a Update slog to v2 2026-01-15 10:58:35 -08:00
Renovate Bot
0e291719c9 Update golang Docker tag to v1.25 2026-01-15 01:06:41 +00:00
Renovate Bot
884fbaceac Update module git.iamthefij.com/iamthefij/slog to v2 2026-01-15 00:03:12 +00:00
Ian Fijolek
e262afdb1f Merge branch 'master' into next-major 2026-01-13 21:45:27 -08:00
Renovate Bot
a5268ae1f6 Update actions/setup-python action to v6 2026-01-14 05:45:09 +00:00
Renovate Bot
16ad16d873 Update actions/setup-go action to v6 2026-01-14 05:44:37 +00:00
Ian Fijolek
f4fb75610a Update variable interpolation for hcl 2026-01-13 21:43:57 -08:00
Ian Fijolek
0ae7c6dbdf Update default config file to config.hcl 2026-01-13 21:43:03 -08:00
Ian Fijolek
a06ed3540c Remove extra spaces in Makefile 2026-01-13 21:13:19 -08:00
Renovate Bot
200cfd1a2d Update actions/checkout action to v6 2026-01-07 00:02:31 +00:00
Ian Fijolek
bcbac39cad Add migration instructions 2026-01-05 16:32:59 -08:00
Ian Fijolek
afacf40ec8 Update build to better detect tags and versions 2026-01-05 16:20:51 -08:00
Ian Fijolek
c18e9c8771 Update readme with better default descriptions 2025-12-11 16:41:17 -08:00
Ian Fijolek
eb2987d3bc Tidy again and update readme 2025-12-11 16:37:02 -08:00
Ian Fijolek
945c1b1ce0 Update module path to v2 2025-12-11 16:34:18 -08:00
Ian Fijolek
b0ea3dc6d4 Bump go version 2025-12-11 16:26:05 -08:00
Ian Fijolek
5c97f2e5c4 Update defaults and add tests for them 2025-12-11 16:18:26 -08:00
Ian Fijolek
85afa3d9ef Merge branch 'master' into next-major 2025-12-11 16:17:38 -08:00
Renovate Bot
0a7aab7030 Update actions/checkout action to v6 2025-12-12 00:02:32 +00:00
IamTheFij
fb9d637614 Merge pull request 'Update actions/setup-go action to v6' (#13) from renovate/actions-setup-go-6.x into master
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/13
2025-12-11 23:09:33 +00:00
Renovate Bot
98be873220 Update actions/setup-go action to v6 2025-12-11 23:09:33 +00:00
IamTheFij
f59848fb61 Merge pull request 'Update actions/setup-python action to v6' (#14) from renovate/actions-setup-python-6.x into master
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/14
2025-12-11 23:09:11 +00:00
Renovate Bot
e74fe89cab Update actions/setup-python action to v6 2025-12-11 23:09:11 +00:00
IamTheFij
1bc8ab5dac Merge pull request 'Update alpine Docker tag to v3.23' (#7) from renovate/alpine-3.x into master
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/7
2025-12-11 22:33:11 +00:00
Renovate Bot
f21dce1cc6 Update alpine Docker tag to v3.23 2025-12-11 22:33:11 +00:00
IamTheFij
cfcdf04990 Merge pull request 'Update module github.com/prometheus/client_golang to v1.23.2' (#9) from renovate/github.com-prometheus-client_golang-1.x into master
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/9
2025-12-11 22:29:30 +00:00
Renovate Bot
9892af48d1 Update module github.com/prometheus/client_golang to v1.23.2 2025-12-11 20:46:36 +00:00
IamTheFij
c8e914d1b8 Merge pull request 'Switch to gitea actions' (#11) from gitea-actions into master
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/11
2025-12-11 19:07:28 +00:00
Ian Fijolek
845604c54c Use temporary hadolint hook location 2025-12-11 11:03:39 -08:00
Ian Fijolek
49acca1c79 Switch to gitea actions 2025-12-10 23:17:42 -08:00
IamTheFij
2bdafd908d Merge pull request 'Update golang Docker tag to v1.25' (#8) from renovate/golang-1.x into master
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/8
2025-12-10 19:27:55 +00:00
Renovate Bot
b349ada44e Update golang Docker tag to v1.25 2025-12-10 19:23:55 +00:00
IamTheFij
fbf92d924c Merge pull request 'Configure Renovate' (#6) from renovate/configure into master
Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/6
2025-12-10 19:19:21 +00:00
Renovate Bot
fd292b005c Add renovate.json 2025-12-10 18:23:06 +00:00
Ian Fijolek
3ef06fb78d Stop getting errors when tzdata updates 2025-02-13 13:28:06 -08:00
Ian Fijolek
4aef7b7458 Remove redundant logging 2025-02-13 12:17:59 -08:00
Ian Fijolek
be2e8121c5 Refactor validation for alert and monitor to return errors 2025-02-13 12:17:59 -08:00
Ian Fijolek
9e20c00dde Move monitor init to it's own method and refactor config validate to return err 2025-02-13 12:17:59 -08:00
Ian Fijolek
3fb418151b Update readme and update some test files to be better examples 2025-02-13 12:17:59 -08:00
Ian Fijolek
df1c7aa74b Refactor test package and some field types
Fairly big test refactor and changing some of the fields from pointers
2025-02-13 12:17:59 -08:00
Ian Fijolek
7c72eabd6b Initial step of hcl migration 2025-02-13 12:17:46 -08:00
IamTheFij
0535bdf156 Fix incorrect alertCount 2025-02-13 12:12:01 -08:00
Ian Fijolek
03f0ab69fe Add documentation for default_alert_every 2025-02-13 11:26:39 -08:00
Ian Fijolek
9ec62528d9 Make linters happy 2024-11-14 13:13:16 -08:00
Ian Fijolek
312821fa8d Add pycompat warning 2024-11-14 13:09:23 -08:00
Ian Fijolek
32745c816c Improve test structures using subtests 2024-11-14 11:35:26 -08:00
Ian Fijolek
3f6c8f5a22 Breaking: Remove 'SecondsOrDuration' for check_interval
Now requires an explicit duration unit. Eg. 30s
2024-11-14 11:18:39 -08:00
Ian Fijolek
67d7e0574e Breaking: Remove python compat flag 2024-11-14 11:18:05 -08:00
Ian Fijolek
7604138c9e Use buildx 2024-04-03 12:15:11 -07:00
Ian Fijolek
f58b4c1495 Adds ability to run specified alerts on startup
This is helpful to determine if your alerts are valid before an actual failure
2024-04-03 12:03:17 -07:00
Ian Fijolek
6a2b44673e Upgrade prometheus client and protobuf 2024-04-03 11:28:01 -07:00
Ian Fijolek
01cca50532 Add tzdata
Allows setting container timezone using TZ env variable
2023-08-11 06:20:35 -07:00
Ian Fijolek
2789aa63e4 More loosely pins apk packages 2023-08-11 06:20:15 -07:00
Ian Fijolek
37db4b2db0 Update error string when failing to send alert
Wrap both originating errors
2023-08-10 16:23:02 -04:00
Ian Fijolek
41a1dbeceb Add date format functions 2023-08-10 16:22:30 -04:00
Ian Fijolek
c02d64d674 Update go to 1.20 2023-08-10 16:21:33 -04:00
Ian Fijolek
46f4561bea Update alpine and system package versions
Bump to alpine 3.18
2023-06-14 16:52:04 -07:00
Ian Fijolek
a1e0e9698b Add dig and nslookup 2023-05-05 14:07:53 -07:00
Ian Fijolek
ded4e129a1 Switch from deprecated ioutil 2023-04-18 16:17:06 -07:00
Ian Fijolek
95cb24ac04 Upgrade golangci-lint pre-commit hook 2023-04-18 16:16:53 -07:00
Ian Fijolek
e6447b615f Upgrade some dependencies 2023-04-18 16:09:41 -07:00
Ian Fijolek
2680eabd40 Rebuild when mod files change 2023-04-18 16:09:30 -07:00
Ian Fijolek
23340e823f Update go version in go.mod 2023-04-18 16:02:04 -07:00
Ian Fijolek
99b8723abc Add curl script to simplify http healthchecks 2023-04-18 15:56:59 -07:00
39 changed files with 1429 additions and 1114 deletions
+8 -44
View File
@@ -4,7 +4,7 @@ name: test
steps:
- name: test
image: golang:1.17
image: golang:1.26
environment:
VERSION: ${DRONE_TAG:-${DRONE_COMMIT}}
commands:
@@ -30,7 +30,7 @@ trigger:
steps:
- name: build all binaries
image: golang:1.17
image: golang:1.26
environment:
VERSION: ${DRONE_TAG:-${DRONE_COMMIT}}
commands:
@@ -60,51 +60,15 @@ steps:
when:
event: tag
- name: push image - arm
image: plugins/docker
- name: Build and publish docker images
image: thegeeklab/drone-docker-buildx
settings:
repo: iamthefij/minitor-go
auto_tag: true
auto_tag_suffix: linux-arm
username:
from_secret: docker_username
password:
from_secret: docker_password
build_args:
- ARCH=arm
- REPO=arm32v7
- name: push image - arm64
image: plugins/docker
settings:
repo: iamthefij/minitor-go
auto_tag: true
auto_tag_suffix: linux-arm64
username:
from_secret: docker_username
password:
from_secret: docker_password
build_args:
- ARCH=arm64
- REPO=arm64v8
- name: push image - amd64
image: plugins/docker
settings:
repo: iamthefij/minitor-go
auto_tag: true
auto_tag_suffix: linux-amd64
username:
from_secret: docker_username
password:
from_secret: docker_password
- name: publish manifest
image: plugins/manifest
settings:
spec: manifest.tmpl
auto_tag: true
ignore_missing: true
platforms:
- linux/amd64
- linux/arm64
- linux/arm
username:
from_secret: docker_username
password:
+112
View File
@@ -0,0 +1,112 @@
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@v5
with:
# list of Docker images to use as base name for tags
images: |
${{ github.REPOSITORY }}
# generate Docker tags based on the following events/attributes
tags: |
type=ref,event=branch
type=ref,event=pr
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
type=semver,pattern={{major}}
- name: Login to Docker Hub
uses: docker/login-action@v3
if: "${{ github.event_name != 'pull_request' }}"
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Build and push
uses: docker/build-push-action@v6
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
+1
View File
@@ -14,6 +14,7 @@
# User configuration
config.yml
config.hcl
# Output binary
minitor
+23 -25
View File
@@ -1,36 +1,34 @@
---
version: "2"
linters:
enable:
- errcheck
- errname
- errorlint
- exhaustive
- gofumpt
- goimports
- gomnd
- goprintffuncname
- gosec
- govet
- ineffassign
- misspell
- tagliatelle
- tenv
- mnd
- modernize
- staticcheck
- tagalign
- testpackage
- thelper
- tparallel
- unconvert
- unused
- wrapcheck
- wsl
disable:
- gochecknoglobals
linters-settings:
gosec:
excludes:
- G204
tagliatelle:
case:
rules:
yaml: snake
issues:
exclude-rules:
- path: _test\.go
linters:
- gosec
- wsl_v5
exclusions:
generated: lax
presets:
- common-false-positives
rules:
- linters:
- gosec
path: _test\.go
formatters:
enable:
- gofumpt
- goimports
+4 -4
View File
@@ -1,7 +1,7 @@
---
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.4.0
rev: v6.0.0
hooks:
- id: check-added-large-files
- id: check-yaml
@@ -11,10 +11,10 @@ repos:
- id: end-of-file-fixer
- id: check-merge-conflict
- repo: https://github.com/golangci/golangci-lint
rev: v1.50.1
rev: v2.10.1
hooks:
- id: golangci-lint
- repo: https://github.com/hadolint/hadolint
rev: v2.12.1-beta
rev: refs/pull/1152/head
hooks:
- id: hadolint
- id: hadolint-github
+6 -5
View File
@@ -1,11 +1,11 @@
ARG REPO=library
FROM ${REPO}/alpine:3.12
FROM alpine:3.23
RUN mkdir /app
WORKDIR /app/
# Add common checking tools
RUN apk --no-cache add bash=~5.0 curl=~7.79 jq=~1.6
# hadolint ignore=DL3018
RUN apk --no-cache add bash=~5 curl=~8 jq=~1 bind-tools=~9 tzdata
# Add minitor user for running as non-root
RUN addgroup -S minitor && adduser -S minitor -G minitor
@@ -15,8 +15,9 @@ COPY ./scripts /app/scripts
RUN chmod -R 755 /app/scripts
# Copy minitor in
ARG ARCH=amd64
COPY ./dist/minitor-linux-${ARCH} ./minitor
ARG TARGETOS
ARG TARGETARCH
COPY ./dist/minitor-${TARGETOS}-${TARGETARCH} ./minitor
# Drop to non-root user
USER minitor
+7 -7
View File
@@ -1,7 +1,5 @@
ARG REPO=library
FROM golang:1.17 AS builder
FROM golang:1.26 AS builder
RUN mkdir /app
WORKDIR /app
COPY ./go.mod ./go.sum /app/
@@ -9,12 +7,13 @@ RUN go mod download
COPY ./*.go /app/
ARG ARCH=amd64
ARG TARGETOS
ARG TARGETARCH
ARG VERSION=dev
ENV CGO_ENABLED=0 GOOS=linux GOARCH=${ARCH}
ENV CGO_ENABLED=0 GOOS=$TARGETOS GOARCH=${TARGETARCH}
RUN go build -ldflags "-X main.version=${VERSION}" -a -installsuffix nocgo -o minitor .
FROM ${REPO}/alpine:3.12
FROM alpine:3.23
RUN mkdir /app
WORKDIR /app/
@@ -22,7 +21,8 @@ WORKDIR /app/
COPY --from=builder /app/minitor .
# Add common checking tools
RUN apk --no-cache add bash=~5.0 curl=~7.79 jq=~1.6
# hadolint ignore=DL3018
RUN apk --no-cache add bash=~5 curl=~8 jq=~1 bind-tools=~9 tzdata
# Add minitor user for running as non-root
RUN addgroup -S minitor && adduser -S minitor -G minitor
+6 -6
View File
@@ -1,6 +1,6 @@
DOCKER_TAG ?= minitor-go-${USER}
VERSION ?= $(shell git describe --tags --dirty)
GOFILES = *.go
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))
@@ -63,14 +63,14 @@ docker-build:
.PHONY: docker-run
docker-run: docker-build
docker run --rm -v $(shell pwd)/config.yml:/root/config.yml $(DOCKER_TAG)
docker run --rm -v $(shell pwd)/sample-config.hcl:/root/config.hcl $(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 $@
go build -ldflags '-X "main.version=${VERSION}"' -a -installsuffix nocgo \
-o $@
.PHONY: $(TARGET_ALIAS)
$(TARGET_ALIAS):
@@ -79,11 +79,11 @@ $(TARGET_ALIAS):
# Arch specific docker build targets
.PHONY: docker-build-arm
docker-build-arm: dist/minitor-linux-arm
docker build --build-arg REPO=arm32v7 --build-arg ARCH=arm . -t ${DOCKER_TAG}-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 --build-arg REPO=arm64v8 --build-arg ARCH=arm64 . -t ${DOCKER_TAG}-linux-arm64
docker build --platform linux/arm64 . -t ${DOCKER_TAG}-linux-arm64
# Cross run on host architechture
.PHONY: docker-run-arm
+115 -65
View File
@@ -4,7 +4,7 @@ A minimal monitoring system
## What does it do?
Minitor accepts a YAML configuration file with a set of commands to run and a set of alerts to execute when those commands fail. It is designed to be as simple as possible and relies on other command line tools to do checks and issue alerts.
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.
## But why?
@@ -17,7 +17,7 @@ I'm running a few small services and found Sensu, Consul, Nagios, etc. to all be
Install and execute with:
```bash
go get github.com/iamthefij/minitor-go
go install github.com/iamthefij/minitor-go/v2@latest
minitor
```
@@ -27,7 +27,7 @@ If locally developing you can use:
make run
```
It will read the contents of `config.yml` and begin its loop. You could also run it directly and provide a new config file via the `-config` argument.
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
@@ -38,54 +38,83 @@ You can pull this repository directly from Docker:
docker pull iamthefij/minitor-go:latest
```
The Docker image uses a default `config.yml` that is copied from `sample-config.yml`. This won't really do anything for you, so when you run the Docker image, you should supply your own `config.yml` file:
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/config.yml:/app/config.yml iamthefij/minitor-go:latest
docker run -v $PWD/sample-config.hcl:/app/config.hcl iamthefij/minitor-go:latest
```
Images are provided for `amd64`, `arm`, and `arm64` architechtures.
You can configure the timezone for the container by passing a `TZ` env variable. Eg. `TZ=America/Los_Angeles`.
## Configuring
In this repo, you can explore the `sample-config.yml` file for an example, but the general structure is as follows. It should be noted that environment variable interpolation happens on load of the YAML file.
In this repo, you can explore the `sample-config.hcl` file for an example, but the general structure is as follows. If you are passing environment variables to your commands or alerts, you should be aware that `${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 or 0.|
|`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.|
|`monitors`|List of all monitors. Detailed description below|
|`alerts`|List of all alerts. Detailed description below|
|`monitor`|block listing monitors. Detailed description below|
|`alert`|List of all alerts. Detailed description below|
### Monitors
All monitors should be listed under `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`|Specifies the command that should be executed, either in exec or shell form. This command's exit value will determine whether the check is successful|
|`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|
|`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
Alerts exist as objects keyed under `alerts`. Their key should be the name of the Alert. This is used in your monitor setup in `alert_down` and `alert_up`.
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`.
Eachy alert allows the following configuration:
```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, either in exec or shell 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|
|`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:
@@ -94,10 +123,38 @@ Also, when alerts are executed, they will be passed through Go's format function
|`{{.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 ISO datetime of the last successful check|
|`{{.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.
@@ -112,6 +169,48 @@ minitor -metrics
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:
```yaml
check_interval: 60
monitors:
- name: example
command: "false"
alert_down: ["log"]
alerts:
log:
command: ["echo", "Minitor up={{.IsUp}} for {{.MonitorName}}"]
```
Would now look like this in v2:
```hcl
check_interval = "1m"
monitor "example" {
# example showing string to shell command migration
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
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.
@@ -119,52 +218,3 @@ Whether you're looking to submit a patch or tell me I broke something, you can c
Primary Repo: https://git.iamthefij.com/iamthefij/minitor.git
Github Mirror: https://github.com/IamTheFij/minitor.git
## Original Minitor
This is a reimplementation of [Minitor](https://git.iamthefij.com/iamthefij/minitor) in Go
Minitor is already a minimal monitoring tool. Python 3 was a quick way to get something live, but Python itself comes with a large footprint. Thus Go feels like a better fit for the project, longer term.
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.
### Differences from Python version
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, `AlertNotice` defined in `alert.go` and the built in Go templating format. Eg.
minitor-py:
```yaml
alerts:
log:
command: 'echo {monitor_name}'
```
minitor-go:
```yaml
alerts:
log:
command: 'echo {{.MonitorName}}'
```
Interval durations have changed from being an integer number of seconds to a duration string supported by Go, for example:
minitor-py:
```yaml
check_interval: 90
```
minitor-go:
```yaml
check_interval: 1m30s
```
For the time being, legacy configs for the Python version of Minitor should be compatible if you apply the `-py-compat` flag when running Minitor. Eventually, this flag will go away when later breaking changes are introduced.
## Future
Future, potentially breaking changes
- [ ] Consider value of templating vs injecting values into Env variables
- [ ] Async checking
- [ ] Revisit metrics and see if they all make sense
- [ ] Consider dropping `alert_up` and `alert_down` in favor of using Go templates that offer more control of messaging (Breaking)
+70 -48
View File
@@ -5,11 +5,10 @@ import (
"errors"
"fmt"
"os/exec"
"strings"
"text/template"
"time"
"git.iamthefij.com/iamthefij/slog"
"git.iamthefij.com/iamthefij/slog/v2"
)
var (
@@ -21,63 +20,99 @@ var (
// Alert is a config driven mechanism for sending a notice
type Alert struct {
Name string
Command CommandOrShell
Name string `hcl:"name,label"`
Command []string `hcl:"command,optional"`
ShellCommand string `hcl:"shell_command,optional"`
commandTemplate []*template.Template
commandShellTemplate *template.Template
}
// AlertNotice captures the context for an alert to be sent
type AlertNotice struct {
AlertCount int16
FailureCount int16
AlertCount int
FailureCount int
IsUp bool
LastSuccess time.Time
MonitorName string
LastCheckOutput string
}
// IsValid returns a boolean indicating if the Alert has been correctly
// configured
func (alert Alert) IsValid() bool {
return !alert.Command.Empty()
// Validate checks that the Alert is properly configured and returns errors if not
func (alert Alert) Validate() error {
hasCommand := len(alert.Command) > 0
hasShellCommand := alert.ShellCommand != ""
var err error
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
func (alert *Alert) BuildTemplates() error {
// TODO: Remove legacy template support later after 1.0
legacy := strings.NewReplacer(
"{alert_count}", "{{.AlertCount}}",
"{alert_message}", "{{.MonitorName}} check has failed {{.FailureCount}} times",
"{failure_count}", "{{.FailureCount}}",
"{last_output}", "{{.LastCheckOutput}}",
"{last_success}", "{{.LastSuccess}}",
"{monitor_name}", "{{.MonitorName}}",
)
slog.Debugf("Building template for alert %s", alert.Name)
switch {
case alert.commandTemplate == nil && alert.Command.Command != nil:
alert.commandTemplate = []*template.Template{}
for i, cmdPart := range alert.Command.Command {
if PyCompat {
cmdPart = legacy.Replace(cmdPart)
// Time format func factory
tff := func(formatString string) func(time.Time) string {
return func(t time.Time) string {
return t.Format(formatString)
}
}
// 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{}
for i, cmdPart := range alert.Command {
alert.commandTemplate = append(alert.commandTemplate, template.Must(
template.New(alert.Name+fmt.Sprint(i)).Parse(cmdPart),
template.New(alert.Name+fmt.Sprint(i)).Funcs(timeFormatFuncs).Parse(cmdPart),
))
}
case alert.commandShellTemplate == nil && alert.Command.ShellCommand != "":
shellCmd := alert.Command.ShellCommand
if PyCompat {
shellCmd = legacy.Replace(shellCmd)
}
case alert.ShellCommand != "":
shellCmd := alert.ShellCommand
alert.commandShellTemplate = template.Must(
template.New(alert.Name).Parse(shellCmd),
template.New(alert.Name).Funcs(timeFormatFuncs).Parse(shellCmd),
)
default:
return fmt.Errorf("No template provided for alert %s: %w", alert.Name, errNoTemplate)
@@ -137,7 +172,7 @@ func (alert Alert) Send(notice AlertNotice) (outputStr string, err error) {
if err != nil {
err = fmt.Errorf(
"Alert '%s' failed to send. Returned %v: %w",
"Alert %s failed to send. Returned %w: %w",
alert.Name,
err,
ErrAlertFailed,
@@ -146,16 +181,3 @@ func (alert Alert) Send(notice AlertNotice) (outputStr string, err error) {
return outputStr, err
}
// NewLogAlert creates an alert that does basic logging using echo
func NewLogAlert() *Alert {
return &Alert{
Name: "log",
Command: CommandOrShell{
Command: []string{
"echo",
"{{.MonitorName}} {{if .IsUp}}has recovered{{else}}check has failed {{.FailureCount}} times{{end}}",
},
},
}
}
+64 -93
View File
@@ -1,166 +1,137 @@
package main
package main_test
import (
"log"
"errors"
"testing"
m "git.iamthefij.com/iamthefij/minitor-go/v2"
)
func TestAlertIsValid(t *testing.T) {
func TestAlertValidate(t *testing.T) {
t.Parallel()
cases := []struct {
alert Alert
expected bool
alert m.Alert
expected error
name string
}{
{Alert{Command: CommandOrShell{Command: []string{"echo", "test"}}}, true, "Command only"},
{Alert{Command: CommandOrShell{ShellCommand: "echo test"}}, true, "CommandShell only"},
{Alert{}, false, "No commands"},
{m.Alert{Command: []string{"echo", "test"}}, nil, "Command only"},
{m.Alert{ShellCommand: "echo test"}, nil, "CommandShell only"},
{m.Alert{Command: []string{"echo", "test"}, ShellCommand: "echo test"}, m.ErrInvalidAlert, "Both commands"},
{m.Alert{}, m.ErrInvalidAlert, "No commands"},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
actual := c.alert.IsValid()
if actual != c.expected {
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expected, actual)
log.Printf("Case failed: %s", c.name)
}
t.Run(c.name, func(t *testing.T) {
t.Parallel()
log.Println("-----")
actual := c.alert.Validate()
hasErr := (actual != nil)
expectErr := (c.expected != nil)
if hasErr != expectErr || !errors.Is(actual, c.expected) {
t.Errorf("expected=%t actual=%t", c.expected, actual)
}
})
}
}
func TestAlertSend(t *testing.T) {
cases := []struct {
alert Alert
notice AlertNotice
alert m.Alert
notice m.AlertNotice
expectedOutput string
expectErr bool
name string
pyCompat bool
}{
{
Alert{Command: CommandOrShell{Command: []string{"echo", "{{.MonitorName}}"}}},
AlertNotice{MonitorName: "test"},
m.Alert{Command: []string{"echo", "{{.MonitorName}}"}},
m.AlertNotice{MonitorName: "test"},
"test\n",
false,
"Command with template",
false,
},
{
Alert{Command: CommandOrShell{ShellCommand: "echo {{.MonitorName}}"}},
AlertNotice{MonitorName: "test"},
m.Alert{ShellCommand: "echo {{.MonitorName}}"},
m.AlertNotice{MonitorName: "test"},
"test\n",
false,
"Command shell with template",
false,
},
{
Alert{Command: CommandOrShell{Command: []string{"echo", "{{.Bad}}"}}},
AlertNotice{MonitorName: "test"},
m.Alert{Command: []string{"echo", "{{.Bad}}"}},
m.AlertNotice{MonitorName: "test"},
"",
true,
"Command with bad template",
false,
},
{
Alert{Command: CommandOrShell{ShellCommand: "echo {{.Bad}}"}},
AlertNotice{MonitorName: "test"},
m.Alert{ShellCommand: "echo {{.Bad}}"},
m.AlertNotice{MonitorName: "test"},
"",
true,
"Command shell with bad template",
false,
},
{
Alert{Command: CommandOrShell{ShellCommand: "echo {alert_message}"}},
AlertNotice{MonitorName: "test", FailureCount: 1},
"test check has failed 1 times\n",
false,
"Command shell with legacy template",
true,
},
// Test default log alert down
{
*NewLogAlert(),
AlertNotice{MonitorName: "Test", FailureCount: 1, IsUp: false},
"Test check has failed 1 times\n",
false,
"Default log alert down",
false,
},
// Test default log alert up
{
*NewLogAlert(),
AlertNotice{MonitorName: "Test", IsUp: true},
"Test has recovered\n",
false,
"Default log alert up",
false,
},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
// Set PyCompat to value of compat flag
PyCompat = c.pyCompat
err := c.alert.BuildTemplates()
if err != nil {
t.Errorf("Send(%v output), error building templates: %v", c.name, err)
}
t.Run(c.name, func(t *testing.T) {
t.Parallel()
output, err := c.alert.Send(c.notice)
hasErr := (err != nil)
err := c.alert.BuildTemplates()
if err != nil {
t.Errorf("Send(%v output), error building templates: %v", c.name, err)
}
if output != c.expectedOutput {
t.Errorf("Send(%v output), expected=%v actual=%v", c.name, c.expectedOutput, output)
log.Printf("Case failed: %s", c.name)
}
output, err := c.alert.Send(c.notice)
hasErr := (err != nil)
if hasErr != c.expectErr {
t.Errorf("Send(%v err), expected=%v actual=%v", c.name, "Err", err)
log.Printf("Case failed: %s", c.name)
}
if output != c.expectedOutput {
t.Errorf("Send(%v output), expected=%v actual=%v", c.name, c.expectedOutput, output)
}
// Set PyCompat back to default value
PyCompat = false
log.Println("-----")
if hasErr != c.expectErr {
t.Errorf("Send(%v err), expected=%v actual=%v", c.name, "Err", err)
}
})
}
}
func TestAlertSendNoTemplates(t *testing.T) {
alert := Alert{}
notice := AlertNotice{}
alert := m.Alert{}
notice := m.AlertNotice{}
output, err := alert.Send(notice)
if err == nil {
t.Errorf("Send(no template), expected=%v actual=%v", "Err", output)
}
log.Println("-----")
}
func TestAlertBuildTemplate(t *testing.T) {
cases := []struct {
alert Alert
alert m.Alert
expectErr bool
name string
}{
{Alert{Command: CommandOrShell{Command: []string{"echo", "test"}}}, false, "Command only"},
{Alert{Command: CommandOrShell{ShellCommand: "echo test"}}, false, "CommandShell only"},
{Alert{}, true, "No commands"},
{m.Alert{Command: []string{"echo", "test"}}, false, "Command only"},
{m.Alert{ShellCommand: "echo test"}, false, "CommandShell only"},
{m.Alert{}, true, "No commands"},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
err := c.alert.BuildTemplates()
hasErr := (err != nil)
if hasErr != c.expectErr {
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expectErr, err)
log.Printf("Case failed: %s", c.name)
}
t.Run(c.name, func(t *testing.T) {
t.Parallel()
log.Println("-----")
err := c.alert.BuildTemplates()
hasErr := (err != nil)
if hasErr != c.expectErr {
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expectErr, err)
}
})
}
}
+96 -152
View File
@@ -2,164 +2,126 @@ package main
import (
"errors"
"io/ioutil"
"fmt"
"time"
"git.iamthefij.com/iamthefij/slog"
"gopkg.in/yaml.v2"
"git.iamthefij.com/iamthefij/slog/v2"
"github.com/hashicorp/hcl/v2/hclsimple"
)
var errInvalidConfig = errors.New("Invalid configuration")
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
type Config struct {
CheckInterval SecondsOrDuration `yaml:"check_interval"`
DefaultAlertAfter int16 `yaml:"default_alert_after"`
DefaultAlertEvery *int16 `yaml:"default_alert_every"`
DefaultAlertDown []string `yaml:"default_alert_down"`
DefaultAlertUp []string `yaml:"default_alert_up"`
Monitors []*Monitor
Alerts map[string]*Alert
CheckIntervalStr string `hcl:"check_interval"`
CheckInterval time.Duration
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
}
// CommandOrShell type wraps a string or list of strings
// for executing a command directly or in a shell
type CommandOrShell struct {
ShellCommand string
Command []string
}
// Empty checks if the Command has a value
func (cos CommandOrShell) Empty() bool {
return (cos.ShellCommand == "" && cos.Command == nil)
}
// UnmarshalYAML allows unmarshalling either a string or slice of strings
// and parsing them as either a command or a shell command.
func (cos *CommandOrShell) UnmarshalYAML(unmarshal func(interface{}) error) error {
var cmd []string
err := unmarshal(&cmd)
// Error indicates this is shell command
// 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 {
var shellCmd string
err := unmarshal(&shellCmd)
if err != nil {
return err
}
cos.ShellCommand = shellCmd
} else {
cos.Command = cmd
return fmt.Errorf("failed to parse top level check_interval duration: %w", err)
}
return nil
}
// SecondsOrDuration wraps a duration value for parsing a duration or seconds from YAML
// NOTE: This should be removed in favor of only parsing durations once compatibility is broken
type SecondsOrDuration struct {
value time.Duration
}
// Value returns a duration value
func (sod SecondsOrDuration) Value() time.Duration {
return sod.value
}
// UnmarshalYAML allows unmarshalling a duration value or seconds if an int was provided
func (sod *SecondsOrDuration) UnmarshalYAML(unmarshal func(interface{}) error) error {
var seconds int64
err := unmarshal(&seconds)
if err == nil {
sod.value = time.Second * time.Duration(seconds)
return nil
if config.DefaultAlertAfter == 0 {
minAlertAfter := 1
config.DefaultAlertAfter = minAlertAfter
}
// Error indicates that we don't have an int
err = unmarshal(&sod.value)
return err
}
// IsValid checks config validity and returns true if valid
func (config Config) IsValid() (isValid bool) {
isValid = true
// Validate alerts
if config.Alerts == nil || len(config.Alerts) == 0 {
// This should never happen because there is a default alert named 'log' for now
slog.Errorf("Invalid alert configuration: Must provide at least one alert")
isValid = false
}
for _, alert := range config.Alerts {
if !alert.IsValid() {
slog.Errorf("Invalid alert configuration: %+v", alert.Name)
isValid = false
} else {
slog.Debugf("Loaded alert %s", alert.Name)
}
}
// Validate monitors
if config.Monitors == nil || len(config.Monitors) == 0 {
slog.Errorf("Invalid monitor configuration: Must provide at least one monitor")
isValid = false
if config.DefaultAlertEvery == nil {
defaultDefaultAlertEvery := -1
config.DefaultAlertEvery = &defaultDefaultAlertEvery
}
for _, monitor := range config.Monitors {
if !monitor.IsValid() {
slog.Errorf("Invalid monitor configuration: %s", monitor.Name)
isValid = false
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
func (config Config) IsValid() error {
var err error
// 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
if len(config.Monitors) == 0 {
err = errors.Join(err, ErrNoMonitors)
}
for _, monitor := range config.Monitors {
err = errors.Join(err, monitor.Validate())
// Check that all Monitor alerts actually exist
for _, isUp := range []bool{true, false} {
for _, alertName := range monitor.GetAlertNames(isUp) {
if _, ok := config.Alerts[alertName]; !ok {
slog.Errorf(
"Invalid monitor configuration: %s. Unknown alert %s",
monitor.Name, alertName,
if _, ok := config.GetAlert(alertName); !ok {
err = errors.Join(
err,
fmt.Errorf("%w: %s. %w: %s", ErrInvalidMonitor, monitor.Name, ErrUnknownAlert, alertName),
)
isValid = false
}
}
}
}
return isValid
return err
}
// Init performs extra initialization on top of loading the config from file
func (config *Config) Init() (err error) {
for _, monitor := range config.Monitors {
if monitor.AlertAfter == 0 && config.DefaultAlertAfter > 0 {
monitor.AlertAfter = config.DefaultAlertAfter
}
if monitor.AlertEvery == nil && config.DefaultAlertEvery != nil {
monitor.AlertEvery = config.DefaultAlertEvery
}
if len(monitor.AlertDown) == 0 && len(config.DefaultAlertDown) > 0 {
monitor.AlertDown = config.DefaultAlertDown
}
if len(monitor.AlertUp) == 0 && len(config.DefaultAlertUp) > 0 {
monitor.AlertUp = config.DefaultAlertUp
// GetAlert returns an alert by name
func (c Config) GetAlert(name string) (*Alert, bool) {
if c.alertLookup == nil {
c.alertLookup = map[string]*Alert{}
for _, alert := range c.Alerts {
c.alertLookup[alert.Name] = alert
}
}
for name, alert := range config.Alerts {
alert.Name = name
v, ok := c.alertLookup[name]
return v, ok
}
// BuildAllTemplates builds all alert templates
func (c *Config) BuildAllTemplates() (err error) {
for _, alert := range c.Alerts {
if err = alert.BuildTemplates(); err != nil {
return
}
@@ -169,41 +131,23 @@ func (config *Config) Init() (err error) {
}
// LoadConfig will read config from the given path and parse it
func LoadConfig(filePath string) (config Config, err error) {
data, err := ioutil.ReadFile(filePath)
if err != nil {
return
}
func LoadConfig(filePath string) (Config, error) {
var config Config
err = yaml.Unmarshal(data, &config)
if err != nil {
return
if err := hclsimple.DecodeFile(filePath, nil, &config); err != nil {
return config, errors.Join(ErrLoadingConfig, err)
}
slog.Debugf("Config values:\n%v\n", config)
// Add log alert if not present
if PyCompat {
// Initialize alerts list if not present
if config.Alerts == nil {
config.Alerts = map[string]*Alert{}
}
if _, ok := config.Alerts["log"]; !ok {
config.Alerts["log"] = NewLogAlert()
}
}
// Finish initializing configuration
if err = config.Init(); err != nil {
return
if err := config.Init(); err != nil {
return config, errors.Join(ErrConfigInit, err)
}
if !config.IsValid() {
err = errInvalidConfig
return
if err := config.IsValid(); err != nil {
return config, errors.Join(ErrInvalidConfig, err)
}
return config, err
return config, nil
}
+151 -104
View File
@@ -1,144 +1,191 @@
package main
package main_test
import (
"log"
"errors"
"testing"
"time"
m "git.iamthefij.com/iamthefij/minitor-go/v2"
)
func TestLoadConfig(t *testing.T) {
cases := []struct {
configPath string
expectErr bool
name string
pyCompat bool
configPath string
expectedErr error
name string
}{
{"./test/valid-config.yml", false, "Valid config file", false},
{"./test/valid-config-default-values.yml", false, "Valid config file with default values", false},
{"./test/valid-default-log-alert.yml", false, "Valid config file with default log alert PyCompat", true},
{"./test/valid-default-log-alert.yml", true, "Invalid config file no log alert", false},
{"./test/does-not-exist", true, "Invalid config path", false},
{"./test/invalid-config-type.yml", true, "Invalid config type for key", false},
{"./test/invalid-config-missing-alerts.yml", true, "Invalid config missing alerts", false},
{"./test/invalid-config-unknown-alert.yml", true, "Invalid config unknown alert", false},
{"./test/does-not-exist", m.ErrLoadingConfig, "Invalid config path"},
{"./test/invalid-config-wrong-hcl-type.hcl", m.ErrLoadingConfig, "Incorrect HCL type"},
{"./test/invalid-config-missing-alerts.hcl", m.ErrNoAlerts, "Invalid config missing alerts"},
{"./test/invalid-config-missing-alerts.hcl", m.ErrInvalidConfig, "Invalid config general"},
{"./test/invalid-config-invalid-duration.hcl", m.ErrConfigInit, "Invalid config type for key"},
{"./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 {
log.Printf("Testing case %s", c.name)
// Set PyCompat based on compatibility mode
PyCompat = c.pyCompat
_, err := LoadConfig(c.configPath)
hasErr := (err != nil)
if hasErr != c.expectErr {
t.Errorf("LoadConfig(%v), expected_error=%v actual=%v", c.name, c.expectErr, err)
log.Printf("Case failed: %s", c.name)
}
t.Run(c.name, func(t *testing.T) {
t.Parallel()
// Set PyCompat to default value
PyCompat = false
_, 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 TestIntervalParsing(t *testing.T) {
log.Printf("Testing case TestIntervalParsing")
config, err := LoadConfig("./test/valid-config.yml")
if err != nil {
t.Errorf("Failed loading config: %v", err)
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",
},
}
oneSecond := time.Second
tenSeconds := 10 * time.Second
oneMinute := time.Minute
for _, c := range cases {
// validate top level interval seconds represented as an int
if config.CheckInterval.Value() != oneSecond {
t.Errorf("Incorrectly parsed int seconds. expected=%v actual=%v", oneSecond, config.CheckInterval)
t.Run(c.name, func(t *testing.T) {
t.Parallel()
config, err := m.LoadConfig(c.configPath)
if err != nil {
t.Errorf("Got error when loading config file %q: %s", c.configPath, err)
}
// 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
})
}
if config.Monitors[0].CheckInterval.Value() != tenSeconds {
t.Errorf("Incorrectly parsed seconds duration. expected=%v actual=%v", oneSecond, config.CheckInterval)
}
if config.Monitors[1].CheckInterval.Value() != oneMinute {
t.Errorf("Incorrectly parsed seconds duration. expected=%v actual=%v", oneSecond, config.CheckInterval)
}
log.Println("-----")
}
// TestMultiLineConfig is a more complicated test stepping through the parsing
// and execution of mutli-line strings presented in YAML
func TestMultiLineConfig(t *testing.T) {
log.Println("Testing multi-line string config")
t.Parallel()
config, err := LoadConfig("./test/valid-verify-multi-line.yml")
config, err := m.LoadConfig("./test/valid-verify-multi-line.hcl")
if err != nil {
t.Fatalf("TestMultiLineConfig(load), expected=no_error actual=%v", err)
}
log.Println("-----")
log.Println("TestMultiLineConfig(parse > string)")
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
expected := "echo 'Some string with stuff'; echo \"<angle brackets>\"; exit 1\n"
actual := config.Monitors[0].Command.ShellCommand
if expected != actual {
t.Error("Heredoc mismatch")
t.Errorf("string expected=`%v`", expected)
t.Errorf("string actual =`%v`", actual)
}
if expected != actual {
t.Errorf("TestMultiLineConfig(>) failed")
t.Logf("string expected=`%v`", expected)
t.Logf("string actual =`%v`", actual)
t.Logf("bytes expected=%v", []byte(expected))
t.Logf("bytes actual =%v", []byte(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")
}
log.Println("-----")
log.Println("TestMultiLineConfig(execute > string)")
// Verify the output of the monitor is as expected
expected = "Some string with stuff\n<angle brackets>\n"
actual = notice.LastCheckOutput
_, notice := config.Monitors[0].Check()
if notice == nil {
t.Fatalf("Did not receive an alert notice")
}
if expected != actual {
t.Error("Output mismatch")
t.Errorf("string expected=`%v`", expected)
t.Errorf("string actual =`%v`", actual)
}
})
expected = "Some string with stuff\n<angle brackets>\n"
actual = notice.LastCheckOutput
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'")
}
if expected != actual {
t.Errorf("TestMultiLineConfig(execute > string) check failed")
t.Logf("string expected=`%v`", expected)
t.Logf("string actual =`%v`", actual)
t.Logf("bytes expected=%v", []byte(expected))
t.Logf("bytes actual =%v", []byte(actual))
}
expected := " echo 'Some string with stuff'\n echo '<angle brackets>'\n"
actual := alert.ShellCommand
log.Println("-----")
log.Println("TestMultiLineConfig(parse | string)")
if expected != actual {
t.Error("Heredoc mismatch")
t.Errorf("string expected=`%v`", expected)
t.Errorf("string actual =`%v`", actual)
}
expected = "echo 'Some string with stuff'\necho '<angle brackets>'\n"
actual = config.Alerts["log_shell"].Command.ShellCommand
actual, err = alert.Send(m.AlertNotice{})
if err != nil {
t.Fatal("Execution of alert failed")
}
if expected != actual {
t.Errorf("TestMultiLineConfig(|) failed")
t.Logf("string expected=`%v`", expected)
t.Logf("string actual =`%v`", actual)
t.Logf("bytes expected=%v", []byte(expected))
t.Logf("bytes actual =%v", []byte(actual))
}
log.Println("-----")
log.Println("TestMultiLineConfig(execute | string)")
actual, err = config.Alerts["log_shell"].Send(AlertNotice{})
if err != nil {
t.Errorf("Execution of alert failed")
}
expected = "Some string with stuff\n<angle brackets>\n"
if expected != actual {
t.Errorf("TestMultiLineConfig(execute | string) check failed")
t.Logf("string expected=`%v`", expected)
t.Logf("string actual =`%v`", actual)
t.Logf("bytes expected=%v", []byte(expected))
t.Logf("bytes actual =%v", []byte(actual))
}
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)
}
})
}
+23 -5
View File
@@ -1,9 +1,27 @@
module git.iamthefij.com/iamthefij/minitor-go
module git.iamthefij.com/iamthefij/minitor-go/v2
go 1.15
go 1.26.0
require (
git.iamthefij.com/iamthefij/slog v1.3.0
github.com/prometheus/client_golang v1.2.1
gopkg.in/yaml.v2 v2.2.4
git.iamthefij.com/iamthefij/slog/v2 v2.0.1
github.com/hashicorp/hcl/v2 v2.11.1
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/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 v0.0.0-20150314170334-ad45545899c7 // 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 v1.8.0 // indirect
go.yaml.in/yaml/v2 v2.4.2 // indirect
golang.org/x/sys v0.35.0 // indirect
golang.org/x/text v0.28.0 // indirect
google.golang.org/protobuf v1.36.8 // indirect
)
+86 -70
View File
@@ -1,80 +1,96 @@
git.iamthefij.com/iamthefij/slog v1.3.0 h1:4Hu5PQvDrW5e3FrTS3q2iIXW0iPvhNY/9qJsqDR3K3I=
git.iamthefij.com/iamthefij/slog v1.3.0/go.mod h1:1RUj4hcCompZkAxXCRfUX786tb3cM/Zpkn97dGfUfbg=
github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
git.iamthefij.com/iamthefij/slog/v2 v2.0.1 h1:eXf3ga0aMTkm0l6EMYOQpg34S+dQw7cN8o+W1Cg/0C0=
git.iamthefij.com/iamthefij/slog/v2 v2.0.1/go.mod h1:VFjX1e1tfHADyQr2wJBAz0JUQT+K/5FBjzSHgUKOuu8=
github.com/agext/levenshtein v1.2.1 h1:QmvMAjj2aEICytGiWzmxoE0x2KZvE0fvmqMOfy2tjT8=
github.com/agext/levenshtein v1.2.1/go.mod h1:JEDfjyjHDjOF/1e4FlBE/PkbqA9OfWu2ki2W0IB5558=
github.com/apparentlymart/go-dump v0.0.0-20180507223929-23540a00eaa3/go.mod h1:oL81AME2rN47vu18xqj1S1jPIPuN7afo62yKTNn3XMM=
github.com/apparentlymart/go-textseg v1.0.0/go.mod h1:z96Txxhf3xSFMPmb5X/1W05FF/Nj9VFpLOpjS5yuumk=
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/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/cespare/xxhash/v2 v2.1.0 h1:yTUvW7Vhb89inJ+8irsUqiWjh8iT6sQPZiQzI6ReGkA=
github.com/cespare/xxhash/v2 v2.1.0/go.mod h1:dgIUBU3pDso/gPgZ1osOZ0iQf77oPR28Tjxl5dIMyVM=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
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/go-test/deep v1.0.3 h1:ZrJSEWsXzPOxaZnFteGEfooLba+ju3FYIbOrS+rQd68=
github.com/go-test/deep v1.0.3/go.mod h1:wGDj63lr65AM2AQyKZd/NYHGb0R+1RLqB8NKt3aSFNA=
github.com/golang/protobuf v1.1.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/golang/protobuf v1.3.2 h1:6nsPYzhq5kReh6QImI3k5qWzO4PEbvbIW2cwSfR/6xs=
github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
github.com/json-iterator/go v1.1.7/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
github.com/matttproud/golang_protobuf_extensions v1.0.1 h1:4hp9jkHxhMHkqkrB3Ix0jegS5sx/RkqARlsWZ6pIwiU=
github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/golang/protobuf v1.3.4/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
github.com/hashicorp/hcl/v2 v2.11.1 h1:yTyWcXcm9XB0TEkyU/JCRU6rYy4K+mgLtzn2wlrJbcc=
github.com/hashicorp/hcl/v2 v2.11.1/go.mod h1:FwWsfWEjyV/CMj8s/gqAuiviY72rJ1/oayI9WftqcKg=
github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kylelemons/godebug v0.0.0-20170820004349-d65d576e9348/go.mod h1:B69LEHPfb2qLo0BaaOLcbitczOKLWTsrBG9LczfCD4k=
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
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/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/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=
github.com/prometheus/client_golang v1.2.1 h1:JnMpQc6ppsNgw9QPAGF6Dod479itz7lvlsMzzNayLOI=
github.com/prometheus/client_golang v1.2.1/go.mod h1:XMU6Z2MjaRKVu/dC1qupJI9SiNkDYzz3xecMgSW/F+U=
github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4 h1:gQz4mCbXsO+nc9n1hCxHcGA3Zx3Eo+UHZoInFGUIXNM=
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y86RQel1bk4=
github.com/prometheus/common v0.7.0 h1:L+1lyG48J1zAQXA3RBX/nG/B3gjlHq0zTt2tlbJLyCY=
github.com/prometheus/common v0.7.0/go.mod h1:DjGbpBbp5NYNiECxcL/VnbXCCaQpKd3tt26CguLLsqA=
github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
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/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o=
github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg=
github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
github.com/prometheus/common v0.66.1 h1:h5E0h5/Y8niHc5DlaLlWLArTQI7tMrsfQjHV+d9ZoGs=
github.com/prometheus/common v0.66.1/go.mod h1:gcaUsgf3KfRSwHY4dIMXLPV0K/Wg1oZ8+SbZk/HH/dA=
github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
github.com/sergi/go-diff v1.0.0 h1:Kpca3qRNrduNnOQeazBd0ysaKrUJiIuISHxogkT9RPQ=
github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=
github.com/spf13/pflag v1.0.2/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
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-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/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20190613194153-d28f0bde5980/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/crypto v0.0.0-20190426145343-a29dc8fdc734/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/net v0.0.0-20180811021610-c39426892332/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
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/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20191010194322-b09406accb47/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20190502175342-a43fa875dd82/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=
gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
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=
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/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.4 h1:/eiJrUcujPVeJ3xlSWaiNi3uSVmDGBK1pDHUHAnao1I=
gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+47 -13
View File
@@ -4,9 +4,10 @@ import (
"errors"
"flag"
"fmt"
"strings"
"time"
"git.iamthefij.com/iamthefij/slog"
"git.iamthefij.com/iamthefij/slog/v2"
)
var (
@@ -17,16 +18,13 @@ var (
// Metrics contains all active metrics
Metrics = NewMetrics()
// PyCompat enables support for legacy Python templates
PyCompat = false
// version of minitor being run
version = "dev"
errUnknownAlert = errors.New("unknown alert")
)
func sendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) error {
func SendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) error {
slog.Debugf("Received an alert notice from %s", alertNotice.MonitorName)
alertNames := monitor.GetAlertNames(alertNotice.IsUp)
@@ -41,7 +39,7 @@ func sendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) erro
}
for _, alertName := range alertNames {
if alert, ok := config.Alerts[alertName]; ok {
if alert, ok := config.GetAlert(alertName); ok {
output, err := alert.Send(*alertNotice)
if err != nil {
slog.Errorf(
@@ -67,7 +65,7 @@ func sendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) erro
return nil
}
func checkMonitors(config *Config) error {
func CheckMonitors(config *Config) error {
// TODO: Run this in goroutines and capture exceptions
for _, monitor := range config.Monitors {
if monitor.ShouldCheck() {
@@ -79,7 +77,7 @@ func checkMonitors(config *Config) error {
Metrics.CountCheck(monitor.Name, success, monitor.LastCheckMilliseconds(), hasAlert)
if alertNotice != nil {
err := sendAlerts(config, monitor, alertNotice)
err := SendAlerts(config, monitor, alertNotice)
// If there was an error in sending an alert, exit early and bubble it up
if err != nil {
return err
@@ -91,13 +89,41 @@ func checkMonitors(config *Config) error {
return nil
}
func SendStartupAlerts(config *Config, alertNames []string) error {
for _, alertName := range alertNames {
var err error
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() {
showVersion := flag.Bool("version", false, "Display the version of minitor and exit")
configPath := flag.String("config", "config.yml", "Alternate configuration path (default: config.yml)")
configPath := flag.String("config", "config.hcl", "Alternate configuration path (default: config.hcl)")
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(&PyCompat, "py-compat", false, "Enables support for legacy Python Minitor config. Will eventually be removed. (default: false)")
flag.IntVar(&MetricsPort, "metrics-port", MetricsPort, "The port that Prometheus metrics should be exported on, if enabled. (default: 8080)")
flag.Parse()
@@ -110,7 +136,7 @@ func main() {
// Load configuration
config, err := LoadConfig(*configPath)
slog.OnErrFatalf(err, "Error loading config: %v", err)
slog.OnErrFatalf(err, "Error loading config")
// Serve metrics exporter, if specified
if ExportMetrics {
@@ -119,11 +145,19 @@ func main() {
go ServeMetrics()
}
if *startupAlerts != "" {
alertNames := strings.Split(*startupAlerts, ",")
err = SendStartupAlerts(&config, alertNames)
slog.OnErrPanicf(err, "Error running startup alerts")
}
// Start main loop
for {
err = checkMonitors(&config)
err = CheckMonitors(&config)
slog.OnErrPanicf(err, "Error checking monitors")
time.Sleep(config.CheckInterval.Value())
time.Sleep(config.CheckInterval)
}
}
+142 -92
View File
@@ -1,136 +1,186 @@
package main
package main_test
import "testing"
import (
"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) {
cases := []struct {
config Config
expectErr bool
name string
config m.Config
expectFailureError bool
expectRecoverError bool
name string
}{
{
config: Config{},
expectErr: false,
name: "Empty",
},
{
config: Config{
Monitors: []*Monitor{
config: m.Config{
CheckIntervalStr: "1s",
Monitors: []*m.Monitor{
{
Name: "Success",
Command: CommandOrShell{Command: []string{"true"}},
Name: "Success",
},
},
},
expectErr: false,
name: "Monitor success, no alerts",
expectFailureError: false,
expectRecoverError: false,
name: "No alerts",
},
{
config: Config{
Monitors: []*Monitor{
config: m.Config{
CheckIntervalStr: "1s",
Monitors: []*m.Monitor{
{
Name: "Failure",
Command: CommandOrShell{Command: []string{"false"}},
AlertAfter: 1,
},
},
},
expectErr: false,
name: "Monitor failure, no alerts",
},
{
config: Config{
Monitors: []*Monitor{
{
Name: "Success",
Command: CommandOrShell{Command: []string{"ls"}},
alertCount: 1,
},
},
},
expectErr: false,
name: "Monitor recovery, no alerts",
},
{
config: Config{
Monitors: []*Monitor{
{
Name: "Failure",
Command: CommandOrShell{Command: []string{"false"}},
AlertDown: []string{"unknown"},
AlertAfter: 1,
},
},
},
expectErr: true,
name: "Monitor failure, unknown alerts",
},
{
config: Config{
Monitors: []*Monitor{
{
Name: "Success",
Command: CommandOrShell{Command: []string{"true"}},
AlertUp: []string{"unknown"},
alertCount: 1,
AlertAfter: 1,
},
},
},
expectErr: true,
name: "Monitor recovery, unknown alerts",
expectFailureError: true,
expectRecoverError: true,
name: "Unknown alerts",
},
{
config: Config{
Monitors: []*Monitor{
config: m.Config{
CheckIntervalStr: "1s",
Monitors: []*m.Monitor{
{
Name: "Failure",
Command: CommandOrShell{Command: []string{"false"}},
AlertDown: []string{"good"},
AlertUp: []string{"good"},
AlertAfter: 1,
},
},
Alerts: map[string]*Alert{
"good": {
Command: CommandOrShell{Command: []string{"true"}},
},
},
Alerts: []*m.Alert{{
Name: "good",
Command: []string{"true"},
}},
},
expectErr: false,
name: "Monitor failure, successful alert",
expectFailureError: false,
expectRecoverError: false,
name: "Successful alert",
},
{
config: Config{
Monitors: []*Monitor{
config: m.Config{
CheckIntervalStr: "1s",
Monitors: []*m.Monitor{
{
Name: "Failure",
Command: CommandOrShell{Command: []string{"false"}},
AlertDown: []string{"bad"},
AlertUp: []string{"bad"},
AlertAfter: 1,
},
},
Alerts: map[string]*Alert{
"bad": {
Name: "bad",
Command: CommandOrShell{Command: []string{"false"}},
},
},
Alerts: []*m.Alert{{
Name: "bad",
Command: []string{"false"},
}},
},
expectErr: true,
name: "Monitor failure, bad alert",
expectFailureError: true,
expectRecoverError: true,
name: "Failing alert",
},
}
for _, c := range cases {
err := c.config.Init()
if err != nil {
t.Errorf("checkMonitors(%s): unexpected error reading config: %v", c.name, err)
}
err = checkMonitors(&c.config)
if err == nil && c.expectErr {
t.Errorf("checkMonitors(%s): Expected panic, the code did not panic", c.name)
} else if err != nil && !c.expectErr {
t.Errorf("checkMonitors(%s): Did not expect an error, but we got one anyway: %v", c.name, err)
}
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"},
},
},
},
expectErr: false,
startupAlerts: []string{"good"},
name: "Successful alert",
},
{
config: m.Config{
CheckIntervalStr: "1s",
Alerts: []*m.Alert{
{
Name: "bad",
Command: []string{"false"},
},
},
},
expectErr: true,
startupAlerts: []string{"bad"},
name: "Failed alert",
},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
t.Parallel()
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)
}
})
}
}
-25
View File
@@ -1,25 +0,0 @@
image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}{{else}}latest{{/if}}
{{#if build.tags}}
tags:
{{#each build.tags}}
- {{this}}
{{/each}}
{{/if}}
manifests:
-
image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}-{{/if}}linux-amd64
platform:
architecture: amd64
os: linux
-
image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}-{{/if}}linux-arm64
platform:
architecture: arm64
os: linux
variant: v8
-
image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}-{{/if}}linux-arm
platform:
architecture: arm
os: linux
variant: v7
+128 -56
View File
@@ -1,61 +1,142 @@
package main
import (
"errors"
"fmt"
"math"
"os/exec"
"time"
"git.iamthefij.com/iamthefij/slog"
"git.iamthefij.com/iamthefij/slog/v2"
)
// Monitor represents a particular periodic check of a command
type Monitor struct { //nolint:maligned
// Config values
AlertAfter int16 `yaml:"alert_after"`
AlertEvery *int16 `yaml:"alert_every"`
CheckInterval SecondsOrDuration `yaml:"check_interval"`
Name string
AlertDown []string `yaml:"alert_down"`
AlertUp []string `yaml:"alert_up"`
Command CommandOrShell
CheckIntervalStr *string `hcl:"check_interval,optional"`
CheckInterval time.Duration
Name string `hcl:"name,label"`
AlertCount int
AlertAfter int `hcl:"alert_after,optional"`
AlertEvery *int `hcl:"alert_every,optional"`
AlertDown []string `hcl:"alert_down,optional"`
AlertUp []string `hcl:"alert_up,optional"`
Command []string `hcl:"command,optional"`
ShellCommand string `hcl:"shell_command,optional"`
// Other values
alertCount int16
failureCount int16
failureCount int
lastCheck time.Time
lastSuccess time.Time
lastOutput string
lastCheckDuration time.Duration
}
// IsValid returns a boolean indicating if the Monitor has been correctly
// configured
func (monitor Monitor) IsValid() bool {
return (!monitor.Command.Empty() &&
monitor.getAlertAfter() > 0 &&
monitor.AlertDown != nil)
// Init initializes the Monitor with default values
func (monitor *Monitor) Init(defaultAlertAfter int, defaultAlertEvery *int, defaultAlertDown []string, defaultAlertUp []string) error {
// Parse the check_interval string into a time.Duration
if monitor.CheckIntervalStr != nil {
var err error
monitor.CheckInterval, err = time.ParseDuration(*monitor.CheckIntervalStr)
if err != nil {
return fmt.Errorf("failed to parse check_interval duration for monitor %s: %w", monitor.Name, err)
}
}
// 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
}
// ShouldCheck returns a boolean indicating if the Monitor is ready to be
// be checked again
// Validate checks that the Monitor is properly configured and returns errors if not
func (monitor Monitor) Validate() error {
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 {
if monitor.lastCheck.IsZero() {
if monitor.lastCheck.IsZero() || monitor.CheckInterval == 0 {
return true
}
sinceLastCheck := time.Since(monitor.lastCheck)
return sinceLastCheck >= monitor.CheckInterval.Value()
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) {
var cmd *exec.Cmd
if monitor.Command.Command != nil {
cmd = exec.Command(monitor.Command.Command[0], monitor.Command.Command[1:]...)
if len(monitor.Command) > 0 {
cmd = exec.Command(monitor.Command[0], monitor.Command[1:]...)
} else if monitor.ShellCommand != "" {
cmd = ShellCommand(monitor.ShellCommand)
} else {
cmd = ShellCommand(monitor.Command.ShellCommand)
slog.Fatalf("Monitor %s has no command configured", monitor.Name)
}
checkStartTime := time.Now()
@@ -68,9 +149,9 @@ func (monitor *Monitor) Check() (bool, *AlertNotice) {
isSuccess := (err == nil)
if isSuccess {
alertNotice = monitor.success()
alertNotice = monitor.Success()
} else {
alertNotice = monitor.failure()
alertNotice = monitor.Failure()
}
slog.Debugf("Command output: %s", monitor.lastOutput)
@@ -86,9 +167,18 @@ func (monitor *Monitor) Check() (bool, *AlertNotice) {
return isSuccess, alertNotice
}
// GetAlertNames gives a list of alert names for a given monitor status
func (monitor Monitor) GetAlertNames(up bool) []string {
if up {
return monitor.AlertUp
}
return monitor.AlertDown
}
// IsUp returns the status of the current monitor
func (monitor Monitor) IsUp() bool {
return monitor.alertCount == 0
return monitor.AlertCount == 0
}
// LastCheckMilliseconds gives number of miliseconds the last check ran for
@@ -96,36 +186,36 @@ func (monitor Monitor) LastCheckMilliseconds() int64 {
return monitor.lastCheckDuration.Milliseconds()
}
func (monitor *Monitor) success() (notice *AlertNotice) {
func (monitor *Monitor) Success() (notice *AlertNotice) {
if !monitor.IsUp() {
// Alert that we have recovered
notice = monitor.createAlertNotice(true)
}
monitor.failureCount = 0
monitor.alertCount = 0
monitor.AlertCount = 0
monitor.lastSuccess = time.Now()
return
}
func (monitor *Monitor) failure() (notice *AlertNotice) {
func (monitor *Monitor) Failure() (notice *AlertNotice) {
monitor.failureCount++
// If we haven't hit the minimum failures, we can exit
if monitor.failureCount < monitor.getAlertAfter() {
if monitor.failureCount < monitor.AlertAfter {
slog.Debugf(
"%s failed but did not hit minimum failures. "+
"Count: %v alert after: %v",
monitor.Name,
monitor.failureCount,
monitor.getAlertAfter(),
monitor.AlertAfter,
)
return
}
// Take number of failures after minimum
failureCount := (monitor.failureCount - monitor.getAlertAfter())
failureCount := (monitor.failureCount - monitor.AlertAfter)
// Use alert cadence to determine if we should alert
switch {
@@ -141,43 +231,25 @@ func (monitor *Monitor) failure() (notice *AlertNotice) {
}
default:
// Handle negative numbers indicating an exponential backoff
if failureCount >= int16(math.Pow(2, float64(monitor.alertCount))-1) { //nolint:gomnd
if failureCount >= int(math.Pow(2, float64(monitor.AlertCount))-1) { //nolint:mnd
notice = monitor.createAlertNotice(false)
}
}
// If we're going to alert, increment count
if notice != nil {
monitor.alertCount++
monitor.AlertCount++
notice.AlertCount = monitor.AlertCount
}
return notice
}
func (monitor Monitor) getAlertAfter() int16 {
// TODO: Come up with a better way than this method
// Zero is one!
if monitor.AlertAfter == 0 {
return 1
}
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
}
return monitor.AlertDown
}
func (monitor Monitor) createAlertNotice(isUp bool) *AlertNotice {
// TODO: Maybe add something about recovery status here
return &AlertNotice{
MonitorName: monitor.Name,
AlertCount: monitor.alertCount,
AlertCount: monitor.AlertCount,
FailureCount: monitor.failureCount,
LastCheckOutput: monitor.lastOutput,
LastSuccess: monitor.lastSuccess,
+162 -165
View File
@@ -1,233 +1,234 @@
package main
package main_test
import (
"log"
"errors"
"reflect"
"testing"
"time"
m "git.iamthefij.com/iamthefij/minitor-go/v2"
)
// TestMonitorIsValid tests the Monitor.IsValid()
func TestMonitorIsValid(t *testing.T) {
func TestMonitorValidate(t *testing.T) {
t.Parallel()
cases := []struct {
monitor Monitor
expected bool
monitor m.Monitor
expected error
name string
}{
{Monitor{Command: CommandOrShell{Command: []string{"echo", "test"}}, AlertDown: []string{"log"}}, true, "Command only"},
{Monitor{Command: CommandOrShell{ShellCommand: "echo test"}, AlertDown: []string{"log"}}, true, "CommandShell only"},
{Monitor{Command: CommandOrShell{Command: []string{"echo", "test"}}}, false, "No AlertDown"},
{Monitor{AlertDown: []string{"log"}}, false, "No commands"},
{Monitor{Command: CommandOrShell{Command: []string{"echo", "test"}}, AlertDown: []string{"log"}, AlertAfter: -1}, false, "Invalid alert threshold, -1"},
{m.Monitor{AlertAfter: 1, Command: []string{"echo", "test"}, AlertDown: []string{"log"}}, nil, "Command only"},
{m.Monitor{AlertAfter: 1, ShellCommand: "echo test", AlertDown: []string{"log"}}, nil, "CommandShell only"},
{m.Monitor{AlertAfter: 1, Command: []string{"echo", "test"}}, m.ErrInvalidMonitor, "No AlertDown"},
{m.Monitor{AlertAfter: 1, AlertDown: []string{"log"}}, m.ErrInvalidMonitor, "No commands"},
{m.Monitor{AlertAfter: -1, Command: []string{"echo", "test"}, AlertDown: []string{"log"}}, m.ErrInvalidMonitor, "Invalid alert threshold, -1"},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
actual := c.monitor.IsValid()
if actual != c.expected {
t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expected, actual)
log.Printf("Case failed: %s", c.name)
}
t.Run(c.name, func(t *testing.T) {
t.Parallel()
log.Println("-----")
actual := c.monitor.Validate()
hasErr := (actual != nil)
expectErr := (c.expected != nil)
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()
func TestMonitorShouldCheck(t *testing.T) {
timeNow := time.Now()
timeTenSecAgo := time.Now().Add(time.Second * -10)
timeTwentySecAgo := time.Now().Add(time.Second * -20)
t.Parallel()
cases := []struct {
monitor Monitor
expected bool
name string
}{
{Monitor{}, true, "Empty"},
{Monitor{lastCheck: timeNow, CheckInterval: SecondsOrDuration{time.Second * 15}}, false, "Just checked"},
{Monitor{lastCheck: timeTenSecAgo, CheckInterval: SecondsOrDuration{time.Second * 15}}, false, "-10s"},
{Monitor{lastCheck: timeTwentySecAgo, CheckInterval: SecondsOrDuration{time.Second * 15}}, true, "-20s"},
// Create a monitor that should check every second and then verify it checks with some sleeps
monitor := m.Monitor{ShellCommand: "true", CheckInterval: time.Second}
if !monitor.ShouldCheck() {
t.Errorf("New monitor should be ready to check")
}
for _, c := range cases {
actual := c.monitor.ShouldCheck()
if actual != c.expected {
t.Errorf("ShouldCheck(%v), expected=%t actual=%t", c.name, c.expected, actual)
}
monitor.Check()
if monitor.ShouldCheck() {
t.Errorf("Monitor should not be ready to check after a check")
}
time.Sleep(time.Second)
if !monitor.ShouldCheck() {
t.Errorf("Monitor should be ready to check after a second")
}
}
// TestMonitorIsUp tests the Monitor.IsUp()
func TestMonitorIsUp(t *testing.T) {
cases := []struct {
monitor Monitor
expected bool
name string
}{
{Monitor{}, true, "Empty"},
{Monitor{alertCount: 1}, false, "Has alert"},
{Monitor{alertCount: -1}, false, "Negative alerts"},
{Monitor{alertCount: 0}, true, "No alerts"},
t.Parallel()
// Creating a monitor that should alert after 2 failures. The monitor should be considered up until we reach two failed checks
monitor := m.Monitor{ShellCommand: "false", AlertAfter: 2}
if !monitor.IsUp() {
t.Errorf("New monitor should be considered up")
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
monitor.Check()
actual := c.monitor.IsUp()
if actual != c.expected {
t.Errorf("IsUp(%v), expected=%t actual=%t", c.name, c.expected, actual)
log.Printf("Case failed: %s", c.name)
}
if !monitor.IsUp() {
t.Errorf("Monitor should be considered up with one failure and no alerts")
}
log.Println("-----")
monitor.Check()
if monitor.IsUp() {
t.Errorf("Monitor should be considered down with one alert")
}
}
// TestMonitorGetAlertNames tests that proper alert names are returned
func TestMonitorGetAlertNames(t *testing.T) {
cases := []struct {
monitor Monitor
monitor m.Monitor
up bool
expected []string
name string
}{
{Monitor{}, true, nil, "Empty up"},
{Monitor{}, false, nil, "Empty down"},
{Monitor{AlertUp: []string{"alert"}}, true, []string{"alert"}, "Return up"},
{Monitor{AlertDown: []string{"alert"}}, false, []string{"alert"}, "Return down"},
{m.Monitor{}, true, nil, "Empty up"},
{m.Monitor{}, false, nil, "Empty down"},
{m.Monitor{AlertUp: []string{"alert"}}, true, []string{"alert"}, "Return up"},
{m.Monitor{AlertDown: []string{"alert"}}, false, []string{"alert"}, "Return down"},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
actual := c.monitor.GetAlertNames(c.up)
if !EqualSliceString(actual, c.expected) {
t.Errorf("GetAlertNames(%v), expected=%v actual=%v", c.name, c.expected, actual)
log.Printf("Case failed: %s", c.name)
}
t.Run(c.name, func(t *testing.T) {
t.Parallel()
log.Println("-----")
actual := c.monitor.GetAlertNames(c.up)
if !reflect.DeepEqual(actual, c.expected) {
t.Errorf("GetAlertNames(%v), expected=%v actual=%v", c.name, c.expected, actual)
}
})
}
}
// TestMonitorSuccess tests the Monitor.success()
func TestMonitorSuccess(t *testing.T) {
func TestMonitorAlertCount(t *testing.T) {
alertEvery := 1
cases := []struct {
monitor Monitor
expectNotice bool
checkSuccess bool
alertCount int
name string
}{
{Monitor{}, false, "Empty"},
{Monitor{alertCount: 0}, false, "No alerts"},
{Monitor{alertCount: 1}, true, "Has alert"},
{false, 1, "First failure and first alert"},
{false, 2, "Second failure and first alert"},
{true, 2, "Success should preserve past alert count"},
{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 {
log.Printf("Testing case %s", c.name)
t.Logf("Testing case %s", c.name)
notice := c.monitor.success()
hasNotice := (notice != nil)
if hasNotice != c.expectNotice {
t.Errorf("success(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
log.Printf("Case failed: %s", c.name)
var notice *m.AlertNotice
if c.checkSuccess {
notice = monitor.Success()
} else {
notice = monitor.Failure()
}
log.Println("-----")
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)
}
}
}
// TestMonitorFailureAlertAfter tests that alerts will not trigger until
// hitting the threshold provided by AlertAfter
func TestMonitorFailureAlertAfter(t *testing.T) {
var alertEvery int16 = 1
var alertEveryOne int = 1
cases := []struct {
monitor Monitor
monitor m.Monitor
numChecks int
expectNotice bool
name string
}{
{Monitor{AlertAfter: 1}, true, "Empty"}, // Defaults to true because and AlertEvery default to 0
{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: &alertEvery}, true, "Alert after 1: first failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: &alertEvery}, true, "Alert after 1: second failure"},
{Monitor{failureCount: 0, AlertAfter: 20, AlertEvery: &alertEvery}, false, "Alert after 20: first failure"},
{Monitor{failureCount: 19, AlertAfter: 20, AlertEvery: &alertEvery}, true, "Alert after 20: 20th failure"},
{Monitor{failureCount: 20, AlertAfter: 20, AlertEvery: &alertEvery}, true, "Alert after 20: 21st failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 1}, 1, true, "Empty After 1"}, // Defaults to true because and AlertEvery default to 0
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryOne}, 1, true, "Alert after 1: first failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryOne}, 2, true, "Alert after 1: second failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 1, false, "Alert after 20: first failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 20, true, "Alert after 20: 20th failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 21, true, "Alert after 20: 21st failure"},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
notice := c.monitor.failure()
hasNotice := (notice != nil)
t.Run(c.name, func(t *testing.T) {
t.Parallel()
if hasNotice != c.expectNotice {
t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
log.Printf("Case failed: %s", c.name)
}
hasNotice := false
log.Println("-----")
for i := 0; i < c.numChecks; i++ {
_, notice := c.monitor.Check()
hasNotice = (notice != nil)
}
if hasNotice != c.expectNotice {
t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
}
})
}
}
// TestMonitorFailureAlertEvery tests that alerts will trigger
// on the expected intervals
func TestMonitorFailureAlertEvery(t *testing.T) {
var alertEvery0, alertEvery1, alertEvery2 int16
alertEvery0 = 0
alertEvery1 = 1
alertEvery2 = 2
cases := []struct {
monitor Monitor
expectNotice bool
name string
monitor m.Monitor
expectedNotice []bool
name string
}{
/*
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 nil
{m.Monitor{ShellCommand: "false", AlertAfter: 1}, []bool{true}, "No AlertEvery set"}, // Defaults to true because AlertAfter and AlertEvery default to nil
// Alert first time only, after 1
{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: &alertEvery0}, true, "Alert first time only after 1: first failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: &alertEvery0}, false, "Alert first time only after 1: second failure"},
{Monitor{failureCount: 2, AlertAfter: 1, AlertEvery: &alertEvery0}, false, "Alert first time only after 1: third failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: new(0)}, []bool{true, false, false}, "Alert first time only after 1"},
// Alert every time, after 1
{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: &alertEvery1}, true, "Alert every time after 1: first failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: &alertEvery1}, true, "Alert every time after 1: second failure"},
{Monitor{failureCount: 2, AlertAfter: 1, AlertEvery: &alertEvery1}, true, "Alert every time after 1: third failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: new(1)}, []bool{true, true, true}, "Alert every time after 1"},
// Alert every other time, after 1
{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: &alertEvery2}, true, "Alert every other time after 1: first failure"},
{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: &alertEvery2}, false, "Alert every other time after 1: second failure"},
{Monitor{failureCount: 2, AlertAfter: 1, AlertEvery: &alertEvery2}, true, "Alert every other time after 1: third failure"},
{Monitor{failureCount: 3, AlertAfter: 1, AlertEvery: &alertEvery2}, false, "Alert every other time after 1: fourth failure"},
{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: new(2)}, []bool{true, false, true, false}, "Alert every other time after 1"},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
notice := c.monitor.failure()
hasNotice := (notice != nil)
t.Run(c.name, func(t *testing.T) {
t.Parallel()
if hasNotice != c.expectNotice {
t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
log.Printf("Case failed: %s", c.name)
}
for i, expectNotice := range c.expectedNotice {
_, notice := c.monitor.Check()
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
// with an exponential backoff after repeated failures
func TestMonitorFailureExponential(t *testing.T) {
var alertEveryExp int16 = -1
var alertEveryExp int = -1
cases := []struct {
expectNotice bool
@@ -245,20 +246,18 @@ func TestMonitorFailureExponential(t *testing.T) {
// Unlike previous tests, this one requires a static Monitor with repeated
// calls to the failure method
monitor := Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: &alertEveryExp}
monitor := m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryExp}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
t.Run(c.name, func(t *testing.T) {
// NOTE: These tests are not parallel because they rely on the state of the Monitor
_, notice := monitor.Check()
hasNotice := (notice != nil)
notice := monitor.failure()
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("-----")
if hasNotice != c.expectNotice {
t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
}
})
}
}
@@ -271,53 +270,51 @@ func TestMonitorCheck(t *testing.T) {
}
cases := []struct {
monitor Monitor
monitor m.Monitor
expect expected
name string
}{
{
Monitor{Command: CommandOrShell{Command: []string{"echo", "success"}}},
m.Monitor{AlertAfter: 1, Command: []string{"echo", "success"}},
expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"},
"Test successful command",
},
{
Monitor{Command: CommandOrShell{ShellCommand: "echo success"}},
m.Monitor{AlertAfter: 1, ShellCommand: "echo success"},
expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"},
"Test successful command shell",
},
{
Monitor{Command: CommandOrShell{Command: []string{"total", "failure"}}},
m.Monitor{AlertAfter: 1, Command: []string{"total", "failure"}},
expected{isSuccess: false, hasNotice: true, lastOutput: ""},
"Test failed command",
},
{
Monitor{Command: CommandOrShell{ShellCommand: "false"}},
m.Monitor{AlertAfter: 1, ShellCommand: "false"},
expected{isSuccess: false, hasNotice: true, lastOutput: ""},
"Test failed command shell",
},
}
for _, c := range cases {
log.Printf("Testing case %s", c.name)
isSuccess, notice := c.monitor.Check()
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)
}
t.Run(c.name, func(t *testing.T) {
t.Parallel()
hasNotice := (notice != nil)
if hasNotice != c.expect.hasNotice {
t.Errorf("Check(%v) (notice), expected=%t actual=%t", c.name, c.expect.hasNotice, hasNotice)
log.Printf("Case failed: %s", c.name)
}
isSuccess, notice := c.monitor.Check()
if isSuccess != c.expect.isSuccess {
t.Errorf("Check(%v) (success), expected=%t actual=%t", c.name, c.expect.isSuccess, isSuccess)
}
lastOutput := c.monitor.lastOutput
if lastOutput != c.expect.lastOutput {
t.Errorf("Check(%v) (output), expected=%v actual=%v", c.name, c.expect.lastOutput, lastOutput)
log.Printf("Case failed: %s", c.name)
}
hasNotice := (notice != nil)
if hasNotice != c.expect.hasNotice {
t.Errorf("Check(%v) (notice), expected=%t actual=%t", c.name, c.expect.hasNotice, hasNotice)
}
log.Println("-----")
lastOutput := c.monitor.LastOutput()
if lastOutput != c.expect.lastOutput {
t.Errorf("Check(%v) (output), expected=%v actual=%v", c.name, c.expect.lastOutput, lastOutput)
}
})
}
}
+3
View File
@@ -0,0 +1,3 @@
{
"$schema": "https://docs.renovatebot.com/renovate-schema.json"
}
+52
View File
@@ -0,0 +1,52 @@
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
}
-42
View File
@@ -1,42 +0,0 @@
---
check_interval: 5
monitors:
- name: 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: 10 # Must be at minimum the global `check_interval`
alert_after: 3
alert_every: -1 # Defaults to -1 for exponential backoff. 0 to disable repeating
- name: 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: 5
alert_after: 3
alert_every: -1
alerts:
log_down:
command: ["echo", "Minitor failure for {{.MonitorName}}"]
log_up:
command: ["echo", "Minitor recovery for {{.MonitorName}}"]
email_up:
command:
[sendmail, "me@minitor.mon", "Recovered: {monitor_name}", "We're back!"]
mailgun_down:
command: >
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:${MAILGUN_API_KEY}"
sms_down:
command: >
curl -s -X POST -F "Body=Failure! {{.MonitorName}} has failed"
-F "From=${AVAILABLE_NUMBER}" -F "To=${MY_PHONE}"
"https://api.twilio.com/2010-04-01/Accounts/${ACCOUNT_SID}/Messages"
-u "${ACCOUNT_SID}:${AUTH_TOKEN}"
+6
View File
@@ -0,0 +1,6 @@
#! /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 "$@"
+1
View File
@@ -0,0 +1 @@
check_interval = "woops, I'm not an int!"
+7
View File
@@ -0,0 +1,7 @@
check_interval = "1s"
monitor "Command" {
command = ["echo", "$PATH"]
alert_down = [ "alert_down", "log_shell", "log_command" ]
alert_every = 0
}
-8
View File
@@ -1,8 +0,0 @@
check_interval: 1
monitors:
- name: Command
command: ['echo', '$PATH']
alert_down: [ 'alert_down', 'log_shell', 'log_command' ]
# alert_every: -1
alert_every: 0
-1
View File
@@ -1 +0,0 @@
check_interval: woops, I'm not an int!
+12
View File
@@ -0,0 +1,12 @@
check_interval = "1s"
monitor "Command" {
command = ["echo", "$PATH"]
alert_down = ["not_log"]
alert_every = 0
}
alert "log" {
command = ["true"]
}
-13
View File
@@ -1,13 +0,0 @@
check_interval: 1
monitors:
- name: Command
command: ['echo', '$PATH']
alert_down: [ 'not_log']
# alert_every: -1
alert_every: 0
alerts:
log:
command: ['true']
+12
View File
@@ -0,0 +1,12 @@
check_interval = "1s"
alert "log_command" {
command = "should be a list"
}
monitor "Command" {
command = ["echo", "$PATH"]
alert_down = ["log_command"]
alert_every = 2
check_interval = "10s"
}
+16
View File
@@ -0,0 +1,16 @@
check_interval = "1s"
default_alert_down = ["log_command"]
default_alert_every = 0
default_alert_after = 2
monitor "Default" {
command = ["echo"]
}
monitor "Command" {
command = ["echo", "$PATH"]
}
alert "log_command" {
command = ["echo", "default", "'command!!!'", "{{.MonitorName}}"]
}
-12
View File
@@ -1,12 +0,0 @@
---
check_interval: 1
default_alert_down: ["log_command"]
default_alert_after: 1
monitors:
- name: Command
command: ["echo", "$PATH"]
alerts:
log_command:
command: ["echo", "regular", '"command!!!"', "{{.MonitorName}}"]
+34
View File
@@ -0,0 +1,34 @@
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 $PATH
exit 1
EOF
alert_down = ["log_command", "log_shell"]
alert_after = 5
alert_every = 0
check_interval = "1m"
}
-25
View File
@@ -1,25 +0,0 @@
---
check_interval: 1
monitors:
- name: Command
command: ["echo", "$PATH"]
alert_down: ["log_command", "log_shell"]
alert_every: 0
check_interval: 10s
- name: Shell
command: >
echo 'Some string with stuff';
echo 'another line';
echo $PATH;
exit 1
alert_down: ["log_command", "log_shell"]
alert_after: 5
alert_every: 0
check_interval: 1m
alerts:
log_command:
command: ["echo", "regular", '"command!!!"', "{{.MonitorName}}"]
log_shell:
command: echo "Failure on {{.MonitorName}} User is $USER"
-8
View File
@@ -1,8 +0,0 @@
---
check_interval: 1
monitors:
- name: Command
command: ['echo', '$PATH']
alert_down: ['log']
alert_every: 0
+19
View File
@@ -0,0 +1,19 @@
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
}
-18
View File
@@ -1,18 +0,0 @@
---
check_interval: 1
monitors:
- name: Shell
command: >
echo 'Some string with stuff';
echo "<angle brackets>";
exit 1
alert_down: ['log_shell']
alert_after: 1
alert_every: 0
alerts:
log_shell:
command: |
echo 'Some string with stuff'
echo '<angle brackets>'
+16 -8
View File
@@ -1,6 +1,9 @@
package main
import "testing"
import (
"fmt"
"testing"
)
func TestUtilEqualSliceString(t *testing.T) {
cases := []struct {
@@ -21,12 +24,17 @@ func TestUtilEqualSliceString(t *testing.T) {
}
for _, c := range cases {
actual := EqualSliceString(c.a, c.b)
if actual != c.expected {
t.Errorf(
"EqualSliceString(%v, %v), expected=%v actual=%v",
c.a, c.b, c.expected, actual,
)
}
t.Run(fmt.Sprintf("%v %v", c.a, c.b), func(t *testing.T) {
t.Parallel()
actual := EqualSliceString(c.a, c.b)
if actual != c.expected {
t.Errorf(
"EqualSliceString(%v, %v), expected=%v actual=%v",
c.a, c.b, c.expected, actual,
)
}
})
}
}