Add the GitHub Actions workflows
A lint gate on every push, a manual deploy form, and a connectivity workflow for when a deploy hangs instead of failing. Nothing deploys on a push: merging changes what would be deployed, a person still decides when. The stack name and pull policy reach a shell command, so they are validated through env: rather than interpolated into a run: block. Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
This commit is contained in:
Lucas Winther
co-authored by
Claude Opus 5
Claude Opus 5
parent
9b9e39e67f
commit
a0e56c96b7
@@ -0,0 +1,127 @@
|
||||
---
|
||||
# Diagnostics, for when a deploy job hangs instead of failing.
|
||||
#
|
||||
# Two jobs, deliberately separate:
|
||||
#
|
||||
# ping uses the real deploy key and asks Ansible to talk to every host. This
|
||||
# is the right first thing to run after setting the secrets up, and the
|
||||
# right first thing to run when a deploy misbehaves. It changes nothing.
|
||||
# probe uses no credentials at all and answers a narrower question: where do
|
||||
# the packets stop? Run it when ping times out.
|
||||
#
|
||||
# The distinction that matters, and the reason `probe` exists:
|
||||
#
|
||||
# Permission denied (publickey) the key is wrong — you reached sshd
|
||||
# Connection refused you reached the host, nothing is listening
|
||||
# Connection timed out packets are being dropped in transit
|
||||
#
|
||||
# Only the third is a network problem, and no amount of re-pasting the key will
|
||||
# fix it. See docs/connectivity.md.
|
||||
name: connectivity
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
hosts:
|
||||
description: Space-separated hosts to probe (defaults to the inventory)
|
||||
required: false
|
||||
default: edge.example.com app.example.com
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
ping:
|
||||
name: ansible ping
|
||||
runs-on: ${{ vars.DEPLOY_RUNNER || 'ubuntu-latest' }}
|
||||
environment: production
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
- name: Install the pinned toolchain
|
||||
run: |
|
||||
set -eu
|
||||
scripts/check.sh --print-specs | head -1 | xargs -d '\n' pip install --quiet
|
||||
- name: Load the deploy key
|
||||
env:
|
||||
SSH_KEY_BACKEND: ci
|
||||
SSH_PRIVATE_KEY_B64: ${{ secrets.SSH_PRIVATE_KEY_B64 }}
|
||||
run: |
|
||||
set -eu
|
||||
SSH_KEY_PATH="$(scripts/load-ssh-key.sh)"
|
||||
echo "SSH_KEY_PATH=$SSH_KEY_PATH" >> "$GITHUB_ENV"
|
||||
# Success looks like `SUCCESS => {"ping": "pong"}` for every host. That
|
||||
# proves the runner decoded the key, reached port 22, authenticated, and
|
||||
# ran Python on the far side — which is everything a deploy needs except
|
||||
# the playbook itself.
|
||||
- name: Ping every host in the inventory
|
||||
working-directory: ansible
|
||||
run: ansible all -m ansible.builtin.ping
|
||||
|
||||
probe:
|
||||
name: network probe
|
||||
runs-on: ${{ vars.DEPLOY_RUNNER || 'ubuntu-latest' }}
|
||||
# A report, not a gate. Every section must run even when the thing it probes
|
||||
# is unreachable, which is the normal case when you are running this.
|
||||
continue-on-error: true
|
||||
steps:
|
||||
- name: Probe
|
||||
env:
|
||||
HOSTS: ${{ github.event.inputs.hosts }}
|
||||
run: |
|
||||
set +e
|
||||
|
||||
# A bare TCP connect can be answered by a transparent proxy that then
|
||||
# says nothing, which looks like success and is not. Real sshd greets
|
||||
# first, so the banner is the only honest proof you reached the server.
|
||||
ssh_banner() {
|
||||
b=$(timeout 6 bash -c "exec 3<>/dev/tcp/$1/${2:-22}; head -c 12 <&3" 2>/dev/null || true)
|
||||
case "$b" in
|
||||
SSH-*) printf ' %-26s %-5s OK, sshd replied: %s\n' "$1" "${2:-22}" "$b" ;;
|
||||
'') printf ' %-26s %-5s NO REPLY (dropped, or a silent proxy)\n' "$1" "${2:-22}" ;;
|
||||
*) printf ' %-26s %-5s answered, but not sshd: %s\n' "$1" "${2:-22}" "$b" ;;
|
||||
esac
|
||||
}
|
||||
|
||||
# Distinguishes "refused" (allowed out, nothing listening) from
|
||||
# "filtered" (dropped in transit). This is the whole point of the job:
|
||||
# if every port but 443 is filtered, you are behind an egress allowlist
|
||||
# and no alternative SSH port will help.
|
||||
port_state() {
|
||||
# `rc=0; out=$(...) || rc=$?` and not `out=$(...); rc=$?` — the
|
||||
# latter is a failing simple command, which under set -e ends the
|
||||
# step before rc is ever read, so a filtered port aborts the report
|
||||
# instead of describing it.
|
||||
rc=0
|
||||
out=$(timeout 5 bash -c "cat < /dev/null > /dev/tcp/$1/$2" 2>&1) || rc=$?
|
||||
if [ "$rc" -eq 0 ]; then s='open'
|
||||
elif printf '%s' "$out" | grep -qi refused; then
|
||||
s='refused -> port allowed out'
|
||||
elif [ "$rc" -eq 124 ]; then
|
||||
s='filtered -> blocked in transit'
|
||||
else
|
||||
s="unclear (rc=$rc) $out"
|
||||
fi
|
||||
printf ' %-26s %-5s %s\n' "$1" "$2" "$s"
|
||||
}
|
||||
|
||||
printf '== 0. does this runner have a network at all? ==\n'
|
||||
printf ' DNS: '; getent hosts github.com >/dev/null 2>&1 && echo resolves || echo 'CANNOT RESOLVE'
|
||||
printf ' https external: '
|
||||
curl -s -o /dev/null -w '%{http_code}\n' --max-time 10 \
|
||||
https://github.com || echo 'NO EGRESS'
|
||||
printf ' egress address: '; curl -s --max-time 10 https://ifconfig.me || echo unknown
|
||||
|
||||
printf '\n\n== 1. SSH to the target hosts ==\n'
|
||||
for h in $HOSTS; do ssh_banner "$h"; done
|
||||
|
||||
printf '\n== 2. SSH elsewhere: is outbound 22 blocked wholesale? ==\n'
|
||||
ssh_banner github.com
|
||||
|
||||
printf '\n== 3. Which ports are allowed out at all? ==\n'
|
||||
for h in $HOSTS; do
|
||||
port_state "$h" 22
|
||||
port_state "$h" 443
|
||||
done
|
||||
Reference in New Issue
Block a user