mirror of
https://github.com/kevinveenbirkenbach/computer-playbook.git
synced 2026-11-06 19:01:54 +00:00
kevinveenbirkenbachandClaude Opus 5
21f0172921
ba8a72309 bounded scripts/install/apt.sh and d50ba46b0 bounded the swarm
bootstrap; these three were the remainder, and one of them was still
costing whole jobs. docker_dataroot.sh hung Nextcloud#7 (job 96179137223,
run 32284644282) for 5h40m: "installing zfsutils-linux for zpool" at
19:50:39 is the last line before "rc=124 after 20400s" at 01:30:39, with
nothing in between. distros.sh's global budget is the only ceiling below
these calls, so one stalled fetch also takes the untried distros with it.
Both update and install are wrapped, not just update - that hang sat in
the install, and apt-get install fetches from the same mirror. Constants
come verbatim from scripts/install/apt.sh:19-20 rather than being
re-derived.
host_deploy.sh runs inside a container via `docker exec ... sh -c`, where
POSIX sh has no arrays, so its options are a word-split string instead.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
69 lines
3.3 KiB
Bash
Executable File
69 lines
3.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Install a host role inside its pkgmgr distro container against localhost.
|
|
# Env: GUIDE_ROLE, GUIDE_RUNTIME_IMAGE, INFINITO_DISTRO,
|
|
# INFINITO_RESCUE_DIAGNOSTICS_BASE.
|
|
set -euo pipefail
|
|
|
|
: "${INFINITO_RESCUE_DIAGNOSTICS_BASE:?}"
|
|
: "${INFINITO_DISTRO:?}"
|
|
|
|
# Exception: strip the clone/cd lines because the checkout is already
|
|
# mounted; running them would clone a fresh tree and lose the CI changes.
|
|
awk '/^### Production$/{p=1} p && /^```bash$/{c=1; next} c && /^```$/{exit} c' \
|
|
"roles/${GUIDE_ROLE}/README.md" |
|
|
grep -vE '^git clone |^cd core$' >/tmp/host-deploy.sh
|
|
test -s /tmp/host-deploy.sh
|
|
|
|
sed -i "s#<your-ssh-public-key>#ssh-ed25519 AAAA_TEST_DUMMY_KEY github-ci-dummy@infinito#" /tmp/host-deploy.sh
|
|
|
|
docker pull "${GUIDE_RUNTIME_IMAGE}"
|
|
|
|
# Exception: the pkgmgr base image ships no init of its own.
|
|
PREP="$(docker run -d --entrypoint sleep "${GUIDE_RUNTIME_IMAGE}" infinity)"
|
|
docker exec "${PREP}" sh -c '
|
|
set -e
|
|
if command -v apt-get >/dev/null 2>&1; then
|
|
APT_TIMEOUT=10m
|
|
APT_OPTS="-o Acquire::Retries=5 -o Acquire::http::Timeout=30 -o Acquire::https::Timeout=30"
|
|
timeout -k 30 "$APT_TIMEOUT" apt-get $APT_OPTS update
|
|
DEBIAN_FRONTEND=noninteractive timeout -k 30 "$APT_TIMEOUT" apt-get $APT_OPTS install -y systemd systemd-sysv libnss-myhostname
|
|
elif command -v dnf >/dev/null 2>&1; then
|
|
dnf install -y systemd
|
|
elif command -v pacman >/dev/null 2>&1; then
|
|
pacman -Sy --noconfirm --needed archlinux-keyring
|
|
pacman -Syu --noconfirm --needed systemd
|
|
rm -rf /var/cache/pacman/pkg/*
|
|
fi
|
|
grep -q myhostname /etc/nsswitch.conf || sed -i "s/^hosts:.*/& myhostname/" /etc/nsswitch.conf
|
|
[ -e /sbin/init ] || ln -sf /lib/systemd/systemd /sbin/init
|
|
'
|
|
BOOT_IMAGE="guide-boot:${GUIDE_ROLE}"
|
|
docker commit "${PREP}" "${BOOT_IMAGE}" >/dev/null
|
|
docker rm -f "${PREP}" >/dev/null 2>&1 || true # nocheck: shell-or-true -- cleanup of a possibly already-removed container
|
|
|
|
CID="$(docker run -d --privileged --cgroupns=host \
|
|
-v /sys/fs/cgroup:/sys/fs/cgroup:rw \
|
|
--tmpfs /run --tmpfs /run/lock \
|
|
-v "${PWD}:${PWD}" \
|
|
--entrypoint /sbin/init \
|
|
"${BOOT_IMAGE}")"
|
|
# shellcheck disable=SC2154
|
|
trap 'rc=$?; if [ "${rc}" -ne 0 ]; then _rescue="${INFINITO_RESCUE_DIAGNOSTICS_BASE}/${INFINITO_DISTRO}/${GUIDE_ROLE}"; INFINITO_RESCUE_DIAGNOSTICS_DIR="${_rescue}" python3 utils/diagnostics/container.py "${GUIDE_ROLE}" "guide host boot failure" || true; bash scripts/tests/deploy/utils/rescue_index.sh "${_rescue}"; fi; docker rm -f "${CID}" >/dev/null 2>&1 || true; docker rmi -f "${BOOT_IMAGE}" >/dev/null 2>&1 || true' EXIT # nocheck: shell-or-true -- best-effort diagnostics + teardown in the EXIT trap
|
|
|
|
for _ in $(seq 1 40); do
|
|
state="$(docker exec "${CID}" systemctl is-system-running 2>/dev/null || true)"
|
|
case "${state}" in running | degraded) break ;; esac
|
|
sleep 3
|
|
done
|
|
state="$(docker exec "${CID}" systemctl is-system-running 2>/dev/null || true)"
|
|
case "${state}" in
|
|
running | degraded) ;;
|
|
*)
|
|
echo "systemd never reached a running state (last: ${state:-unknown})" >&2
|
|
docker exec "${CID}" systemctl --no-pager status 2>/dev/null | head -n 20 >&2 || true # nocheck: shell-or-true -- diagnostics dump on the failure path
|
|
exit 1
|
|
;;
|
|
esac
|
|
docker exec "${CID}" bash -lc 'systemctl unmask systemd-logind && systemctl start systemd-logind && loginctl enable-linger root && systemctl start user@0.service'
|
|
docker exec -i -w "${PWD}" "${CID}" bash -s </tmp/host-deploy.sh
|