miner/deploy/infra-setup.sh

#!/usr/bin/env bash
# One-time provisioning of a mining host for the CI deploy in
# .gitea/workflows/deploy.yaml (quantus/miner#8). The miner role of
# lair/quantus's script/infra-setup.sh, moved here so the deployer and its
# sudoers grant list live in the same repo and cannot drift: the deploy
# preflights the target's `sudo -n -l` against the SUDO block below.
#
# Convention: ~/git/architecture/deployment-gitea-actions.md §1–§2. Run from a
# workstation with admin (sudo) ssh access to the targets — NOT the gitea_ci
# account. Idempotent; re-running is a no-op. Skips unreachable hosts.
#
#   ./deploy/infra-setup.sh --pubkey ~/.ssh/id_gitea_ci.pub
#   ./deploy/infra-setup.sh --pubkey ~/.ssh/id_gitea_ci.pub --miner-hosts benjy.hanzalova.internal
#
# The runner keypair is NOT generated here. It already exists at
# ~/.ssh/id_gitea_ci and is shared by every project's RSYNC_SSH_KEY secret and
# every host's gitea_ci authorized_keys — regenerating it would silently break
# every other deploy on the fleet.
#
# Re-run this whenever the deploy gains a new file to ship or a new privileged
# command; the preflight fails up front naming the missing paths rather than
# dying partway through an rsync with "sudo: a password is required".
set -euo pipefail

ADMIN_USER="${ADMIN_USER:-$USER}"
# Must agree with the deploy matrix in .gitea/workflows/deploy.yaml.
MINER_HOSTS="${MINER_HOSTS-benjy.hanzalova.internal quadbrat.hanzalova.internal beast.hanzalova.internal}"
PUBKEY=""

while [ $# -gt 0 ]; do
  case "$1" in
    --pubkey)      PUBKEY="$2"; shift 2 ;;
    --miner-hosts) MINER_HOSTS="$2"; shift 2 ;;
    --admin)       ADMIN_USER="$2"; shift 2 ;;
    *) echo "unknown arg: $1" >&2; exit 2 ;;
  esac
done
[ -n "$PUBKEY" ] && [ -r "$PUBKEY" ] || { echo "--pubkey <file> is required and must be readable" >&2; exit 2; }

provision_miner() {
  local host="$1"
  echo "== ${host} (miner) =="
  if ! ssh -o ConnectTimeout=8 -o BatchMode=yes "${ADMIN_USER}@${host}" true; then
    echo "  ! unreachable as ${ADMIN_USER} — skipping" >&2
    return 1
  fi

  # All privileged work in one remote `sudo bash`. The runner pubkey is the only
  # dynamic value, passed as $1 (single line, no quoting hazard). The sudoers
  # `\=` are the required escapes — visudo rejects a bare `=` in a command arg.
  # The `*` in an rsync line matches rsync's --server arg vector; the trailing
  # literal destination is what actually bounds the rule.
  ssh "${ADMIN_USER}@${host}" "sudo bash -seu -- '$(cat "$PUBKEY")'" <<'REMOTE'
    PUBKEY="$1"

    # /bin/bash, NOT nologin. The deploy runs `ssh gitea_ci@host <command>`, and
    # a nologin shell refuses that with "This account is currently not
    # available": the key authenticates, then the command cannot run.
    if ! getent passwd gitea_ci >/dev/null; then
      useradd --system --create-home --home-dir /var/lib/gitea_ci \
              --shell /bin/bash gitea_ci
      echo "  + created gitea_ci"
    else
      echo "  = gitea_ci already present"
    fi
    cur=$(getent passwd gitea_ci | cut -d: -f7)
    if [ "$cur" != /bin/bash ]; then
      usermod -s /bin/bash gitea_ci
      echo "  ~ gitea_ci shell was ${cur} — set to /bin/bash so ssh commands can run"
    fi

    install -d -o gitea_ci -g gitea_ci -m 0700 /var/lib/gitea_ci/.ssh
    ak=/var/lib/gitea_ci/.ssh/authorized_keys
    touch "$ak"
    grep -qxF "$PUBKEY" "$ak" || printf '%s\n' "$PUBKEY" >> "$ak"
    chown gitea_ci:gitea_ci "$ak"
    chmod 0600 "$ak"
    usermod -aG systemd-journal gitea_ci

    # The GPU must be present and enumerable before a miner deploy is worth
    # attempting; failing here beats a green deploy that mines nothing.
    if ! command -v nvidia-smi >/dev/null; then
      echo "  ! nvidia-smi not found — this host has no usable NVIDIA driver" >&2
      exit 1
    fi
    nvidia-smi --query-gpu=name --format=csv,noheader | sed 's/^/  = gpu: /'

    tmp=/etc/sudoers.d/.quantus-miner_gitea_ci.tmp
    cat > "$tmp" <<'SUDO'
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /usr/local/bin/quantus-miner
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/systemd/system/quantus-miner.service
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/sysusers.d/quantus-miner.conf
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/quantus-miner/miner.env
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/quantus-miner/miner-auth-token
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/quantus-miner/miner-tls-cert-sha256
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/firewalld/services/quantus-miner-metrics.xml
gitea_ci ALL=(root) NOPASSWD: /usr/bin/firewall-cmd --get-default-zone
gitea_ci ALL=(root) NOPASSWD: /usr/bin/firewall-cmd --reload
gitea_ci ALL=(root) NOPASSWD: /usr/bin/firewall-cmd --permanent --zone\=* --add-rich-rule\=*
gitea_ci ALL=(root) NOPASSWD: /usr/bin/firewall-cmd --zone\=* --add-rich-rule\=*
gitea_ci ALL=(root) NOPASSWD: /usr/bin/firewall-cmd --zone\=* --query-rich-rule\=*
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemd-sysusers
gitea_ci ALL=(root) NOPASSWD: /usr/bin/install -d -o root -g quantus-miner -m 0750 /etc/quantus-miner
gitea_ci ALL=(root) NOPASSWD: /usr/bin/install -d -o quantus-miner -g quantus-miner -m 0750 /var/lib/quantus-miner
gitea_ci ALL=(root) NOPASSWD: /usr/sbin/restorecon -R /usr/local/bin/quantus-miner /etc/quantus-miner /var/lib/quantus-miner
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl daemon-reload
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl enable quantus-miner.service
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl restart quantus-miner.service
# stop/start (not just restart) so the benchmark harness (bench.yaml) can pause
# mining for a measurement window and resume it afterwards.
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl stop quantus-miner.service
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl start quantus-miner.service
# The benchmark measures under the miner's GPU profile, which stopping the unit
# resets (its ExecStopPost). bench-on-host.sh re-applies it for the window and
# restores whichever profile the host was in afterwards.
gitea_ci ALL=(root) NOPASSWD: /usr/local/bin/nvidia-power-limit.sh miner
gitea_ci ALL=(root) NOPASSWD: /usr/local/bin/nvidia-power-limit.sh default
# Rollback: the deploy keeps the previous binary as .prev (cp) and restores it
# with install when validate fails; cp back would hit "Text file busy" on the
# running binary, install unlinks the destination first. Deploying from main means a bad commit reaches production;
# this is what makes that survivable.
gitea_ci ALL=(root) NOPASSWD: /usr/bin/cp -p /usr/local/bin/quantus-miner /usr/local/bin/quantus-miner.prev
gitea_ci ALL=(root) NOPASSWD: /usr/bin/install -m 0755 /usr/local/bin/quantus-miner.prev /usr/local/bin/quantus-miner
SUDO
    chmod 0440 "$tmp"
    visudo -cf "$tmp"
    mv "$tmp" /etc/sudoers.d/quantus-miner_gitea_ci
    echo "  = sudoers quantus-miner_gitea_ci installed and visudo-verified"
REMOTE
}

rc=0
for h in $MINER_HOSTS; do
  provision_miner "$h" || rc=1
done
echo
echo "done. remaining operator steps:"
echo "  1. confirm RSYNC_SSH_KEY is set in the repo's Actions secrets"
echo "  2. push to main, or run the deploy workflow manually (mode: validate first)"
exit $rc