lab/labsim/lib.sh

#!/bin/bash
# Shared helpers for the lab network simulation.
# shellcheck disable=SC2034

LIBVIRT_URI="${LIBVIRT_URI:-qemu:///system}"
IMG_DIR="${IMG_DIR:-/var/lib/libvirt/images/labsim}"
BASE_IMAGE="${BASE_IMAGE:-$IMG_DIR/alpine-base.qcow2}"
ALPINE_URL="${ALPINE_URL:-https://dl-cdn.alpinelinux.org/alpine/latest-stable/releases/cloud/generic_alpine-3.24.1-x86_64-bios-cloudinit-r0.qcow2}"

VM_MEM="${VM_MEM:-256}"      # MB — Alpine is happy here
VM_CPUS="${VM_CPUS:-1}"
VM_DISK="${VM_DISK:-1G}"
PREFIX="labsim"

CONF="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/vlans.conf"

log()  { printf '\033[0;36m[labsim]\033[0m %s\n' "$*"; }
warn() { printf '\033[1;33m[labsim]\033[0m %s\n' "$*" >&2; }
die()  { printf '\033[0;31m[labsim]\033[0m %s\n' "$*" >&2; exit 1; }

virsh_q() { sudo virsh --connect "$LIBVIRT_URI" "$@"; }

net_name() { echo "${PREFIX}-vlan$1"; }
vm_name()  { echo "${PREFIX}-$1-$2"; }          # labsim-2-k8s
# Linux bridge names are capped at 15 chars — keep it short and unique.
br_name()  { echo "vbr-ls$1"; }

require_tools() {
  for t in virsh virt-install qemu-img genisoimage; do
    command -v "$t" >/dev/null 2>&1 || die "missing required tool: $t"
  done
  sudo -n true 2>/dev/null || warn "sudo may prompt for a password"
}

find_ssh_pubkey() {
  local home="${SUDO_USER:+/home/$SUDO_USER}"
  home="${home:-$HOME}"
  for n in id_ed25519 id_ecdsa id_rsa; do
    [ -f "$home/.ssh/$n.pub" ] && { cat "$home/.ssh/$n.pub"; return; }
  done
  die "no SSH public key found in $home/.ssh"
}

# Populate SELECTED[] from argv (VLAN ids) or the whole config.
selected_vlans() {
  SELECTED=()
  local want=("$@")
  while IFS= read -r line; do
    [[ "$line" =~ ^[[:space:]]*# ]] && continue
    [[ -z "${line// }" ]] && continue
    local vid="${line%%:*}"
    if [ ${#want[@]} -eq 0 ]; then
      SELECTED+=("$line")
    else
      for w in "${want[@]}"; do [ "$w" = "$vid" ] && SELECTED+=("$line"); done
    fi
  done < "$CONF"
  [ ${#SELECTED[@]} -gt 0 ] || die "no VLANs selected (checked $CONF)"
}

# cloud-init NoCloud seed: static addressing + SSH key + hello-world HTTP.
build_seed() {
  local iso="$1" vm="$2" vid="$3" name="$4" prefix="$5" ip="$6" real="$7" pubkey="$8"
  local tmp; tmp="$(mktemp -d)"

  cat > "$tmp/meta-data" <<EOF
instance-id: $vm
local-hostname: $vm
EOF

  # Alpine's cloud-init does not reliably apply netplan-style network-config,
  # and these networks have no DHCP server on purpose — so configure the
  # interface the Alpine-native way instead (verified: hostname applied but no
  # address, i.e. the seed was read and network-config was ignored).
  #
  # The default route deliberately points at the router under test (.1), not
  # the host (.2), so a broken/absent router shows up as a failed test rather
  # than being silently papered over by host routing. post-up ... || true keeps
  # the interface up even while no router exists yet.
  cat > "$tmp/network-config" <<EOF
version: 1
config:
  - type: physical
    name: eth0
    subnets:
      - type: static
        address: $ip
        netmask: 255.255.255.0
        # Default route via the router under test. Without this the VMs can
        # reach their own /24 and their gateway, but nothing beyond it — which
        # looks exactly like "the router is broken" in the matrix.
        gateway: ${prefix}.1
EOF

  cat > "$tmp/user-data" <<EOF
#cloud-config
hostname: $vm
users:
  - name: alpine
    # NOTE: this Alpine image ships no sudo (and cloud-init's sudo: directive
    # is therefore inert). For privileged work in these VMs, ssh as root —
    # the key is installed there too.
    shell: /bin/ash
    # Without this cloud-init leaves the account locked ("!*" in /etc/shadow)
    # and sshd refuses key auth for it — verified on the first build.
    lock_passwd: false
    plain_text_passwd: labsim
    ssh_authorized_keys:
      - $pubkey
ssh_authorized_keys:
  - $pubkey
disable_root: false
chpasswd:
  list: |
    root:labsim
  expire: false
write_files:
  - path: /etc/network/interfaces
    content: |
      auto lo
      iface lo inet loopback
      auto eth0
      iface eth0 inet static
        address $ip
        netmask 255.255.255.0
        post-up ip route add default via ${prefix}.1 || true
  - path: /var/www/index.html
    content: |
      <html><body>
      <h1>labsim vlan $vid — $name</h1>
      <p>host: $vm</p>
      <p>address: $ip/24</p>
      <p>gateway under test: ${prefix}.1</p>
      <p>mirrors production: $real</p>
      </body></html>
  - path: /etc/local.d/labsim-http.start
    permissions: '0755'
    content: |
      #!/bin/sh
      # This image's busybox has no httpd applet ("applet not found"), and the
      # VMs are isolated so apk cannot fetch one. python3 is already present
      # (cloud-init depends on it), so serve with http.server — no packages,
      # no internet.
      #
      # Two traps already hit here, both silent:
      #  - start-stop-daemon --exec /usr/bin/python3 matches cloud-init's OWN
      #    python3 at boot, says "already running", starts nothing.
      #  - busybox pgrep -f PATTERN matches its own argv, so a
      #    "skip if running" guard always fires (verified: guard_exit=0 with
      #    nothing listening).
      # So: no guard, no start-stop-daemon. Binding twice is harmless — the
      # second just fails to bind.
      nohup /usr/bin/python3 -m http.server 80 --directory /var/www \\
        >/var/log/labsim-http.log 2>&1 &
runcmd:
  # cloud-init's network-config (v1, above) already applies the address, so do
  # NOT restart networking here — it fails, and one failing runcmd aborts every
  # command after it, which is what silently left httpd unstarted. Each command
  # is || true for the same reason.
  - [ sh, -c, "rc-update add sshd default || true" ]
  - [ sh, -c, "rc-update add local default || true" ]
  - [ sh, -c, "/etc/local.d/labsim-http.start || true" ]
EOF

  # Validate before building the ISO. The heredoc above is intentionally
  # unquoted (it interpolates $ip/$prefix), which means backticks or $( ) in
  # ANY line — including comments — get executed by the host shell and their
  # output silently corrupts the YAML. Cheap check, expensive bug.
  python3 -c "import yaml,sys; yaml.safe_load(open(sys.argv[1]))" "$tmp/user-data" \
    || die "generated user-data is not valid YAML (backticks or \$( ) in build_seed?): $tmp/user-data"

  sudo genisoimage -quiet -output "$iso" -volid cidata -joliet -rock \
    "$tmp/user-data" "$tmp/meta-data" "$tmp/network-config"
  rm -rf "$tmp"
}

ssh_to() {
  local ip="$1"; shift
  timeout 12 ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null \
    -o ConnectTimeout=5 -o BatchMode=yes -o LogLevel=ERROR \
    "alpine@$ip" "$@" 2>/dev/null
}

wait_ready() {
  local deadline=$((SECONDS + 240)) pending=1
  while [ $SECONDS -lt $deadline ]; do
    pending=0
    for entry in "${SELECTED[@]}"; do
      IFS=: read -r vid _n prefix _r <<<"$entry"
      # Wait for BOTH: sshd is up well before cloud-init's runcmd starts the
      # web server, so checking SSH alone reports "ready" then shows HTTP FAIL.
      ssh_to "${prefix}.10" true >/dev/null 2>&1 \
        && curl -sS -o /dev/null --max-time 4 "http://${prefix}.10/" 2>/dev/null \
        || pending=$((pending + 1))
    done
    [ $pending -eq 0 ] && { log "all ${#SELECTED[@]} VMs reachable"; return 0; }
    sleep 5
  done
  warn "$pending VM(s) still not answering SSH after 240s — see status below"
  return 0
}

status_table() {
  printf '  %-18s %-6s %-16s %-9s %-7s %s\n' VM VLAN ADDRESS STATE SSH HTTP
  printf '  %-18s %-6s %-16s %-9s %-7s %s\n' ------------------ ------ ---------------- --------- ------- ----
  for entry in "${SELECTED[@]}"; do
    IFS=: read -r vid name prefix _r <<<"$entry"
    local vm ip state ssh http
    vm="$(vm_name "$vid" "$name")"; ip="${prefix}.10"
    state="$(virsh_q domstate "$vm" 2>/dev/null | head -1 | tr -d '\n')"
    [ -z "$state" ] && state="absent"
    ssh_to "$ip" true >/dev/null 2>&1 && ssh=ok || ssh=FAIL
    if curl -sS -o /dev/null --max-time 5 "http://$ip/" 2>/dev/null; then http=ok; else http=FAIL; fi
    printf '  %-18s %-6s %-16s %-9s %-7s %s\n' "$vm" "$vid" "$ip" "$state" "$ssh" "$http"
  done
}