Unverified Commit a0f54df2 authored by Minseong Choi's avatar Minseong Choi 💬
Browse files

fix(bootstrap): fail the nano install when the unit does not stay up 

install_nano_service printed "enabled and started" straight after
systemctl restart, which returns as soon as the process is forked. An
upgrade that keeps an old felis.toml the new binary rejects (an
[[auth_source]] without a prefix, say) left the unit crash-looping in
auto-restart while the installer reported success, and every login
through the proxy failed.

The install now waits two seconds and asks systemctl is-active. A unit
that exited is in "activating (auto-restart)", which is-active does not
count as active; on real systemd a unit whose process exits 1 under
Restart=on-failure reads activating/auto-restart and is-active returns
non-zero, while a running one reads active/running and returns 0. On
failure the install prints the unit's last 20 journal lines and stops.
This also surfaces a nano unit locked out of an existing 0700 /etc/felis.

The harness runs the extracted function with systemctl stubbed both
ways. Without the check, the dead-unit cases fail.
parent 26f685be

deploy/bootstrap.sh

+7 −0
Changes for deploy/bootstrap.sh: 7 added lines, 0 removed lines.
Original line number Diff line number Diff line
@@ -2379,6 +2379,13 @@ EOF 
  # restart, not `enable --now`: on a re-run the service is already active and --now would

  # leave the OLD binary running against the NEW unit. Converge means converge.

  systemctl restart felis-nano

  # restart returns as soon as the process is forked. A config the new binary rejects, or a

  # file it cannot open, only shows once it has exited and the unit sits in auto-restart.

  sleep 2

  if ! systemctl is-active --quiet felis-nano; then

    journalctl -u felis-nano -n 20 --no-pager || true

    die "felis-nano did not stay up; its last log lines are above"

  fi

  ok "felis-nano.service enabled and started (listen ${FELIS_NANO_LISTEN})"

}

deploy/bootstrap_test.sh

+32 −0
Changes for deploy/bootstrap_test.sh: 32 added lines, 0 removed lines.
Original line number Diff line number Diff line
@@ -206,6 +206,38 @@ else 
  echo "SKIP directory modes: this filesystem ignores chmod"

fi



# --- install_nano_service reports a unit that dies at once ------------------------------

# A config the new binary rejects leaves the unit in auto-restart; the install must say so

# instead of printing "started" over a proxy whose every login now fails.



iblock="$(awk '/^install_nano_service\(\) \{/,/^}/' "$BS")"

[ -n "$iblock" ] || { echo "FAIL: no install_nano_service found in $BS"; exit 1; }

[ "$(printf '%s\n' "$iblock" | wc -l)" -lt 50 ] \

  || { echo "FAIL: the extracted block is not the function -- did its closing brace move?"; exit 1; }



run_nano_service() { # exit status systemctl is-active reports

  ACTIVE="$1" NANO_SERVICE="$sdir/felis-nano.service" HOST_BIN=/usr/local/bin/felis \

    STATE_DIR=/etc/felis FELIS_NANO_LISTEN=127.0.0.1:25580 bash -c '

    die() { printf "DIE: %s\n" "$*"; exit 1; }

    ok() { printf "OK: %s\n" "$*"; }

    sleep() { :; }

    systemctl() { if [ "$1" = is-active ]; then return "$ACTIVE"; fi; }

    journalctl() { printf "JOURNAL: config: needs prefix\n"; }

    '"$iblock"'

    install_nano_service'

}



out="$(run_nano_service 3)"

expect "a unit that dies at once fails the install" "DIE: felis-nano did not stay up" "$out"

expect "the failure shows the unit's own log" "JOURNAL: config: needs prefix" "$out"

case "$out" in

  *"OK: felis-nano.service"*) echo "FAIL a dead unit must not be reported as started"; fails=$((fails + 1)) ;;

  *) echo "PASS a dead unit is not reported as started" ;;

esac



out="$(run_nano_service 0)"

expect "a unit that stays up is reported as started" "OK: felis-nano.service enabled and started" "$out"



# ---------------------------------------------------------------------------------------

if [ "$fails" -eq 0 ]; then

  echo "ALL PASS"