jschoubben
ee2648188d
96 comments across the two repos named records that no longer exist. Each now points at the consolidated record that holds its reasoning -- ADR 0034 (a test defends a decision) is 0017, the eight host records are 0005, the four lab records are 0016. Worth noting for next time: these are references from outside HQ, so renumbering there is not free. It cost 38 files here.
97 lines
4.5 KiB
Bash
Executable File
97 lines
4.5 KiB
Bash
Executable File
#!/bin/sh
|
|
# Tests for nox-mesh-host-rollback.
|
|
#
|
|
# It runs on a machine where the host will not start, which is the one moment nobody can afford
|
|
# it to be wrong — and the one moment it is hardest to debug. So it is tested here, against a
|
|
# real filesystem, with a stub package manager that records what it was asked to do.
|
|
set -eu
|
|
cd "$(dirname "$0")"
|
|
SCRIPT="$PWD/nox-mesh-host-rollback"
|
|
PASS=0; FAIL=0
|
|
|
|
setup() {
|
|
WORK="$(mktemp -d)"
|
|
export MESH_HOST_STATE_DIR="$WORK/state"
|
|
export MESH_HOST_PKG_CACHE="$WORK/cache"
|
|
export MESH_HOST_PACKAGE="nox-mesh-host"
|
|
mkdir -p "$MESH_HOST_STATE_DIR" "$MESH_HOST_PKG_CACHE" "$WORK/bin"
|
|
|
|
# Stubs on PATH. Not mocks of the script's own logic — the boundary is real commands, and
|
|
# these record the calls so a test can assert what the script asked the machine to do.
|
|
cat > "$WORK/bin/pacman" <<'STUB'
|
|
#!/bin/sh
|
|
echo "$@" >> "$MESH_HOST_STATE_DIR/pacman.calls"
|
|
[ -n "${STUB_PACMAN_FAILS:-}" ] && exit 1
|
|
exit 0
|
|
STUB
|
|
cat > "$WORK/bin/systemctl" <<'STUB'
|
|
#!/bin/sh
|
|
echo "$@" >> "$MESH_HOST_STATE_DIR/systemctl.calls"
|
|
exit 0
|
|
STUB
|
|
chmod +x "$WORK/bin/pacman" "$WORK/bin/systemctl"
|
|
PATH="$WORK/bin:$PATH"; export PATH
|
|
unset STUB_PACMAN_FAILS || true
|
|
}
|
|
|
|
check() { # name, condition-description, actual, expected
|
|
if [ "$3" = "$4" ]; then PASS=$((PASS+1)); printf ' ok %s\n' "$1"
|
|
else FAIL=$((FAIL+1)); printf ' FAIL %s\n %s\n got: %s\n expected: %s\n' "$1" "$2" "$3" "$4"; fi
|
|
}
|
|
|
|
# --- a normal rollback ---------------------------------------------------------------------
|
|
setup
|
|
echo "1.4.2" > "$MESH_HOST_STATE_DIR/known-good"
|
|
touch "$MESH_HOST_PKG_CACHE/nox-mesh-host-1.4.2-1-x86_64.pkg.tar.zst"
|
|
"$SCRIPT" >/dev/null 2>&1
|
|
check "installs the known-good version" "pacman is asked to install the cached package" \
|
|
"$(grep -c 'nox-mesh-host-1.4.2' "$MESH_HOST_STATE_DIR/pacman.calls" 2>/dev/null || echo 0)" "1"
|
|
# It installs and stops. The launcher execs the host next, and starting it here would run two
|
|
# (novox/hq ADR 0005).
|
|
check "does not start anything itself" "the launcher owns starting" \
|
|
"$([ -f "$MESH_HOST_STATE_DIR/systemctl.calls" ] && echo started || echo not-started)" "not-started"
|
|
check "records that it rolled back" "the attempted marker holds the version" \
|
|
"$(cat "$MESH_HOST_STATE_DIR/rollback-attempted" 2>/dev/null || echo MISSING)" "1.4.2"
|
|
|
|
# --- it rolls back only once ---------------------------------------------------------------
|
|
setup
|
|
echo "1.4.2" > "$MESH_HOST_STATE_DIR/known-good"
|
|
echo "1.4.2" > "$MESH_HOST_STATE_DIR/rollback-attempted"
|
|
touch "$MESH_HOST_PKG_CACHE/nox-mesh-host-1.4.2-1-x86_64.pkg.tar.zst"
|
|
"$SCRIPT" >/dev/null 2>&1
|
|
check "does not roll back twice" "a second failure is the machine, not the binary" \
|
|
"$([ -f "$MESH_HOST_STATE_DIR/pacman.calls" ] && echo called || echo not-called)" "not-called"
|
|
|
|
# --- nothing to roll back to ---------------------------------------------------------------
|
|
setup
|
|
set +e; "$SCRIPT" >/dev/null 2>&1; RC=$?; set -e
|
|
check "no known-good: does nothing" "a host that never reconciled has no version to return to" \
|
|
"$([ -f "$MESH_HOST_STATE_DIR/pacman.calls" ] && echo called || echo not-called)" "not-called"
|
|
# The exit code is asserted from a real run, not from a literal. An earlier version of this
|
|
# compared "0" to "0" and could not fail — which hid an injected fault that made the script die
|
|
# here instead of returning cleanly.
|
|
check "no known-good: exits zero" "an installation failure is not a rollback failure" "$RC" "0"
|
|
|
|
setup
|
|
printf ' \n' > "$MESH_HOST_STATE_DIR/known-good"
|
|
"$SCRIPT" >/dev/null 2>&1
|
|
check "blank known-good: refuses to guess" "installing nothing and reporting success is the fault this prevents" \
|
|
"$([ -f "$MESH_HOST_STATE_DIR/pacman.calls" ] && echo called || echo not-called)" "not-called"
|
|
|
|
# --- the cache was cleaned ------------------------------------------------------------------
|
|
setup
|
|
echo "1.4.2" > "$MESH_HOST_STATE_DIR/known-good"
|
|
set +e; "$SCRIPT" >/dev/null 2>&1; RC=$?; set -e
|
|
check "missing package: fails loudly" "cannot roll back, and says so rather than reporting success" "$RC" "1"
|
|
|
|
# --- the package manager refuses -------------------------------------------------------------
|
|
setup
|
|
echo "1.4.2" > "$MESH_HOST_STATE_DIR/known-good"
|
|
touch "$MESH_HOST_PKG_CACHE/nox-mesh-host-1.4.2-1-x86_64.pkg.tar.zst"
|
|
STUB_PACMAN_FAILS=1 ; export STUB_PACMAN_FAILS
|
|
set +e; "$SCRIPT" >/dev/null 2>&1; RC=$?; set -e
|
|
check "pacman fails: exits non-zero" "a failed rollback is a failure the launcher must see" "$RC" "1"
|
|
|
|
printf '\nrollback: %d passed, %d failed\n' "$PASS" "$FAIL"
|
|
[ "$FAIL" -eq 0 ]
|