Files
stalwart-migrator/internal/cutover/unit_test.go
T
jcoffey-dev 9faa21f4f1 Fix the three defects that cost a production restore
A live migration on 2026-08-24 stopped a production mail server and then
discovered the host's stalwart-cli was 0.13.4 - present, but from when the
CLI shipped with the server, with no `apply` command. The migration needs
v1.0.2+ from the separately-versioned stalwartlabs/cli repository.

Recovery was closed in both directions. v0.16's recovery-mode boot had
already bumped the store schema to v6, so the 0.15.5 binary refused to
reopen it ("expected 5 or below, found 6"). Going forward needed
export.json, which this tool's own failure path had deleted - and
regenerating it required a settings dump from a live v0.15 instance that
could no longer start. The operator restored a day-old snapshot and lost a
day of mail across nine domains.

Three fixes:

1. preflight.CheckExternalTools verifies stalwart-cli exists and is v1.0.2
   or later, and that python3 runs - before anything is touched. Every fact
   needed to prevent this was available in under a second from a stopped
   state. Skipped for a patch upgrade, which invokes neither tool.

2. A failed run no longer deletes its work directory. Cleaning up on every
   exit path was right for a sandboxed rehearsal and catastrophic here:
   once the service is stopped the settings dump cannot be regenerated, so
   deleting it removes the only way forward. The failure now prints the
   resume command instead.

3. `run --resume <id>` continues an interrupted run. The checkpoint
   machinery existed but never engaged, because run created a new run every
   invocation - so a retry re-ran preflight against a binary already moved
   aside, and failed. Completed steps are skipped from the checkpoint.

Proven against a VM built to match the failure: stalwart-cli 0.15.5,
accounts and mail seeded.

  * preflight refused, service still active, mail still accepted
  * a stub CLI passing --version and failing apply left the run stopped
    with all eight inputs intact and the resume command printed
  * --resume carried it to a clean finish: five seconds of downtime,
    listeners regenerated, admin role restored, quotas rebuilt

That failure-path test is the one that should have run before production.
Every earlier test had stalwart-cli installed from the start, and the one
failure I did exercise happened to leave its artifacts behind.
2026-08-23 23:20:47 -07:00

168 lines
5.9 KiB
Go

// SPDX-FileCopyrightText: 2026 LINUXexpert-org
// SPDX-License-Identifier: GPL-3.0-or-later
package cutover
import (
"strings"
"testing"
)
const realisticUnit = `[Unit]
Description=Stalwart Mail Server
After=network.target
[Service]
Type=simple
User=stalwart
ExecStart=/usr/local/bin/stalwart --config /etc/stalwart/config.toml
Restart=on-failure
LimitNOFILE=65536
ProtectSystem=strict
ReadWritePaths=/var/lib/stalwart
[Install]
WantedBy=multi-user.target
`
func TestRewriteUnitRepointsExecStart(t *testing.T) {
got, err := RewriteUnit(realisticUnit, "/usr/local/bin/stalwart", "/etc/stalwart/config.json")
if err != nil {
t.Fatal(err)
}
if !strings.Contains(got, "ExecStart=/usr/local/bin/stalwart --config /etc/stalwart/config.json") {
t.Errorf("ExecStart not repointed:\n%s", got)
}
}
// The operator's unit is theirs: hardening options, limits and paths this
// tool has no opinion about must survive untouched.
func TestRewriteUnitPreservesEverythingElse(t *testing.T) {
got, err := RewriteUnit(realisticUnit, "/opt/stalwart/bin/stalwart", "")
if err != nil {
t.Fatal(err)
}
for _, want := range []string{
"Description=Stalwart Mail Server", "User=stalwart", "Restart=on-failure",
"LimitNOFILE=65536", "ProtectSystem=strict", "ReadWritePaths=/var/lib/stalwart",
"WantedBy=multi-user.target",
} {
if !strings.Contains(got, want) {
t.Errorf("rewrite dropped %q:\n%s", want, got)
}
}
if !strings.Contains(got, "ExecStart=/opt/stalwart/bin/stalwart --config /etc/stalwart/config.toml") {
t.Errorf("existing --config should be preserved when no new one is given:\n%s", got)
}
}
func TestRewriteUnitAddsConfigWhenTheUnitHasNone(t *testing.T) {
got, err := RewriteUnit("[Service]\nExecStart=/usr/local/bin/stalwart\n", "/usr/local/bin/stalwart", "/etc/stalwart/config.json")
if err != nil {
t.Fatal(err)
}
if !strings.Contains(got, "ExecStart=/usr/local/bin/stalwart --config /etc/stalwart/config.json") {
t.Errorf("--config not added:\n%s", got)
}
}
func TestRewriteUnitKeepsSystemdExecPrefixes(t *testing.T) {
got, err := RewriteUnit("[Service]\nExecStart=-@/old/stalwart --config /c\n", "/new/stalwart", "")
if err != nil {
t.Fatal(err)
}
if !strings.Contains(got, "ExecStart=-@/new/stalwart --config /c") {
t.Errorf("systemd exec prefix characters were dropped, changing what the unit means:\n%s", got)
}
}
// Leaving STALWART_RECOVERY_MODE=1 in the unit is the documented footgun
// from §4.5: the service would recovery-boot on every restart, forever.
func TestRewriteUnitStripsRecoveryEnvironmentLines(t *testing.T) {
unit := `[Service]
Environment=STALWART_RECOVERY_MODE=1
Environment="STALWART_RECOVERY_ADMIN=admin:hunter2"
Environment=RUST_LOG=info
ExecStart=/usr/local/bin/stalwart
`
got, err := RewriteUnit(unit, "/usr/local/bin/stalwart", "")
if err != nil {
t.Fatal(err)
}
for _, gone := range []string{"STALWART_RECOVERY_MODE", "STALWART_RECOVERY_ADMIN"} {
if strings.Contains(got, gone) {
t.Errorf("%s survived the rewrite - the service would recovery-boot on every restart:\n%s", gone, got)
}
}
if !strings.Contains(got, "Environment=RUST_LOG=info") {
t.Errorf("unrelated Environment line was dropped:\n%s", got)
}
}
// A line this tool only partly understands is one it must not edit.
func TestRewriteUnitRefusesAMixedEnvironmentLine(t *testing.T) {
unit := "[Service]\nEnvironment=RUST_LOG=info STALWART_RECOVERY_MODE=1\nExecStart=/usr/local/bin/stalwart\n"
_, err := RewriteUnit(unit, "/usr/local/bin/stalwart", "")
if err == nil {
t.Fatal("want refusal for an Environment line mixing recovery and other variables, got nil")
}
if !strings.Contains(err.Error(), "by hand") {
t.Errorf("error %q should tell the operator what to do about it", err)
}
}
func TestRewriteUnitRefusesAUnitWithNoExecStart(t *testing.T) {
_, err := RewriteUnit("[Unit]\nDescription=Something else entirely\n", "/usr/local/bin/stalwart", "")
if err == nil {
t.Fatal("want refusal for a unit with no ExecStart, got nil")
}
if !strings.Contains(err.Error(), "right unit file") {
t.Errorf("error %q should question whether this is the right file", err)
}
}
func TestRewriteUnitHandlesMultipleExecStartLines(t *testing.T) {
unit := "[Service]\nExecStart=\nExecStart=/old/stalwart --config /c\n"
got, err := RewriteUnit(unit, "/new/stalwart", "")
if err == nil {
t.Fatalf("an empty ExecStart= names no executable and should be refused, got:\n%s", got)
}
}
// A real production unit writes ExecStart=... --config=/path. Only matching
// the separated "--config /path" form appended a second flag, leaving the
// service started with two configs and using the v0.15 one - which v0.16
// cannot read as a store descriptor. Found while preparing a live
// migration, before it ran.
func TestRewriteUnitReplacesTheEqualsFormConfig(t *testing.T) {
unit := "[Service]\nExecStart=/opt/stalwart/bin/stalwart --config=/opt/stalwart/etc/config.toml\n"
got, err := RewriteUnit(unit, "/opt/stalwart/bin/stalwart", "/opt/stalwart/etc/config.json")
if err != nil {
t.Fatal(err)
}
if strings.Count(got, "--config") != 1 {
t.Errorf("expected exactly one --config argument, got:\n%s", got)
}
if !strings.Contains(got, "--config=/opt/stalwart/etc/config.json") {
t.Errorf("equals-form config not replaced:\n%s", got)
}
if strings.Contains(got, "config.toml") {
t.Errorf("the old config path survived:\n%s", got)
}
}
// The separated form must keep working; both spellings are real.
func TestRewriteUnitReplacesTheSeparatedFormConfig(t *testing.T) {
unit := "[Service]\nExecStart=/usr/local/bin/stalwart --config /etc/stalwart/config.toml\n"
got, err := RewriteUnit(unit, "/usr/local/bin/stalwart", "/etc/stalwart/config.json")
if err != nil {
t.Fatal(err)
}
if strings.Count(got, "--config") != 1 {
t.Errorf("expected exactly one --config argument, got:\n%s", got)
}
if !strings.Contains(got, "--config /etc/stalwart/config.json") {
t.Errorf("separated-form config not replaced:\n%s", got)
}
}