jcoffey-dev
7e04351b0f
Two changes that arrived together: the cutover phase (ARCHITECTURE.md 4.5) is implemented, and the rollback phase is deleted. Recovery from a failed migration is now explicitly the operator's own snapshot or backup, and out of scope for this tool. internal/cutover implements 4.5 as seven checkpointed steps: verify the staged binary's version, install it, preserve and rewrite the service definition, reload, start, wait for a healthy JMAP session, recalculate quotas. The unit is rewritten in place rather than generated from a template. An operator's unit carries hardening options, limits and dependencies this tool has no business having an opinion about, and regenerating it would silently drop them. It repoints ExecStart (preserving systemd's -@:+! prefix characters and every argument after the executable), updates --config, and strips recovery-mode Environment lines - leaving STALWART_RECOVERY_MODE=1 set would recovery-boot the service on every restart, forever. It refuses on a unit with no ExecStart, and on an Environment line mixing a recovery variable with others: a line it only partly understands is one it must not edit. Quota recalculation is the one step allowed to fail without failing the phase. Its wire format is grounded in Stalwart's x:Task schema reference - Task/set creating one AccountMaintenance per account with maintenanceType recalculateQuota - but the upgrade guide only documents the WebUI path, so two details remain inferred and are called out in stalwartapi/task.go: whether the schema's "read-only" annotation on accountId/maintenanceType means "immutable after creation", and whether a finished task simply leaves the queue (TaskStatus documents Pending/Retry/Failed with no success state). Warning rather than failing is the honest response to that uncertainty, and stale counters are an accounting problem next to calling for a restore of a machine that is otherwise migrated and serving mail. Docker deployments are refused outright: cutting a container over means pulling an image and recreating it, not swapping a binary. On removing rollback. The implementation worked and was tested, and it was removed because restoring bytes correctly is not the hard part. It copied file contents and permissions and verified every restored file against a manifest - and did not preserve ownership. Run as root, as this tool requires, it would have produced a byte-perfect, checksum-verified, root-owned data directory that Stalwart, running as its own user, could not open, and it would have reported success. The PostgreSQL path was worse: pg_dump without --clean emits CREATE TABLE + COPY, which fails replaying into a database whose tables still exist, and the ON_ERROR_STOP=1 added so a half-applied restore couldn't be reported as success turned that into a hard failure. None of it had ever run against a real server. A filesystem snapshot has none of these failure modes, because it never lost the metadata to begin with. So cutover's gate is no longer rollback.CanRollBack but an explicit RecoveryPointConfirmed acknowledgement. That is an assertion, not a check - this tool cannot verify someone else's snapshot - and its only value is that nobody migrates a production mail server having never been asked the question. Two consequences are accepted deliberately: restoring any pre-migration recovery point discards mail delivered since, and a failed migration now stops and reports rather than undoing itself. What the tool still does to make a manual restore easier: the old binary is preserved and never deleted, the original service definition is preserved before the rewrite, the settings and principals dumps stay on disk, and every artifact path and checksum stays in the checkpoint where `status <run-id>` can print it. Also removed: the `confirm` command stub and RollbackWindowClosed, whose only purpose was closing a rollback window that no longer exists, and checkpoint.PhaseRollback. Old state.json files still load - JSON ignores the now-unknown field. Still open, and recorded in 8: cutover ignores systemd drop-ins, so an ExecStart or Environment override in stalwart.service.d/*.conf is invisible to the rewrite - including the recovery variable it exists to strip; nothing prevents concurrent runs on the same run-id; and nothing in this repo has ever run against a real Stalwart, real systemd, or a real store.
128 lines
4.3 KiB
Go
128 lines
4.3 KiB
Go
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)
|
|
}
|
|
}
|