Files
felhom.eu/hub/internal/store/pragma_test.go
T
admin 0fc54e0122
gates / gates (push) Successful in 7s
hub v0.88.0 — the WAL that never was (R-172)
store.New opened the DB with `?_journal_mode=WAL&_busy_timeout=5000`, which is
mattn/go-sqlite3 syntax. The driver is modernc.org/sqlite, whose applyQueryParams
reads only _pragma/_time_format/_time_integer_format/_txlock/_inttotime and
IGNORES anything else WITHOUT AN ERROR. So the hub ran in rollback-journal mode
with busy_timeout=0 for its entire life while its own source said otherwise.

Surfaced as a false HOST STALE banner: in rollback-journal mode a reader excludes
a writer, so rendering an operator page blocks a host report; the hub 500s, the
agent waits its full 15-minute interval without retrying, and staleness fires at
30 minutes — two collisions is a false alarm plus an operator email. 13 collisions
in one pod lifetime; the alarm fired twice on 2026-08-02 for a host that was up
two days and reconciling throughout.

The observable that proved it: a 128 MB /data/hub.db with no -wal/-shm beside it
while the DB was open.

Fix: ?_pragma=journal_mode(WAL)&_pragma=busy_timeout(5000)&_txlock=immediate.
_txlock=immediate is not optional — database/sql's Begin() is DEFERRED, so a
read-then-write tx must upgrade its lock and a failed upgrade is
SQLITE_BUSY_SNAPSHOT, which busy_timeout does NOT retry; this store has 10+
db.Begin() sites and they are all write paths.

Every test asserts what the DATABASE reports, never the DSN string — a string
test would have passed for the whole life of the bug. Red-proof: restoring the
shipped DSN reproduces journal_mode="delete", the missing -wal, and the live
"database is locked (5) (SQLITE_BUSY)".

Operational consequence handled: a WAL DB cannot be copied by taking hub.db
alone — a bare `cat` opens cleanly and silently omits the newest writes. The
break-glass retrieval in operations/nodes.md used exactly that; it and the
recovery-inventory note are now WAL-aware.
2026-08-02 21:06:29 +02:00

231 lines
8.0 KiB
Go

package store
import (
"database/sql"
"io"
"log"
"os"
"path/filepath"
"sync"
"testing"
"time"
)
// R-172 — the connection pragmas must actually be APPLIED, not merely requested.
//
// THE DEFECT THESE PIN. The DSN read `?_journal_mode=WAL&_busy_timeout=5000` — mattn/go-sqlite3
// syntax — while the driver is modernc.org/sqlite, which ignores unknown parameters WITHOUT AN
// ERROR. The hub therefore ran in rollback-journal mode with busy_timeout=0 for its entire life,
// and nothing said so. Any test that asserted the DSN STRING would have passed throughout.
//
// So every assertion below reads the value back from the DATABASE.
// newPragmaStore is a sibling of host_test.go's newTestStore that also returns the DB PATH, because
// two of the checks below are about the files SQLite creates beside it.
func newPragmaStore(t *testing.T) (*Store, string) {
t.Helper()
path := filepath.Join(t.TempDir(), "hub.db")
s, err := New(path, log.New(io.Discard, "", 0))
if err != nil {
t.Fatalf("New: %v", err)
}
t.Cleanup(func() { s.Close() })
return s, path
}
func TestStorePragmasAreActuallyApplied(t *testing.T) {
// RED-PROOF: restore the old DSN (`?_journal_mode=WAL&_busy_timeout=5000`) and this fails with
// journal_mode=delete, busy_timeout=0 — i.e. it reproduces the shipped bug exactly.
// Demonstrated in hub REPORT.md.
s, _ := newPragmaStore(t)
var journal string
if err := s.db.QueryRow("PRAGMA journal_mode").Scan(&journal); err != nil {
t.Fatalf("read journal_mode: %v", err)
}
if journal != "wal" {
t.Fatalf("journal_mode = %q, want \"wal\" — in rollback-journal mode a reader blocks a writer, "+
"so rendering an operator page can 500 a host report (R-172)", journal)
}
var busy int
if err := s.db.QueryRow("PRAGMA busy_timeout").Scan(&busy); err != nil {
t.Fatalf("read busy_timeout: %v", err)
}
if busy < 5000 {
t.Fatalf("busy_timeout = %d, want >= 5000 — without it SQLite returns SQLITE_BUSY immediately "+
"instead of waiting, and the hub turns that into an HTTP 500", busy)
}
}
func TestStoreWALFilesExistWhileOpen(t *testing.T) {
// The on-disk observable that EXPOSED the bug in production, pinned as a test: in WAL mode the
// `-wal` and `-shm` files must exist beside an open database. Their absence on the live hub is
// what proved the pragma was never applied, so it is the check to keep.
s, path := newPragmaStore(t)
// A write guarantees the WAL is materialised rather than merely configured.
if _, err := s.db.Exec(`CREATE TABLE IF NOT EXISTS r172_probe (k TEXT)`); err != nil {
t.Fatalf("probe write: %v", err)
}
if _, err := s.db.Exec(`INSERT INTO r172_probe (k) VALUES ('x')`); err != nil {
t.Fatalf("probe insert: %v", err)
}
for _, suffix := range []string{"-wal", "-shm"} {
if _, err := os.Stat(path + suffix); err != nil {
t.Fatalf("%s is missing beside an OPEN database (%v) — this is exactly the signature that "+
"proved the live hub was NOT in WAL mode", filepath.Base(path+suffix), err)
}
}
}
func TestStoreReaderDoesNotBlockWriter(t *testing.T) {
// THE CONSEQUENCE, not the mechanism. A held READ transaction — what rendering an operator page
// does — must not make a concurrent write fail. In rollback-journal mode it does, and that is the
// whole of R-172: `Failed to save host-report …: database is locked (5) (SQLITE_BUSY)`.
s, _ := newPragmaStore(t)
if _, err := s.db.Exec(`CREATE TABLE IF NOT EXISTS r172_probe (k TEXT)`); err != nil {
t.Fatalf("setup: %v", err)
}
if _, err := s.db.Exec(`INSERT INTO r172_probe (k) VALUES ('seed')`); err != nil {
t.Fatalf("seed: %v", err)
}
// Hold a read open for the whole write.
rows, err := s.db.Query(`SELECT k FROM r172_probe`)
if err != nil {
t.Fatalf("open read: %v", err)
}
defer rows.Close()
if !rows.Next() {
t.Fatal("expected a seeded row")
}
done := make(chan error, 1)
go func() {
_, err := s.db.Exec(`INSERT INTO r172_probe (k) VALUES ('concurrent')`)
done <- err
}()
select {
case err := <-done:
if err != nil {
t.Fatalf("a write FAILED while a read was open: %v — this is the live 500 (R-172)", err)
}
case <-time.After(15 * time.Second):
t.Fatal("a write BLOCKED indefinitely while a read was open")
}
}
func TestStoreConcurrentWritersDoNotReturnBusy(t *testing.T) {
// Writers still serialise under WAL; busy_timeout is what turns that into a WAIT rather than an
// error. Several concurrent writers must all succeed — the host report, the event save and a UI
// action genuinely do overlap on this hub.
s, _ := newPragmaStore(t)
if _, err := s.db.Exec(`CREATE TABLE IF NOT EXISTS r172_probe (k TEXT)`); err != nil {
t.Fatalf("setup: %v", err)
}
const writers = 8
var wg sync.WaitGroup
errs := make(chan error, writers)
for i := 0; i < writers; i++ {
wg.Add(1)
go func() {
defer wg.Done()
if _, err := s.db.Exec(`INSERT INTO r172_probe (k) VALUES ('w')`); err != nil {
errs <- err
}
}()
}
wg.Wait()
close(errs)
for err := range errs {
t.Fatalf("a concurrent writer returned an error instead of waiting: %v", err)
}
}
func TestStoreTransactionUpgradeDoesNotReturnBusySnapshot(t *testing.T) {
// `_txlock=immediate` is the parameter that is easy to leave out, and WAL + busy_timeout alone
// would not cover this. With a DEFERRED transaction (database/sql's default), a tx that reads and
// then writes must upgrade its lock, and a failed upgrade is SQLITE_BUSY_SNAPSHOT — which
// busy_timeout does NOT retry. This store has 10+ db.Begin() sites and they are all write paths.
//
// RED-PROOF: drop `&_txlock=immediate` from sqliteDSNParams and this test becomes able to fail
// (it is inherently racy without it, which is precisely the point — an un-retryable error that
// appears only under contention is the worst kind to ship). Demonstrated in hub REPORT.md.
s, _ := newPragmaStore(t)
if _, err := s.db.Exec(`CREATE TABLE IF NOT EXISTS r172_probe (k TEXT)`); err != nil {
t.Fatalf("setup: %v", err)
}
if _, err := s.db.Exec(`INSERT INTO r172_probe (k) VALUES ('seed')`); err != nil {
t.Fatalf("seed: %v", err)
}
// Two read-then-write transactions racing is the upgrade shape.
const txs = 6
var wg sync.WaitGroup
errs := make(chan error, txs)
for i := 0; i < txs; i++ {
wg.Add(1)
go func() {
defer wg.Done()
tx, err := s.db.Begin()
if err != nil {
errs <- err
return
}
var n int
if err := tx.QueryRow(`SELECT COUNT(*) FROM r172_probe`).Scan(&n); err != nil {
tx.Rollback()
errs <- err
return
}
if _, err := tx.Exec(`INSERT INTO r172_probe (k) VALUES ('tx')`); err != nil {
tx.Rollback()
errs <- err
return
}
if err := tx.Commit(); err != nil {
errs <- err
}
}()
}
wg.Wait()
close(errs)
for err := range errs {
t.Fatalf("a read-then-write transaction failed under contention: %v — this is the "+
"SQLITE_BUSY_SNAPSHOT that busy_timeout cannot retry, and _txlock=immediate prevents", err)
}
}
// TestSQLiteDriverIgnoresMattnStyleParams is the regression guard for the ROOT CAUSE, not the symptom.
//
// It documents, executably, that the old DSN syntax is silently ignored by this driver — so anyone
// who "tidies" the pragmas back to the more familiar mattn form gets a failing test instead of a
// hub that quietly reverts to rollback-journal mode for another few months.
func TestSQLiteDriverIgnoresMattnStyleParams(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "mattnstyle.db")
db, err := sql.Open("sqlite", path+"?_journal_mode=WAL&_busy_timeout=5000")
if err != nil {
t.Fatalf("open: %v", err)
}
defer db.Close()
var journal string
if err := db.QueryRow("PRAGMA journal_mode").Scan(&journal); err != nil {
t.Fatalf("read journal_mode: %v", err)
}
if journal == "wal" {
t.Skip("this driver now honours mattn-style parameters — the R-172 trap is gone; simplify " +
"sqliteDSNParams and delete this test")
}
if journal != "delete" {
t.Fatalf("journal_mode = %q, expected the driver to IGNORE the mattn-style parameter and leave "+
"the default; if this changed, re-read sqliteDSNParams", journal)
}
}