fix(server): shut down through fx so buffered reports flush (closes #22)
check / check (push) Failing after 0s
check / check (push) Failing after 0s
The server ran os.Exit at the end of its own goroutine, which raced fx's teardown and could kill the process before reportbuf's OnStop flushed the buffer — losing up to a full flush window of telemetry on every restart, silently and with exit 0. The server now requests shutdown through fx.Shutdowner, so fx runs every OnStop in dependency order. The http.Server is built synchronously in OnStart before the serving goroutine starts, so shutdown can no longer race or nil-deref it; the field is never written and read from two goroutines without a happens-before edge. A listen failure now exits non-zero via fx.ExitCode(1). reportbuf's OnStop is guarded by sync.Once. writeTimeout now exceeds the chi per-request budget, with a comment, so that budget is reachable. Dead startupTime, exitCode, and cancelFunc fields are gone. A new test buffers a report and asserts it reaches disk after the fx lifecycle stops. Model: opus-4-8
This commit is contained in:
@@ -1,13 +1,77 @@
|
||||
package reportbuf_test
|
||||
|
||||
import (
|
||||
"os"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
_ "sneak.berlin/go/netwatch/internal/reportbuf"
|
||||
"sneak.berlin/go/netwatch/internal/config"
|
||||
"sneak.berlin/go/netwatch/internal/globals"
|
||||
"sneak.berlin/go/netwatch/internal/logger"
|
||||
"sneak.berlin/go/netwatch/internal/reportbuf"
|
||||
|
||||
"go.uber.org/fx"
|
||||
"go.uber.org/fx/fxtest"
|
||||
)
|
||||
|
||||
func TestImport(t *testing.T) {
|
||||
t.Parallel()
|
||||
// Compilation check — verifies the package parses
|
||||
// and all imports resolve.
|
||||
// TestFlushOnShutdown proves the flush-on-shutdown path: a
|
||||
// report appended after start but before the periodic flush
|
||||
// window must reach disk when the fx lifecycle stops. This is
|
||||
// the exact case that silent data loss on restart used to
|
||||
// destroy.
|
||||
func TestFlushOnShutdown(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
t.Setenv("DATA_DIR", dir)
|
||||
|
||||
var buf *reportbuf.Buffer
|
||||
|
||||
app := fxtest.New(t,
|
||||
fx.Provide(
|
||||
globals.New,
|
||||
logger.New,
|
||||
config.New,
|
||||
reportbuf.New,
|
||||
),
|
||||
fx.Populate(&buf),
|
||||
)
|
||||
|
||||
app.RequireStart()
|
||||
|
||||
err := buf.Append(map[string]string{"probe": "shutdown"})
|
||||
if err != nil {
|
||||
t.Fatalf("append report: %v", err)
|
||||
}
|
||||
|
||||
// RequireStop runs the reportbuf OnStop hook, which is the
|
||||
// only code path that flushes buffered reports on shutdown.
|
||||
app.RequireStop()
|
||||
|
||||
if !hasReportFile(t, dir) {
|
||||
t.Fatal("no report file on disk after shutdown; " +
|
||||
"the buffered report was lost")
|
||||
}
|
||||
}
|
||||
|
||||
func hasReportFile(t *testing.T, dir string) bool {
|
||||
t.Helper()
|
||||
|
||||
entries, err := os.ReadDir(dir)
|
||||
if err != nil {
|
||||
t.Fatalf("read data dir: %v", err)
|
||||
}
|
||||
|
||||
for _, e := range entries {
|
||||
if strings.HasSuffix(e.Name(), ".jsonl.zst") {
|
||||
info, statErr := e.Info()
|
||||
if statErr != nil {
|
||||
t.Fatalf("stat %s: %v", e.Name(), statErr)
|
||||
}
|
||||
|
||||
if info.Size() > 0 {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user