Skip to content

fix(tailnet): prevent redial after Coord graceful restart #15586

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 19, 2024
Merged

fix(tailnet): prevent redial after Coord graceful restart #15586

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions tailnet/controllers.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1163,10 +1163,17 @@ func (c *Controller) Run(ctx context.Context) {
// Sadly retry doesn't support quartz.Clock yet so this is not
// influenced by the configured clock.
for retrier := retry.New(50*time.Millisecond, 10*time.Second); retrier.Wait(c.ctx); {
// Check the context again before dialing, since `retrier.Wait()` could return true
// if the delay is 0, even if the context was canceled. This ensures we don't redial
// after a graceful shutdown.
if c.ctx.Err() != nil {
return
}

tailnetClients, err := c.Dialer.Dial(c.ctx, c.ResumeTokenCtrl)
if err != nil {
if xerrors.Is(err, context.Canceled) {
continue
if xerrors.Is(err, context.Canceled) || xerrors.Is(err, context.DeadlineExceeded) {
return
}
errF := slog.Error(err)
var sdkErr *codersdk.Error
Expand Down
12 changes: 8 additions & 4 deletions tailnet/controllers_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@ import (

"github.com/google/uuid"
"github.com/hashicorp/yamux"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/mock/gomock"
"golang.org/x/xerrors"
Expand Down Expand Up @@ -1071,6 +1070,7 @@ func TestController_Disconnects(t *testing.T) {
close(call.Resps)

_ = testutil.RequireRecvCtx(testCtx, t, peersLost)
_ = testutil.RequireRecvCtx(testCtx, t, uut.Closed())
}

func TestController_TelemetrySuccess(t *testing.T) {
Expand Down Expand Up @@ -1210,24 +1210,28 @@ type pipeDialer struct {

func (p *pipeDialer) Dial(_ context.Context, _ tailnet.ResumeTokenController) (tailnet.ControlProtocolClients, error) {
s, c := net.Pipe()
p.t.Cleanup(func() {
_ = s.Close()
_ = c.Close()
})
go func() {
err := p.svc.ServeConnV2(p.ctx, s, p.streamID)
p.logger.Debug(p.ctx, "piped tailnet service complete", slog.Error(err))
}()
client, err := tailnet.NewDRPCClient(c, p.logger)
if !assert.NoError(p.t, err) {
if err != nil {
_ = c.Close()
return tailnet.ControlProtocolClients{}, err
}
coord, err := client.Coordinate(context.Background())
if !assert.NoError(p.t, err) {
if err != nil {
_ = c.Close()
return tailnet.ControlProtocolClients{}, err
}

derps := &tailnet.DERPFromDRPCWrapper{}
derps.Client, err = client.StreamDERPMaps(context.Background(), &proto.StreamDERPMapsRequest{})
if !assert.NoError(p.t, err) {
if err != nil {
_ = c.Close()
return tailnet.ControlProtocolClients{}, err
}
Expand Down
Loading