fix: fix graceful disconnect in DialWorkspaceAgent #11993
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,106 @@ | ||
| package codersdk | ||
|
|
||
| import ( | ||
| "context" | ||
| "io" | ||
| "net/http" | ||
| "net/http/httptest" | ||
| "sync/atomic" | ||
| "testing" | ||
| "time" | ||
|
|
||
| "github.com/google/uuid" | ||
| "github.com/stretchr/testify/assert" | ||
| "github.com/stretchr/testify/require" | ||
| "nhooyr.io/websocket" | ||
| "tailscale.com/tailcfg" | ||
|
|
||
| "cdr.dev/slog" | ||
| "cdr.dev/slog/sloggers/slogtest" | ||
| "github.com/coder/coder/v2/tailnet" | ||
| "github.com/coder/coder/v2/tailnet/proto" | ||
| "github.com/coder/coder/v2/tailnet/tailnettest" | ||
| "github.com/coder/coder/v2/testutil" | ||
| ) | ||
|
|
||
| func TestTailnetAPIConnector_Disconnects(t *testing.T) { | ||
| t.Parallel() | ||
| testCtx := testutil.Context(t, testutil.WaitShort) | ||
| ctx, cancel := context.WithCancel(testCtx) | ||
| logger := slogtest.Make(t, &slogtest.Options{ | ||
| // we get EOF when we simulate a DERPMap error | ||
| IgnoredErrorIs: append(slogtest.DefaultIgnoredErrorIs, io.EOF), | ||
| }).Leveled(slog.LevelDebug) | ||
| agentID := uuid.UUID{0x55} | ||
| clientID := uuid.UUID{0x66} | ||
| fCoord := tailnettest.NewFakeCoordinator() | ||
| var coord tailnet.Coordinator = fCoord | ||
| coordPtr := atomic.Pointer[tailnet.Coordinator]{} | ||
| coordPtr.Store(&coord) | ||
| derpMapCh := make(chan *tailcfg.DERPMap) | ||
| defer close(derpMapCh) | ||
| svc, err := tailnet.NewClientService( | ||
| logger, &coordPtr, | ||
| time.Millisecond, func() *tailcfg.DERPMap { return <-derpMapCh }, | ||
| ) | ||
| require.NoError(t, err) | ||
|
|
||
| svr := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { | ||
| sws, err := websocket.Accept(w, r, nil) | ||
| if !assert.NoError(t, err) { | ||
| return | ||
| } | ||
| ctx, nc := websocketNetConn(r.Context(), sws, websocket.MessageBinary) | ||
| err = svc.ServeConnV2(ctx, nc, tailnet.StreamID{ | ||
| Name: "client", | ||
| ID: clientID, | ||
| Auth: tailnet.ClientTunnelAuth{AgentID: agentID}, | ||
| }) | ||
| assert.NoError(t, err) | ||
| })) | ||
|
|
||
| fConn := newFakeTailnetConn() | ||
|
|
||
| uut := runTailnetAPIConnector(ctx, logger, agentID, svr.URL, &websocket.DialOptions{}, fConn) | ||
|
|
||
| call := testutil.RequireRecvCtx(ctx, t, fCoord.CoordinateCalls) | ||
| reqTun := testutil.RequireRecvCtx(ctx, t, call.Reqs) | ||
| require.NotNil(t, reqTun.AddTunnel) | ||
|
|
||
| _ = testutil.RequireRecvCtx(ctx, t, uut.connected) | ||
|
|
||
| // simulate a problem with DERPMaps by sending nil | ||
| testutil.RequireSendCtx(ctx, t, derpMapCh, nil) | ||
|
|
||
| // this should cause the coordinate call to hang up WITHOUT disconnecting | ||
| reqNil := testutil.RequireRecvCtx(ctx, t, call.Reqs) | ||
| require.Nil(t, reqNil) | ||
|
|
||
| // ...and then reconnect | ||
| call = testutil.RequireRecvCtx(ctx, t, fCoord.CoordinateCalls) | ||
| reqTun = testutil.RequireRecvCtx(ctx, t, call.Reqs) | ||
| require.NotNil(t, reqTun.AddTunnel) | ||
|
|
||
| // canceling the context should trigger the disconnect message | ||
| cancel() | ||
| reqDisc := testutil.RequireRecvCtx(testCtx, t, call.Reqs) | ||
| require.NotNil(t, reqDisc) | ||
| require.NotNil(t, reqDisc.Disconnect) | ||
| } | ||
|
|
||
| type fakeTailnetConn struct{} | ||
|
|
||
| func (*fakeTailnetConn) UpdatePeers([]*proto.CoordinateResponse_PeerUpdate) error { | ||
| // TODO implement me | ||
| panic("implement me") | ||
| } | ||
|
Comment on lines
+93
to
+96
There was a problem hiding this comment. Can we call There was a problem hiding this comment.
changing to |
||
|
|
||
| func (*fakeTailnetConn) SetAllPeersLost() {} | ||
|
|
||
| func (*fakeTailnetConn) SetNodeCallback(func(*tailnet.Node)) {} | ||
|
|
||
| func (*fakeTailnetConn) SetDERPMap(*tailcfg.DERPMap) {} | ||
|
|
||
| func newFakeTailnetConn() *fakeTailnetConn { | ||
| return &fakeTailnetConn{} | ||
| } | ||
|
Comment on lines
+91
to
+106
There was a problem hiding this comment. Should this live in There was a problem hiding this comment. I don't think so, because the |
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(Non-blocking) I figure this is a best-effort situation, but will 1 second be enough? Does this need to be a configurable knob?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it should be plenty, even on a slow connection because we're not waiting for a reply. I definitely don't want to plumb configuration thru.
It is a best effort as you say --- consequence of not doing this is that the agent on the other side will see it as "lost" and possibly still try to handshake with it for up to 15 minutes.