Skip to content

fix: routinely ping agent websocket to ensure liveness #5824

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 4 commits into from
Jan 23, 2023
Merged

fix: routinely ping agent websocket to ensure liveness #5824

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
03f0745
fix: routinely ping agent websocket to ensure liveness
coadler Jan 23, 2023
4f01023
add comment
coadler Jan 23, 2023
a56c9f1
fixup! add comment
coadler Jan 23, 2023
a72fc72
use `websocket.StatusGoingAway`
coadler Jan 23, 2023
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
3 changes: 3 additions & 0 deletions agent/agent.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -430,6 +430,9 @@ func (a *agent) createTailnet(ctx context.Context, derpMap *tailcfg.DERPMap) (_
// runCoordinator runs a coordinator and returns whether a reconnect
// should occur.
func (a *agent) runCoordinator(ctx context.Context, network *tailnet.Conn) error {
ctx, cancel := context.WithCancel(ctx)
defer cancel()

coordinator, err := a.client.ListenWorkspaceAgent(ctx)
if err != nil {
return err
Expand Down
1 change: 1 addition & 0 deletions cli/agent.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,7 @@ func workspaceAgent() *cobra.Command {
slog.F("version", version),
)
client := codersdk.New(coderURL)
client.Logger = logger
// Set a reasonable timeout so requests can't hang forever!
client.HTTPClient.Timeout = 10 * time.Second

Expand Down
36 changes: 36 additions & 0 deletions codersdk/workspaceagents.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -340,6 +340,42 @@ func (c *Client) ListenWorkspaceAgent(ctx context.Context) (net.Conn, error) {
return nil, readBodyAsError(res)
}

// Ping once every 30 seconds to ensure that the websocket is alive. If we
// don't get a response within 30s we kill the websocket and reconnect.
// See: https://github.com/coder/coder/pull/5824
go func() {
tick := 30 * time.Second
ticker := time.NewTicker(tick)
defer ticker.Stop()
defer func() {
c.Logger.Debug(ctx, "coordinate pinger exited")
}()
for {
select {
case <-ctx.Done():
return
case start := <-ticker.C:
ctx, cancel := context.WithTimeout(ctx, tick)

err := conn.Ping(ctx)
if err != nil {
c.Logger.Error(ctx, "workspace agent coordinate ping", slog.Error(err))

err := conn.Close(websocket.StatusGoingAway, "Ping failed")
if err != nil {
c.Logger.Error(ctx, "close workspace agent coordinate websocket", slog.Error(err))
}

cancel()
return
}

c.Logger.Debug(ctx, "got coordinate pong", slog.F("took", time.Since(start)))
cancel()
}
}
}()

return websocket.NetConn(ctx, conn, websocket.MessageBinary), nil
}

Expand Down
6 changes: 2 additions & 4 deletions provisionerd/provisionerd_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,9 +12,6 @@ import (
"testing"
"time"

"github.com/coder/coder/provisionerd/runner"
"github.com/coder/coder/testutil"

"github.com/hashicorp/yamux"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
Expand All @@ -26,11 +23,12 @@ import (

"cdr.dev/slog"
"cdr.dev/slog/sloggers/slogtest"

"github.com/coder/coder/provisionerd"
"github.com/coder/coder/provisionerd/proto"
"github.com/coder/coder/provisionerd/runner"
"github.com/coder/coder/provisionersdk"
sdkproto "github.com/coder/coder/provisionersdk/proto"
"github.com/coder/coder/testutil"
)

func TestMain(m *testing.M) {
Expand Down