mirror of
https://github.com/coder/coder.git
synced 2026-09-24 15:04:27 +08:00
feat: structured disconnect attribution for agent logs (#25191)
Implements [PLAT-60](https://linear.app/codercom/issue/PLAT-60/enhance-disconnect-logs-with-structured-reason-attribution): adds structured disconnect attribution to disconnect logs throughout the agent and tailnet packages. Every disconnect log site now carries structured slog fields. All existing logs remain; existing messages are preserved with the fields added alongside. New fields on disconnect log lines: - `connect_type` — which layer disconnected: `server_to_agent`, `agent_to_client`, or `client_to_server` - `disconnect_reason` — categorical reason: `graceful`, `network_error`, `server_shutdown`, etc. - `disconnect_expected` — whether the disconnect is normal operation (`true`) or should be investigated (`false`) - `disconnect_initiator` — who started it: `client`, `agent`, `server`, or `network` (control-plane sites only) - `disconnect_detail` — free-form supplemental info (where useful) ## What's covered **Control plane (`server_to_agent`):** coordination RPC, DERP map subscriber, agent runLoop, agent Close, `BasicCoordination.Close`, `Controller.run`. **Data plane (`agent_to_client`):** SSH sessions, reconnecting PTY, JetBrains port-forwarding. <details> <summary>Control-plane sites</summary> | Site | Reason | Initiator | |---|---|---| | `agent/agent.go` `runLoop` EOF | `network_error` | `network` | | `agent/agent.go` `runCoordinator` deferred exit | `server_shutdown` / `graceful` / `network_error` | `agent` / `server` / `network` | | `agent/agent.go` `runDERPMapSubscriber` deferred exit | same (shared `classifyCoordinatorRPCExit`) | same | | `agent/agent.go` `Close` shutdown timeout | `server_shutdown` + detail | `agent` | | `agent/agent.go` `Close` clean coord disconnect | `server_shutdown` | `agent` | | `tailnet/controllers.go` `BasicCoordination.Close` | `graceful` or `network_error` | `c.initiator` | | `tailnet/controllers.go` `Controller.run` `net.ErrClosed` | `network_error` | `network` | </details> <details> <summary>Data-plane sites</summary> | Site | Reason | Notes | |---|---|---| | `agent/agentssh/agentssh.go` SSH session closed | free-form (`graceful`, `process exited with error status: N`, etc.) | Also sets `closeCause("normal exit")` for clean exits so coderd's `connection_log.DisconnectReason` is no longer empty | | `agent/reconnectingpty/server.go` PTY closed | `server_shutdown`, error string, or `graceful` | | | `agent/agentssh/jetbrainstrack.go` channel closed | `normal close` or error string | Previously passed empty reason | </details> <details> <summary>Bug fix</summary> The deferred `disconnected from coordination RPC` log no longer fires when the initial `Coordinate()` RPC call fails before any connection is established. </details> Refs PLAT-60. --- _This PR was prepared by Coder Agents on behalf of @Emyrk._ **Manually QA'd a lot of common disconnects** --------- Co-authored-by: Coder Agents <noreply@coder.com>
This commit is contained in:
co-authored by
Coder Agents
parent
c9c933a300
commit
1afc6d4fd0
@@ -462,17 +462,23 @@ func (s *Server) sessionHandler(session ssh.Session) {
|
||||
logger.Warn(ctx, "invalid magic ssh session type specified", slog.F("raw_type", magicTypeRaw))
|
||||
}
|
||||
|
||||
closeCause := func(string) {}
|
||||
closeCause := func(_ string) {}
|
||||
if reportSession {
|
||||
var reason string
|
||||
closeCause = func(r string) { reason = r }
|
||||
var reason codersdk.DisconnectReason
|
||||
closeCause = func(r string) { reason = codersdk.DisconnectReason(r) }
|
||||
|
||||
scr := &sessionCloseTracker{Session: session}
|
||||
session = scr
|
||||
|
||||
disconnected := s.config.ReportConnection(id, magicType, remoteAddrString)
|
||||
defer func() {
|
||||
disconnected(scr.exitCode(), reason)
|
||||
logger.Info(ctx, "ssh session closed",
|
||||
codersdk.ConnectionDirectionAgentToClient.SlogField(),
|
||||
reason.SlogField(),
|
||||
reason.SlogExpectedField(),
|
||||
slog.F("exit_code", scr.exitCode()),
|
||||
)
|
||||
disconnected(scr.exitCode(), string(reason))
|
||||
}()
|
||||
}
|
||||
|
||||
@@ -567,6 +573,7 @@ func (s *Server) sessionHandler(session ssh.Session) {
|
||||
_ = session.Exit(MagicSessionErrorCode)
|
||||
return
|
||||
}
|
||||
closeCause(string(codersdk.DisconnectReasonGraceful))
|
||||
logger.Info(ctx, "normal ssh session exit")
|
||||
_ = session.Exit(0)
|
||||
}
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
gossh "golang.org/x/crypto/ssh"
|
||||
|
||||
"cdr.dev/slog/v3"
|
||||
"github.com/coder/coder/v2/codersdk"
|
||||
)
|
||||
|
||||
// localForwardChannelData is copied from the ssh package.
|
||||
@@ -85,9 +86,13 @@ func (w *JetbrainsChannelWatcher) Accept() (gossh.Channel, <-chan *gossh.Request
|
||||
Channel: c,
|
||||
done: func() {
|
||||
w.jetbrainsCounter.Add(-1)
|
||||
disconnected(0, "")
|
||||
disconnected(0, "normal close")
|
||||
// nolint: gocritic // JetBrains is a proper noun and should be capitalized
|
||||
w.logger.Debug(context.Background(), "JetBrains watcher channel closed")
|
||||
w.logger.Debug(context.Background(), "JetBrains channel closed",
|
||||
codersdk.ConnectionDirectionAgentToClient.SlogField(),
|
||||
codersdk.DisconnectReasonGraceful.SlogField(),
|
||||
codersdk.DisconnectReasonGraceful.SlogExpectedField(),
|
||||
)
|
||||
},
|
||||
}, r, err
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user