- Notifications
You must be signed in to change notification settings - Fork928
feat(coderd): add prometheus metrics to servertailnet#11988
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.
By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.
Already on GitHub?Sign in to your account
Merged
Uh oh!
There was an error while loading.Please reload this page.
Merged
Changes fromall commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Jump to
Jump to file
Failed to load files.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Diff view
Diff view
There are no files selected for viewing
6 changes: 5 additions & 1 deletioncoderd/coderd.go
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
79 changes: 19 additions & 60 deletionscoderd/database/pubsub/pubsub_test.go
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
54 changes: 53 additions & 1 deletioncoderd/tailnet.go
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 |
|---|---|---|
| @@ -14,6 +14,7 @@ import ( | ||
| "time" | ||
| "github.com/google/uuid" | ||
| "github.com/prometheus/client_golang/prometheus" | ||
| "go.opentelemetry.io/otel/trace" | ||
| "golang.org/x/xerrors" | ||
| "tailscale.com/derp" | ||
| @@ -97,6 +98,18 @@ func NewServerTailnet( | ||
| agentConnectionTimes: map[uuid.UUID]time.Time{}, | ||
| agentTickets: map[uuid.UUID]map[uuid.UUID]struct{}{}, | ||
| transport: tailnetTransport.Clone(), | ||
| connsPerAgent: prometheus.NewGaugeVec(prometheus.GaugeOpts{ | ||
| Namespace: "coder", | ||
| Subsystem: "servertailnet", | ||
| Name: "open_connections", | ||
| Help: "Total number of TCP connections currently open to workspace agents.", | ||
| }, []string{"network"}), | ||
| totalConns: prometheus.NewCounterVec(prometheus.CounterOpts{ | ||
| Namespace: "coder", | ||
| Subsystem: "servertailnet", | ||
| Name: "connections_total", | ||
| Help: "Total number of TCP connections made to workspace agents.", | ||
| }, []string{"network"}), | ||
| } | ||
| tn.transport.DialContext = tn.dialContext | ||
| // These options are mostly just picked at random, and they can likely be | ||
| @@ -170,6 +183,16 @@ func NewServerTailnet( | ||
| return tn, nil | ||
| } | ||
| func (s *ServerTailnet) Describe(descs chan<- *prometheus.Desc) { | ||
| s.connsPerAgent.Describe(descs) | ||
| s.totalConns.Describe(descs) | ||
| } | ||
| func (s *ServerTailnet) Collect(metrics chan<- prometheus.Metric) { | ||
| s.connsPerAgent.Collect(metrics) | ||
| s.totalConns.Collect(metrics) | ||
| } | ||
| func (s *ServerTailnet) expireOldAgents() { | ||
| const ( | ||
| tick = 5 * time.Minute | ||
| @@ -304,6 +327,9 @@ type ServerTailnet struct { | ||
| agentTickets map[uuid.UUID]map[uuid.UUID]struct{} | ||
| transport *http.Transport | ||
| connsPerAgent *prometheus.GaugeVec | ||
| totalConns *prometheus.CounterVec | ||
| } | ||
| func (s *ServerTailnet) ReverseProxy(targetURL, dashboardURL *url.URL, agentID uuid.UUID) *httputil.ReverseProxy { | ||
| @@ -349,7 +375,18 @@ func (s *ServerTailnet) dialContext(ctx context.Context, network, addr string) ( | ||
| return nil, xerrors.Errorf("no agent id attached") | ||
| } | ||
| nc, err := s.DialAgentNetConn(ctx, agentID, network, addr) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| s.connsPerAgent.WithLabelValues("tcp").Inc() | ||
| s.totalConns.WithLabelValues("tcp").Inc() | ||
| return &instrumentedConn{ | ||
| Conn: nc, | ||
| agentID: agentID, | ||
| connsPerAgent: s.connsPerAgent, | ||
| }, nil | ||
| } | ||
| func (s *ServerTailnet) ensureAgent(agentID uuid.UUID) error { | ||
| @@ -455,3 +492,18 @@ func (s *ServerTailnet) Close() error { | ||
| <-s.derpMapUpdaterClosed | ||
| return nil | ||
| } | ||
| type instrumentedConn struct { | ||
| net.Conn | ||
| agentID uuid.UUID | ||
| closeOnce sync.Once | ||
| connsPerAgent *prometheus.GaugeVec | ||
| } | ||
| func (c *instrumentedConn) Close() error { | ||
| c.closeOnce.Do(func() { | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. are network connectionsalways explicitly closed? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. This one I'm not 100% sure on. Admittedly, I found this idea from a stackoverflow post which seemed to work for a couple other people. Was planning to get this into dev and monitor to make sure it works as intended with a lot more usage than I can reproduce myself. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. I guess maybe theyshould be and this gauge will tell us if there's a leak... | ||
| c.connsPerAgent.WithLabelValues("tcp").Dec() | ||
| }) | ||
| return c.Conn.Close() | ||
| } | ||
38 changes: 38 additions & 0 deletionscoderd/tailnet_test.go
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
50 changes: 50 additions & 0 deletionstestutil/prometheus.go
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 +1,50 @@ | ||
| package testutil | ||
| import ( | ||
| "testing" | ||
| dto "github.com/prometheus/client_model/go" | ||
| "github.com/stretchr/testify/require" | ||
| ) | ||
| func PromGaugeHasValue(t testing.TB, metrics []*dto.MetricFamily, value float64, name string, label ...string) bool { | ||
| t.Helper() | ||
| for _, family := range metrics { | ||
| if family.GetName() != name { | ||
| continue | ||
| } | ||
| ms := family.GetMetric() | ||
| metricsLoop: | ||
| for _, m := range ms { | ||
| require.Equal(t, len(label), len(m.GetLabel())) | ||
| for i, lv := range label { | ||
| if lv != m.GetLabel()[i].GetValue() { | ||
| continue metricsLoop | ||
| } | ||
| } | ||
| return value == m.GetGauge().GetValue() | ||
| } | ||
| } | ||
| return false | ||
| } | ||
| func PromCounterHasValue(t testing.TB, metrics []*dto.MetricFamily, value float64, name string, label ...string) bool { | ||
| t.Helper() | ||
| for _, family := range metrics { | ||
| if family.GetName() != name { | ||
| continue | ||
| } | ||
| ms := family.GetMetric() | ||
| metricsLoop: | ||
| for _, m := range ms { | ||
| require.Equal(t, len(label), len(m.GetLabel())) | ||
| for i, lv := range label { | ||
| if lv != m.GetLabel()[i].GetValue() { | ||
| continue metricsLoop | ||
| } | ||
| } | ||
| return value == m.GetCounter().GetValue() | ||
| } | ||
| } | ||
| return false | ||
| } |
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.