Skip to content

perf: don't call GetUserByID unnecessarily for Agents metrics loops #19395

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 6 commits into from
Aug 21, 2025
Merged

perf: don't call GetUserByID unnecessarily for Agents metrics loops #19395

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
eb527fe
cache the seen user IDs in each iteration of the Agents metric loop to
cstyan Aug 18, 2025
a65de4a
Only cache the username instead of the entire user object
cstyan Aug 18, 2025
6376d48
better optimization for metrics related GetUserByID calls
cstyan Aug 18, 2025
332acb5
TYPO not
cstyan Aug 18, 2025
43b1228
don't need fallback DB query anymore since we added username min length
cstyan Aug 21, 2025
ff0680e
fix stats_tests.go based on username/not calling GetUserByID
cstyan Aug 21, 2025
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
20 changes: 6 additions & 14 deletions coderd/agentapi/stats_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,11 +41,12 @@ func TestUpdateStates(t *testing.T) {
Name: "tpl",
}
workspace = database.Workspace{
ID: uuid.New(),
OwnerID: user.ID,
TemplateID: template.ID,
Name: "xyz",
TemplateName: template.Name,
ID: uuid.New(),
OwnerID: user.ID,
OwnerUsername: user.Username,
TemplateID: template.ID,
Name: "xyz",
TemplateName: template.Name,
}
agent = database.WorkspaceAgent{
ID: uuid.New(),
Expand Down Expand Up @@ -138,9 +139,6 @@ func TestUpdateStates(t *testing.T) {
// Workspace gets fetched.
dbM.EXPECT().GetWorkspaceByAgentID(gomock.Any(), agent.ID).Return(workspace, nil)

// User gets fetched to hit the UpdateAgentMetricsFn.
dbM.EXPECT().GetUserByID(gomock.Any(), user.ID).Return(user, nil)

// We expect an activity bump because ConnectionCount > 0.
dbM.EXPECT().ActivityBumpWorkspace(gomock.Any(), database.ActivityBumpWorkspaceParams{
WorkspaceID: workspace.ID,
Expand Down Expand Up @@ -380,9 +378,6 @@ func TestUpdateStates(t *testing.T) {
LastUsedAt: now.UTC(),
}).Return(nil)

// User gets fetched to hit the UpdateAgentMetricsFn.
dbM.EXPECT().GetUserByID(gomock.Any(), user.ID).Return(user, nil)

resp, err := api.UpdateStats(context.Background(), req)
require.NoError(t, err)
require.Equal(t, &agentproto.UpdateStatsResponse{
Expand Down Expand Up @@ -498,9 +493,6 @@ func TestUpdateStates(t *testing.T) {
LastUsedAt: now,
}).Return(nil)

// User gets fetched to hit the UpdateAgentMetricsFn.
dbM.EXPECT().GetUserByID(gomock.Any(), user.ID).Return(user, nil)

// Ensure that pubsub notifications are sent.
notifyDescription := make(chan struct{})
ps.SubscribeWithErr(wspubsub.WorkspaceEventChannel(workspace.OwnerID),
Expand Down
19 changes: 7 additions & 12 deletions coderd/prometheusmetrics/prometheusmetrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,29 +328,24 @@ func Agents(ctx context.Context, logger slog.Logger, registerer prometheus.Regis
templateVersionName = "unknown"
}

user, err := db.GetUserByID(ctx, workspace.OwnerID)
if err != nil {
logger.Error(ctx, "can't get user from the database", slog.F("user_id", workspace.OwnerID), slog.Error(err))
agentsGauge.WithLabelValues(VectorOperationAdd, 0, user.Username, workspace.Name, templateName, templateVersionName)
continue
}
// username :=

agents, err := db.GetWorkspaceAgentsInLatestBuildByWorkspaceID(ctx, workspace.ID)
if err != nil {
logger.Error(ctx, "can't get workspace agents", slog.F("workspace_id", workspace.ID), slog.Error(err))
agentsGauge.WithLabelValues(VectorOperationAdd, 0, user.Username, workspace.Name, templateName, templateVersionName)
agentsGauge.WithLabelValues(VectorOperationAdd, 0, workspace.OwnerUsername, workspace.Name, templateName, templateVersionName)
continue
}

if len(agents) == 0 {
logger.Debug(ctx, "workspace agents are unavailable", slog.F("workspace_id", workspace.ID))
agentsGauge.WithLabelValues(VectorOperationAdd, 0, user.Username, workspace.Name, templateName, templateVersionName)
agentsGauge.WithLabelValues(VectorOperationAdd, 0, workspace.OwnerUsername, workspace.Name, templateName, templateVersionName)
continue
}

for _, agent := range agents {
// Collect information about agents
agentsGauge.WithLabelValues(VectorOperationAdd, 1, user.Username, workspace.Name, templateName, templateVersionName)
agentsGauge.WithLabelValues(VectorOperationAdd, 1, workspace.OwnerUsername, workspace.Name, templateName, templateVersionName)

connectionStatus := agent.Status(agentInactiveDisconnectTimeout)
node := (*coordinator.Load()).Node(agent.ID)
Expand All @@ -360,7 +355,7 @@ func Agents(ctx context.Context, logger slog.Logger, registerer prometheus.Regis
tailnetNode = node.ID.String()
}

agentsConnectionsGauge.WithLabelValues(VectorOperationSet, 1, agent.Name, user.Username, workspace.Name, string(connectionStatus.Status), string(agent.LifecycleState), tailnetNode)
agentsConnectionsGauge.WithLabelValues(VectorOperationSet, 1, agent.Name, workspace.OwnerUsername, workspace.Name, string(connectionStatus.Status), string(agent.LifecycleState), tailnetNode)

if node == nil {
logger.Debug(ctx, "can't read in-memory node for agent", slog.F("agent_id", agent.ID))
Expand All @@ -385,7 +380,7 @@ func Agents(ctx context.Context, logger slog.Logger, registerer prometheus.Regis
}
}

agentsConnectionLatenciesGauge.WithLabelValues(VectorOperationSet, latency, agent.Name, user.Username, workspace.Name, region.RegionName, fmt.Sprintf("%v", node.PreferredDERP == regionID))
agentsConnectionLatenciesGauge.WithLabelValues(VectorOperationSet, latency, agent.Name, workspace.OwnerUsername, workspace.Name, region.RegionName, fmt.Sprintf("%v", node.PreferredDERP == regionID))
}
}

Expand All @@ -397,7 +392,7 @@ func Agents(ctx context.Context, logger slog.Logger, registerer prometheus.Regis
}

for _, app := range apps {
agentsAppsGauge.WithLabelValues(VectorOperationAdd, 1, agent.Name, user.Username, workspace.Name, app.DisplayName, string(app.Health))
agentsAppsGauge.WithLabelValues(VectorOperationAdd, 1, agent.Name, workspace.OwnerUsername, workspace.Name, app.DisplayName, string(app.Health))
}
}
}
Expand Down
7 changes: 1 addition & 6 deletions coderd/workspacestats/reporter.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,13 +126,8 @@ func (r *Reporter) ReportAgentStats(ctx context.Context, now time.Time, workspac

// update prometheus metrics
if r.opts.UpdateAgentMetricsFn != nil {
user, err := r.opts.Database.GetUserByID(ctx, workspace.OwnerID)
if err != nil {
return xerrors.Errorf("get user: %w", err)
}

r.opts.UpdateAgentMetricsFn(ctx, prometheusmetrics.AgentMetricLabels{
Username: user.Username,
Username: workspace.OwnerUsername,
WorkspaceName: workspace.Name,
AgentName: workspaceAgent.Name,
TemplateName: templateName,
Expand Down
Loading