Skip to content

Update metric key for compatibility for new prometheus metric #1224

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

Open
csg-pr-bot wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update metric key for compatibility for new prometheus metric #1224

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion common/config/config.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -585,7 +585,7 @@ type Config struct {
MemoryUsageMetric string `env:"STARHUB_SERVER_PROMETHEUS_MEMORY_USAGE_METRIC" default:"container_memory_usage_bytes"`
RequestCountMetric string `env:"STARHUB_SERVER_PROMETHEUS_REQUEST_COUNT_METRIC" default:"revision_request_count"`
RequestLatencyMetric string `env:"STARHUB_SERVER_PROMETHEUS_REQUEST_LATENCY_METRIC" default:"revision_app_request_latencies_bucket"`
MetricKeys []string `env:"STARHUB_SERVER_PROMETHEUS_METRIC_KEYS" default:"[pod,service_name,namespace,response_code_class,le]"`
MetricKeys []string `env:"STARHUB_SERVER_PROMETHEUS_METRIC_KEYS" default:"[pod,service_name,namespace,http_response_status_code,response_code_class,le]"`
}

Feishu struct {
Expand Down
2 changes: 1 addition & 1 deletion common/config/config.toml.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,4 +320,4 @@ cpu_limit_metric = "kube_pod_container_resource_limits"
memory_usage_metric = "container_memory_usage_bytes"
request_count_metric = "revision_request_count"
request_latency_metric = "revision_app_request_latencies_bucket"
metric_keys = ["pod", "service_name", "namespace", "response_code_class", "le"]
metric_keys = ["pod", "service_name", "namespace", "http_response_status_code", "response_code_class", "le"]
17 changes: 12 additions & 5 deletions component/monitor.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,8 @@ func (m *monitorComponentImpl) CPUUsage(ctx context.Context, req *types.MonitorR
}
query := fmt.Sprintf("avg_over_time(rate(%s{pod='%s',namespace='%s',container='%s'}[1m])[%s:])[%s:%s]",
m.metrics.cpuUsage, req.Instance, namespace, container, req.LastDuration, req.LastDuration, req.TimeRange)
slog.InfoContext(ctx, "cpu-usage", slog.Any("query", query))
slog.InfoContext(ctx, "cpu-usage", slog.Any("query", query),
slog.Any("metricKeys", m.metrics.metricKeys), slog.Any("len", len(m.metrics.metricKeys)))

promeResp, err := m.client.SerialData(query)
if err != nil {
Expand Down Expand Up @@ -152,7 +153,8 @@ func (m *monitorComponentImpl) MemoryUsage(ctx context.Context, req *types.Monit

query := fmt.Sprintf("avg_over_time(%s{pod='%s',namespace='%s',container='%s'}[%s:])[%s:%s]",
m.metrics.memoryUsage, req.Instance, namespace, container, req.LastDuration, req.LastDuration, req.TimeRange)
slog.InfoContext(ctx, "memory-usage", slog.Any("query", query))
slog.InfoContext(ctx, "memory-usage", slog.Any("query", query),
slog.Any("metricKeys", m.metrics.metricKeys), slog.Any("len", len(m.metrics.metricKeys)))

promeResp, err := m.client.SerialData(query)
if err != nil {
Expand Down Expand Up @@ -197,7 +199,8 @@ func (m *monitorComponentImpl) RequestCount(ctx context.Context, req *types.Moni
// issue: github.com/knative/serving/issues/14925
query := fmt.Sprintf("avg_over_time(%s{pod_name='%s',namespace='%s'}[%s:])[%s:%s]",
m.metrics.requestCount, req.Instance, namespace, req.LastDuration, req.LastDuration, req.TimeRange)
slog.InfoContext(ctx, "request-count", slog.Any("query", query))
slog.InfoContext(ctx, "request-count", slog.Any("query", query),
slog.Any("metricKeys", m.metrics.metricKeys), slog.Any("len", len(m.metrics.metricKeys)))

promeResp, err := m.client.SerialData(query)
if err != nil {
Expand Down Expand Up @@ -254,11 +257,12 @@ func (m *monitorComponentImpl) RequestLatency(ctx context.Context, req *types.Mo

query := fmt.Sprintf("sum(increase(%s{pod_name='%s',namespace='%s'}[%s:])) by (le)",
m.metrics.requestLatency, req.Instance, namespace, req.LastDuration)
slog.Debug("request-latency", slog.Any("query", query))
slog.InfoContext(ctx, "request-latency", slog.Any("query", query),
slog.Any("metricKeys", m.metrics.metricKeys), slog.Any("len", len(m.metrics.metricKeys)))

promeResp, err := m.client.SerialData(query)
if err != nil {
return nil, fmt.Errorf("fail to get cpu memory usage error: %w", err)
return nil, fmt.Errorf("failed to get request latency error: %w", err)
}
slog.Debug("get request latency", slog.Any("promeResp", promeResp))
resp := types.MonitorRequestLatencyResp{}
Expand Down Expand Up @@ -343,6 +347,9 @@ func (m *monitorComponentImpl) getMetrics(metrics map[string]string) map[string]
if key == "pod" {
result["instance"] = v
}
if key == "http_response_status_code" {
result["response_code_class"] = v
}
}
}
return result
Expand Down
Loading