Skip to content

Add Prometheus metrics for cache circuit breaker state #1018

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
hman38705 merged 1 commit into from
Jun 30, 2026
Merged

Add Prometheus metrics for cache circuit breaker state #1018

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
22 changes: 22 additions & 0 deletions performance/config/alerts.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,28 @@ groups:
description: "Cache hit rate is {{ $value | humanizePercentage }}, below 80% threshold"
runbook_url: "https://docs.predictiq.com/runbooks/low-cache-hit-rate"

- alert: CacheCircuitBreakerOpen
expr: cache_circuit_breaker_state{state="open"} == 1
for: 2m
labels:
severity: critical
component: cache
annotations:
summary: "Redis cache circuit breaker has been open for 2+ minutes"
description: "The Redis cache circuit breaker is open, causing cache bypass and degraded performance. Check Redis connectivity and health."
runbook_url: "https://docs.predictiq.com/runbooks/cache-circuit-breaker-open"

- alert: CacheCircuitBreakerHalfOpen
expr: cache_circuit_breaker_state{state="half_open"} == 1
for: 1m
labels:
severity: warning
component: cache
annotations:
summary: "Redis cache circuit breaker is in half-open state"
description: "The Redis cache circuit breaker is probing for recovery. If this persists, Redis may be unstable."
runbook_url: "https://docs.predictiq.com/runbooks/cache-circuit-breaker-half-open"

- name: database_performance
interval: 30s
rules:
Expand Down
217 changes: 212 additions & 5 deletions performance/config/grafana-dashboard.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,11 +242,218 @@
"notifications": []
}
},
{
"id": 11,
"title": "Cache Circuit Breaker State",
"type": "stat",
"gridPos": { "x": 12, "y": 16, "w": 6, "h": 4 },
"targets": [
{
"expr": "cache_circuit_breaker_state{state=\"closed\"}",
"legendFormat": "Closed",
"refId": "A"
},
{
"expr": "cache_circuit_breaker_state{state=\"open\"}",
"legendFormat": "Open",
"refId": "B"
},
{
"expr": "cache_circuit_breaker_state{state=\"half_open\"}",
"legendFormat": "Half-Open",
"refId": "C"
}
],
"options": {
"colorMode": "background",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
},
"textMode": "value_and_name"
},
"fieldConfig": {
"defaults": {
"mappings": [
{
"type": "value",
"options": {
"0": {
"text": "Inactive",
"color": "transparent"
},
"1": {
"text": "Active",
"color": "green"
}
}
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"value": null,
"color": "transparent"
},
{
"value": 1,
"color": "green"
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "Open"
},
"properties": [
{
"id": "thresholds",
"value": {
"mode": "absolute",
"steps": [
{
"value": null,
"color": "transparent"
},
{
"value": 1,
"color": "red"
}
]
}
},
{
"id": "mappings",
"value": [
{
"type": "value",
"options": {
"0": {
"text": "Inactive",
"color": "transparent"
},
"1": {
"text": "OPEN - Cache Bypassed",
"color": "red"
}
}
}
]
}
]
},
{
"matcher": {
"id": "byName",
"options": "Half-Open"
},
"properties": [
{
"id": "thresholds",
"value": {
"mode": "absolute",
"steps": [
{
"value": null,
"color": "transparent"
},
{
"value": 1,
"color": "yellow"
}
]
}
},
{
"id": "mappings",
"value": [
{
"type": "value",
"options": {
"0": {
"text": "Inactive",
"color": "transparent"
},
"1": {
"text": "Half-Open - Probing",
"color": "yellow"
}
}
}
]
}
]
}
]
}
},
{
"id": 12,
"title": "Cache Circuit Breaker State Timeline",
"type": "graph",
"gridPos": { "x": 18, "y": 16, "w": 6, "h": 4 },
"targets": [
{
"expr": "cache_circuit_breaker_state{state=\"open\"}",
"legendFormat": "Open",
"refId": "A"
},
{
"expr": "cache_circuit_breaker_state{state=\"half_open\"}",
"legendFormat": "Half-Open",
"refId": "B"
}
],
"yaxes": [
{
"format": "short",
"label": "State",
"max": 1,
"min": 0
}
],
"alert": {
"name": "Cache Circuit Breaker Open",
"conditions": [
{
"evaluator": {
"params": [1],
"type": "gt"
},
"operator": {
"type": "and"
},
"query": {
"params": ["A", "2m", "now"]
},
"reducer": {
"params": [],
"type": "avg"
},
"type": "query"
}
],
"executionErrorState": "alerting",
"frequency": "1m",
"handler": 1,
"message": "Redis cache circuit breaker has been open for more than 2 minutes",
"noDataState": "no_data",
"notifications": []
}
},
{
"id": 6,
"title": "Database Query Time (p95)",
"type": "graph",
"gridPos": { "x": 12, "y": 16, "w": 12, "h": 8 },
"gridPos": { "x": 0, "y": 20, "w": 12, "h": 8 },
"targets": [
{
"expr": "histogram_quantile(0.95, rate(db_query_duration_seconds_bucket[5m]))",
Expand Down Expand Up @@ -293,7 +500,7 @@
"id": 7,
"title": "Database Connection Pool — Active vs Idle",
"type": "graph",
"gridPos": { "x": 0, "y": 24, "w": 12, "h": 8 },
"gridPos": { "x": 12, "y": 20, "w": 12, "h": 8 },
"targets": [
{
"expr": "db_pool_connections_active{pool=\"main\"}",
Expand Down Expand Up @@ -345,7 +552,7 @@
"id": 10,
"title": "Database Pool Acquire Duration (p95)",
"type": "graph",
"gridPos": { "x": 12, "y": 24, "w": 12, "h": 8 },
"gridPos": { "x": 0, "y": 28, "w": 12, "h": 8 },
"targets": [
{
"expr": "histogram_quantile(0.95, rate(db_pool_acquire_duration_seconds_bucket{pool=\"main\"}[5m]))",
Expand Down Expand Up @@ -397,7 +604,7 @@
"id": 8,
"title": "Contract Gas Costs",
"type": "graph",
"gridPos": { "x": 12, "y": 24, "w": 12, "h": 8 },
"gridPos": { "x": 12, "y": 28, "w": 12, "h": 8 },
"targets": [
{
"expr": "contract_gas_used{operation=\"create_market\"}",
Expand Down Expand Up @@ -454,7 +661,7 @@
"id": 9,
"title": "System Health Overview",
"type": "stat",
"gridPos": { "x": 0, "y": 32, "w": 24, "h": 4 },
"gridPos": { "x": 0, "y": 36, "w": 24, "h": 4 },
"targets": [
{
"expr": "up{job=\"predictiq-api\"}",
Expand Down
Loading