snowball/stack-orchestrator
2
0
Fork 0
forked from cerc-io/stack-orchestrator
Code Pull Requests Activity

Update monitoring stack with additional dashboards and watcher metrics (#693)

Browse Source 
* Include retry jobs and update default refresh intervals

* Add prometheus blackbox exporter and it's dashboard

* Add NodeJS application dashboard

* Allow UI updates

* Update watcher dashboards for upstream and external chain heads

* Update watcher dashboards with watcher config metrics

* Upgrade sushiswap and azimuth watchers

* Removed fixed title size values

* Update instructions

* Update instructions for env config

* Update instructions with setup
This commit is contained in:
prathamesh0
2023-12-21 09:26:37 +05:30
committed by GitHub
parent 42b92f7e23
commit 4a1a46facc
26 changed files with 12143 additions and 231 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stack_orchestrator/data/compose/docker-compose-prom-server.yml
+25
View File
@@ -18,5 +18,30 @@ services:
extra_hosts:
- "host.docker.internal:host-gateway"
blackbox:
image: prom/blackbox-exporter:latest
restart: always
volumes:
- ../config/monitoring/blackbox.yml:/etc/blackbox_exporter/config.yml
ports:
- '9115'
extra_hosts:
- "host.docker.internal:host-gateway"
chain-head-exporter:
image: cerc/watcher-ts:local
restart: always
working_dir: /app/packages/cli
environment:
ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
FIL_RPC_ENDPOINT: ${CERC_FIL_RPC_ENDPOINT}
ETH_RPC_API_KEY: ${CERC_INFURA_KEY}
PORT: ${CERC_METRICS_PORT}
command: ["sh", "-c", "yarn export-metrics:chain-heads"]
ports:
- '5000'
extra_hosts:
- "host.docker.internal:host-gateway"
volumes:
prometheus_data:
stack_orchestrator/data/config/monitoring/blackbox.yml
+7
View File
@@ -0,0 +1,7 @@
modules:
http_2xx:
prober: http
timeout: 5s
http:
valid_status_codes: [] #default to 2xx
method: GET
stack_orchestrator/data/config/monitoring/grafana/dashboards/.gitkeep
View File
stack_orchestrator/data/config/monitoring/grafana/dashboards/nodejs-app-dashboard.json
+943
View File
@@ -0,0 +1,943 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "node.js prometheus client basic metrics",
"editable": true,
"fiscalYearStartMonth": 0,
"gnetId": 11159,
"graphTooltip": 0,
"id": 15,
"links": [],
"liveNow": false,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 10,
"x": 0,
"y": 0
},
"hiddenSeries": false,
"id": 6,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"paceLength": 10,
"percentage": false,
"pluginVersion": "10.2.2",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "irate(process_cpu_user_seconds_total{instance=~\"$instance\"}[2m]) * 100",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "User CPU - {{instance}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "irate(process_cpu_system_seconds_total{instance=~\"$instance\"}[2m]) * 100",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Sys CPU - {{instance}}",
"refId": "B"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Process CPU Usage",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "percent",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 9,
"x": 10,
"y": 0
},
"hiddenSeries": false,
"id": 8,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"paceLength": 10,
"percentage": false,
"pluginVersion": "10.2.2",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_eventloop_lag_seconds{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Event Loop Lag",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "text",
"mode": "fixed"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 5,
"x": 19,
"y": 0
},
"id": 2,
"interval": "",
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"textMode": "name",
"wideLayout": true
},
"pluginVersion": "10.2.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "sum(nodejs_version_info{instance=~\"$instance\"}) by (version)",
"format": "time_series",
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{version}}",
"refId": "A"
}
],
"title": "Node.js Version",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "#F2495C",
"mode": "fixed"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 19,
"y": 3
},
"id": 4,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "10.2.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "sum(changes(process_start_time_seconds{instance=~\"$instance\"}[1m]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Process Restart Times",
"type": "stat"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 16,
"x": 0,
"y": 7
},
"hiddenSeries": false,
"id": 7,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"paceLength": 10,
"percentage": false,
"pluginVersion": "10.2.2",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "process_resident_memory_bytes{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Process Memory - {{instance}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_heap_size_total_bytes{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Heap Total - {{instance}}",
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_heap_size_used_bytes{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Heap Used - {{instance}}",
"refId": "C"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_external_memory_bytes{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "External Memory - {{instance}}",
"refId": "D"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Process Memory Usage",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 7
},
"hiddenSeries": false,
"id": 9,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"paceLength": 10,
"percentage": false,
"pluginVersion": "10.2.2",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_active_handles_total{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Active Handler - {{instance}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_active_requests_total{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Active Request - {{instance}}",
"refId": "B"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Active Handlers/Requests Total",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 8,
"x": 0,
"y": 14
},
"hiddenSeries": false,
"id": 10,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"rightSide": false,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"paceLength": 10,
"percentage": false,
"pluginVersion": "10.2.2",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_heap_space_size_total_bytes{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Heap Total - {{instance}} - {{space}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Heap Total Detail",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 8,
"x": 8,
"y": 14
},
"hiddenSeries": false,
"id": 11,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"rightSide": false,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"paceLength": 10,
"percentage": false,
"pluginVersion": "10.2.2",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_heap_space_size_used_bytes{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Heap Used - {{instance}} - {{space}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Heap Used Detail",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 14
},
"hiddenSeries": false,
"id": 12,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"rightSide": false,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"paceLength": 10,
"percentage": false,
"pluginVersion": "10.2.2",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "nodejs_heap_space_size_available_bytes{instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Heap Used - {{instance}} - {{space}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Heap Available Detail",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
}
],
"refresh": "10s",
"schemaVersion": 38,
"tags": [
"nodejs"
],
"templating": {
"list": [
{
"current": {
"selected": true,
"text": [
"All"
],
"value": [
"$__all"
]
},
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"definition": "label_values(nodejs_version_info, instance)",
"hide": 0,
"includeAll": true,
"label": "instance",
"multi": true,
"name": "instance",
"options": [],
"query": "label_values(nodejs_version_info, instance)",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-15m",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "",
"title": "NodeJS Application Dashboard",
"uid": "PTSqcpJWk",
"version": 3,
"weekStart": ""
}
stack_orchestrator/data/config/monitoring/grafana/dashboards/prometheus-blackbox-exporter.json
+1097
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/provisioning/dashboards/dashboards.yml
+1
View File
@@ -4,6 +4,7 @@ providers:
- name: dashboards
type: file
updateIntervalSeconds: 10
allowUiUpdates: true
options:
path: /etc/grafana/dashboards
foldersFromFilesStructure: true
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboard-template.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/azimuth-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/censures-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/claims-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/conditional-star-release-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/delegated-sending-watcher-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/ecliptic-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/linear-star-release-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/azimuth/polls-watcher-dashboard.json
+904 -19
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/sushi/merkl-sushiswap-watcher-dashboard.json
+907 -25
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/grafana/watcher-dashboards/sushi/sushiswap-watcher-dashboard.json
+908 -26
View File
File diff suppressed because it is too large Load Diff
stack_orchestrator/data/config/monitoring/prometheus/prometheus.yml
+31 -1
View File
@@ -1,5 +1,5 @@
global:
scrape_interval: 15s
scrape_interval: 10s
evaluation_interval: 15s
rule_files:
@@ -10,3 +10,33 @@ scrape_configs:
- job_name: prometheus
static_configs:
- targets: ['localhost:9090']
- job_name: 'blackbox'
scrape_interval: 10s
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
# Add URLs to be monitored below
- targets:
# - https://github.com
relabel_configs:
- source_labels: [__address__]
regex: (.*)(:80)?
target_label: __param_target
- source_labels: [__param_target]
regex: (.*)
target_label: instance
replacement: ${1}
- source_labels: []
regex: .*
target_label: __address__
replacement: blackbox:9115
- job_name: chain_heads
scrape_interval: 10s
metrics_path: /metrics
scheme: http
static_configs:
- targets: ['chain-head-exporter:5000']
stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/watcher-config-template.toml
-2
View File
@@ -84,8 +84,6 @@
subgraphEventsOrder = true
# Filecoin block time: https://docs.filecoin.io/basics/the-blockchain/blocks-and-tipsets#blocktime
blockDelayInMilliSecs = 30000
prefetchBlocksInMem = false
prefetchBlockCount = 10
# Boolean to switch between modes of processing events when starting the server.
# Setting to true will fetch filtered events and required blocks in a range of blocks and then process them.
stack_orchestrator/data/config/watcher-sushiswap-v3/watcher-config-template.toml
-2
View File
@@ -84,8 +84,6 @@
subgraphEventsOrder = true
# Filecoin block time: https://docs.filecoin.io/basics/the-blockchain/blocks-and-tipsets#blocktime
blockDelayInMilliSecs = 30000
prefetchBlocksInMem = false
prefetchBlockCount = 10
# Boolean to switch between modes of processing events when starting the server.
# Setting to true will fetch filtered events and required blocks in a range of blocks and then process them.
stack_orchestrator/data/stacks/azimuth/README.md
+16
View File
@@ -40,20 +40,36 @@ network:
ports:
watcher-db:
- 0.0.0.0:15432:5432
azimuth-watcher-job-runner:
- 0.0.0.0:9000:9000
azimuth-watcher-server:
- 0.0.0.0:3001:3001
censures-watcher-job-runner:
- 0.0.0.0:9002:9002
censures-watcher-server:
- 0.0.0.0:3002:3002
claims-watcher-job-runner:
- 0.0.0.0:9004:9004
claims-watcher-server:
- 0.0.0.0:3003:3003
conditional-star-release-watcher-job-runner:
- 0.0.0.0:9006:9006
conditional-star-release-watcher-server:
- 0.0.0.0:3004:3004
delegated-sending-watcher-job-runner:
- 0.0.0.0:9008:9008
delegated-sending-watcher-server:
- 0.0.0.0:3005:3005
ecliptic-watcher-job-runner:
- 0.0.0.0:9010:9010
ecliptic-watcher-server:
- 0.0.0.0:3006:3006
linear-star-release-watcher-job-runner:
- 0.0.0.0:9012:9012
linear-star-release-watcher-server:
- 0.0.0.0:3007:3007
polls-watcher-job-runner:
- 0.0.0.0:9014:9014
polls-watcher-server:
- 0.0.0.0:3008:3008
gateway-server:
stack_orchestrator/data/stacks/azimuth/stack.yml
+1 -1
View File
@@ -1,7 +1,7 @@
version: "1.0"
name: azimuth
repos:
- github.com/cerc-io/azimuth-watcher-ts@v0.1.2
- github.com/cerc-io/azimuth-watcher-ts@v0.1.3
containers:
- cerc/watcher-azimuth
pods:
stack_orchestrator/data/stacks/monitoring/README.md
+50 -1
View File
@@ -1,8 +1,26 @@
# monitoring
* Instructions to setup and run a Prometheus server and Grafana dashboard
* Comes with the following built-in exporters / dashboards:
* [Prometheus Blackbox Exporter](https://grafana.com/grafana/dashboards/7587-prometheus-blackbox-exporter/) - for tracking HTTP endpoints
* [NodeJS Application Dashboard](https://grafana.com/grafana/dashboards/11159-nodejs-application-dashboard/) - for default NodeJS metrics
* Chain Head Exporter - for tracking chain heads given external ETH RPC endpoints
* See [monitoring-watchers.md](./monitoring-watchers.md) for an example usage of the stack with pre-configured dashboards for watchers
## Setup
Clone required repositories:
```bash
laconic-so --stack monitoring setup-repositories --git-ssh --pull
```
Build the container images:
```bash
laconic-so --stack monitoring build-containers
```
## Create a deployment
First, create a spec file for the deployment, which will map the stack's ports and volumes to the host:
@@ -43,7 +61,7 @@ laconic-so --stack monitoring deploy create --spec-file monitoring-spec.yml --de
### Prometheus Config
Add desired scrape configs to prometheus config file (`monitoring-deployment/config/monitoring/prometheus/prometheus.yml`) in the deployment folder; for example:
* Add desired scrape configs to prometheus config file (`monitoring-deployment/config/monitoring/prometheus/prometheus.yml`) in the deployment folder; for example:
```yml
...
@@ -54,12 +72,43 @@ Add desired scrape configs to prometheus config file (`monitoring-deployment/con
- targets: ['<METRICS_ENDPOINT_HOST>:<METRICS_ENDPOINT_PORT>']
```
* Also update the `blackbox` job to add any endpoints to be monitored on the Blackbox dashboard:
```yml
...
- job_name: 'blackbox'
...
static_configs:
# Add URLs to be monitored below
- targets:
- <HTTP_ENDPOINT_1>
- <HTTP_ENDPOINT_2>
```
Note: Use `host.docker.internal` as host to access ports on the host machine
### Grafana Config
Place the dashboard json files in grafana dashboards config directory (`monitoring-deployment/config/monitoring/grafana/dashboards`) in the deployment folder
### Env
Set the following env variables in the deployment env config file (`monitoring-deployment/config.env`):
```bash
# External ETH RPC endpoint (ethereum)
# (Optional, default: https://mainnet.infura.io/v3)
CERC_ETH_RPC_ENDPOINT=
# Infura key to be used
# (Optional, used with ETH_RPC_ENDPOINT if provided)
CERC_INFURA_KEY=
# External ETH RPC endpoint (filecoin)
# (Optional, default: https://api.node.glif.io/rpc/v1)
CERC_FIL_RPC_ENDPOINT=
```
## Start the stack
Start the deployment:
stack_orchestrator/data/stacks/monitoring/monitoring-watchers.md
+18 -1
View File
@@ -4,7 +4,7 @@ Instructions to setup and run monitoring stack with pre-configured watcher dashb
## Create a deployment
First, create a spec file for the deployment, which will map the stack's ports and volumes to the host:
After completing [setup](./README.md#setup), create a spec file for the deployment, which will map the stack's ports and volumes to the host:
```bash
laconic-so --stack monitoring deploy init --output monitoring-watchers-spec.yml
@@ -41,7 +41,14 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
```yml
...
- job_name: 'blackbox'
...
static_configs:
- targets:
- <AZIMUTH_GATEWAY_GQL_ENDPOINT>
...
- job_name: azimuth
scrape_interval: 10s
metrics_path: /metrics
scheme: http
static_configs:
@@ -71,6 +78,7 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
instance: 'polls'
- job_name: sushi
scrape_interval: 20s
metrics_path: /metrics
scheme: http
static_configs:
@@ -90,6 +98,15 @@ In the deployment folder, copy over the pre-configured watcher dashboard JSON fi
cp -r monitoring-watchers-deployment/config/monitoring/grafana/watcher-dashboards/* monitoring-watchers-deployment/config/monitoring/grafana/dashboards/
```
### Env
Set the following env variables in the deployment env config file (`monitoring-watchers-deployment/config.env`):
```bash
# Infura key to be used
CERC_INFURA_KEY=
```
## Start the stack
Start the deployment:
stack_orchestrator/data/stacks/monitoring/stack.yml
+2
View File
@@ -1,7 +1,9 @@
version: "0.1"
name: monitoring
repos:
- github.com/cerc-io/watcher-ts@v0.2.79
containers:
- cerc/watcher-ts
pods:
- prom-server
- grafana
stack_orchestrator/data/stacks/sushiswap-v3/stack.yml
+1 -1
View File
@@ -2,7 +2,7 @@ version: "1.0"
name: sushiswap-v3
description: "SushiSwap v3 watcher stack"
repos:
- github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.4
- github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.5
containers:
- cerc/watcher-sushiswap-v3
pods: