[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[taler-grid5k] 136/189: update dashboards
From: |
gnunet |
Subject: |
[taler-grid5k] 136/189: update dashboards |
Date: |
Thu, 28 Apr 2022 10:48:26 +0200 |
This is an automated email from the git hooks/post-receive script.
marco-boss pushed a commit to branch master
in repository grid5k.
commit e23550c7a508d92755636803a503353dc5d74125
Author: Boss Marco <bossm8@bfh.ch>
AuthorDate: Fri Apr 8 20:32:38 2022 +0200
update dashboards
---
additional/grafana/database.json | 4 +-
additional/grafana/exchange.json | 33 +-
additional/grafana/load-statistics.json | 1205 +--
additional/grafana/nodes.json | 13820 +++++++++++++++++++++++++++
additional/grafana/proxy.json | 6 +-
additional/grafana/request-statistics.json | 46 +-
additional/grafana/transactions.json | 72 +-
configs/etc/monitor/promtail.yaml | 6 +
experiment/scripts/data-backup.sh | 2 +
experiment/scripts/monitor.sh | 2 +-
10 files changed, 14244 insertions(+), 952 deletions(-)
diff --git a/additional/grafana/database.json b/additional/grafana/database.json
index db11983..1d3140a 100644
--- a/additional/grafana/database.json
+++ b/additional/grafana/database.json
@@ -67,7 +67,7 @@
"gnetId": 6742,
"graphTooltip": 1,
"id": null,
- "iteration": 1649317559908,
+ "iteration": 1649441739195,
"links": [],
"liveNow": false,
"panels": [
@@ -2980,6 +2980,6 @@
"timezone": "",
"title": "Database",
"uid": "2FTtdeOnk",
- "version": 98,
+ "version": 99,
"weekStart": ""
}
\ No newline at end of file
diff --git a/additional/grafana/exchange.json b/additional/grafana/exchange.json
index 818273c..c3cf1c6 100644
--- a/additional/grafana/exchange.json
+++ b/additional/grafana/exchange.json
@@ -365,8 +365,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "",
"fieldConfig": {
@@ -386,7 +386,7 @@
"tooltip": false,
"viz": false
},
- "lineInterpolation": "smooth",
+ "lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
@@ -444,7 +444,12 @@
},
"targets": [
{
- "expr": "rate({app=\"taler-database\"} |~ \"duration:\" [1m])",
+ "datasource": {
+ "type": "loki",
+ "uid": "${DS_LOKI}"
+ },
+ "expr": "rate({app=\"taler-database\", type=\"slow-query\"} [1m])",
+ "hide": false,
"refId": "A"
}
],
@@ -725,8 +730,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "Number of queries which took longer than the configured
duration",
"fieldConfig": {
@@ -774,7 +779,11 @@
"pluginVersion": "8.4.3",
"targets": [
{
- "expr": "sum(count_over_time({app=\"taler-database\"} |~ \"duration:
(.*) plan:\" [$__range]))",
+ "datasource": {
+ "type": "loki",
+ "uid": "${DS_LOKI}"
+ },
+ "expr": "sum(count_over_time({app=\"taler-database\",
type=\"slow-query\"} [$__range]))",
"instant": true,
"range": false,
"refId": "A"
@@ -847,7 +856,11 @@
"pluginVersion": "8.4.3",
"targets": [
{
- "expr": "sum by (query) (count_over_time({app=\"taler-database\"} |~
\"011Query Text:\" | regexp \".*011Query Text: (?P<query>.*)\" [$__range]))",
+ "datasource": {
+ "type": "loki",
+ "uid": "${DS_LOKI}"
+ },
+ "expr": "sum by (query) (count_over_time({app=\"taler-database\",
type=\"slow-query\"} | regexp \"(?P<query>.*)\" [$__range]))",
"instant": true,
"range": false,
"refId": "A"
@@ -919,7 +932,7 @@
"type": "table"
}
],
- "refresh": "30s",
+ "refresh": "10s",
"schemaVersion": 35,
"style": "dark",
"tags": [
@@ -937,6 +950,6 @@
"timezone": "",
"title": "Exchange",
"uid": "NYO0EIE7k",
- "version": 16,
+ "version": 31,
"weekStart": ""
}
\ No newline at end of file
diff --git a/additional/grafana/load-statistics.json
b/additional/grafana/load-statistics.json
index d3dc9e4..b2f361c 100644
--- a/additional/grafana/load-statistics.json
+++ b/additional/grafana/load-statistics.json
@@ -19,6 +19,12 @@
],
"__elements": [],
"__requires": [
+ {
+ "type": "panel",
+ "id": "bargauge",
+ "name": "Bar gauge",
+ "version": ""
+ },
{
"type": "grafana",
"id": "grafana",
@@ -37,6 +43,18 @@
"name": "Prometheus",
"version": "1.0.0"
},
+ {
+ "type": "panel",
+ "id": "stat",
+ "name": "Stat",
+ "version": ""
+ },
+ {
+ "type": "panel",
+ "id": "table",
+ "name": "Table",
+ "version": ""
+ },
{
"type": "panel",
"id": "timeseries",
@@ -78,19 +96,20 @@
"x": 0,
"y": 0
},
- "id": 13,
+ "id": 18,
"panels": [],
- "title": "Exchange",
+ "title": "Cryptographic Operations",
"type": "row"
},
{
+ "description": "Number of signatures created with the configured cipher
of the exchange (rsa or cs).",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
- "axisLabel": "",
+ "axisLabel": "Signatures per Second",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
@@ -102,7 +121,7 @@
"viz": false
},
"lineInterpolation": "linear",
- "lineWidth": 2,
+ "lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
@@ -126,47 +145,18 @@
"value": null
}
]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byRegexp",
- "options": "CPU Busy"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
- },
- {
- "id": "unit",
- "value": "percent"
- }
- ]
},
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- }
- ]
+ "unit": "none"
+ },
+ "overrides": []
},
"gridPos": {
- "h": 9,
+ "h": 8,
"w": 12,
"x": 0,
"y": 1
},
- "id": 2,
- "maxDataPoints": 500,
+ "id": 22,
"options": {
"legend": {
"calcs": [],
@@ -185,39 +175,24 @@
"uid": "${DS_PROMETHEUS}"
},
"exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
- "instant": false,
+ "expr": "sum by(type) (rate(taler_exchange_num_signatures{}[1m]))",
"interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
+ "legendFormat": "{{ type }}",
"refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
- },
- "exemplar": true,
- "expr": "100 - (avg by (instance)
(rate(node_cpu_seconds_total{mode=\"idle\",
component=\"exchange\"}[$__rate_interval]))*100)",
- "hide": false,
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "CPU Busy",
- "refId": "B"
}
],
- "title": " [Exchange] Requests vs CPU",
+ "title": "Signatures",
"type": "timeseries"
},
{
- "description": "",
+ "description": "Number of signature verifications with the configured
cipher of the exchange (rsa or cs).",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
- "axisLabel": "",
+ "axisLabel": "Verifications per Second",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
@@ -229,7 +204,7 @@
"viz": false
},
"lineInterpolation": "linear",
- "lineWidth": 2,
+ "lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
@@ -253,47 +228,18 @@
"value": null
}
]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byRegexp",
- "options": "Network (.*)"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
- },
- {
- "id": "unit",
- "value": "bps"
- }
- ]
},
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- }
- ]
+ "unit": "none"
+ },
+ "overrides": []
},
"gridPos": {
- "h": 9,
+ "h": 8,
"w": 12,
"x": 12,
"y": 1
},
- "id": 7,
- "maxDataPoints": 500,
+ "id": 20,
"options": {
"legend": {
"calcs": [],
@@ -307,48 +253,29 @@
},
"targets": [
{
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
"exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
+ "expr": "sum by (type)
(rate(taler_exchange_num_signature_verifications{}[1m]))",
"interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
+ "legendFormat": "{{ type }}",
"refId": "A"
- },
- {
- "exemplar": true,
- "expr":
"sum(rate(node_network_receive_bytes_total{component=\"exchange\"}[$__rate_interval])
+ rate(node_network_transmit_bytes_total{component=\"exchange\"}
[$__rate_interval]))*8",
- "hide": false,
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "Network Bandwidth",
- "refId": "B"
}
],
- "title": "[Exchange] Requests vs Network Traffic",
+ "title": "Signature Verifications",
"type": "timeseries"
},
{
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 10
- },
- "id": 21,
- "panels": [],
- "title": "Wallet",
- "type": "row"
- },
- {
- "description": "Number of requests versus average wallet node CPU usage",
+ "description": "Number of key exchanges",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
- "axisLabel": "",
+ "axisLabel": "Signatures per Second",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
@@ -360,7 +287,7 @@
"viz": false
},
"lineInterpolation": "linear",
- "lineWidth": 2,
+ "lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
@@ -384,47 +311,18 @@
"value": null
}
]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byRegexp",
- "options": "CPU Busy"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
- },
- {
- "id": "unit",
- "value": "percent"
- }
- ]
},
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- }
- ]
+ "unit": "none"
+ },
+ "overrides": []
},
"gridPos": {
- "h": 9,
+ "h": 8,
"w": 12,
"x": 0,
- "y": 11
+ "y": 9
},
- "id": 19,
- "maxDataPoints": 500,
+ "id": 23,
"options": {
"legend": {
"calcs": [],
@@ -443,28 +341,13 @@
"uid": "${DS_PROMETHEUS}"
},
"exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
- "instant": false,
+ "expr": "sum by (type) (rate(taler_exchange_num_keyexchanges{}
[2m]))",
"interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
+ "legendFormat": "{{ type }}",
"refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
- },
- "exemplar": true,
- "expr": "100 - (avg(rate(node_cpu_seconds_total{mode=\"idle\",
component=\"wallet\"}[$__rate_interval]))*100)",
- "hide": false,
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "CPU Busy",
- "refId": "B"
}
],
- "title": " [Wallet] Requests vs Average CPU",
+ "title": "Key Exchanges",
"type": "timeseries"
},
{
@@ -473,33 +356,38 @@
"h": 1,
"w": 24,
"x": 0,
- "y": 20
+ "y": 17
},
- "id": 15,
+ "id": 16,
"panels": [],
"title": "Database",
"type": "row"
},
{
+ "datasource": {
+ "type": "datasource",
+ "uid": "-- Mixed --"
+ },
+ "description": "",
"fieldConfig": {
"defaults": {
"color": {
- "mode": "palette-classic"
+ "mode": "thresholds"
},
"custom": {
- "axisLabel": "",
+ "axisLabel": "Slow Queries / Second",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
+ "fillOpacity": 19,
+ "gradientMode": "hue",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
- "lineWidth": 2,
+ "lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
@@ -521,53 +409,32 @@
{
"color": "green",
"value": null
- }
- ]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byRegexp",
- "options": "CPU Busy"
- },
- "properties": [
+ },
{
- "id": "custom.axisPlacement",
- "value": "right"
+ "color": "#EAB839",
+ "value": 5
},
{
- "id": "unit",
- "value": "percent"
+ "color": "red",
+ "value": 10
}
]
},
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- }
- ]
+ "unit": "SQ/s"
+ },
+ "overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
- "y": 21
+ "y": 18
},
- "id": 3,
- "maxDataPoints": 500,
+ "id": 4,
"options": {
"legend": {
"calcs": [],
- "displayMode": "list",
+ "displayMode": "hidden",
"placement": "bottom"
},
"tooltip": {
@@ -578,40 +445,26 @@
"targets": [
{
"datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
- },
- "exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
- "interval": "",
- "legendFormat": "Requests",
- "refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
+ "type": "loki",
+ "uid": "${DS_LOKI}"
},
- "exemplar": true,
- "expr": "100 - (avg by (instance)
(rate(node_cpu_seconds_total{mode=\"idle\",
component=\"database\"}[$__rate_interval]))*100)",
+ "expr": "rate({app=\"taler-database\", type=\"slow-query\"} [1m])",
"hide": false,
- "interval": "",
- "legendFormat": "CPU Busy",
- "refId": "B"
+ "refId": "A"
}
],
- "title": "[Database] Requests vs CPU",
+ "title": "Slow Queries",
"type": "timeseries"
},
{
- "description": "",
+ "description": "Serialization Errors per Second and Request-Type",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
- "axisLabel": "",
+ "axisLabel": "Serialization Errors / Second",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
@@ -623,7 +476,7 @@
"viz": false
},
"lineInterpolation": "linear",
- "lineWidth": 2,
+ "lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
@@ -647,47 +500,18 @@
"value": null
}
]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byRegexp",
- "options": "Network (.*)"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
- },
- {
- "id": "unit",
- "value": "bps"
- }
- ]
},
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- }
- ]
+ "unit": "none"
+ },
+ "overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
- "y": 21
+ "y": 18
},
- "id": 8,
- "maxDataPoints": 500,
+ "id": 2,
"options": {
"legend": {
"calcs": [],
@@ -699,181 +523,94 @@
"sort": "none"
}
},
+ "pluginVersion": "8.2.5",
"targets": [
{
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
"exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
+ "expr": "sum by (type)
(rate(taler_exchange_serialization_failures{}[1m]))",
+ "instant": false,
"interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
+ "legendFormat": "{{type}}",
"refId": "A"
- },
- {
- "exemplar": true,
- "expr":
"sum(rate(node_network_receive_bytes_total{component=\"database\"}[$__rate_interval])
+ rate(node_network_transmit_bytes_total{component=\"database\"}
[$__rate_interval]))*8",
- "hide": false,
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "Network Bandwidth",
- "refId": "B"
}
],
- "title": "[Database] Requests vs Network Traffic",
+ "title": "Serialization Errors",
+ "transformations": [],
"type": "timeseries"
},
{
- "description": "",
+ "description": "Number of serialization errors by request endpoint
(type) since the last exchange restarts",
"fieldConfig": {
"defaults": {
"color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 2,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
+ "mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
- "color": "green",
+ "color": "text",
"value": null
- }
- ]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "Database Size"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
},
{
- "id": "unit",
- "value": "bytes"
- }
- ]
- },
- {
- "matcher": {
- "id": "byName",
- "options": "Total Requests"
- },
- "properties": [
- {
- "id": "unit",
- "value": "short"
+ "color": "red",
+ "value": 100
}
]
}
- ]
+ },
+ "overrides": []
},
"gridPos": {
- "h": 9,
- "w": 12,
+ "h": 8,
+ "w": 10,
"x": 0,
- "y": 30
+ "y": 27
},
- "id": 5,
- "maxDataPoints": 500,
+ "id": 6,
"options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom"
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
+ "displayMode": "basic",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showUnfilled": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
"targets": [
{
"exemplar": true,
- "expr": "nginx_http_requests_total{}",
+ "expr": "sort_desc (sum by(type)
(taler_exchange_serialization_failures{}))",
+ "instant": true,
"interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
+ "legendFormat": "{{type}}",
"refId": "A"
- },
- {
- "exemplar": true,
- "expr": "sum(pg_database_size_bytes{instance=\"127.0.0.1:9187\"})",
- "hide": false,
- "interval": "",
- "legendFormat": "Database Size",
- "refId": "C"
}
],
- "title": "Total Requests vs Disk Space used",
- "type": "timeseries"
+ "title": "Serialization Errors by Request Type",
+ "transformations": [],
+ "type": "bargauge"
},
{
- "description": "",
+ "description": "Total number of serialization errors that happened since
last exchange restarts",
"fieldConfig": {
"defaults": {
"color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 2,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
+ "fixedColor": "text",
+ "mode": "fixed"
},
"mappings": [],
+ "noValue": "0",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -884,242 +621,127 @@
]
}
},
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- },
- {
- "matcher": {
- "id": "byRegexp",
- "options": "I/O Utilization(.*)"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
- },
- {
- "id": "unit",
- "value": "percentunit"
- }
- ]
- }
- ]
+ "overrides": []
},
"gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 30
+ "h": 4,
+ "w": 4,
+ "x": 10,
+ "y": 27
},
- "id": 9,
- "maxDataPoints": 500,
+ "id": 8,
"options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom"
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "8.4.3",
"targets": [
{
- "datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
- },
"exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
+ "expr": "sum(taler_exchange_serialization_failures{})",
"interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
+ "legendFormat": "",
"refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
- },
- "exemplar": true,
- "expr": "sum by (device)
(rate(node_disk_io_time_seconds_total{component=\"database\"}
[$__rate_interval]))",
- "hide": false,
- "interval": "",
- "legendFormat": "I/O Utilization ({{device}})",
- "refId": "C"
}
],
- "title": "Requests vs I/O Utilization",
- "type": "timeseries"
+ "title": "Total Serialization Errors",
+ "type": "stat"
},
{
- "description": "",
+ "description": "Number of serialization errors per request since the
last exchange restarts",
"fieldConfig": {
"defaults": {
"color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 2,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "nan",
+ "result": {
+ "index": 0,
+ "text": "-"
+ }
+ },
+ "type": "special"
}
- },
- "mappings": [],
+ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
- "color": "green",
+ "color": "text",
"value": null
- }
- ]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "Cache Hit Rate"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
},
{
- "id": "unit",
- "value": "percentunit"
+ "color": "red",
+ "value": 2
}
]
},
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- }
- ]
+ "unit": "percentunit"
+ },
+ "overrides": []
},
"gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 39
+ "h": 8,
+ "w": 10,
+ "x": 14,
+ "y": 27
},
- "id": 10,
- "maxDataPoints": 500,
+ "id": 12,
"options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom"
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
+ "displayMode": "basic",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showUnfilled": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
"targets": [
{
"exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
+ "expr": "sort_desc(sum by(type)
(rate(taler_exchange_serialization_failures{}[10m]))\n/\nsum by(type)
(rate(taler_exchange_received_requests{}[10m])))",
+ "instant": true,
"interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
+ "legendFormat": "{{type}}",
"refId": "A"
- },
- {
- "exemplar": true,
- "expr": "pg_stat_database_blks_hit{instance=\"127.0.0.1:9187\",
server=\"db.perf.taler:5432\", datname!~\"postgres|template.*|\"} /
(pg_stat_database_blks_read{instance=\"127.0.0.1:9187\",
server=\"db.perf.taler:5432\", datname!~\"postgres|template.*|\"} +
pg_stat_database_blks_hit{instance=\"127.0.0.1:9187\",
server=\"db.perf.taler:5432\", datname!~\"postgres|template.*|\"})",
- "hide": false,
- "interval": "",
- "legendFormat": "Cache Hit Rate",
- "refId": "C"
}
],
- "title": "Requests vs Cache Hit Rate",
- "type": "timeseries"
+ "title": "Serialization Errors / Request",
+ "type": "bargauge"
},
{
"datasource": {
"type": "datasource",
"uid": "-- Mixed --"
},
- "description": "",
+ "description": "Number of queries which took longer than the configured
duration",
"fieldConfig": {
"defaults": {
"color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 2,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
+ "fixedColor": "text",
+ "mode": "fixed"
},
"mappings": [],
+ "noValue": "0",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -1130,131 +752,61 @@
]
}
},
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "Slow Queries"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
- },
- {
- "id": "custom.axisLabel",
- "value": "Slow Queries / Second"
- },
- {
- "id": "unit",
- "value": "none"
- },
- {
- "id": "custom.lineStyle",
- "value": {
- "fill": "solid"
- }
- },
- {
- "id": "custom.fillOpacity",
- "value": 15
- }
- ]
- },
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
- }
- ]
- }
- ]
+ "overrides": []
},
"gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 39
+ "h": 4,
+ "w": 4,
+ "x": 10,
+ "y": 31
},
- "id": 11,
- "maxDataPoints": 500,
+ "id": 10,
"options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom"
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "8.4.3",
"targets": [
- {
- "datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
- },
- "exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "Requests",
- "refId": "A"
- },
{
"datasource": {
"type": "loki",
"uid": "${DS_LOKI}"
},
- "expr": "rate({app=\"taler-database\"} |~ \"duration:\" [1m])",
- "hide": false,
- "legendFormat": "Slow Queries",
- "refId": "C"
+ "expr": "sum(count_over_time({app=\"taler-database\",
type=\"slow-query\"} [$__range]))",
+ "instant": true,
+ "range": false,
+ "refId": "A"
}
],
- "title": "Requests vs Slow Queries",
- "type": "timeseries"
+ "title": "Total Slow Queries",
+ "type": "stat"
},
{
- "description": "Serialization Errors per Second and Request-Type",
+ "datasource": {
+ "type": "loki",
+ "uid": "${DS_LOKI}"
+ },
+ "description": "",
"fieldConfig": {
"defaults": {
"color": {
- "mode": "palette-classic"
+ "mode": "thresholds"
},
"custom": {
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "opacity",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 2,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
+ "align": "auto",
+ "displayMode": "json-view",
+ "filterable": false
},
"mappings": [],
"thresholds": {
@@ -1265,222 +817,127 @@
"value": null
}
]
- },
- "unit": "none"
+ }
},
"overrides": [
{
"matcher": {
"id": "byName",
- "options": "Serialization Errors"
+ "options": "Count"
},
"properties": [
{
- "id": "custom.axisPlacement",
- "value": "right"
- },
- {
- "id": "custom.axisLabel",
- "value": "Serialization Errors / Second"
- },
- {
- "id": "unit"
- }
- ]
- },
- {
- "matcher": {
- "id": "byName",
- "options": "Requests"
- },
- "properties": [
- {
- "id": "custom.axisLabel",
- "value": "Requests / Second"
+ "id": "custom.width",
+ "value": 100
}
]
}
]
},
"gridPos": {
- "h": 9,
- "w": 12,
+ "h": 7,
+ "w": 24,
"x": 0,
- "y": 48
+ "y": 35
},
- "id": 18,
+ "id": 14,
"options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom"
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "pluginVersion": "8.2.5",
+ "footer": {
+ "fields": "",
+ "reducer": [
+ "sum"
+ ],
+ "show": false
+ },
+ "frameIndex": 1,
+ "showHeader": true,
+ "sortBy": []
+ },
+ "pluginVersion": "8.4.3",
"targets": [
{
- "exemplar": true,
- "expr": "sum(rate(nginx_http_requests_total{} [$__rate_interval]))",
- "hide": false,
- "interval": "",
- "legendFormat": "Requests",
- "refId": "B"
- },
- {
- "exemplar": true,
- "expr": "sum (rate(taler_exchange_serialization_failures{}[1m]))",
- "instant": false,
- "interval": "",
- "legendFormat": "Serialization Errors",
+ "datasource": {
+ "type": "loki",
+ "uid": "${DS_LOKI}"
+ },
+ "expr": "sum by (query) (count_over_time({app=\"taler-database\",
type=\"slow-query\"} | regexp \"(?P<query>.*)\" [$__range]))",
+ "instant": true,
+ "range": false,
"refId": "A"
}
],
- "title": "Requests vs Serialization Errors",
- "transformations": [],
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "datasource",
- "uid": "-- Mixed --"
- },
- "description": "",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 2,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- }
- ]
- },
- "unit": "s"
- },
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "Slow Queries"
- },
- "properties": [
- {
- "id": "custom.axisPlacement",
- "value": "right"
+ "title": "Slow Query Occurences",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Query": {
+ "aggregations": [
+ "count"
+ ],
+ "operation": "groupby"
},
- {
- "id": "custom.axisLabel",
- "value": "Slow Queries / Second"
+ "Value": {
+ "aggregations": [
+ "lastNotNull"
+ ],
+ "operation": "aggregate"
},
- {
- "id": "unit",
- "value": "none"
+ "Value #A": {
+ "aggregations": [
+ "lastNotNull"
+ ],
+ "operation": "aggregate"
},
- {
- "id": "custom.drawStyle",
- "value": "line"
- },
- {
- "id": "custom.lineStyle"
+ "app": {
+ "aggregations": [
+ "count"
+ ],
+ "operation": "aggregate"
},
- {
- "id": "custom.fillOpacity",
- "value": 15
+ "query": {
+ "aggregations": [],
+ "operation": "groupby"
}
- ]
+ }
}
- ]
- },
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 48
- },
- "id": 16,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom"
},
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "targets": [
{
- "datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
- },
- "expr": "rate({app=\"taler-database\"} |~ \"duration:\" [1m])",
- "hide": false,
- "legendFormat": "Slow Queries",
- "refId": "A",
- "resolution": 1
+ "id": "organize",
+ "options": {
+ "excludeByName": {},
+ "indexByName": {},
+ "renameByName": {
+ "Value #A (lastNotNull)": "Count",
+ "Value (lastNotNull)": "Count",
+ "app (count)": "Count",
+ "query": "Query"
+ }
+ }
},
{
- "datasource": {
- "type": "prometheus",
- "uid": "${DS_PROMETHEUS}"
- },
- "exemplar": true,
- "expr": "avg
((rate(taler_requests_response_time_hist_sum{endpoint!~\"keys|terms\",
status=\"200\"} [2m]) ) /
(rate(taler_requests_response_time_hist_count{endpoint!~\"keys|terms\",
status=\"200\"} [2m])))",
- "hide": false,
- "interval": "",
- "legendFormat": "Average Response Time",
- "refId": "B"
+ "id": "sortBy",
+ "options": {
+ "fields": {},
+ "sort": [
+ {
+ "desc": true,
+ "field": "Count"
+ }
+ ]
+ }
}
],
- "title": "Proxy Response Time vs Slow Queries",
- "type": "timeseries"
+ "type": "table"
}
],
- "refresh": "",
+ "refresh": "10s",
"schemaVersion": 35,
"style": "dark",
"tags": [
- "taler",
- "performance"
+ "performance",
+ "taler"
],
"templating": {
"list": []
@@ -1491,8 +948,8 @@
},
"timepicker": {},
"timezone": "",
- "title": "Load Statistics",
- "uid": "rkyhDAt7z",
- "version": 60,
+ "title": "Exchange",
+ "uid": "NYO0EIE7k",
+ "version": 32,
"weekStart": ""
}
\ No newline at end of file
diff --git a/additional/grafana/nodes.json b/additional/grafana/nodes.json
new file mode 100644
index 0000000..b911c03
--- /dev/null
+++ b/additional/grafana/nodes.json
@@ -0,0 +1,13820 @@
+{
+ "__inputs": [
+ {
+ "name": "DS_PROMETHEUS",
+ "label": "Prometheus",
+ "description": "",
+ "type": "datasource",
+ "pluginId": "prometheus",
+ "pluginName": "Prometheus"
+ }
+ ],
+ "__elements": [],
+ "__requires": [
+ {
+ "type": "panel",
+ "id": "gauge",
+ "name": "Gauge",
+ "version": ""
+ },
+ {
+ "type": "grafana",
+ "id": "grafana",
+ "name": "Grafana",
+ "version": "8.4.3"
+ },
+ {
+ "type": "panel",
+ "id": "graph",
+ "name": "Graph (old)",
+ "version": ""
+ },
+ {
+ "type": "datasource",
+ "id": "prometheus",
+ "name": "Prometheus",
+ "version": "1.0.0"
+ },
+ {
+ "type": "panel",
+ "id": "stat",
+ "name": "Stat",
+ "version": ""
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "$$hashKey": "object:1058",
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "target": {
+ "limit": 100,
+ "matchAny": false,
+ "tags": [],
+ "type": "dashboard"
+ },
+ "type": "dashboard"
+ }
+ ]
+ },
+ "editable": true,
+ "fiscalYearStartMonth": 0,
+ "gnetId": 1860,
+ "graphTooltip": 0,
+ "id": null,
+ "iteration": 1649441854879,
+ "links": [
+ {
+ "icon": "external link",
+ "tags": [],
+ "title": "Github",
+ "type": "link",
+ "url": "https://github.com/rfrail3/grafana-dashboards"
+ },
+ {
+ "icon": "external link",
+ "tags": [],
+ "title": "Grafana",
+ "type": "link",
+ "url": "https://grafana.com/grafana/dashboards/1860"
+ }
+ ],
+ "liveNow": false,
+ "panels": [
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 261,
+ "panels": [],
+ "title": "Quick CPU / Mem / Disk",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Busy state of all CPU cores together",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)",
+ "value": null
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 85
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 95
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 0,
+ "y": 1
+ },
+ "id": 20,
+ "links": [],
+ "options": {
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr":
"(((count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by
(cpu))) - avg(sum by
(mode)(rate(node_cpu_seconds_total{mode='idle',instance=\"$node\",job=\"$job\"}[$__rate_interval]))))
* 100) / count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"})
by (cpu))",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "CPU Busy",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Busy state of all CPU cores together (5 min average)",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)",
+ "value": null
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 85
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 95
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 3,
+ "y": 1
+ },
+ "id": 155,
+ "links": [],
+ "options": {
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr": "avg(node_load5{instance=\"$node\",job=\"$job\"}) /
count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))
* 100",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Sys Load (5m avg)",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Busy state of all CPU cores together (15 min average)",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)",
+ "value": null
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 85
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 95
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 6,
+ "y": 1
+ },
+ "id": 19,
+ "links": [],
+ "options": {
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr": "avg(node_load15{instance=\"$node\",job=\"$job\"}) /
count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))
* 100",
+ "hide": false,
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Sys Load (15m avg)",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Non available RAM memory",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)",
+ "value": null
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 80
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 90
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 9,
+ "y": 1
+ },
+ "hideTimeOverride": false,
+ "id": 16,
+ "links": [],
+ "options": {
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr":
"((node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}) /
(node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} )) * 100",
+ "format": "time_series",
+ "hide": true,
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "100 -
((node_memory_MemAvailable_bytes{instance=\"$node\",job=\"$job\"} * 100) /
node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "RAM Used",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Used Swap",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)",
+ "value": null
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 10
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 25
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 12,
+ "y": 1
+ },
+ "id": 21,
+ "links": [],
+ "options": {
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr":
"((node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"}) /
(node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} )) * 100",
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "SWAP Used",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Used Root FS",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)",
+ "value": null
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 80
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 90
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 15,
+ "y": 1
+ },
+ "id": 154,
+ "links": [],
+ "options": {
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "text": {}
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr": "100 -
((node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",mountpoint=\"/\",fstype!=\"rootfs\"}
* 100) /
node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",mountpoint=\"/\",fstype!=\"rootfs\"})",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Root FS Used",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Total number of CPU cores",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 18,
+ "y": 1
+ },
+ "id": 14,
+ "links": [],
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr":
"count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by
(cpu))",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "CPU Cores",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "System uptime",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 4,
+ "x": 20,
+ "y": 1
+ },
+ "hideTimeOverride": true,
+ "id": 15,
+ "links": [],
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr": "node_time_seconds{instance=\"$node\",job=\"$job\"} -
node_boot_time_seconds{instance=\"$node\",job=\"$job\"}",
+ "intervalFactor": 2,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Uptime",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Total RootFS",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)",
+ "value": null
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 70
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 90
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 18,
+ "y": 3
+ },
+ "id": 23,
+ "links": [],
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr":
"node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",mountpoint=\"/\",fstype!=\"rootfs\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "RootFS Total",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Total RAM",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 20,
+ "y": 3
+ },
+ "id": 75,
+ "links": [],
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr":
"node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "RAM Total",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Total SWAP",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 22,
+ "y": 3
+ },
+ "id": 18,
+ "links": [],
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "8.4.3",
+ "targets": [
+ {
+ "expr":
"node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "SWAP Total",
+ "type": "stat"
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 5
+ },
+ "id": 263,
+ "panels": [],
+ "title": "Basic CPU / Mem / Net / Disk",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "Busy": "#EAB839",
+ "Busy Iowait": "#890F02",
+ "Busy other": "#1F78C1",
+ "Idle": "#052B51",
+ "Idle - Waiting for something to happen": "#052B51",
+ "guest": "#9AC48A",
+ "idle": "#052B51",
+ "iowait": "#EAB839",
+ "irq": "#BF1B00",
+ "nice": "#C15C17",
+ "softirq": "#E24D42",
+ "steal": "#FCE2DE",
+ "system": "#508642",
+ "user": "#5195CE"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "description": "Basic CPU info",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 6
+ },
+ "hiddenSeries": false,
+ "id": 77,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 250,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": true,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Busy Iowait",
+ "color": "#890F02"
+ },
+ {
+ "alias": "Idle",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "Busy System",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "Busy User",
+ "color": "#0A437C"
+ },
+ {
+ "alias": "Busy Other",
+ "color": "#6D1F62"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by
(instance)(rate(node_cpu_seconds_total{mode=\"system\",instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Busy System",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(instance)(rate(node_cpu_seconds_total{mode='user',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Busy User",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(instance)(rate(node_cpu_seconds_total{mode='iowait',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Busy Iowait",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(instance)(rate(node_cpu_seconds_total{mode=~\".*irq\",instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Busy IRQs",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr": "sum
(rate(node_cpu_seconds_total{mode!='idle',mode!='user',mode!='system',mode!='iowait',mode!='irq',mode!='softirq',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Busy Other",
+ "refId": "E",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='idle',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Idle",
+ "refId": "F",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "CPU Basic",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:123",
+ "format": "short",
+ "label": "",
+ "logBase": 1,
+ "max": "100",
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:124",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "SWAP Used": "#BF1B00",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap Used": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "description": "Basic memory usage",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 6
+ },
+ "hiddenSeries": false,
+ "id": 78,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "RAM Total",
+ "color": "#E0F9D7",
+ "fill": 0,
+ "stack": false
+ },
+ {
+ "alias": "RAM Cache + Buffer",
+ "color": "#052B51"
+ },
+ {
+ "alias": "RAM Free",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "Avaliable",
+ "color": "#DEDAF7",
+ "fill": 0,
+ "stack": false
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "RAM Total",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}
- node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"} -
(node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} +
node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "RAM Used",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} +
node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "RAM Cache + Buffer",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "RAM Free",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr":
"(node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "SWAP Used",
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Basic",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Recv_bytes_eth2": "#7EB26D",
+ "Recv_bytes_lo": "#0A50A1",
+ "Recv_drop_eth2": "#6ED0E0",
+ "Recv_drop_lo": "#E0F9D7",
+ "Recv_errs_eth2": "#BF1B00",
+ "Recv_errs_lo": "#CCA300",
+ "Trans_bytes_eth2": "#7EB26D",
+ "Trans_bytes_lo": "#0A50A1",
+ "Trans_drop_eth2": "#6ED0E0",
+ "Trans_drop_lo": "#E0F9D7",
+ "Trans_errs_eth2": "#BF1B00",
+ "Trans_errs_lo": "#CCA300",
+ "recv_bytes_lo": "#0A50A1",
+ "recv_drop_eth0": "#99440A",
+ "recv_drop_lo": "#967302",
+ "recv_errs_eth0": "#BF1B00",
+ "recv_errs_lo": "#890F02",
+ "trans_bytes_eth0": "#7EB26D",
+ "trans_bytes_lo": "#0A50A1",
+ "trans_drop_eth0": "#99440A",
+ "trans_drop_lo": "#967302",
+ "trans_errs_eth0": "#BF1B00",
+ "trans_errs_lo": "#890F02"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Basic network info per interface",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 13
+ },
+ "hiddenSeries": false,
+ "id": 74,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "recv {{device}}",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_network_transmit_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "trans {{device}} ",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Basic",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bps",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "pps",
+ "label": "",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 3,
+ "description": "Disk space used of all filesystems mounted",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 13
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 152,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "100 -
((node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}
* 100) /
node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}}",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk Space Used Basic",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "logBase": 1,
+ "max": "100",
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 20
+ },
+ "id": 265,
+ "panels": [],
+ "title": "CPU / Memory / Net / Disk",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "Idle - Waiting for something to happen": "#052B51",
+ "guest": "#9AC48A",
+ "idle": "#052B51",
+ "iowait": "#EAB839",
+ "irq": "#BF1B00",
+ "nice": "#C15C17",
+ "softirq": "#E24D42",
+ "steal": "#FCE2DE",
+ "system": "#508642",
+ "user": "#5195CE"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 21
+ },
+ "hiddenSeries": false,
+ "id": 3,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 250,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": true,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode=\"system\",instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "interval": "10s",
+ "intervalFactor": 2,
+ "legendFormat": "System - Processes executing in kernel mode",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='user',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "User - Normal processes executing in user mode",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='nice',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Nice - Niced processes executing in user mode",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='idle',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Idle - Waiting for something to happen",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='iowait',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Iowait - Waiting for I/O to complete",
+ "refId": "E",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='irq',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Irq - Servicing interrupts",
+ "refId": "F",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='softirq',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Softirq - Servicing softirqs",
+ "refId": "G",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='steal',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Steal - Time spent in other operating systems when
running in a virtualized environment",
+ "refId": "H",
+ "step": 240
+ },
+ {
+ "expr": "sum by
(mode)(rate(node_cpu_seconds_total{mode='guest',instance=\"$node\",job=\"$job\"}[$__rate_interval]))
* 100",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Guest - Time spent running a virtual CPU for a
guest operating system",
+ "refId": "I",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "CPU",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "percentage",
+ "logBase": 1,
+ "max": "100",
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap - Swap memory usage": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839",
+ "Unused - Free memory unassigned": "#052B51"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 21
+ },
+ "hiddenSeries": false,
+ "id": 24,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Hardware Corrupted - *./",
+ "stack": false
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}
- node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_Slab_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_PageTables_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_SwapCached_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Apps - Memory used by user-space applications",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_PageTables_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "PageTables - Memory used to map between virtual and
physical memory addresses",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_SwapCached_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "SwapCache - Memory that keeps track of pages that
have been fetched from swap but not yet been modified",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Slab_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Slab - Memory used by the kernel to cache data
structures for its own use (caches like inode, dentry, etc)",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Cache - Parked file data (file content) cache",
+ "refId": "E",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Buffers - Block device (e.g. harddisk) cache",
+ "refId": "F",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Unused - Free memory unassigned",
+ "refId": "G",
+ "step": 240
+ },
+ {
+ "expr":
"(node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} -
node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Swap - Swap space used",
+ "refId": "H",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_HardwareCorrupted_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Hardware Corrupted - Amount of RAM that the kernel
identified as corrupted / not working",
+ "refId": "I",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Stack",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "receive_packets_eth0": "#7EB26D",
+ "receive_packets_lo": "#E24D42",
+ "transmit_packets_eth0": "#7EB26D",
+ "transmit_packets_lo": "#E24D42"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 33
+ },
+ "hiddenSeries": false,
+ "id": 84,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:5871",
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_network_transmit_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Transmit",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:5884",
+ "format": "bps",
+ "label": "bits out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:5885",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 3,
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 33
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 156,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": false,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'} -
node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}}",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk Space Used",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 45
+ },
+ "hiddenSeries": false,
+ "id": 229,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Read.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - Reads completed",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Writes completed",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk IOps",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "iops",
+ "label": "IO read (-) / write (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "io time": "#890F02"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 3,
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 45
+ },
+ "hiddenSeries": false,
+ "id": 42,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*read*./",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*sda.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde.*/",
+ "color": "#E24D42"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_read_bytes_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Successfully read bytes",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_written_bytes_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Successfully written bytes",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "I/O Usage Read / Write",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:965",
+ "format": "Bps",
+ "label": "bytes read (-) / write (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:966",
+ "format": "ms",
+ "label": "",
+ "logBase": 1,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "io time": "#890F02"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 3,
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 4,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 57
+ },
+ "hiddenSeries": false,
+ "id": 127,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_io_time_seconds_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}
[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}}",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "I/O Utilization",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1041",
+ "format": "percentunit",
+ "label": "%util",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1042",
+ "format": "s",
+ "label": "",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 69
+ },
+ "id": 266,
+ "panels": [],
+ "title": "Memory Meminfo",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 70
+ },
+ "hiddenSeries": false,
+ "id": 136,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 2,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_Inactive_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Inactive - Memory which has been less recently
used. It is more eligible to be reclaimed for other purposes",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Active_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Active - Memory that has been used more recently
and usually not reclaimed unless absolutely necessary",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Active / Inactive",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 70
+ },
+ "hiddenSeries": false,
+ "id": 135,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Committed_AS - *./"
+ },
+ {
+ "alias": "/.*CommitLimit - *./",
+ "color": "#BF1B00",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_Committed_AS_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Committed_AS - Amount of memory presently allocated
on the system",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_CommitLimit_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "CommitLimit - Amount of memory currently available
to be allocated on the system",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Commited",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 80
+ },
+ "hiddenSeries": false,
+ "id": 191,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_Inactive_file_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Inactive_file - File-backed memory on inactive LRU
list",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_Inactive_anon_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Inactive_anon - Anonymous and swap cache on
inactive LRU list, including tmpfs (shmem)",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_Active_file_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Active_file - File-backed memory on active LRU
list",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_Active_anon_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Active_anon - Anonymous and swap cache on active
least-recently-used (LRU) list, including tmpfs",
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Active / Inactive Detail",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "bytes",
+ "logBase": 1,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#052B51",
+ "Total RAM + Swap": "#052B51",
+ "Total Swap": "#614D93",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 80
+ },
+ "hiddenSeries": false,
+ "id": 130,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 2,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_Writeback_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Writeback - Memory which is actively being written
back to disk",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_WritebackTmp_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "WritebackTmp - Memory used by FUSE for temporary
writeback buffers",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Dirty_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Dirty - Memory which is waiting to get written back
to the disk",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Writeback and Dirty",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 90
+ },
+ "hiddenSeries": false,
+ "id": 138,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:4131",
+ "alias": "ShmemHugePages - Memory used by shared memory (shmem) and
tmpfs allocated with huge pages",
+ "fill": 0
+ },
+ {
+ "$$hashKey": "object:4138",
+ "alias": "ShmemHugePages - Memory used by shared memory (shmem) and
tmpfs allocated with huge pages",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_memory_Mapped_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Mapped - Used memory in mapped pages files which
have been mmaped, such as libraries",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Shmem_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Shmem - Used shared memory (shared between several
processes, thus including RAM disks)",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_ShmemHugePages_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "ShmemHugePages - Memory used by shared memory
(shmem) and tmpfs allocated with huge pages",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_ShmemPmdMapped_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "ShmemPmdMapped - Ammount of shared (shmem/tmpfs)
memory backed by huge pages",
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Shared and Mapped",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:4106",
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:4107",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#052B51",
+ "Total RAM + Swap": "#052B51",
+ "Total Swap": "#614D93",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 90
+ },
+ "hiddenSeries": false,
+ "id": 131,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 2,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_SUnreclaim_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "SUnreclaim - Part of Slab, that cannot be reclaimed
on memory pressure",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_SReclaimable_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "SReclaimable - Part of Slab, that might be
reclaimed, such as caches",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Slab",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#052B51",
+ "Total RAM + Swap": "#052B51",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 100
+ },
+ "hiddenSeries": false,
+ "id": 70,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_VmallocChunk_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "VmallocChunk - Largest contigious block of vmalloc
area which is free",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_VmallocTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "VmallocTotal - Total size of vmalloc memory area",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_VmallocUsed_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "VmallocUsed - Amount of vmalloc area which is used",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Vmalloc",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 100
+ },
+ "hiddenSeries": false,
+ "id": 159,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_memory_Bounce_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Bounce - Memory used for block device bounce
buffers",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Bounce",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#052B51",
+ "Total RAM + Swap": "#052B51",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 110
+ },
+ "hiddenSeries": false,
+ "id": 129,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Inactive *./",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_AnonHugePages_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "AnonHugePages - Memory in anonymous huge pages",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_AnonPages_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "AnonPages - Memory in user pages not backed by
files",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Anonymous",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 110
+ },
+ "hiddenSeries": false,
+ "id": 160,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 2,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_KernelStack_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "KernelStack - Kernel memory stack. This is not
reclaimable",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Percpu_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "PerCPU - Per CPU memory allocated dynamically by
loadable modules",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Kernel / CPU",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#806EB7",
+ "Total RAM + Swap": "#806EB7",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 120
+ },
+ "hiddenSeries": false,
+ "id": 140,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_HugePages_Free{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "HugePages_Free - Huge pages in the pool that are
not yet allocated",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_HugePages_Rsvd{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "HugePages_Rsvd - Huge pages for which a commitment
to allocate from the pool has been made, but no allocation has yet been made",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_HugePages_Surp{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "HugePages_Surp - Huge pages in the pool above the
value in /proc/sys/vm/nr_hugepages",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory HugePages Counter",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "pages",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": "",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#806EB7",
+ "Total RAM + Swap": "#806EB7",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 120
+ },
+ "hiddenSeries": false,
+ "id": 71,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 2,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_HugePages_Total{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "HugePages - Total size of the pool of huge pages",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_Hugepagesize_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Hugepagesize - Huge Page size",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory HugePages Size",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": "",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#052B51",
+ "Total RAM + Swap": "#052B51",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 130
+ },
+ "hiddenSeries": false,
+ "id": 128,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": false,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_DirectMap1G_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "DirectMap1G - Amount of pages mapped as this size",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_DirectMap2M_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "DirectMap2M - Amount of pages mapped as this size",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_memory_DirectMap4k_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "DirectMap4K - Amount of pages mapped as this size",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory DirectMap",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 130
+ },
+ "hiddenSeries": false,
+ "id": 137,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_Unevictable_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Unevictable - Amount of unevictable memory that
can't be swapped out for a variety of reasons",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_memory_Mlocked_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "MLocked - Size of pages locked to memory using the
mlock() system call",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Unevictable and MLocked",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#052B51",
+ "Total RAM + Swap": "#052B51",
+ "Total Swap": "#614D93",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 140
+ },
+ "hiddenSeries": false,
+ "id": 132,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_memory_NFS_Unstable_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "NFS Unstable - Memory in NFS pages sent to the
server, but not yet commited to the storage",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory NFS",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 150
+ },
+ "id": 267,
+ "panels": [],
+ "title": "Memory Vmstat",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 151
+ },
+ "hiddenSeries": false,
+ "id": 176,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*out/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_vmstat_pgpgin{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Pagesin - Page in operations",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_vmstat_pgpgout{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Pagesout - Page out operations",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Pages In / Out",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "pages out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 151
+ },
+ "hiddenSeries": false,
+ "id": 22,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*out/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_vmstat_pswpin{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Pswpin - Pages swapped in",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_vmstat_pswpout{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Pswpout - Pages swapped out",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Pages Swap In / Out",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "pages out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Apps": "#629E51",
+ "Buffers": "#614D93",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Free": "#0A437C",
+ "Hardware Corrupted - Amount of RAM that the kernel identified as
corrupted / not working": "#CFFAFF",
+ "Inactive": "#584477",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "RAM_Free": "#E0F9D7",
+ "Slab": "#806EB7",
+ "Slab_Cache": "#E0752D",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Swap_Free": "#2F575E",
+ "Unused": "#EAB839"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 161
+ },
+ "hiddenSeries": false,
+ "id": 175,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 350,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:6118",
+ "alias": "Pgfault - Page major and minor fault operations",
+ "fill": 0,
+ "stack": false
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_vmstat_pgfault{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Pgfault - Page major and minor fault operations",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_vmstat_pgmajfault{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Pgmajfault - Major page fault operations",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_vmstat_pgfault{instance=\"$node\",job=\"$job\"}[$__rate_interval])
-
rate(node_vmstat_pgmajfault{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Pgminfault - Minor page fault operations",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Memory Page Faults",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6133",
+ "format": "short",
+ "label": "faults",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6134",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "Active": "#99440A",
+ "Buffers": "#58140C",
+ "Cache": "#6D1F62",
+ "Cached": "#511749",
+ "Committed": "#508642",
+ "Dirty": "#6ED0E0",
+ "Free": "#B7DBAB",
+ "Inactive": "#EA6460",
+ "Mapped": "#052B51",
+ "PageTables": "#0A50A1",
+ "Page_Tables": "#0A50A1",
+ "Slab_Cache": "#EAB839",
+ "Swap": "#BF1B00",
+ "Swap_Cache": "#C15C17",
+ "Total": "#511749",
+ "Total RAM": "#052B51",
+ "Total RAM + Swap": "#052B51",
+ "Total Swap": "#614D93",
+ "VmallocUsed": "#EA6460"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 2,
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 161
+ },
+ "hiddenSeries": false,
+ "id": 307,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_vmstat_oom_kill{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "oom killer invocations ",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "OOM Killer",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:5373",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:5374",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 171
+ },
+ "id": 293,
+ "panels": [],
+ "title": "System Timesync",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 172
+ },
+ "hiddenSeries": false,
+ "id": 260,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Variation*./",
+ "color": "#890F02"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_timex_estimated_error_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Estimated error in seconds",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_timex_offset_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Time offset in between local system and reference
clock",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_timex_maxerror_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Maximum error in seconds",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Time Syncronized Drift",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": "seconds",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 172
+ },
+ "hiddenSeries": false,
+ "id": 291,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_timex_loop_time_constant{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Phase-locked loop time adjust",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Time PLL Adjust",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 182
+ },
+ "hiddenSeries": false,
+ "id": 168,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Variation*./",
+ "color": "#890F02"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_timex_sync_status{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Is clock synchronized to a reliable server (1 =
yes, 0 = no)",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_timex_frequency_adjustment_ratio{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Local clock frequency adjustment",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Time Syncronized Status",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 182
+ },
+ "hiddenSeries": false,
+ "id": 294,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_timex_tick_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Seconds between clock ticks",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_timex_tai_offset_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "International Atomic Time (TAI) offset",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Time Misc",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": "seconds",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 192
+ },
+ "id": 312,
+ "panels": [],
+ "title": "System Processes",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 193
+ },
+ "hiddenSeries": false,
+ "id": 62,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_procs_blocked{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Processes blocked waiting for I/O to complete",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_procs_running{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Processes in runnable state",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Processes Status",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6500",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6501",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 193
+ },
+ "hiddenSeries": false,
+ "id": 315,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_processes_state{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ state }}",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Processes State",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6500",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6501",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 203
+ },
+ "hiddenSeries": false,
+ "id": 148,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_forks_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Processes forks second",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Processes Forks",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6640",
+ "format": "short",
+ "label": "forks / sec",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6641",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 203
+ },
+ "hiddenSeries": false,
+ "id": 149,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Max.*/",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(process_virtual_memory_bytes{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Processes virtual memory size in bytes",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"process_resident_memory_max_bytes{instance=\"$node\",job=\"$job\"}",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Maximum amount of virtual memory available in
bytes",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"rate(process_virtual_memory_bytes{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Processes virtual memory size in bytes",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr":
"rate(process_virtual_memory_max_bytes{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Maximum amount of virtual memory available in
bytes",
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Processes Memory",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "decbytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 213
+ },
+ "hiddenSeries": false,
+ "id": 313,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:709",
+ "alias": "PIDs limit",
+ "color": "#F2495C",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_processes_pids{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Number of PIDs",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_processes_max_processes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "PIDs limit",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "PIDs Number and Limit",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6500",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6501",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 213
+ },
+ "hiddenSeries": false,
+ "id": 305,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:4963",
+ "alias": "/.*waiting.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_schedstat_running_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "CPU {{ cpu }} - seconds spent running a process",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_schedstat_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "CPU {{ cpu }} - seconds spent by processing waiting
for this CPU",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Process schedule stats Running / Waiting",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:4860",
+ "format": "s",
+ "label": "seconds",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:4861",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 223
+ },
+ "hiddenSeries": false,
+ "id": 314,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:709",
+ "alias": "Threads limit",
+ "color": "#F2495C",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_processes_threads{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Allocated threads",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_processes_max_threads{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Threads limit",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Threads Number and Limit",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6500",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6501",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 233
+ },
+ "id": 269,
+ "panels": [],
+ "title": "System Misc",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 234
+ },
+ "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": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_context_switches_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Context switches",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_intr_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Interrupts",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Context Switches / Interrupts",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 234
+ },
+ "hiddenSeries": false,
+ "id": 7,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_load1{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 4,
+ "legendFormat": "Load 1m",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_load5{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 4,
+ "legendFormat": "Load 5m",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "node_load15{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 4,
+ "legendFormat": "Load 15m",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "System Load",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6261",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6262",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 244
+ },
+ "hiddenSeries": false,
+ "id": 259,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Critical*./",
+ "color": "#E24D42",
+ "fill": 0
+ },
+ {
+ "alias": "/.*Max*./",
+ "color": "#EF843C",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_interrupts_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ type }} - {{ info }}",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Interrupts Detail",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 244
+ },
+ "hiddenSeries": false,
+ "id": 306,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_schedstat_timeslices_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "CPU {{ cpu }}",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Schedule timeslices executed by each cpu",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:4860",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:4861",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 254
+ },
+ "hiddenSeries": false,
+ "id": 151,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_entropy_available_bits{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Entropy available to random number generators",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Entropy",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6568",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6569",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 254
+ },
+ "hiddenSeries": false,
+ "id": 308,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(process_cpu_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Time spent",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "CPU time spent in user and system contexts",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:4860",
+ "format": "s",
+ "label": "seconds",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:4861",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 264
+ },
+ "hiddenSeries": false,
+ "id": 64,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:6323",
+ "alias": "/.*Max*./",
+ "color": "#890F02",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "process_max_fds{instance=\"$node\",job=\"$job\"}",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Maximum open file descriptors",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "process_open_fds{instance=\"$node\",job=\"$job\"}",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Open file descriptors",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "File Descriptors",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6338",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6339",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 274
+ },
+ "id": 304,
+ "panels": [],
+ "title": "Hardware Misc",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 275
+ },
+ "hiddenSeries": false,
+ "id": 158,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:6726",
+ "alias": "/.*Critical*./",
+ "color": "#E24D42",
+ "fill": 0
+ },
+ {
+ "$$hashKey": "object:6727",
+ "alias": "/.*Max*./",
+ "color": "#EF843C",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_hwmon_temp_celsius{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ chip }} {{ sensor }} temp",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_hwmon_temp_crit_alarm_celsius{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ chip }} {{ sensor }} Critical Alarm",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_hwmon_temp_crit_celsius{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ chip }} {{ sensor }} Critical",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr":
"node_hwmon_temp_crit_hyst_celsius{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ chip }} {{ sensor }} Critical Historical",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr":
"node_hwmon_temp_max_celsius{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ chip }} {{ sensor }} Max",
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Hardware temperature monitor",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:6750",
+ "format": "celsius",
+ "label": "temperature",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:6751",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 275
+ },
+ "hiddenSeries": false,
+ "id": 300,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:1655",
+ "alias": "/.*Max*./",
+ "color": "#EF843C",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_cooling_device_cur_state{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Current {{ name }} in {{ type }}",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_cooling_device_max_state{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Max {{ name }} in {{ type }}",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Throttle cooling device",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1678",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1679",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 285
+ },
+ "hiddenSeries": false,
+ "id": 302,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_power_supply_online{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ power_supply }} online",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Power supply",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1678",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1679",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 295
+ },
+ "id": 296,
+ "panels": [],
+ "title": "Systemd",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 296
+ },
+ "hiddenSeries": false,
+ "id": 297,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_systemd_socket_accepted_connections_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{ name }} Connections",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Systemd Sockets",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 296
+ },
+ "hiddenSeries": false,
+ "id": 298,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Failed",
+ "color": "#F2495C"
+ },
+ {
+ "alias": "Inactive",
+ "color": "#FF9830"
+ },
+ {
+ "alias": "Active",
+ "color": "#73BF69"
+ },
+ {
+ "alias": "Deactivating",
+ "color": "#FFCB7D"
+ },
+ {
+ "alias": "Activating",
+ "color": "#C8F2C2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_systemd_units{instance=\"$node\",job=\"$job\",state=\"activating\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Activating",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_systemd_units{instance=\"$node\",job=\"$job\",state=\"active\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Active",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_systemd_units{instance=\"$node\",job=\"$job\",state=\"deactivating\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Deactivating",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr":
"node_systemd_units{instance=\"$node\",job=\"$job\",state=\"failed\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Failed",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr":
"node_systemd_units{instance=\"$node\",job=\"$job\",state=\"inactive\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Inactive",
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Systemd Units State",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 306
+ },
+ "id": 270,
+ "panels": [],
+ "title": "Storage Disk",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "The number (after merges) of I/O requests completed per
second for the device",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 307
+ },
+ "hiddenSeries": false,
+ "id": 9,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:2033",
+ "alias": "/.*Read.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "$$hashKey": "object:2034",
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "$$hashKey": "object:2035",
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "$$hashKey": "object:2036",
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "$$hashKey": "object:2037",
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "$$hashKey": "object:2038",
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "$$hashKey": "object:2039",
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "$$hashKey": "object:2040",
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "$$hashKey": "object:2041",
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "$$hashKey": "object:2042",
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "$$hashKey": "object:2043",
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "$$hashKey": "object:2044",
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "$$hashKey": "object:2045",
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "$$hashKey": "object:2046",
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "$$hashKey": "object:2047",
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "$$hashKey": "object:2048",
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "$$hashKey": "object:2049",
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "$$hashKey": "object:2050",
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "$$hashKey": "object:2051",
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "$$hashKey": "object:2052",
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "$$hashKey": "object:2053",
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - Reads completed",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Writes completed",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk IOps Completed",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:2186",
+ "format": "iops",
+ "label": "IO read (-) / write (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:2187",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "The number of bytes read from or written to the device
per second",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 307
+ },
+ "hiddenSeries": false,
+ "id": 33,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Read.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_read_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - Read bytes",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_written_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Written bytes",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk R/W Data",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:369",
+ "format": "Bps",
+ "label": "bytes read (-) / write (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:370",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "The average time for requests issued to the device to be
served. This includes the time spent by the requests in queue and the time
spent servicing them.",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 3,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 317
+ },
+ "hiddenSeries": false,
+ "id": 37,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Read.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_read_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])
/
rate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - r_await",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_write_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])
/
rate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - w_await",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk Average Wait Time",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:441",
+ "format": "s",
+ "label": "time. read (-) / write (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:442",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "The average queue length of the requests that were
issued to the device",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 317
+ },
+ "hiddenSeries": false,
+ "id": 35,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_io_time_weighted_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}}",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Average Queue Size",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:513",
+ "format": "none",
+ "label": "aqu-sz",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:514",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "The number of read and write requests merged per second
that were queued to the device",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 327
+ },
+ "hiddenSeries": false,
+ "id": 133,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Read.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_reads_merged_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Read merged",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_writes_merged_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Write merged",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk R/W Merged",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:585",
+ "format": "iops",
+ "label": "I/Os",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:586",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Percentage of elapsed time during which I/O requests
were issued to the device (bandwidth utilization for the device). Device
saturation occurs when this value is close to 100% for devices serving requests
serially. But for devices serving requests in parallel, such as RAID arrays
and modern SSDs, this number does not reflect their performance limits.",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 3,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 327
+ },
+ "hiddenSeries": false,
+ "id": 36,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_io_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - IO",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_discard_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - discard",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Time Spent Doing I/Os",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:657",
+ "format": "percentunit",
+ "label": "%util",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:658",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "The number of outstanding requests at the instant the
sample was taken. Incremented as requests are given to appropriate struct
request_queue and decremented as they finish.",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 337
+ },
+ "hiddenSeries": false,
+ "id": 34,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_io_now{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - IO now",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Instantaneous Queue Size",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:729",
+ "format": "iops",
+ "label": "I/Os",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:730",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 337
+ },
+ "hiddenSeries": false,
+ "id": 301,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null as zero",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:2034",
+ "alias": "/.*sda_.*/",
+ "color": "#7EB26D"
+ },
+ {
+ "$$hashKey": "object:2035",
+ "alias": "/.*sdb_.*/",
+ "color": "#EAB839"
+ },
+ {
+ "$$hashKey": "object:2036",
+ "alias": "/.*sdc_.*/",
+ "color": "#6ED0E0"
+ },
+ {
+ "$$hashKey": "object:2037",
+ "alias": "/.*sdd_.*/",
+ "color": "#EF843C"
+ },
+ {
+ "$$hashKey": "object:2038",
+ "alias": "/.*sde_.*/",
+ "color": "#E24D42"
+ },
+ {
+ "$$hashKey": "object:2039",
+ "alias": "/.*sda1.*/",
+ "color": "#584477"
+ },
+ {
+ "$$hashKey": "object:2040",
+ "alias": "/.*sda2_.*/",
+ "color": "#BA43A9"
+ },
+ {
+ "$$hashKey": "object:2041",
+ "alias": "/.*sda3_.*/",
+ "color": "#F4D598"
+ },
+ {
+ "$$hashKey": "object:2042",
+ "alias": "/.*sdb1.*/",
+ "color": "#0A50A1"
+ },
+ {
+ "$$hashKey": "object:2043",
+ "alias": "/.*sdb2.*/",
+ "color": "#BF1B00"
+ },
+ {
+ "$$hashKey": "object:2044",
+ "alias": "/.*sdb3.*/",
+ "color": "#E0752D"
+ },
+ {
+ "$$hashKey": "object:2045",
+ "alias": "/.*sdc1.*/",
+ "color": "#962D82"
+ },
+ {
+ "$$hashKey": "object:2046",
+ "alias": "/.*sdc2.*/",
+ "color": "#614D93"
+ },
+ {
+ "$$hashKey": "object:2047",
+ "alias": "/.*sdc3.*/",
+ "color": "#9AC48A"
+ },
+ {
+ "$$hashKey": "object:2048",
+ "alias": "/.*sdd1.*/",
+ "color": "#65C5DB"
+ },
+ {
+ "$$hashKey": "object:2049",
+ "alias": "/.*sdd2.*/",
+ "color": "#F9934E"
+ },
+ {
+ "$$hashKey": "object:2050",
+ "alias": "/.*sdd3.*/",
+ "color": "#EA6460"
+ },
+ {
+ "$$hashKey": "object:2051",
+ "alias": "/.*sde1.*/",
+ "color": "#E0F9D7"
+ },
+ {
+ "$$hashKey": "object:2052",
+ "alias": "/.*sdd2.*/",
+ "color": "#FCEACA"
+ },
+ {
+ "$$hashKey": "object:2053",
+ "alias": "/.*sde3.*/",
+ "color": "#F9E2D2"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_disk_discards_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - Discards completed",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_disk_discards_merged_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Discards merged",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Disk IOps Discards completed / merged",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:2186",
+ "format": "iops",
+ "label": "IOs",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:2187",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 347
+ },
+ "id": 271,
+ "panels": [],
+ "title": "Storage Filesystem",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "decimals": 3,
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 348
+ },
+ "hiddenSeries": false,
+ "id": 43,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}} - Available",
+ "metric": "",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_filesystem_free_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}} - Free",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}} - Size",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Filesystem space available",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:3826",
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:3827",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 348
+ },
+ "hiddenSeries": false,
+ "id": 41,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_filesystem_files_free{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}} - Free file nodes",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "File Nodes Free",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:3894",
+ "format": "short",
+ "label": "file nodes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:3895",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 358
+ },
+ "hiddenSeries": false,
+ "id": 28,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_filefd_maximum{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 4,
+ "legendFormat": "Max open files",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_filefd_allocated{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Open files",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "File Descriptor",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "files",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 358
+ },
+ "hiddenSeries": false,
+ "id": 219,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_filesystem_files{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}} - File nodes total",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "File Nodes Size",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "file Nodes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {
+ "/ ReadOnly": "#890F02"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 368
+ },
+ "hiddenSeries": false,
+ "id": 44,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 6,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_filesystem_readonly{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}} - ReadOnly",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_filesystem_device_error{instance=\"$node\",job=\"$job\",device!~'rootfs',fstype!~'tmpfs'}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{mountpoint}} - Device error",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Filesystem in ReadOnly / Error",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:3670",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "max": "1",
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:3671",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 378
+ },
+ "id": 272,
+ "panels": [],
+ "title": "Network Traffic",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "receive_packets_eth0": "#7EB26D",
+ "receive_packets_lo": "#E24D42",
+ "transmit_packets_eth0": "#7EB26D",
+ "transmit_packets_lo": "#E24D42"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 379
+ },
+ "hiddenSeries": false,
+ "id": 60,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_packets_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_network_transmit_packets_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Transmit",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic by Packets",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "packets out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 379
+ },
+ "hiddenSeries": false,
+ "id": 142,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_errs_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive errors",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_network_transmit_errs_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Rransmit errors",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Errors",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "packets out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 389
+ },
+ "hiddenSeries": false,
+ "id": 143,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_drop_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive drop",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_network_transmit_drop_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Transmit drop",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Drop",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "packets out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 389
+ },
+ "hiddenSeries": false,
+ "id": 141,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_compressed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive compressed",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_network_transmit_compressed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Transmit compressed",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Compressed",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "packets out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 399
+ },
+ "hiddenSeries": false,
+ "id": 146,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_multicast_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive multicast",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Multicast",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "packets out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 399
+ },
+ "hiddenSeries": false,
+ "id": 144,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_fifo_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive fifo",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_network_transmit_fifo_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Transmit fifo",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Fifo",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "packets out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 409
+ },
+ "hiddenSeries": false,
+ "id": 145,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:576",
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_receive_frame_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Receive frame",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Frame",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:589",
+ "format": "pps",
+ "label": "packets out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:590",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 409
+ },
+ "hiddenSeries": false,
+ "id": 231,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_transmit_carrier_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Statistic transmit_carrier",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Carrier",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 419
+ },
+ "hiddenSeries": false,
+ "id": 232,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Trans.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_network_transmit_colls_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} - Transmit colls",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Traffic Colls",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 419
+ },
+ "hiddenSeries": false,
+ "id": 61,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:663",
+ "alias": "NF conntrack limit",
+ "color": "#890F02",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_nf_conntrack_entries{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "NF conntrack entries",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_nf_conntrack_entries_limit{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "NF conntrack limit",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "NF Contrack",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:678",
+ "format": "short",
+ "label": "entries",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:679",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 429
+ },
+ "hiddenSeries": false,
+ "id": 230,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_arp_entries{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{ device }} - ARP entries",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "ARP Entries",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "Entries",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 429
+ },
+ "hiddenSeries": false,
+ "id": 288,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 1,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_network_mtu_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{ device }} - Bytes",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "MTU",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": 0,
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 439
+ },
+ "hiddenSeries": false,
+ "id": 280,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 1,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_network_speed_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{ device }} - Speed",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Speed",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": 0,
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 439
+ },
+ "hiddenSeries": false,
+ "id": 289,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 1,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_network_transmit_queue_length{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{ device }} - Interface transmit queue length",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Queue Length",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": 0,
+ "format": "none",
+ "label": "packets",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 449
+ },
+ "hiddenSeries": false,
+ "id": 290,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:232",
+ "alias": "/.*Dropped.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_softnet_processed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "CPU {{cpu}} - Processed",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_softnet_dropped_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "CPU {{cpu}} - Dropped",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Softnet Packets",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:207",
+ "format": "short",
+ "label": "packetes drop (-) / process (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:208",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 449
+ },
+ "hiddenSeries": false,
+ "id": 310,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_softnet_times_squeezed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "CPU {{cpu}} - Squeezed",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Softnet Out of Quota",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:207",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:208",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 459
+ },
+ "hiddenSeries": false,
+ "id": 309,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_network_up{operstate=\"up\",instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{interface}} - Operational state UP",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_network_carrier{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "instant": false,
+ "legendFormat": "{{device}} - Physical link state",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Network Operational Status",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 469
+ },
+ "id": 273,
+ "panels": [],
+ "title": "Network Sockstat",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 470
+ },
+ "hiddenSeries": false,
+ "id": 63,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_sockstat_TCP_alloc{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "TCP_alloc - Allocated sockets",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_TCP_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "TCP_inuse - Tcp sockets currently in use",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_TCP_mem{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "TCP_mem - Used memory for tcp",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_TCP_orphan{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "TCP_orphan - Orphan sockets",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_TCP_tw{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "TCP_tw - Sockets wating close",
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Sockstat TCP",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 470
+ },
+ "hiddenSeries": false,
+ "id": 124,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_sockstat_UDPLITE_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "UDPLITE_inuse - Udplite sockets currently in use",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_UDP_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "UDP_inuse - Udp sockets currently in use",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_UDP_mem{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "UDP_mem - Used memory for udp",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Sockstat UDP",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 480
+ },
+ "hiddenSeries": false,
+ "id": 126,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_sockstat_sockets_used{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Sockets_used - Sockets currently in use",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Sockstat Used",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "sockets",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 480
+ },
+ "hiddenSeries": false,
+ "id": 220,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_sockstat_TCP_mem_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "mem_bytes - TCP sockets in that state",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_sockstat_UDP_mem_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "mem_bytes - UDP sockets in that state",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Sockstat Memory Size",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "bytes",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 490
+ },
+ "hiddenSeries": false,
+ "id": 125,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_sockstat_FRAG_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "FRAG_inuse - Frag sockets currently in use",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_FRAG_memory{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "FRAG_memory - Used memory for frag",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "node_sockstat_RAW_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "RAW_inuse - Raw sockets currently in use",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Sockstat FRAG / RAW",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1572",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1573",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 500
+ },
+ "id": 274,
+ "panels": [],
+ "title": "Network Netstat",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 501
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 221,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:1876",
+ "alias": "/.*Out.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_IpExt_InOctets{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "InOctets - Received octets",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_IpExt_OutOctets{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "OutOctets - Sent octets",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Netstat IP In / Out Octets",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1889",
+ "format": "short",
+ "label": "octects out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1890",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 501
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 81,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": 300,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_Ip_Forwarding{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "Forwarding - IP forwarding",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Netstat IP Forwarding",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1957",
+ "format": "short",
+ "label": "datagrams",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1958",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 511
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 115,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Out.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_Icmp_InMsgs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "InMsgs - Messages which the entity received. Note
that this counter includes all those counted by icmpInErrors",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_Icmp_OutMsgs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "OutMsgs - Messages which this entity attempted to
send. Note that this counter includes all those counted by icmpOutErrors",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "ICMP In / Out",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "messages out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 511
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 50,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Out.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_Icmp_InErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "InErrors - Messages which the entity received but
determined as having ICMP-specific errors (bad ICMP checksums, bad length,
etc.)",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "ICMP Errors",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "messages out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 521
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 55,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Out.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*Snd.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_Udp_InDatagrams{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "InDatagrams - Datagrams received",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_Udp_OutDatagrams{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "OutDatagrams - Datagrams sent",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "UDP In / Out",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "datagrams out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 521
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 109,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_Udp_InErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "InErrors - UDP Datagrams that could not be
delivered to an application",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_Udp_NoPorts{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "NoPorts - UDP Datagrams received on a port with no
listener",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_UdpLite_InErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "legendFormat": "InErrors Lite - UDPLite Datagrams that could not be
delivered to an application",
+ "refId": "C"
+ },
+ {
+ "expr":
"rate(node_netstat_Udp_RcvbufErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "RcvbufErrors - UDP buffer errors received",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_Udp_SndbufErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "SndbufErrors - UDP buffer errors send",
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "UDP Errors",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:4232",
+ "format": "short",
+ "label": "datagrams",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:4233",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 531
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 299,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Out.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*Snd.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_Tcp_InSegs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "instant": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "InSegs - Segments received, including those
received in error. This count includes segments received on currently
established connections",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_Tcp_OutSegs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "OutSegs - Segments sent, including those on current
connections but excluding those containing only retransmitted octets",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "TCP In / Out",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "datagrams out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 531
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 104,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_TcpExt_ListenOverflows{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "ListenOverflows - Times the listen queue of a
socket overflowed",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_TcpExt_ListenDrops{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "ListenDrops - SYNs to LISTEN sockets ignored",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_TcpExt_TCPSynRetrans{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "TCPSynRetrans - SYN-SYN/ACK retransmits to break
down retransmissions in SYN, fast/timeout retransmits",
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_Tcp_RetransSegs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "legendFormat": "RetransSegs - Segments retransmitted - that is, the
number of TCP segments transmitted containing one or more previously
transmitted octets",
+ "refId": "D"
+ },
+ {
+ "expr":
"rate(node_netstat_Tcp_InErrs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "legendFormat": "InErrs - Segments received in error (e.g., bad TCP
checksums)",
+ "refId": "E"
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "TCP Errors",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 541
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 85,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:454",
+ "alias": "/.*MaxConn *./",
+ "color": "#890F02",
+ "fill": 0
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_netstat_Tcp_CurrEstab{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "CurrEstab - TCP connections for which the current
state is either ESTABLISHED or CLOSE- WAIT",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_netstat_Tcp_MaxConn{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "MaxConn - Limit on the total number of TCP
connections the entity can support (Dinamic is \"-1\")",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "TCP Connections",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:469",
+ "format": "short",
+ "label": "connections",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:470",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 541
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 91,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/.*Sent.*/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_TcpExt_SyncookiesFailed{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "SyncookiesFailed - Invalid SYN cookies received",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_TcpExt_SyncookiesRecv{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "SyncookiesRecv - SYN cookies received",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_TcpExt_SyncookiesSent{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "SyncookiesSent - SYN cookies sent",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "TCP SynCookie",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "counter out (-) / in (+)",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 551
+ },
+ "height": "",
+ "hiddenSeries": false,
+ "id": 82,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideZero": false,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "maxPerRow": 12,
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.4.3",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"rate(node_netstat_Tcp_ActiveOpens{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "ActiveOpens - TCP connections that have made a
direct transition to the SYN-SENT state from the CLOSED state",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"rate(node_netstat_Tcp_PassiveOpens{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "PassiveOpens - TCP connections that have made a
direct transition to the SYN-RCVD state from the LISTEN state",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "TCP Direct Transition",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "connections",
+ "logBase": 1,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "collapsed": true,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 561
+ },
+ "id": 279,
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 292
+ },
+ "hiddenSeries": false,
+ "id": 40,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "show": true,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "alertThreshold": true
+ },
+ "percentage": false,
+ "pluginVersion": "8.2.1",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_scrape_collector_duration_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{collector}} - Scrape duration",
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Node Exporter Scrape Time",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": "seconds",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "links": []
+ },
+ "overrides": []
+ },
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 292
+ },
+ "hiddenSeries": false,
+ "id": 157,
+ "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
+ },
+ "percentage": false,
+ "pluginVersion": "8.2.1",
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:1969",
+ "alias": "/.*error.*/",
+ "color": "#F2495C",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr":
"node_scrape_collector_success{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{collector}} - Scrape success",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr":
"node_textfile_scrape_error{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{collector}} - Scrape textfile error (1 =
true)",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeRegions": [],
+ "title": "Node Exporter Scrape",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "mode": "time",
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1484",
+ "format": "short",
+ "label": "counter",
+ "logBase": 1,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1485",
+ "format": "short",
+ "logBase": 1,
+ "show": false
+ }
+ ],
+ "yaxis": {
+ "align": false
+ }
+ }
+ ],
+ "title": "Node Exporter",
+ "type": "row"
+ }
+ ],
+ "refresh": "1m",
+ "schemaVersion": 35,
+ "style": "dark",
+ "tags": [
+ "linux",
+ "performance"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "selected": false,
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "datasource",
+ "multi": false,
+ "name": "DS_PROMETHEUS",
+ "options": [],
+ "query": "prometheus",
+ "queryValue": "",
+ "refresh": 1,
+ "regex": "",
+ "skipUrlSync": false,
+ "type": "datasource"
+ },
+ {
+ "current": {},
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "definition": "",
+ "hide": 0,
+ "includeAll": false,
+ "label": "Job",
+ "multi": false,
+ "name": "job",
+ "options": [],
+ "query": {
+ "query": "label_values(node_uname_info, job)",
+ "refId": "Prometheus-job-Variable-Query"
+ },
+ "refresh": 1,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "current": {},
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "definition": "label_values(node_uname_info{job=\"$job\"}, instance)",
+ "hide": 0,
+ "includeAll": false,
+ "label": "Host:",
+ "multi": false,
+ "name": "node",
+ "options": [],
+ "query": {
+ "query": "label_values(node_uname_info{job=\"$job\"}, instance)",
+ "refId": "Prometheus-node-Variable-Query"
+ },
+ "refresh": 1,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "current": {
+ "selected": false,
+ "text": "[a-z]+|nvme[0-9]+n[0-9]+",
+ "value": "[a-z]+|nvme[0-9]+n[0-9]+"
+ },
+ "hide": 2,
+ "includeAll": false,
+ "multi": false,
+ "name": "diskdevices",
+ "options": [
+ {
+ "selected": true,
+ "text": "[a-z]+|nvme[0-9]+n[0-9]+",
+ "value": "[a-z]+|nvme[0-9]+n[0-9]+"
+ }
+ ],
+ "query": "[a-z]+|nvme[0-9]+n[0-9]+",
+ "skipUrlSync": false,
+ "type": "custom"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "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": "browser",
+ "title": "Nodes",
+ "uid": "rYdddlPWk",
+ "version": 8,
+ "weekStart": ""
+}
\ No newline at end of file
diff --git a/additional/grafana/proxy.json b/additional/grafana/proxy.json
index 8e353f9..ee2949a 100644
--- a/additional/grafana/proxy.json
+++ b/additional/grafana/proxy.json
@@ -61,7 +61,7 @@
"gnetId": 12708,
"graphTooltip": 0,
"id": null,
- "iteration": 1649237780981,
+ "iteration": 1649441826256,
"links": [],
"liveNow": false,
"panels": [
@@ -538,7 +538,7 @@
"uid": "${DS_PROMETHEUS}"
},
"exemplar": true,
- "expr": "avg
((rate(taler_requests_upstream_response_time_sum{endpoint!~\"keys|terms\",
status=\"200\"} [2m]) ) /
(rate(taler_requests_upstream_response_time_count{endpoint!~\"keys|terms\",
status=\"200\"} [2m])))",
+ "expr": "avg
((rate(taler_requests_upstream_response_time_hist_sum{endpoint!~\"keys|terms\",
status=\"200\"} [2m]) ) /
(rate(taler_requests_upstream_response_time_hist_count{endpoint!~\"keys|terms\",
status=\"200\"} [2m])))",
"interval": "",
"legendFormat": "Upstream Response Time",
"refId": "A"
@@ -635,6 +635,6 @@
"timezone": "",
"title": "Proxy",
"uid": "MsjffzSZz",
- "version": 14,
+ "version": 16,
"weekStart": ""
}
\ No newline at end of file
diff --git a/additional/grafana/request-statistics.json
b/additional/grafana/request-statistics.json
index 9931b76..41cbe40 100644
--- a/additional/grafana/request-statistics.json
+++ b/additional/grafana/request-statistics.json
@@ -74,7 +74,7 @@
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
- "iteration": 1649318197276,
+ "iteration": 1649441773439,
"links": [],
"liveNow": false,
"panels": [
@@ -657,8 +657,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "",
"fieldConfig": {
@@ -736,7 +736,12 @@
},
"targets": [
{
- "expr": "rate({app=\"taler-database\"} |~ \"duration:\" [1m])",
+ "datasource": {
+ "type": "loki",
+ "uid": "${DS_LOKI}"
+ },
+ "expr": "rate({app=\"taler-database\", type=\"slow-query\"} [1m])",
+ "hide": false,
"refId": "A"
}
],
@@ -759,8 +764,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "Minimal response time for successful (200) requests to
$endpoint",
"fieldConfig": {
@@ -897,8 +902,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "Maximal response time for successful (200) requests to
$endpoint",
"fieldConfig": {
@@ -1014,8 +1019,9 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
- "exemplar": true,
+ "exemplar": false,
"expr":
"increase(taler_requests_total_requests{endpoint=\"$endpoint\",
status=\"200\"}[$interval])",
+ "instant": true,
"interval": "",
"legendFormat": "",
"refId": "A"
@@ -1183,8 +1189,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "Median response time for successful (200) requests to
$endpoint",
"fieldConfig": {
@@ -1250,8 +1256,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "Standard deviation of response times for successful
(200) requests to $endpoint",
"fieldConfig": {
@@ -1317,8 +1323,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "90% of requests to $endpoint complete successfully (200)
below this time",
"fieldConfig": {
@@ -1433,7 +1439,7 @@
"uid": "${DS_PROMETHEUS}"
},
"exemplar": false,
- "expr":
"rate(taler_requests_request_length_sum{endpoint=\"$endpoint\",
status=\"200\"}[2m]) /
rate(taler_requests_request_length_count{endpoint=\"$endpoint\",
status=\"200\"}[2m])",
+ "expr":
"rate(taler_requests_request_length_hist_sum{endpoint=\"$endpoint\",
status=\"200\"}[2m]) /
rate(taler_requests_request_length_hist_count{endpoint=\"$endpoint\",
status=\"200\"}[2m])",
"instant": true,
"interval": "",
"intervalFactor": 10,
@@ -1533,8 +1539,8 @@
},
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "datasource",
+ "uid": "-- Mixed --"
},
"description": "99% of requests to $endpoint complete successfully (200)
below this time",
"fieldConfig": {
@@ -1649,7 +1655,7 @@
"uid": "${DS_PROMETHEUS}"
},
"exemplar": false,
- "expr": "rate(taler_requests_bytes_sent_sum{endpoint=\"$endpoint\",
status=\"200\"}[2m]) /
rate(taler_requests_bytes_sent_count{endpoint=\"$endpoint\",
status=\"200\"}[2m])",
+ "expr":
"rate(taler_requests_bytes_sent_hist_sum{endpoint=\"$endpoint\",
status=\"200\"}[2m]) /
rate(taler_requests_bytes_sent_hist_count{endpoint=\"$endpoint\",
status=\"200\"}[2m])",
"instant": true,
"interval": "",
"intervalFactor": 10,
@@ -1799,6 +1805,6 @@
"timezone": "browser",
"title": "Request Statistics",
"uid": "WcfSXqDnk",
- "version": 183,
+ "version": 194,
"weekStart": ""
}
\ No newline at end of file
diff --git a/additional/grafana/transactions.json
b/additional/grafana/transactions.json
index 9bc04cd..d7f796a 100644
--- a/additional/grafana/transactions.json
+++ b/additional/grafana/transactions.json
@@ -1135,10 +1135,6 @@
"type": "row"
},
{
- "datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
- },
"description": "Total successful (200) requests to /deposit and
/withdraw per second, measured at the nginx proxy in a 2 minute interval.",
"fieldConfig": {
"defaults": {
@@ -1185,13 +1181,14 @@
"targets": [
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
},
- "expr": "sum by (app) (rate({job=\"proxy\",
endpoint=~\"reserves-withdraw|coins-deposit\", status=\"200\"} [2m]))",
- "queryType": "instant",
- "refId": "A",
- "resolution": 3
+ "exemplar": true,
+ "expr": "sum by (app)
(rate(taler_requests_total_requests{endpoint=~\"reserves-withdraw|coins-deposit\",
status=\"200\"} [2m]))",
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
}
],
"title": "Current TPS ",
@@ -1199,10 +1196,6 @@
"type": "gauge"
},
{
- "datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
- },
"description": "Total successful (200) requests per second to /withdraw
per second, measured at the nginx proxy in a 10 minute interval.",
"fieldConfig": {
"defaults": {
@@ -1250,13 +1243,14 @@
"targets": [
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
},
- "expr": "sum by (app) (rate({job=\"proxy\",
endpoint=\"reserves-withdraw\", status=\"200\"} [10m] ))",
- "queryType": "instant",
- "refId": "A",
- "resolution": 3
+ "exemplar": true,
+ "expr": "sum by (app)
(rate(taler_requests_total_requests{endpoint=\"reserves-withdraw\",
status=\"200\"} [10m] ))",
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
}
],
"title": "Withdrawals per Second ",
@@ -1351,10 +1345,6 @@
"type": "timeseries"
},
{
- "datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
- },
"description": "Total successful (200) requests to /deposit per second,
measured at the nginx proxy in a 10 minute interval.",
"fieldConfig": {
"defaults": {
@@ -1402,13 +1392,14 @@
"targets": [
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
},
- "expr": "sum by (app) (rate({job=\"proxy\",
endpoint=\"coins-deposit\", status=\"200\"} [10m] ))",
- "queryType": "instant",
- "refId": "A",
- "resolution": 3
+ "exemplar": true,
+ "expr": "sum by (app)
(rate(taler_requests_total_requests{endpoint=\"coins-deposit\", status=\"200\"}
[10m] ))",
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
}
],
"title": "Payments per Second",
@@ -1416,10 +1407,6 @@
"type": "stat"
},
{
- "datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
- },
"description": "",
"fieldConfig": {
"defaults": {
@@ -1469,13 +1456,14 @@
"targets": [
{
"datasource": {
- "type": "loki",
- "uid": "${DS_LOKI}"
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
},
- "expr": "(sum(count_over_time({job=\"proxy\",
endpoint=\"coins-deposit\", status=\"200\"} [10m]))) / (sum
(count_over_time({job=\"proxy\", endpoint=\"reserves-withdraw\",
status=\"200\"} [10m])))",
- "queryType": "instant",
- "refId": "A",
- "resolution": 3
+ "exemplar": true,
+ "expr":
"(sum(count_over_time(taler_requests_total_requests{endpoint=\"coins-deposit\",
status=\"200\"} [10m]))) / (sum
(count_over_time(taler_requests_total_requests{endpoint=\"reserves-withdraw\",
status=\"200\"} [10m])))",
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
}
],
"title": "Payments / Withdraw",
@@ -2201,7 +2189,7 @@
"type": "timeseries"
}
],
- "refresh": "1m",
+ "refresh": "30s",
"schemaVersion": 35,
"style": "dark",
"tags": [
@@ -2219,6 +2207,6 @@
"timezone": "",
"title": "Transactions",
"uid": "83vvgKKnk",
- "version": 124,
+ "version": 129,
"weekStart": ""
}
\ No newline at end of file
diff --git a/configs/etc/monitor/promtail.yaml
b/configs/etc/monitor/promtail.yaml
index f4b8524..7cde3ac 100644
--- a/configs/etc/monitor/promtail.yaml
+++ b/configs/etc/monitor/promtail.yaml
@@ -43,6 +43,7 @@ scrape_configs:
type: Histogram
description: "Slow query duration extracted from logs"
source: time
+ max_idle_duration: 24h
config:
buckets: [10,100,200,500,1000,5000,10000,50000]
- match:
@@ -95,6 +96,7 @@ scrape_configs:
type: Gauge
description: "Time taken for Nginx to respond"
source: response_time
+ max_idle_duration: 24h
config:
action: set
#
https://www.robustperception.io/how-does-a-prometheus-histogram-work
@@ -103,6 +105,7 @@ scrape_configs:
type: Histogram
description: "Request Length reported from Nginx"
source: request_length
+ max_idle_duration: 24h
config:
buckets: [1,10,50,100,200,500,1000,2000,5000]
bytes_sent_hist:
@@ -110,6 +113,7 @@ scrape_configs:
type: Histogram
description: "Number of bytes sent, reported from Nginx"
source: bytes_sent
+ max_idle_duration: 24h
config:
buckets: [1,10,50,100,200,500,1000,2000,5000]
response_time_hist:
@@ -117,6 +121,7 @@ scrape_configs:
type: Histogram
description: "Time taken for Nginx to respond"
source: response_time
+ max_idle_duration: 24h
config:
buckets:
[0.001,0.0025,0.005,0.010,0.025,0.050,0.1,0.25,0.5,1,2,5]
upstream_response_time_hist:
@@ -124,6 +129,7 @@ scrape_configs:
type: Histogram
description: "Time taken for the Exchange to respond to Nginx"
source: upstream_response_time
+ max_idle_duration: 24h
config:
buckets:
[0.001,0.0025,0.005,0.010,0.025,0.050,0.1,0.25,0.5,1,2,5]
diff --git a/experiment/scripts/data-backup.sh
b/experiment/scripts/data-backup.sh
index bc84ac0..c250e2e 100755
--- a/experiment/scripts/data-backup.sh
+++ b/experiment/scripts/data-backup.sh
@@ -14,6 +14,8 @@ LOKI_DATA_DIR=/tmp/loki
SNAPSHOT_COPY_PATH=${LOG_DIR}/tmp-data-snapshot
SNAPSHOT_PERS_FILE=${LOG_DIR}/data-snapshot.tar.gz
+mkdir "${SNAPSHOT_COPY_PATH}"
+
END_TIME=$(date +%s)
SNAPSHOT="${PROMETHEUS_DATA_DIR}/$(\
diff --git a/experiment/scripts/monitor.sh b/experiment/scripts/monitor.sh
index 30ec6cd..3e86a05 100755
--- a/experiment/scripts/monitor.sh
+++ b/experiment/scripts/monitor.sh
@@ -223,7 +223,7 @@ function init_monitor() {
systemctl restart prometheus-postgres-exporter \
prometheus \
- taler-prometheus-backup.timer
+ taler-data-backup.timer
exit 0
}
--
To stop receiving notification emails like this one, please contact
gnunet@gnunet.org.
- [taler-grid5k] 173/189: createusers not required for db only, (continued)
- [taler-grid5k] 173/189: createusers not required for db only, gnunet, 2022/04/28
- [taler-grid5k] 121/189: fix gitignore, gnunet, 2022/04/28
- [taler-grid5k] 164/189: update, gnunet, 2022/04/28
- [taler-grid5k] 171/189: fix pg repo in centos, gnunet, 2022/04/28
- [taler-grid5k] 134/189: try source, gnunet, 2022/04/28
- [taler-grid5k] 137/189: fix some issues in recover, gnunet, 2022/04/28
- [taler-grid5k] 150/189: various imrovements / fixes, gnunet, 2022/04/28
- [taler-grid5k] 170/189: add node-exporter service files as not present in centos, gnunet, 2022/04/28
- [taler-grid5k] 139/189: fix taler-perf script, gnunet, 2022/04/28
- [taler-grid5k] 180/189: add centos db initialization script, gnunet, 2022/04/28
- [taler-grid5k] 136/189: update dashboards,
gnunet <=
- [taler-grid5k] 163/189: update centos, gnunet, 2022/04/28
- [taler-grid5k] 165/189: remove --no-install-recommends, gnunet, 2022/04/28
- [taler-grid5k] 174/189: add mitigations=off in grid5000 base.yaml as it gets overriden, gnunet, 2022/04/28
- [taler-grid5k] 183/189: fix promtail, gnunet, 2022/04/28
- [taler-grid5k] 184/189: add documentation, gnunet, 2022/04/28
- [taler-grid5k] 138/189: possibility to start more wirewatchers, gnunet, 2022/04/28
- [taler-grid5k] 172/189: fix bind package in centos, gnunet, 2022/04/28
- [taler-grid5k] 178/189: kernel_params used to disable mitigations, gnunet, 2022/04/28
- [taler-grid5k] 91/189: split up proxy monitoring, gnunet, 2022/04/28
- [taler-grid5k] 167/189: add g5k commit sha again, gnunet, 2022/04/28