mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2026-06-15 23:03:09 +03:00
Compare commits
3 Commits
dependabot
...
add_dash/o
| Author | SHA1 | Date | |
|---|---|---|---|
|
ea4b854e1f | ||
|
|
b2080c26e4 | ||
|
|
283c98d185 |
@@ -5136,6 +5136,350 @@
|
||||
],
|
||||
"title": "Major page faults rate ($instance)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the operating system name and kernel release version for each instance. Use this to quickly correlate incidents with known OS or kernel-specific regressions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10481",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 297
|
||||
},
|
||||
"id": 228,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_os_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, os, release)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "OS info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"os": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"release": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the filesystem type for each storage data path. Use this to quickly identify filesystem-related issues (e.g., NFS, XFS bugs) during incident triage. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10482",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 297
|
||||
},
|
||||
"id": 229,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_fs_info{job=~\"$job_storage\", instance=~\"$instance\"}) by(job, instance, path, fs_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Filesystem info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"path": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"fs_type": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Average duration of fsync system calls. High latency indicates storage I/O that cannot keep up with the write rate. This metric measures only the persistence path (fsyncing to disk), not the page-cache write phase, making it a direct signal for disk performance. Computed as rate(vm_filestream_fsync_duration_seconds_total) / rate(vm_filestream_fsync_calls_total). See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"axisSoftMin": 0,
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"showValues": false,
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"links": [],
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 305
|
||||
},
|
||||
"id": 230,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true,
|
||||
"sortBy": "Last *",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": true,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job_storage\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job_storage\", instance=~\"$instance\"}[$__rate_interval])",
|
||||
"format": "time_series",
|
||||
"instant": false,
|
||||
"legendFormat": "{{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Fsync avg duration ($instance)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"title": "Troubleshooting",
|
||||
|
||||
@@ -5181,6 +5181,374 @@
|
||||
],
|
||||
"title": "Major page faults rate",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the operating system name and kernel release version for each instance. Use this to quickly correlate incidents with known OS or kernel-specific regressions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10481",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 73
|
||||
},
|
||||
"id": 157,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_os_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, os, release)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "OS info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"os": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"release": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the filesystem type for each storage data path. Use this to quickly identify filesystem-related issues (e.g., NFS, XFS bugs) during incident triage. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10482",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 81
|
||||
},
|
||||
"id": 158,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_fs_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, path, fs_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Filesystem info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"path": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"fs_type": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Average duration of fsync system calls. High latency indicates storage I/O that cannot keep up with the write rate. This metric measures only the persistence path (fsyncing to disk), not the page-cache write phase, making it a direct signal for disk performance. Computed as rate(vm_filestream_fsync_duration_seconds_total) / rate(vm_filestream_fsync_calls_total). See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"axisSoftMin": 0,
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"showValues": false,
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"links": [],
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 81
|
||||
},
|
||||
"id": 159,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true,
|
||||
"sortBy": "Last *",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": true,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])",
|
||||
"format": "time_series",
|
||||
"instant": false,
|
||||
"legendFormat": "{{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Fsync avg duration ($instance)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"title": "Troubleshooting",
|
||||
@@ -8742,4 +9110,4 @@
|
||||
"uid": "wNf0q_kZk",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
}
|
||||
|
||||
@@ -5137,6 +5137,350 @@
|
||||
],
|
||||
"title": "Major page faults rate ($instance)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the operating system name and kernel release version for each instance. Use this to quickly correlate incidents with known OS or kernel-specific regressions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10481",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 297
|
||||
},
|
||||
"id": 228,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_os_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, os, release)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "OS info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"os": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"release": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the filesystem type for each storage data path. Use this to quickly identify filesystem-related issues (e.g., NFS, XFS bugs) during incident triage. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10482",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 297
|
||||
},
|
||||
"id": 229,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_fs_info{job=~\"$job_storage\", instance=~\"$instance\"}) by(job, instance, path, fs_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Filesystem info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"path": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"fs_type": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Average duration of fsync system calls. High latency indicates storage I/O that cannot keep up with the write rate. This metric measures only the persistence path (fsyncing to disk), not the page-cache write phase, making it a direct signal for disk performance. Computed as rate(vm_filestream_fsync_duration_seconds_total) / rate(vm_filestream_fsync_calls_total). See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"axisSoftMin": 0,
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"showValues": false,
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"links": [],
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 305
|
||||
},
|
||||
"id": 230,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true,
|
||||
"sortBy": "Last *",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": true,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job_storage\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job_storage\", instance=~\"$instance\"}[$__rate_interval])",
|
||||
"format": "time_series",
|
||||
"instant": false,
|
||||
"legendFormat": "{{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Fsync avg duration ($instance)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"title": "Troubleshooting",
|
||||
|
||||
@@ -5182,6 +5182,374 @@
|
||||
],
|
||||
"title": "Major page faults rate",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the operating system name and kernel release version for each instance. Use this to quickly correlate incidents with known OS or kernel-specific regressions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10481",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 73
|
||||
},
|
||||
"id": 157,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_os_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, os, release)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "OS info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"os": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"release": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the filesystem type for each storage data path. Use this to quickly identify filesystem-related issues (e.g., NFS, XFS bugs) during incident triage. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10482",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 81
|
||||
},
|
||||
"id": 158,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_fs_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, path, fs_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Filesystem info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"path": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"fs_type": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Average duration of fsync system calls. High latency indicates storage I/O that cannot keep up with the write rate. This metric measures only the persistence path (fsyncing to disk), not the page-cache write phase, making it a direct signal for disk performance. Computed as rate(vm_filestream_fsync_duration_seconds_total) / rate(vm_filestream_fsync_calls_total). See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"axisSoftMin": 0,
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"showValues": false,
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"links": [],
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 81
|
||||
},
|
||||
"id": 159,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true,
|
||||
"sortBy": "Last *",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": true,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])",
|
||||
"format": "time_series",
|
||||
"instant": false,
|
||||
"legendFormat": "{{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Fsync avg duration ($instance)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"title": "Troubleshooting",
|
||||
@@ -8743,4 +9111,4 @@
|
||||
"uid": "wNf0q_kZk_vm",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4581,6 +4581,374 @@
|
||||
],
|
||||
"title": "Rows ignored for last 1h ($instance)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the operating system name and kernel release version for each instance. Use this to quickly correlate incidents with known OS or kernel-specific regressions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10481",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 181
|
||||
},
|
||||
"id": 169,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_os_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, os, release)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "OS info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"os": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"release": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the filesystem type for each storage data path. Use this to quickly identify filesystem-related issues (e.g., NFS, XFS bugs) during incident triage. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10482",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 189
|
||||
},
|
||||
"id": 170,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_fs_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, path, fs_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Filesystem info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"path": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"fs_type": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Average duration of fsync system calls. High latency indicates storage I/O that cannot keep up with the write rate. This metric measures only the persistence path (fsyncing to disk), not the page-cache write phase, making it a direct signal for disk performance. Computed as rate(vm_filestream_fsync_duration_seconds_total) / rate(vm_filestream_fsync_calls_total). See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"axisSoftMin": 0,
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"showValues": false,
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"links": [],
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 189
|
||||
},
|
||||
"id": 171,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true,
|
||||
"sortBy": "Last *",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": true,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])",
|
||||
"format": "time_series",
|
||||
"instant": false,
|
||||
"legendFormat": "{{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Fsync avg duration ($instance)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"title": "Troubleshooting",
|
||||
|
||||
@@ -4580,6 +4580,374 @@
|
||||
],
|
||||
"title": "Rows ignored for last 1h ($instance)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the operating system name and kernel release version for each instance. Use this to quickly correlate incidents with known OS or kernel-specific regressions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10481",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 181
|
||||
},
|
||||
"id": 169,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_os_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, os, release)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "OS info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"os": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"release": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows the filesystem type for each storage data path. Use this to quickly identify filesystem-related issues (e.g., NFS, XFS bugs) during incident triage. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10482",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "thresholds"
|
||||
},
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"filterable": true,
|
||||
"footer": {
|
||||
"reducers": []
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Time"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Value"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "job"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.hideFrom.viz",
|
||||
"value": true
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 189
|
||||
},
|
||||
"id": 170,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"filterable": true,
|
||||
"showHeader": true,
|
||||
"showSearch": true
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"exemplar": false,
|
||||
"expr": "sum(vm_fs_info{job=~\"$job\", instance=~\"$instance\"}) by(job, instance, path, fs_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "__auto",
|
||||
"range": false,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Filesystem info",
|
||||
"type": "table",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "groupBy",
|
||||
"options": {
|
||||
"fields": {
|
||||
"job": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"path": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"fs_type": {
|
||||
"aggregations": [],
|
||||
"operation": "groupby"
|
||||
},
|
||||
"instance": {
|
||||
"aggregations": [
|
||||
"uniqueValues"
|
||||
],
|
||||
"operation": "aggregate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Average duration of fsync system calls. High latency indicates storage I/O that cannot keep up with the write rate. This metric measures only the persistence path (fsyncing to disk), not the page-cache write phase, making it a direct signal for disk performance. Computed as rate(vm_filestream_fsync_duration_seconds_total) / rate(vm_filestream_fsync_calls_total). See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"axisSoftMin": 0,
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"showValues": false,
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"links": [],
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 189
|
||||
},
|
||||
"id": 171,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true,
|
||||
"sortBy": "Last *",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": true,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.2.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])",
|
||||
"format": "time_series",
|
||||
"instant": false,
|
||||
"legendFormat": "{{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Fsync avg duration ($instance)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"title": "Troubleshooting",
|
||||
|
||||
@@ -26,6 +26,7 @@ See also [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-rel
|
||||
|
||||
## tip
|
||||
|
||||
* FEATURE: [dashboards](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/dashboards): add `OS info`, `Filesystem info`, and `Fsync avg duration` panels to the Troubleshooting section of the single-node, cluster, and vmagent dashboards. These panels surface `vm_os_info`, `vm_fs_info`, and the `vm_filestream_fsync_*` metrics for faster incident triage. See [#10481](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10481), [#10482](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10482) and [#10432](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432).
|
||||
* BUGFIX: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): fix issue with producing aggregated samples with identical timestamps between flushes. See PR [#10808](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10808) for details.
|
||||
|
||||
## [v1.145.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.145.0)
|
||||
|
||||
Reference in New Issue
Block a user