CadolesKube/typhoon
7
0
Fork 0
mirror of https://github.com/puppetmaster/typhoon.git synced 2025-07-30 09:41:35 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add node-exporter alerts and Grafana dashboard

Browse Source 
* Add Prometheus alerts from node-exporter
* Add Grafana dashboard nodes.json, from node-exporter
* Not adding recording rules, since those are only used
by some node-exporter USE dashboards not being included
This commit is contained in:
Dalton Hubble
2019-11-13 23:39:19 -08:00
parent 8a9e8595ae
commit 525ae23305
4 changed files with 1107 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
addons/prometheus/rules.yaml
View File

@ -865,6 +865,136 @@ data:
}
]
}
node-exporter.yaml: |-
{
"groups": [
{
"name": "node-exporter",
"rules": [
{
"alert": "NodeFilesystemSpaceFillingUp",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left and is filling up.",
"summary": "Filesystem is predicted to run out of space within the next 24 hours."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 40\nand\n predict_linear(node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 24*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemSpaceFillingUp",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left and is filling up fast.",
"summary": "Filesystem is predicted to run out of space within the next 4 hours."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 20\nand\n predict_linear(node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 4*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeFilesystemAlmostOutOfSpace",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left.",
"summary": "Filesystem has less than 5% space left."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 5\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemAlmostOutOfSpace",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left.",
"summary": "Filesystem has less than 3% space left."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 3\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeFilesystemFilesFillingUp",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left and is filling up.",
"summary": "Filesystem is predicted to run out of inodes within the next 24 hours."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 40\nand\n predict_linear(node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 24*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemFilesFillingUp",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left and is filling up fast.",
"summary": "Filesystem is predicted to run out of inodes within the next 4 hours."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 20\nand\n predict_linear(node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 4*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeFilesystemAlmostOutOfFiles",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left.",
"summary": "Filesystem has less than 5% inodes left."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 5\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemAlmostOutOfFiles",
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left.",
"summary": "Filesystem has less than 3% inodes left."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 3\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeNetworkReceiveErrs",
"annotations": {
"description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.",
"summary": "Network interface is reporting many receive errors."
},
"expr": "increase(node_network_receive_errs_total[2m]) > 10\n",
"for": "1h",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeNetworkTransmitErrs",
"annotations": {
"description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.",
"summary": "Network interface is reporting many transmit errors."
},
"expr": "increase(node_network_transmit_errs_total[2m]) > 10\n",
"for": "1h",
"labels": {
"severity": "warning"
}
}
]
}
]
}
prom.yaml: |-
{
"groups": [