From 63d2fbd7800c217284a67583e3085fa1110f1ab1 Mon Sep 17 00:00:00 2001 From: Mark Nellemann Date: Fri, 28 Oct 2022 17:10:22 +0200 Subject: [PATCH] Update dashboards and README's --- README.md | 2 +- client/README.md | 2 +- .../Sysmon - Host Overview.json | 0 .../Sysmon - Power Performance.json | 713 ++++++++++++++++++ .../Sysmon - Process Explorer.json | 0 plugins/os-base/README.md | 24 +- server/README.md | 2 +- 7 files changed, 728 insertions(+), 15 deletions(-) rename doc/{ => dashboards}/Sysmon - Host Overview.json (100%) create mode 100644 doc/dashboards/Sysmon - Power Performance.json rename doc/{ => dashboards}/Sysmon - Process Explorer.json (100%) diff --git a/README.md b/README.md index f358fc2..f1ae1e9 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ Open source system monitoring solution with support for plugins. This software is free to use and is licensed under the [Apache 2.0 License](LICENSE). -- Example dashboards are provided in the [doc/](doc) folder, which can be imported into your Grafana installation. +- Example dashboards are provided in the [doc/dashboards/](doc/dashboards/) folder, which can be imported into your Grafana installation. - Screenshots are available in the [downloads](https://bitbucket.org/mnellemann/sysmon/downloads/) section. diff --git a/client/README.md b/client/README.md index 43f3393..f6e6768 100644 --- a/client/README.md +++ b/client/README.md @@ -1,6 +1,6 @@ # Client / Agent -This is the client/agent component of sysmon, which you install (together with sysmon-plugins) on the hosts where you want to collect metrics. +This is the client/agent component of sysmon, which you install (together with sysmon-plugins) on your hosts. ## Installation diff --git a/doc/Sysmon - Host Overview.json b/doc/dashboards/Sysmon - Host Overview.json similarity index 100% rename from doc/Sysmon - Host Overview.json rename to doc/dashboards/Sysmon - Host Overview.json diff --git a/doc/dashboards/Sysmon - Power Performance.json b/doc/dashboards/Sysmon - Power Performance.json new file mode 100644 index 0000000..55b3318 --- /dev/null +++ b/doc/dashboards/Sysmon - Power Performance.json @@ -0,0 +1,713 @@ +{ + "__inputs": [ + { + "name": "DS_SYSMON", + "label": "sysmon", + "description": "", + "type": "datasource", + "pluginId": "influxdb", + "pluginName": "InfluxDB" + } + ], + "__elements": {}, + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "9.1.3" + }, + { + "type": "datasource", + "id": "influxdb", + "name": "InfluxDB", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "text", + "name": "Text", + "version": "" + }, + { + "type": "panel", + "id": "timeseries", + "name": "Time series", + "version": "" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "datasource", + "uid": "grafana" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "target": { + "limit": 100, + "matchAny": false, + "tags": [], + "type": "dashboard" + }, + "type": "dashboard" + } + ] + }, + "description": "https://bitbucket.org/mnellemann/sysmon/ - Metrics from sysmon agent.", + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 0, + "id": null, + "links": [], + "liveNow": false, + "panels": [ + { + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "gridPos": { + "h": 3, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 28, + "options": { + "content": "## Metrics are collected by an agent running inside of each LPAR / VM / Host.\n \n For more information: [bitbucket.org/mnellemann/sysmon](https://bitbucket.org/mnellemann/sysmon)\n ", + "mode": "markdown" + }, + "pluginVersion": "9.1.3", + "targets": [ + { + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "refId": "A" + } + ], + "transparent": true, + "type": "text" + }, + { + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "description": "Load average as reported by OS.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 14, + "w": 12, + "x": 0, + "y": 3 + }, + "id": 2, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.3", + "targets": [ + { + "alias": "$tag_hostname - $col", + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "groupBy": [ + { + "params": [ + "$__interval" + ], + "type": "time" + }, + { + "params": [ + "hostname" + ], + "type": "tag" + }, + { + "params": [ + "none" + ], + "type": "fill" + } + ], + "measurement": "base_load", + "orderByTime": "ASC", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "5min" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [ + "5min" + ], + "type": "alias" + } + ] + ], + "tags": [ + { + "key": "hostname", + "operator": "=~", + "value": "/^$hostname$/" + } + ] + } + ], + "title": "System Load Average", + "type": "timeseries" + }, + { + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "description": "Shows the number of physical processors consumed.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 14, + "w": 12, + "x": 12, + "y": 3 + }, + "id": 17, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.3", + "targets": [ + { + "alias": "$tag_hostname", + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "groupBy": [ + { + "params": [ + "$__interval" + ], + "type": "time" + }, + { + "params": [ + "hostname" + ], + "type": "tag" + }, + { + "params": [ + "none" + ], + "type": "fill" + } + ], + "measurement": "aix_processor", + "orderByTime": "ASC", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "physc" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + } + ] + ], + "tags": [ + { + "key": "hostname", + "operator": "=~", + "value": "/^$hostname$/" + } + ] + } + ], + "title": "Power - Shared Processors - Physical Cores Consumed", + "type": "timeseries" + }, + { + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "description": "Percentage of the entitled capacity consumed.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": { + "h": 15, + "w": 12, + "x": 0, + "y": 17 + }, + "id": 30, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.3", + "targets": [ + { + "alias": "$tag_hostname", + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "groupBy": [ + { + "params": [ + "$__interval" + ], + "type": "time" + }, + { + "params": [ + "hostname" + ], + "type": "tag" + }, + { + "params": [ + "none" + ], + "type": "fill" + } + ], + "measurement": "aix_processor", + "orderByTime": "ASC", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "entc" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + } + ] + ], + "tags": [ + { + "key": "hostname", + "operator": "=~", + "value": "/^$hostname$/" + } + ] + } + ], + "title": "Power - Shared Processors - Entitled Capacity Consumed", + "type": "timeseries" + }, + { + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "description": "Percentage of logical processor(s) utilization", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": { + "h": 15, + "w": 12, + "x": 12, + "y": 17 + }, + "id": 31, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.3", + "targets": [ + { + "alias": "$tag_hostname", + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "groupBy": [ + { + "params": [ + "$__interval" + ], + "type": "time" + }, + { + "params": [ + "hostname" + ], + "type": "tag" + }, + { + "params": [ + "none" + ], + "type": "fill" + } + ], + "measurement": "aix_processor", + "orderByTime": "ASC", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "lbusy" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + } + ] + ], + "tags": [ + { + "key": "hostname", + "operator": "=~", + "value": "/^$hostname$/" + } + ] + } + ], + "title": "Power - Shared Processors - Logical Processor Utilization", + "type": "timeseries" + } + ], + "refresh": "30s", + "schemaVersion": 37, + "style": "dark", + "tags": [ + "sysmon", + "Power" + ], + "templating": { + "list": [ + { + "current": {}, + "datasource": { + "type": "influxdb", + "uid": "${DS_SYSMON}" + }, + "definition": "SHOW TAG VALUES FROM \"base_memory\" WITH KEY = \"hostname\" WHERE time > now() - 60m", + "hide": 0, + "includeAll": true, + "label": "Host", + "multi": true, + "name": "hostname", + "options": [], + "query": "SHOW TAG VALUES FROM \"base_memory\" WITH KEY = \"hostname\" WHERE time > now() - 60m", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 5, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-7d", + "to": "now-30s" + }, + "timepicker": { + "nowDelay": "30s", + "refresh_intervals": [ + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ] + }, + "timezone": "", + "title": "Sysmon - Power Performance", + "uid": "3zPCIbN4z", + "version": 7, + "weekStart": "" +} \ No newline at end of file diff --git a/doc/Sysmon - Process Explorer.json b/doc/dashboards/Sysmon - Process Explorer.json similarity index 100% rename from doc/Sysmon - Process Explorer.json rename to doc/dashboards/Sysmon - Process Explorer.json diff --git a/plugins/os-base/README.md b/plugins/os-base/README.md index 8470b4e..ef5213f 100644 --- a/plugins/os-base/README.md +++ b/plugins/os-base/README.md @@ -6,15 +6,15 @@ The base plugin uses the [oshi](https://github.com/oshi/oshi) library to get it' Reports the following metrics seen: -- **system** -CPU time spend on system processes. -- **user** - CPU time spend on user processes. -- **nice** - CPU time spend on user processes running at lower priority. -- **iowait** - CPU time spend waiting (for i/o). -- **steal** - CPU time stolen by hypervisor and given to other virtual systems. -- **irq** - CPU time spend by kernel on interrupt requests. -- **softirq** - CPU time spend by kernel on soft interrupt requests. -- **idle** - CPU time spend idling (doing nothing). -- **busy** - CPU time spend working. +- **system** -CPU time (in ms) spend on system processes. +- **user** - CPU time (in ms) spend on user processes. +- **nice** - CPU time (in ms) spend on user processes running at lower priority. +- **iowait** - CPU time (in ms) spend waiting (for i/o). +- **steal** - CPU time (in ms) stolen by hypervisor and given to other virtual systems. +- **irq** - CPU time (in ms) spend by kernel on interrupt requests. +- **softirq** - CPU (in ms) time spend by kernel on soft interrupt requests. +- **idle** - CPU time (in ms) spend idling (doing nothing). +- **busy** - CPU time (in ms) spend working. ## Memory Extension @@ -35,7 +35,7 @@ Metrics reported are: - **reads** - The total number of bytes read. - **writes** - The total number of bytes written. - **iotime** - Time spent on IO in milliseconds. -- **queue** - Lenght of IO queue. +- **queue** - Length of disk IO queue. ## Filesystem Extension @@ -43,7 +43,7 @@ Metrics reported are: - **free_bytes** - Free bytes for filesystem. - **total_bytes** - Total bytes for filesystem. -- **free_inoed** - Free inodes for filesystem. +- **free_inodes** - Free inodes for filesystem. - **total_inodes** - Total inodes for filesystem. ### Configuration @@ -80,4 +80,4 @@ The **include** option let's you specify what processes to report for. [extension.base_process] enabled = true # true or false include = [ "java", "influxd", "grafana-server" ] -``` \ No newline at end of file +``` diff --git a/server/README.md b/server/README.md index adbe477..c1a7b0c 100644 --- a/server/README.md +++ b/server/README.md @@ -10,7 +10,7 @@ See the [doc/systemd.md](doc/systemd.md) or [doc/sysv-init.md](doc/sysv-init.md) ### Influx Database -Create a database for the metrics: +Create a database for the metrics and adjust duration as you prefer: ```text CREATE DATABASE "sysmon" WITH DURATION 90d REPLICATION 1;