Add supervisord application (#13673)

2024-10-07 16:52:45 +00:00 · 2022-01-13 18:19:27 +01:00
parent 42d84da24a
commit 8f8872520a
8 changed files with 322 additions and 0 deletions
--- a/doc/Extensions/Applications.md
+++ b/doc/Extensions/Applications.md
@@ -137,6 +137,7 @@ by following the steps under the `SNMP Extend` heading.
 1. [Seafile](#seafile) - SNMP extend
 1. [SMART](#smart) - SNMP extend
 1. [Squid](#squid) - SNMP proxy
+1. [Supervisord](#supervisord) - SNMP extend
 1. [TinyDNS/djbdns](#tinydns-aka-djbdns) - Agent
 1. [Unbound](#unbound) - SNMP extend, Agent
 1. [UPS-nut](#ups-nut) - SNMP extend
@@ -2182,6 +2183,33 @@ for net-snmp, please see the links below.
 <http://wiki.squid-cache.org/Features/Snmp>
 <http://www.net-snmp.org/wiki/index.php/Snmpd_proxy>

+## Supervisord
+
+It shows you the totals per status and also the uptime per process. That way you can add alerts for instance when there are process in state `FATAL`.
+
+### SNMP Extend
+
+1. Copy the python script to the desired host.
+```
+wget https://github.com/librenms/librenms-agent/raw/master/snmp/supervisord.py -O /etc/snmp/supervisord.py
+```
+Notice that this will use the default unix socket path. Modify the `unix_socket_path` variable in the script if your path differs from the default.
+
+2. Make the script executable
+```
+chmod +x /etc/snmp/supervisord.py
+```
+
+3. Edit your snmpd.conf file (usually /etc/snmp/snmpd.conf) and add:
+```
+extend supervisord /etc/snmp/supervisord.py
+```
+
+4. Restart snmpd on your host
+```
+systemctl restart snmpd
+```
+
 ## TinyDNS aka djbdns

 ### Agent
--- a/includes/html/graphs/application/supervisord_totals.inc.php
+++ b/includes/html/graphs/application/supervisord_totals.inc.php
@@ -0,0 +1,43 @@
+<?php
+
+require 'includes/html/graphs/common.inc.php';
+$name = 'supervisord';
+$app_id = $app['app_id'];
+$scale_min = 0;
+$colours = 'mixed';
+$unit_text = 'Status';
+$unitlen = 10;
+$bigdescrlen = 15;
+$smalldescrlen = 15;
+$dostack = 0;
+$printtotal = 0;
+$addarea = 1;
+$transparency = 15;
+
+$rrd_filename = Rrd::name($device['hostname'], ['app', $name, $app_id]);
+
+$array = [
+    'STOPPED' => ['descr' => 'STOPPED', 'colour' => 'FFC107'],
+    'STARTING' => ['descr' => 'STARTING', 'colour' => '28774F'],
+    'RUNNING' => ['descr' => 'RUNNING', 'colour' => '4CAf50'],
+    'BACKOFF' => ['descr' => 'BACKOFF', 'colour' => 'CDDC39'],
+    'STOPPING' => ['descr' => 'STOPPING', 'colour' => 'D46A6A'],
+    'EXITED' => ['descr' => 'EXITED', 'colour' => 'E74B00'],
+    'FATAL' => ['descr' => 'FATAL', 'colour' => 'E91E63'],
+    'UNKNOWN' => ['descr' => 'UNKNOWN', 'colour' => 'CCCCCC'],
+];
+
+$i = 0;
+if (Rrd::checkRrdExists($rrd_filename)) {
+    foreach ($array as $ds => $var) {
+        $rrd_list[$i]['filename'] = $rrd_filename;
+        $rrd_list[$i]['descr'] = $var['descr'];
+        $rrd_list[$i]['ds'] = $ds;
+        $rrd_list[$i]['colour'] = $var['colour'];
+        $i++;
+    }
+} else {
+    echo "file missing: $rrd_filename";
+}
+
+require 'includes/html/graphs/generic_v3_multiline.inc.php';
--- a/includes/html/graphs/application/supervisord_uptime.inc.php
+++ b/includes/html/graphs/application/supervisord_uptime.inc.php
@@ -0,0 +1,38 @@
+<?php
+
+require 'includes/html/graphs/common.inc.php';
+$name = 'supervisord';
+$app_id = $app['app_id'];
+$scale_min = 0;
+$unit_text = 'Process';
+
+$rrdVar = 'uptime';
+
+$colours = 'mega';
+$dostack = 0;
+$printtotal = 0;
+$addarea = 1;
+$transparency = 15;
+
+$unitlen = 20;
+$bigdescrlen = 25;
+$smalldescrlen = 25;
+
+$processes = Rrd::getRrdApplicationArrays($device, $app['app_id'], 'supervisord');
+
+$int = 0;
+while (isset($processes[$int])) {
+    $process_name = $processes[$int];
+    $rrd_filename = Rrd::name($device['hostname'], ['app', $name, $app_id, $process_name]);
+
+    if (Rrd::checkRrdExists($rrd_filename)) {
+        $rrd_list[] = [
+            'filename' => $rrd_filename,
+            'descr'    => $process_name,
+            'ds'       => $rrdVar,
+        ];
+    }
+    $int++;
+}
+
+require 'includes/html/graphs/generic_multi_line_exact_numbers.inc.php';
--- a/includes/html/pages/apps.inc.php
+++ b/includes/html/pages/apps.inc.php
@@ -367,6 +367,10 @@ $graphs['docker'] = [
    'mem_used',
    'mem_perc',
 ];
+$graphs['supervisord'] = [
+    'totals',
+    'uptime',
+];
 $graphs['chronyd'] = [
    'time',
    'frequency',
--- a/includes/html/pages/device/apps/supervisord.inc.php
+++ b/includes/html/pages/device/apps/supervisord.inc.php
@@ -0,0 +1,26 @@
+<?php
+
+$graphs = [
+    'supervisord_totals' => 'Totals',
+    'supervisord_uptime' => 'Process uptime',
+];
+
+foreach ($graphs as $key => $text) {
+    $graph_type = $key;
+    $graph_array['height'] = '100';
+    $graph_array['width'] = '215';
+    $graph_array['to'] = time();
+    $graph_array['id'] = $app['app_id'];
+    $graph_array['type'] = 'application_' . $key;
+
+    echo '<div class="panel panel-default">
+    <div class="panel-heading">
+        <h3 class="panel-title">' . $text . '</h3>
+    </div>
+    <div class="panel-body">
+    <div class="row">';
+    include 'includes/html/print-graphrow.inc.php';
+    echo '</div>';
+    echo '</div>';
+    echo '</div>';
+}
--- a/includes/polling/applications/supervisord.inc.php
+++ b/includes/polling/applications/supervisord.inc.php
@@ -0,0 +1,52 @@
+<?php
+
+use LibreNMS\Exceptions\JsonAppException;
+use LibreNMS\RRD\RrdDefinition;
+
+$name = 'supervisord';
+$app_id = $app['app_id'];
+$output = 'OK';
+
+try {
+    $supervisord_data = json_app_get($device, $name, 1)['data'];
+} catch (JsonAppException $e) {
+    echo PHP_EOL . $name . ':' . $e->getCode() . ':' . $e->getMessage() . PHP_EOL;
+    update_application($app, 'ERROR', []); // Set empty metrics and error message
+
+    return;
+}
+
+$rrd_name = ['app', $name, $app_id];
+
+$metrics = [];
+$rrd_def = RrdDefinition::make();
+foreach ($supervisord_data['total'] as $status => $value) {
+    $rrd_def->addDataset($status, 'GAUGE', 0);
+}
+
+$fields = $supervisord_data['total'];
+
+$metrics['total'] = $fields;
+$tags = ['name' => $name, 'app_id' => $app_id, 'rrd_def' => $rrd_def, 'rrd_name' => $rrd_name];
+data_update($device, 'app', $tags, $fields);
+
+$rrd_def = RrdDefinition::make()
+    ->addDataset('state', 'GAUGE', 0)
+    ->addDataset('uptime', 'GAUGE', 0);
+
+foreach ($supervisord_data['processes'] as $data) {
+    $process = $data['name'];
+
+    $rrd_name = ['app', $name, $app_id, $process];
+
+    $fields = [
+        'state' => $data['state'],
+        'uptime' => $data['uptime'],
+    ];
+
+    $metrics['process_' . $process] = $fields;
+    $tags = ['name' => $process, 'app_id' => $app_id, 'rrd_def' => $rrd_def, 'rrd_name' => $rrd_name];
+    data_update($device, 'app', $tags, $fields);
+}
+
+update_application($app, $output, $metrics);
--- a/tests/data/linux_supervisord-v1.json
+++ b/tests/data/linux_supervisord-v1.json
@@ -0,0 +1,123 @@
+{
+    "applications": {
+        "discovery": {
+            "applications": [
+                {
+                    "app_type": "supervisord",
+                    "app_state": "UNKNOWN",
+                    "discovered": 1,
+                    "app_state_prev": null,
+                    "app_status": "",
+                    "app_instance": ""
+                }
+            ]
+        },
+        "poller": {
+            "applications": [
+                {
+                    "app_type": "supervisord",
+                    "app_state": "OK",
+                    "discovered": 1,
+                    "app_state_prev": "UNKNOWN",
+                    "app_status": "",
+                    "app_instance": ""
+                }
+            ],
+            "application_metrics": [
+                {
+                    "metric": "process_test-program_00_state",
+                    "value": 20,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "process_test-program_00_uptime",
+                    "value": 70,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "process_test-program_01_state",
+                    "value": 200,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "process_test-program_01_uptime",
+                    "value": 0,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_BACKOFF",
+                    "value": 0,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_EXITED",
+                    "value": 0,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_FATAL",
+                    "value": 1,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_RUNNING",
+                    "value": 1,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_STARTING",
+                    "value": 0,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_STOPPED",
+                    "value": 0,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_STOPPING",
+                    "value": 0,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                },
+                {
+                    "metric": "total_UNKNOWN",
+                    "value": 0,
+                    "value_prev": null,
+                    "app_type": "supervisord"
+                }
+            ]
+        }
+    },
+    "os": {
+        "discovery": {
+            "devices": [
+                {
+                    "sysName": "<private>",
+                    "sysObjectID": ".1.3.6.1.4.1.8072.3.2.10",
+                    "sysDescr": "Linux server 3.10.0-693.5.2.el7.x86_64 #1 SMP Fri Oct 20 20:32:50 UTC 2017 x86_64",
+                    "sysContact": "<private>",
+                    "version": "3.10.0-693.5.2.el7.x86_64",
+                    "hardware": "Generic x86 64-bit",
+                    "features": null,
+                    "os": "linux",
+                    "type": "server",
+                    "serial": null,
+                    "icon": "linux.svg",
+                    "location": "<private>"
+                }
+            ]
+        },
+        "poller": "matches discovery"
+    }
+}
--- a/tests/snmpsim/linux_supervisord-v1.snmprec
+++ b/tests/snmpsim/linux_supervisord-v1.snmprec
@@ -0,0 +1,8 @@
+1.3.6.1.2.1.1.1.0|4|Linux server 3.10.0-693.5.2.el7.x86_64 #1 SMP Fri Oct 20 20:32:50 UTC 2017 x86_64
+1.3.6.1.2.1.1.2.0|6|1.3.6.1.4.1.8072.3.2.10
+1.3.6.1.2.1.1.3.0|67|77550514
+1.3.6.1.2.1.1.4.0|4|<private>
+1.3.6.1.2.1.1.5.0|4|<private>
+1.3.6.1.2.1.1.6.0|4|<private>
+1.3.6.1.4.1.8072.1.3.2.2.1.21.11.115.117.112.101.114.118.105.115.111.114.100|2|1
+1.3.6.1.4.1.8072.1.3.2.3.1.2.11.115.117.112.101.114.118.105.115.111.114.100|4|{"version":1,"data":{"processes":[{"start":1641984698,"state":20,"now":1641984768,"group":"test","name":"test-program_00","error":null,"statename":"RUNNING","stop":1641984697,"uptime":70},{"start":1641982882,"state":200,"now":1641984768,"group":"test","name":"test-program_01","error":"Exited too quickly (process log may have details)","statename":"FATAL","stop":1641982882,"uptime":0}],"total":{"RUNNING":1,"STOPPED":0,"STOPPING":0,"UNKNOWN":0,"FATAL":1,"STARTING":0,"EXITED":0,"BACKOFF":0}},"errorString":0,"error":0}