#!/bin/sh
# -*- sh -*-

: << =cut

=head1 NAME

systemd - Plugin to monitor systemd units state

=head1 APPLICABLE SYSTEMS

Linux systems with systemd installed.

=head1 CONFIGURATION

No configuration is required for this plugin. You may optionally pass warning and critical values for any
of the possible states (active, reloading, inactive, failed, activating, deactivating), and you may
additionally pass both global and state-specific include/exclude filters to include only units you care
about and/or exclude units you don't care about.

(Note that for failed units, default warning and critical values are set to 0 and 10, respectively. No other
states have default levels set.)

Value calculations for each state are made using the following algorithm (all filters performed using \`egrep\`):

1. Global include rules are applied on the output of \`systemctl list-units --all --no-legend\`;
2. Global exclude rules are then applied to the result of that;
3. Then, for each state, this global output is further filtered by include, then exclude rules for the state;
4. Then the result is filtered for the given state and the remaining units counted and listed.

An example configuration might be something like this:

 [systemd_units]
 env.failed_warning 0
 env.failed_critical 5
 env.inactive_warning 10
 env.inactive_critical 20
 env.exclude boring
 env.inactive_exclude sleepy

In the example above, we've overridden the default warning and critical levels for failed units, added warning
and critical levels for inactive units, then filtered out boring units from all results and filtered out sleepy
units from results for the inactive state.

=head1 AUTHOR

Olivier Mehani <shtrom+munin@ssji.net> with contributions from Kael Shipman <kael.shipman@gmail.com>

=head1 LICENSE

GPLv2

=head1 MAGIC MARKERS

 #%# family=auto
 #%# capabilities=autoconf

=cut

. "$MUNIN_LIBDIR/plugins/plugin.sh"

failed_warning="${failed_warning:-0}"
failed_critical="${failed_critical:-10}"

states="active \
	reloading \
	inactive \
	failed \
	activating \
	deactivating"

include="${include:-.*}"
exclude="${exclude:-^$}"

autoconf() {
	which systemctl >/dev/null && \
	       systemctl  --state=failed --no-pager --no-legend	>/dev/null 2>&1 && echo yes || echo "no (No systemctl or error running it)"
}

config () {
	cat << EOF
graph_title Systemd units state
graph_args -l 0
graph_category system
graph_scale no
graph_vlabel units
EOF
	for state in $states; do
		echo "$state.label $state"
		echo "$state.draw AREASTACK"
		print_warning $state
		print_critical $state
	done
}

fetch () {
    # Get all units, filtering by global include/exclude rules
    local state_include state_exclude state_tmp tmp
	tmp=$(systemctl --no-pager --no-legend --all | egrep "$include" | egrep -v "$exclude" | awk '{print $1, $3}')

    # For each state, echo the number of units and some extra info, filtering for state-specific include/excludes
	for state in $states ; do
        # Get state-specific include/excludes, if present
        state_include="$(eval echo "\$${state}_include")"
        state_exclude="$(eval echo "\$${state}_exclude")"
        state_tmp="$tmp"

        # Filter
        if [ -n "$state_include" ]; then
            state_tmp="$(echo "$state_tmp" | egrep "$state_include")"
        fi
        if [ -n "$state_exclude" ]; then
            state_tmp="$(echo "$state_tmp" | egrep -v "$state_exclude")"
        fi

        # Count and output
		count=$(echo "$state_tmp" | grep -c "$state$")
		echo "$state.value $count"
		extinfo=$(echo "$state_tmp" | grep "$state$" | cut -d " " -f 1 | tr '\n' ' ')
		if [ -n "$extinfo" ]; then
			echo "$state.extinfo" "$extinfo"
		fi
	done
}

case $1 in
	"autoconf")
		autoconf
		;;
	"config")
		config
		;;
	*)
		fetch
		;;
esac