lxc_guests

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

: << =cut

=head1 NAME

lxc_guests - collect statistics about containers virtualized via LXC

=head1 CONFIGURATION

  [lxc_guests]
    user root

    # The memory usage of containers are by default drawn as stacked area
    # charts.  Alternatively a non-stacked graph with lines can be configured.
    # Default: true
    #env.ram_display_stacked true

    # lxc container path, default below
    #env.lxcpath /var/lib/lxc

    # exclude the following containers
    # (default none excluded)
    #env.exclude container1 container2

    # path where tasks sysfs files are stored,
    # set this if the various attempts in the
    # code don't work
    # (default none)
    #env.cgrouppath /sys/fs/cgroup/cpuacct/lxc/

=head1 INTERPRETATION

This plugin needs root privilege.

This plugin has been tested with lxc 3 and
lx2 (on Debian buster and Debian jessie,
respectively).

If using lxc 2, make sure you do not have cruft
in your container config files, you can test
it with:
   lxc-cgroup -o /dev/stdout -l INFO -n 104 cpuacct.usage
-- with 104 a valid lxc instance), if you
get a warning, fix the config file.

For the logins graph, the "users" command is required in each
container.

Tested on Debian buster and Debian jessie.


=head1 AUTHOR

vajtsz vajtsz@gmail.com
mitty  mitty@mitty.jp
alphanet schaefer@alphanet.ch (many changes and multigraph)
Lars Kruse <devel@sumpfralle.de>

=head1 LICENSE

2-clause BSD License
or GPLv3 license or later, at your option

=head1 MAGIC MARKERS

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

=cut

set -eu


. "$MUNIN_LIBDIR/plugins/plugin.sh"


lxcpath=${lxcpath:-/var/lib/lxc}
# containers to be ignored
exclude=${exclude:-}
ram_display_stacked=${ram_display_stacked:-true}
# try to guess the location, if empty
cgrouppath=${cgrouppath:-}


# --- FUNCTIONS

get_active_guests() {
   local excludes="$1"
   local guest_name
   for guest_name in $(lxc-ls)
   do
      # handle optional exclude list in $1
      if ! echo "$excludes" | grep -qwF "$guest_name"; then
         if lxc-info -n "$guest_name" --state 2>/dev/null | grep -qw RUNNING; then
            echo "$guest_name"
         fi
      fi
   done
}


get_lxc_cgroup_info() {
   local guest_name="$1"
   local field="$2"
   # lxc3 (lxc < 3: may output some warnings if there is cruft in your config dir)
   lxc-cgroup -o /dev/stdout -l INFO -n "$guest_name" "$field" | sed 's/^.*lxc_cgroup.c:main:[0-9][0-9]* - //' | grep -v set_config_idmaps
}


# find proper sysfs and count it
# Debian 6.0: /sys/fs/cgroup/<container>/tasks
# Ubuntu 12.04 with fstab: /sys/fs/cgroup/lxc/<container>/tasks
# Ubuntu 12.04 with cgroup-lite: /sys/fs/cgroup/cpuacct/lxc/<container>/tasks
# Ubuntu 12.04 with cgroup-bin: /sys/fs/cgroup/cpuacct/sysdefault/lxc/<container>/tasks
# Ubuntu 14.04 /sys/fs/cgroup/systemd/lxc/<container>/tasks
# and with cgmanager on jessie
lxc_count_processes () {
   local guest_name="$1"
   local SYSFS

   [ -z "$guest_name" ] && return 0

   if [ -n "$cgrouppath" ]; then
      SYSFS="$cgrouppath/$guest_name/tasks"
      if [ -e "$SYSFS" ]; then
         wc -l <"$SYSFS"
         return
      fi
   fi

   for SYSFS in \
      "/sys/fs/cgroup/$guest_name/tasks" \
      "/sys/fs/cgroup/lxc/$guest_name/tasks" \
      "/sys/fs/cgroup/cpuacct/lxc/$guest_name/tasks" \
      "/sys/fs/cgroup/systemd/lxc/$guest_name/tasks" \
      "/sys/fs/cgroup/cpuacct/sysdefault/lxc/$guest_name/tasks" \
      "/sys/fs/cgroup/cpu/lxc.payload.$guest_name/tasks"
   do
      if [ -e "$SYSFS" ]; then
         wc -l <"$SYSFS"
         return
      fi
   done

   if [ -e /usr/bin/cgm ]; then
      cgm getvalue cpu "lxc/$guest_name" tasks 2>/dev/null | wc -l
   else
      get_lxc_cgroup_info "$guest_name" "tasks" | wc -l
   fi
}


# change the first character of a string to upper case
title_case() {
   local text="$1"
   printf "%s%s" "$(echo "$text" | cut -c 1 | tr "[:lower:]" "[:upper:]")" "$(echo "$text" | cut -c 2-)"
}


do_autoconf() {
   if [ ! -r /proc/net/dev ]; then
      echo "no (/proc/net/dev cannot be read)"
   elif [ ! -e "$lxcpath" ]; then
      echo "no ($lxcpath is not present)"
   elif [ -z "$(which lxc-ls)" ]; then
      echo "no ('lxc-ls' is not available in PATH)"
   else
      echo yes
   fi
}


do_config() {
   local active_guests guest_name draw_style
   active_guests=$(get_active_guests "$exclude")

   cat <<EOF
multigraph lxc_cpu
graph_title CPU Usage
graph_args -l 0 --base 1000
graph_vlabel USER_HZ
graph_category virtualization
EOF

   for guest_name in $active_guests
   do
      for cpu_usage in user system
      do
         cat <<EOF
$(clean_fieldname "cpu_${cpu_usage}_${guest_name}").label $guest_name: $(title_case "$cpu_usage")
$(clean_fieldname "cpu_${cpu_usage}_${guest_name}").type DERIVE
$(clean_fieldname "cpu_${cpu_usage}_${guest_name}").min 0
EOF
      done
   done

   cat <<EOF

multigraph lxc_cpu_time
graph_title CPU time
graph_args -l 0 --base 1000
graph_vlabel nanosec
graph_category virtualization
EOF

   for guest_name in $active_guests
   do
      cat <<EOF
$(clean_fieldname "cpu_time_${guest_name}").label $guest_name: CPU time
$(clean_fieldname "cpu_time_${guest_name}").type DERIVE
$(clean_fieldname "cpu_time_${guest_name}").min 0
EOF
   done

   cat <<EOF

multigraph lxc_logins
graph_title Logins
graph_category virtualization
EOF

   for guest_name in $active_guests
   do
      cat <<EOF
$(clean_fieldname "logins_${guest_name}").label $guest_name: logins
$(clean_fieldname "logins_${guest_name}").type GAUGE
EOF
   done

   cat <<EOF

multigraph lxc_net
graph_title Network traffic
graph_args --base 1000
graph_vlabel bits in (-) / out (+) per \${graph_period}
graph_category virtualization
graph_info This graph shows the traffic of active LXC containers.
EOF

   for guest_name in $active_guests
   do
      device=$(lxc-info -n "$guest_name" | grep Link | sed 's/Link:\ \+//g')
      if [ -z "$device" ]; then
         continue
      fi
      cat <<EOF
$(clean_fieldname "net_${guest_name}_down").label $guest_name
$(clean_fieldname "net_${guest_name}_down").type DERIVE
$(clean_fieldname "net_${guest_name}_down").graph no
$(clean_fieldname "net_${guest_name}_down").cdef $(clean_fieldname "net_${guest_name}_down"),8,*
$(clean_fieldname "net_${guest_name}_down").min 0
$(clean_fieldname "net_${guest_name}_up").label $guest_name
$(clean_fieldname "net_${guest_name}_up").type DERIVE
$(clean_fieldname "net_${guest_name}_up").negative $(clean_fieldname "net_${guest_name}_down")
$(clean_fieldname "net_${guest_name}_up").cdef $(clean_fieldname "net_${guest_name}_up"),8,*
$(clean_fieldname "net_${guest_name}_up").min 0
EOF
      if [ -r "/sys/class/net/$device/speed" ]; then
         megabit_per_second=$(cat "/sys/class/net/$device/speed")
         bps=$((megabit_per_second * 1000 * 1000))
         cat <<EOF
$(clean_fieldname "net_${guest_name}_down").max $bps
$(clean_fieldname "net_${guest_name}_up").max $bps
EOF
      fi
   done

   cat <<EOF

multigraph lxc_proc
graph_title Processes
graph_args -l 0 --base 1000
graph_vlabel Number of processes
graph_category virtualization
EOF
   for guest_name in $active_guests
   do
      cat <<EOF
$(clean_fieldname "lxc_proc_${guest_name}").label $guest_name: processes
$(clean_fieldname "lxc_proc_${guest_name}").type GAUGE
$(clean_fieldname "lxc_proc_${guest_name}").min 0
EOF
   done

   cat <<EOF

multigraph lxc_ram
graph_title Memory
graph_args -l 0 --base 1024
graph_vlabel byte
graph_category virtualization
EOF

   for guest_name in $active_guests
   do
      if [ "$ram_display_stacked" != "true" ]; then
         draw_style="LINE1"
      else
         draw_style="AREASTACK"
      fi

      cat <<EOF
$(clean_fieldname "mem_usage_${guest_name}").label ${guest_name}: Mem usage
$(clean_fieldname "mem_usage_${guest_name}").type GAUGE
$(clean_fieldname "mem_usage_${guest_name}").draw $draw_style
$(clean_fieldname "mem_cache_${guest_name}").label ${guest_name}: Cache
$(clean_fieldname "mem_cache_${guest_name}").type GAUGE
$(clean_fieldname "mem_active_${guest_name}").label ${guest_name}: Active
$(clean_fieldname "mem_active_${guest_name}").type GAUGE
$(clean_fieldname "mem_inactive_${guest_name}").label ${guest_name}: Inactive
$(clean_fieldname "mem_inactive_${guest_name}").type GAUGE
EOF
   done
}


do_fetch() {
   local active_guests cpu_usage device value_up value_down
   active_guests=$(get_active_guests "$exclude")

   echo "multigraph lxc_cpu"
   for guest_name in $active_guests
   do
      for cpu_usage in user system
      do
         echo "$(clean_fieldname "cpu_${cpu_usage}_${guest_name}").value $(get_lxc_cgroup_info "$guest_name" "cpuacct.stat" | grep "$cpu_usage" | awk '{ print $2; }')"
      done
   done

   echo "multigraph lxc_cpu_time"
   for guest_name in $active_guests
   do
      echo "$(clean_fieldname "cpu_time_${guest_name}").value $(get_lxc_cgroup_info "$guest_name" "cpuacct.usage")"
   done

   echo "multigraph lxc_logins"
   for guest_name in $active_guests
   do
      echo "$(clean_fieldname "logins_${guest_name}").value $(lxc-attach -n "$guest_name" users | wc -w)"
   done

   echo "multigraph lxc_net"
   for guest_name in $active_guests
   do
      device=$(lxc-info -n "$guest_name" | grep Link | sed 's/Link:\ \+//g')
      if [ -z "$device" ]; then
         value_up="U"
         value_down="U"
      else
         value_up=$(grep -E "^ *${device}:" /proc/net/dev | awk '{print $10;}')
         value_down=$(grep -E "^ *${device}:" /proc/net/dev | awk '{print $2;}')
      fi

      cat <<EOF
$(clean_fieldname "net_${guest_name}_up").value $value_up
$(clean_fieldname "net_${guest_name}_down").value $value_down
EOF
   done

   echo "multigraph lxc_proc"
   for guest_name in $active_guests
   do
      echo "$(clean_fieldname "lxc_proc_${guest_name}").value $(lxc_count_processes "$guest_name")"
   done

   echo "multigraph lxc_ram"
   for guest_name in $active_guests
   do
      cat <<EOF
$(clean_fieldname "mem_usage_${guest_name}").value $(get_lxc_cgroup_info "$guest_name" "memory.usage_in_bytes")
$(clean_fieldname "mem_cache_${guest_name}").value $(get_lxc_cgroup_info "$guest_name" "memory.stat" | grep total_cache | awk '{print $2;}')
$(clean_fieldname "mem_active_${guest_name}").value $(get_lxc_cgroup_info "$guest_name" "memory.stat" | grep total_active_anon | awk '{print $2;}')
$(clean_fieldname "mem_inactive_${guest_name}").value $(get_lxc_cgroup_info "$guest_name" "memory.stat" | grep total_inactive_anon | awk '{print $2;}')
EOF
   done
}


case "${1:-}" in
   autoconf)
      do_autoconf
      exit 0
      ;;
   config)
      do_config
      if [ "${MUNIN_CAP_DIRTYCONFIG:-0}" = 1 ]; then do_fetch; fi
      exit 0
      ;;
   "")
      do_fetch
      exit 0
      ;;
   *)
      echo >&2 "Invalid action requested (none of: autoconf / config / '')"
      exit 1
esac