[Bug 1269921] Re: networking services restart hangs due to missing /etc/network/run/ifenslave.* files

Tue Jun 21 17:11:32 UTC 2016

To clarify, my "transform" script just bridges active interfaces.

-- 
You received this bug notification because you are a member of Ubuntu
Foundations Bugs, which is subscribed to ifenslave in Ubuntu.
https://bugs.launchpad.net/bugs/1269921

Title:
  networking services restart hangs due to missing
  /etc/network/run/ifenslave.* files

Status in ifenslave package in Ubuntu:
  Confirmed

Bug description:
  Ubuntu 12.04 LTS
  ifenslave-2.6

  ifup hangs when bonds are configured and networking is restarted via
  '/etc/init.d/networking restart'.  The script in '/etc/network/if-pre-
  up.d' does not recognize the bond master and hangs because the
  '/etc/network/run/ifenslave.*' files are not created.

  ##/etc/network/if-pre-up.d/ifenslave

  #!/bin/sh

  [ "$VERBOSITY" = 1 ] && set -x

  IFSTATE=/run/network/ifstate

  add_master()
  {
  	# Return if $BOND_MASTER is already a bonding interface.
  	[ -f "/sys/class/net/$BOND_MASTER/bonding/slaves" ] && return

  	# If the bonding module is not yet loaded, load it.
  	if [ ! -r /sys/class/net/bonding_masters ]; then
  		modprobe -q bonding

  		FAILED=1
  		echo "Waiting for bonding kernel module to be ready (will timeout after 5s)"
  		for i in $(seq 50); do
  			if [ -r /sys/class/net/bonding_masters ]; then
  				FAILED=0
  				break
  			fi
  			sleep 0.1
  		done

  		if [ "$FAILED" = "1" ]; then
  			echo "/sys/class/net/bonding_masters doesn't exist. Unable to create $BOND_MASTER"
  			exit 1
  		fi

          fi

  	# Create the master interface.
  	if ! grep -sq "\\<$BOND_MASTER\\>" /sys/class/net/bonding_masters; then
  		echo "+$BOND_MASTER" > /sys/class/net/bonding_masters
  	fi
  }

  sysfs_change_down()
  {
  	# Called with :
  	# $1 = basename of the file in bonding/ to write to.
  	# $2 = value to write. Won't write if $2 is empty.
  	if [ "$2" ] ; then
  		# If the value we plan to write is different from the current one...
  		if ! grep -sq "\\<$2\\>" "/sys/class/net/$BOND_MASTER/bonding/$1" ; then
  			# ...and the master is up...
  			if ip link show "$BOND_MASTER" | grep -sq '[<,]UP[,>]' ; then
  				# ...bring the master down.
  				ip link set dev "$BOND_MASTER" down
  			fi
  		fi
  		sysfs "$1" "$2"
  	fi
  }

  sysfs()
  {
  	# Called with :
  	# $1 = basename of the file in bonding/ to write to.
  	# $2 = value to write. Won't write if $2 is empty.
  	if [ "$2" ] ; then
  		echo "$2" > "/sys/class/net/$BOND_MASTER/bonding/$1"
  		return $?
  	fi
  	return 0
  }

  sysfs_add()
  {
  	#??Called with :
  	# $1 = target filename.
  	# $2 = values to write.
  	for value in $2; do
  		# Do not add $2 to $1 if already present.
  		if ! grep -sq "\\<$value\\>" /sys/class/net/$BOND_MASTER/bonding/$1
  		then
  		    sysfs "$1" "+$value"
  		fi 
  	done
  }

  # early_setup_master is the place where we do master setup that need to be done before enslavement.
  early_setup_master()
  {
  	# Warning: the order in wich we write into the sysfs files is important.
  	# Double check in drivers/net/bonding/bond_sysfs.c in linux kernel source tree 
  	# before changing anything here.

  	# fail_over_mac must be set before enslavement of any slaves.
  	sysfs fail_over_mac "$IF_BOND_FAIL_OVER_MAC"
  }

  # late_setup_master runs actions that need to happen after enslavement
  late_setup_master()
  {
  	# primary must be set after mode (because only supported in some modes) and after enslavement.
  	# The first slave in bond-primary found in current slaves becomes the primary.
  	# If no slave in bond-primary is found, then primary does not change.
  	for slave in $IF_BOND_PRIMARY ; do
  		if grep -sq "\\<$slave\\>" "/sys/class/net/$BOND_MASTER/bonding/slaves" ; then
  			sysfs primary "$slave"
  			break
  		fi
  	done

  	# primary_reselect should be set after mode (because only supported in some modes), after enslavement
  	# and after primary. This is currently (2.6.35-rc1) not enforced by the bonding driver, but it is
  	# probably safer to do it in that order.
  	sysfs primary_reselect "$IF_BOND_PRIMARY_RESELECT"

  	# queue_id must be set after enslavement.
  	for iface_queue_id in $IF_BOND_QUEUE_ID
  	do
  		sysfs iface_queue_id $iface_queue_id
  	done

  	# active_slave must be set after mode and after enslavement.
  	# The slave must be up and the underlying link must be up too.
  	# FIXME: We should have a way to write an empty string to active_slave, to set the active_slave to none.
  	if [ "$IF_BOND_ACTIVE_SLAVE" ] ; then
  		# Need to force interface up before. Bonding will refuse to activate a down interface.
  		ip link set "$IF_BOND_ACTIVE_SLAVE" up
  		sysfs active_slave "$IF_BOND_ACTIVE_SLAVE"
  	fi
  }

  enslave_slaves()
  {
  	case "$BOND_SLAVES" in
  		none)
  			BOND_SLAVES=""
  			;;
  		all)
  			BOND_SLAVES=`sed -ne 's/ *\(eth[^:]*\):.*/\1/p' /proc/net/dev`
  			AUTOIF="yes"
  			;;
  	esac

  	[ "$VERBOSITY" = 1 ] && v=-v
  	for slave in $BOND_SLAVES ; do
  		if ( [ "$AUTOIF" ] && grep -q "^$slave=" $IFSTATE ) ; then
  			echo "Not enslaving interface $slave since it is already configured"
  		else
  			# Ensure $slave is down.
  			ip link set "$slave" down 2>/dev/null
  			if ! sysfs_add slaves "$slave" 2>/dev/null ; then
  				echo "Failed to enslave $slave to $BOND_MASTER. Is $BOND_MASTER ready and a bonding interface ?" >&2
  			else
  				# Bring up slave if it is the target of an allow-bondX stanza.
  				# This is usefull to bring up slaves that need extra setup.
  				if [ -z "$(which ifquery)" ] || ifquery --allow \"$BOND_MASTER\" --list | grep -q $slave; then
  					ifup $v --allow "$BOND_MASTER" "$slave"
  				fi
  			fi
  		fi
  	done
  }

  setup_master()
  {
  	# Warning: the order in wich we write into the sysfs files is important.
  	# Double check in drivers/net/bonding/bond_sysfs.c in linux kernel source tree 
  	# before changing anything here.

  	# use_carrier can be set anytime.
  	sysfs use_carrier "$IF_BOND_USE_CARRIER"
  	# num_grat_arp can be set anytime.
  	sysfs num_grat_arp "$IF_BOND_NUM_GRAT_ARP"
  	# num_unsol_na can be set anytime.
  	sysfs num_unsol_na "$IF_BOND_NUM_UNSOL_NA"

  	# xmit_hash_policy can be set anytime.
  	# Changing xmit_hash_policy requires $BOND_MASTER to be down.
  	sysfs_change_down xmit_hash_policy "$IF_BOND_XMIT_HASH_POLICY"

  	# arp_ip_target must be set before arp_interval.
  	sysfs_add arp_ip_target "$IF_BOND_ARP_IP_TARGET"
  	sysfs arp_interval "$IF_BOND_ARP_INTERVAL"

  	# miimon must be set before updelay and downdelay.
  	sysfs miimon "$IF_BOND_MIIMON"
  	sysfs downdelay "$IF_BOND_DOWNDELAY"
  	sysfs updelay "$IF_BOND_UPDELAY"

  	# Changing ad_select requires $BOND_MASTER to be down.
  	sysfs_change_down ad_select "$IF_BOND_AD_SELECT"

  	# Changing mode requires $BOND_MASTER to be down.
  	# Mode should be set after miimon or arp_interval, to avoid a warning in syslog.
  	sysfs_change_down mode "$IF_BOND_MODE"

  	# arp_validate must be after mode (because mode must be active-backup).
  	sysfs arp_validate "$IF_BOND_ARP_VALIDATE"

  	# lacp_rate must be set after mode (because mode must be 802.3ad).
  	# Changing lacp_rate requires $BOND_MASTER to be down.
  	sysfs_change_down lacp_rate "$IF_BOND_LACP_RATE"

  	# Finally bring the bond up, note that without a slave it won't be usable though
  	ip link set dev $BOND_MASTER up
  }

  # Option slaves deprecated, replaced by bond-slaves, but still supported for backward compatibility.
  IF_BOND_SLAVES=${IF_BOND_SLAVES:-$IF_SLAVES}

  if [ "$IF_BOND_MASTER" ] ; then
  	BOND_MASTER="$IF_BOND_MASTER"
  	BOND_SLAVES="$IFACE"
  else
  	if [ "$IF_BOND_SLAVES" ] ; then
  		BOND_MASTER="$IFACE"
  		BOND_SLAVES="$IF_BOND_SLAVES"
  	fi
  fi

  # Exit if nothing to do...
  [ -z "$BOND_MASTER$BOND_SLAVES" ] && exit

  # Always try to create the master, returns if already exists
  add_master

  if [ "$BOND_MASTER" = "$IFACE" ]; then
  	# Setup the master interface
  	early_setup_master
  	setup_master

  	# Indicate that we're done setting up the master
  	# this is required as ifstate is modified at the beginning
  	# of the interface setup, not at the end
  	touch /run/network/ifenslave.$IFACE

  	# Wait for a slave to join, continuing without a slave
  	# would make dhclient, vconfig or brctl fail, so better wait
  	# Timeout after a minute
  	FAILED=1
  	echo "Waiting for a slave to join $BOND_MASTER (will timeout after 60s)"
  	for i in $(seq 600); do
  		if [ -n "$(cat /sys/class/net/$BOND_MASTER/bonding/slaves)" ]; then
  			FAILED=0
  			break
  		fi
  		sleep 0.1
  	done
  	if [ "$FAILED" = "1" ]; then
  		echo "No slave joined $BOND_MASTER, continuing anyway"
  	else
  		# Trigger the udev bridging hook to bridge the bond if needed
  		if [ -x /lib/udev/bridge-network-interface ]; then
  			INTERFACE=$BOND_MASTER /lib/udev/bridge-network-interface
  		fi

  		# Trigger the udev bridging hook to tag the bond if needed
  		if [ -x /lib/udev/vlan-network-interface ]; then
  			INTERFACE=$BOND_MASTER /lib/udev/vlan-network-interface
  		fi
  	fi
  else
  	# Wait for the master to be ready
  	[ ! -f /run/network/ifenslave.$BOND_MASTER ] && echo "Waiting for bond master $BOND_MASTER to be ready"
  	while :; do
  		if [ -f /run/network/ifenslave.$BOND_MASTER ]; then
  			break
  		fi
  		sleep 0.1
  	done

  	# Only setup one slave at once
  	BOND_SLAVES=$IFACE enslave_slaves

  	# Call late_setup_master every time we add a slave as we don't have a way to know
  	# when all the slaves are up
  	BOND_SLAVES=$IFACE late_setup_master
  fi
  exit 0

  ## /etc/network/interfaces
  # This file describes the network interfaces available on your system
  # and how they will be activated. For more information, see interfaces(5).
  # chef managed!

  auto eth1
  iface  eth1 inet manual
    bond-master bond0
    bond-primary eth1

  # default bridge interface
   auto backend
  iface backend inet manual
    bridge_fd 0  
    bridge_ports vlan10  
    bridge_stp off  

  # failover nic team
   auto bond0
  iface bond0 inet manual
    bond-miimon 100  
    bond-mode active-backup  
    bond-primary eth1  
    bond-slaves none  

  # The VM network interface
   auto eth0
  iface eth0 inet static
    address 10.0.2.15  
    broadcast 10.0.2.255  
    gateway 10.0.2.0  
    netmask 255.255.255.0  

  # The loopback interface
   auto lo
  iface lo inet loopback

  # default vlan interface
   auto vlan10
  iface vlan10 inet manual
    vlan_raw_device bond0

  ProblemType: Bug
  DistroRelease: Ubuntu 12.04
  Package: ifenslave-2.6 1.1.0-19ubuntu5
  ProcVersionSignature: Ubuntu 3.2.0-32.51-generic 3.2.30
  Uname: Linux 3.2.0-32-generic x86_64
  ApportVersion: 2.0.1-0ubuntu17.1
  Architecture: amd64
  Date: Thu Jan 16 17:34:48 2014
  InstallationMedia: Ubuntu-Server 12.04.1 LTS "Precise Pangolin" - Release amd64 (20120817.3)
  MarkForUpload: True
  ProcEnviron:
   TERM=xterm
   PATH=(custom, no user)
   LANG=en_US.UTF-8
   SHELL=/bin/bash
  SourcePackage: ifenslave-2.6
  UpgradeStatus: No upgrade log present (probably fresh install)

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/ifenslave/+bug/1269921/+subscriptions