Re: [PATCH net-next 1/2] selftests: bonding: up/down delay w/ slave link flapping

[Paolo Abeni]

On Fri, 2022-11-18 at 15:30 -0500, Jonathan Toppins wrote:
> Verify when a bond is configured with {up,down}delay and the link state
> of slave members flaps if there are no remaining members up the bond
> should immediately select a member to bring up. (from bonding.txt
> section 13.1 paragraph 4)
> 
> Suggested-by: Liang Li <liali@xxxxxxxxxx>
> Signed-off-by: Jonathan Toppins <jtoppins@xxxxxxxxxx>
> ---
>  .../selftests/drivers/net/bonding/Makefile    |   4 +-
>  .../selftests/drivers/net/bonding/lag_lib.sh  | 107 ++++++++++++++++++
>  .../net/bonding/mode-1-recovery-updelay.sh    |  45 ++++++++
>  .../net/bonding/mode-2-recovery-updelay.sh    |  45 ++++++++
>  .../selftests/drivers/net/bonding/settings    |   2 +-
>  5 files changed, 201 insertions(+), 2 deletions(-)
>  create mode 100755 tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
>  create mode 100755 tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
> 
> diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
> index 6b8d2e2f23c2..0f3921908b07 100644
> --- a/tools/testing/selftests/drivers/net/bonding/Makefile
> +++ b/tools/testing/selftests/drivers/net/bonding/Makefile
> @@ -5,7 +5,9 @@ TEST_PROGS := \
>  	bond-arp-interval-causes-panic.sh \
>  	bond-break-lacpdu-tx.sh \
>  	bond-lladdr-target.sh \
> -	dev_addr_lists.sh
> +	dev_addr_lists.sh \
> +	mode-1-recovery-updelay.sh \
> +	mode-2-recovery-updelay.sh
>  
>  TEST_FILES := \
>  	lag_lib.sh \
> diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
> index 16c7fb858ac1..6dc9af1f2428 100644
> --- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
> +++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
> @@ -1,6 +1,8 @@
>  #!/bin/bash
>  # SPDX-License-Identifier: GPL-2.0
>  
> +NAMESPACES=""
> +
>  # Test that a link aggregation device (bonding, team) removes the hardware
>  # addresses that it adds on its underlying devices.
>  test_LAG_cleanup()
> @@ -59,3 +61,108 @@ test_LAG_cleanup()
>  
>  	log_test "$driver cleanup mode $mode"
>  }
> +
> +# Build a generic 2 node net namespace with 2 connections
> +# between the namespaces
> +#
> +#  +-----------+       +-----------+
> +#  | node1     |       | node2     |
> +#  |           |       |           |
> +#  |           |       |           |
> +#  |      eth0 +-------+ eth0      |
> +#  |           |       |           |
> +#  |      eth1 +-------+ eth1      |
> +#  |           |       |           |
> +#  +-----------+       +-----------+
> +lag_setup2x2()
> +{
> +	local state=${1:-down}
> +	local namespaces="lag_node1 lag_node2"
> +
> +	# create namespaces
> +	for n in ${namespaces}; do
> +		ip netns add ${n}
> +	done
> +
> +	# wire up namespaces
> +	ip link add name lag1 type veth peer name lag1-end
> +	ip link set dev lag1 netns lag_node1 $state name eth0
> +	ip link set dev lag1-end netns lag_node2 $state name eth0
> +
> +	ip link add name lag1 type veth peer name lag1-end
> +	ip link set dev lag1 netns lag_node1 $state name eth1
> +	ip link set dev lag1-end netns lag_node2 $state name eth1
> +
> +	NAMESPACES="${namespaces}"
> +}
> +
> +# cleanup all lag related namespaces and remove the bonding module
> +lag_cleanup()
> +{
> +	for n in ${NAMESPACES}; do
> +		ip netns delete ${n} >/dev/null 2>&1 || true
> +	done
> +	modprobe -r bonding
> +}
> +
> +SWITCH="lag_node1"
> +CLIENT="lag_node2"
> +CLIENTIP="172.20.2.1"
> +SWITCHIP="172.20.2.2"
> +
> +lag_setup_network()
> +{
> +	lag_setup2x2 "down"
> +
> +	# create switch
> +	ip netns exec ${SWITCH} ip link add br0 up type bridge
> +	ip netns exec ${SWITCH} ip link set eth0 master br0 up
> +	ip netns exec ${SWITCH} ip link set eth1 master br0 up
> +	ip netns exec ${SWITCH} ip addr add ${SWITCHIP}/24 dev br0
> +}
> +
> +lag_reset_network()
> +{
> +	ip netns exec ${CLIENT} ip link del bond0
> +	ip netns exec ${SWITCH} ip link set eth0 up
> +	ip netns exec ${SWITCH} ip link set eth1 up
> +}
> +
> +create_bond()
> +{
> +	# create client
> +	ip netns exec ${CLIENT} ip link set eth0 down
> +	ip netns exec ${CLIENT} ip link set eth1 down
> +
> +	ip netns exec ${CLIENT} ip link add bond0 type bond $@
> +	ip netns exec ${CLIENT} ip link set eth0 master bond0
> +	ip netns exec ${CLIENT} ip link set eth1 master bond0
> +	ip netns exec ${CLIENT} ip link set bond0 up
> +	ip netns exec ${CLIENT} ip addr add ${CLIENTIP}/24 dev bond0
> +}
> +
> +test_bond_recovery()
> +{
> +	RET=0
> +
> +	create_bond $@
> +
> +	# verify connectivity
> +	ip netns exec ${CLIENT} ping ${SWITCHIP} -c 5 >/dev/null 2>&1

Minor nit: here and below you reduce the count number, to shorten
significantly the tests runtime.

> +	check_err $? "No connectivity"
> +
> +	# force the links of the bond down
> +	ip netns exec ${SWITCH} ip link set eth0 down
> +	sleep 2
> +	ip netns exec ${SWITCH} ip link set eth0 up
> +	ip netns exec ${SWITCH} ip link set eth1 down
> +
> +	# re-verify connectivity
> +	ip netns exec ${CLIENT} ping ${SWITCHIP} -c 5 >/dev/null 2>&1
> +
> +	local rc=$?
> +	check_err $rc "Bond failed to recover"
> +	log_test "$1 ($2) bond recovery"
> +	lag_reset_network
> +	return 0

Minor nit: the return statement is not needed here.


Cheers,

Paolo