sonic-buildimage/files/scripts/swss.sh

268 lines
7.5 KiB
Bash
Raw Normal View History

#!/bin/bash
DEPENDENT="radv dhcp_relay"
MULTI_INST_DEPENDENT="teamd"
function debug()
{
/usr/bin/logger $1
/bin/echo `date` "- $1" >> ${DEBUGLOG}
}
function lock_service_state_change()
{
debug "Locking ${LOCKFILE} from ${SERVICE}$DEV service"
exec {LOCKFD}>${LOCKFILE}
/usr/bin/flock -x ${LOCKFD}
trap "/usr/bin/flock -u ${LOCKFD}" 0 2 3 15
debug "Locked ${LOCKFILE} (${LOCKFD}) from ${SERVICE}$DEV service"
}
function unlock_service_state_change()
{
debug "Unlocking ${LOCKFILE} (${LOCKFD}) from ${SERVICE}$DEV service"
/usr/bin/flock -u ${LOCKFD}
}
function check_warm_boot()
{
SYSTEM_WARM_START=`$SONIC_DB_CLI STATE_DB hget "WARM_RESTART_ENABLE_TABLE|system" enable`
SERVICE_WARM_START=`$SONIC_DB_CLI STATE_DB hget "WARM_RESTART_ENABLE_TABLE|${SERVICE}" enable`
if [[ x"$SYSTEM_WARM_START" == x"true" ]] || [[ x"$SERVICE_WARM_START" == x"true" ]]; then
WARM_BOOT="true"
else
WARM_BOOT="false"
fi
}
function check_fast_boot()
{
if [[ $($SONIC_DB_CLI STATE_DB GET "FAST_REBOOT|system") == "1" ]]; then
FAST_BOOT="true"
else
FAST_BOOT="false"
fi
}
function validate_restore_count()
{
if [[ x"$WARM_BOOT" == x"true" ]]; then
RESTORE_COUNT=`$SONIC_DB_CLI STATE_DB hget "WARM_RESTART_TABLE|orchagent" restore_count`
# We have to make sure db data has not been flushed.
if [[ -z "$RESTORE_COUNT" ]]; then
WARM_BOOT="false"
fi
fi
}
function wait_for_database_service()
{
# Wait for redis server start before database clean
until [[ $($SONIC_DB_CLI PING | grep -c PONG) -gt 0 ]]; do
sleep 1;
done
# Wait for configDB initialization
until [[ $($SONIC_DB_CLI CONFIG_DB GET "CONFIG_DB_INITIALIZED") ]];
do sleep 1;
done
}
# This function cleans up the tables with specific prefixes from the database
# $1 the index of the database
# $2 the string of a list of table prefixes
function clean_up_tables()
{
$SONIC_DB_CLI $1 EVAL "
local tables = {$2}
for i = 1, table.getn(tables) do
local matches = redis.call('KEYS', tables[i])
for j,name in ipairs(matches) do
redis.call('DEL', name)
end
end" 0
}
start_peer_and_dependent_services() {
check_warm_boot
if [[ x"$WARM_BOOT" != x"true" ]]; then
if [[ ! -z $DEV ]]; then
/bin/systemctl start ${PEER}@$DEV
else
/bin/systemctl start ${PEER}
fi
for dep in ${DEPENDENT}; do
/bin/systemctl start ${dep}
done
for dep in ${MULTI_INST_DEPENDENT}; do
if [[ ! -z $DEV ]]; then
/bin/systemctl start ${dep}@$DEV
else
/bin/systemctl start ${dep}
fi
done
fi
}
stop_peer_and_dependent_services() {
# if warm/fast start enabled or peer lock exists, don't stop peer service docker
if [[ x"$WARM_BOOT" != x"true" ]] && [[ x"$FAST_BOOT" != x"true" ]]; then
if [[ ! -z $DEV ]]; then
/bin/systemctl stop ${PEER}@$DEV
else
/bin/systemctl stop ${PEER}
fi
for dep in ${DEPENDENT}; do
/bin/systemctl stop ${dep}
done
for dep in ${MULTI_INST_DEPENDENT}; do
if [[ ! -z $DEV ]]; then
/bin/systemctl stop ${dep}@$DEV
else
/bin/systemctl stop ${dep}
fi
done
fi
}
start() {
debug "Starting ${SERVICE}$DEV service..."
lock_service_state_change
wait_for_database_service
check_warm_boot
validate_restore_count
debug "Warm boot flag: ${SERVICE}$DEV ${WARM_BOOT}."
# Don't flush DB during warm boot
if [[ x"$WARM_BOOT" != x"true" ]]; then
debug "Flushing APP, ASIC, COUNTER, CONFIG, and partial STATE databases ..."
$SONIC_DB_CLI APPL_DB FLUSHDB
$SONIC_DB_CLI ASIC_DB FLUSHDB
$SONIC_DB_CLI COUNTERS_DB FLUSHDB
$SONIC_DB_CLI FLEX_COUNTER_DB FLUSHDB
[Dynamic buffer calc] Support dynamic buffer calculation (#6194) **- Why I did it** To support dynamic buffer calculation. This PR also depends on the following PRs for sub modules - [sonic-swss: [buffermgr/bufferorch] Support dynamic buffer calculation #1338](https://github.com/Azure/sonic-swss/pull/1338) - [sonic-swss-common: Dynamic buffer calculation #361](https://github.com/Azure/sonic-swss-common/pull/361) - [sonic-utilities: Support dynamic buffer calculation #973](https://github.com/Azure/sonic-utilities/pull/973) **- How I did it** 1. Introduce field `buffer_model` in `DEVICE_METADATA|localhost` to represent which buffer model is running in the system currently: - `dynamic` for the dynamic buffer calculation model - `traditional` for the traditional model in which the `pg_profile_lookup.ini` is used 2. Add the tables required for the feature: - ASIC_TABLE in platform/\<vendor\>/asic_table.j2 - PERIPHERAL_TABLE in platform/\<vendor\>/peripheral_table.j2 - PORT_PERIPHERAL_TABLE on a per-platform basis in device/\<vendor\>/\<platform\>/port_peripheral_config.j2 for each platform with gearbox installed. - DEFAULT_LOSSLESS_BUFFER_PARAMETER and LOSSLESS_TRAFFIC_PATTERN in files/build_templates/buffers_config.j2 - Add lossless PGs (3-4) for each port in files/build_templates/buffers_config.j2 3. Copy the newly introduced j2 files into the image and rendering them when the system starts 4. Update the CLI options for buffermgrd so that it can start with dynamic mode 5. Fetches the ASIC vendor name in orchagent: - fetch the vendor name when creates the docker and pass it as a docker environment variable - `buffermgrd` can use this passed-in variable 6. Clear buffer related tables from STATE_DB when swss docker starts 7. Update the src/sonic-config-engine/tests/sample_output/buffers-dell6100.json according to the buffer_config.j2 8. Remove buffer pool sizes for ingress pools and egress_lossy_pool Update the buffer settings for dynamic buffer calculation
2020-12-13 13:35:39 -06:00
clean_up_tables STATE_DB "'PORT_TABLE*', 'MGMT_PORT_TABLE*', 'VLAN_TABLE*', 'VLAN_MEMBER_TABLE*', 'LAG_TABLE*', 'LAG_MEMBER_TABLE*', 'INTERFACE_TABLE*', 'MIRROR_SESSION*', 'VRF_TABLE*', 'FDB_TABLE*', 'FG_ROUTE_TABLE*', 'BUFFER_POOL*', 'BUFFER_PROFILE*'"
fi
# start service docker
/usr/bin/${SERVICE}.sh start $DEV
debug "Started ${SERVICE}$DEV service..."
# Unlock has to happen before reaching out to peer service
unlock_service_state_change
}
wait() {
start_peer_and_dependent_services
# Allow some time for peer container to start
# NOTE: This assumes Docker containers share the same names as their
# corresponding services
for SECS in {1..60}; do
if [[ ! -z $DEV ]]; then
RUNNING=$(docker inspect -f '{{.State.Running}}' ${PEER}$DEV)
else
RUNNING=$(docker inspect -f '{{.State.Running}}' ${PEER})
fi
[docker-teamd]: Add teamd as a depedent service to swss (#5628) **- Why I did it** On teamd docker restart, the swss and syncd needs to be restarted as there are dependent resources present. **- How I did it** Add the teamd as a dependent service for swss Updated the docker-wait script to handle service and dependent services separately. Handle the case of warm-restart for the dependent service **- How to verify it** Verified the following scenario's with the following testbed VM1 ----------------------------[DUT 6100] -----------------------VM2, ping traffic continuous between VMs 1. Stop teamd docker alone > swss, syncd dockers seen going away > The LAG reference count error messages seen for a while till swss docker stops. > Dockers back up. 2. Enable WR mode for teamd. Stop teamd docker alone > swss, syncd dockers not removed. > The LAG reference count error messages not seen > Repeated stop teamd docker test - same result, no effect on swss/syncd. 3. Stop swss docker. > swss, teamd, syncd goes off - dockers comes back correctly, interfaces up 4. Enable WR mode for swss . Stop swss docker > swss goes off not affecting syncd/teamd dockers. 5. Config reload > no reference counter error seen, dockers comes back correctly, with interfaces up 6. Warm reboot, observations below > swss docker goes off first > teamd + syncd goes off to the end of WR process. > dockers comes back up fine. > ping traffic between VM's was NOT HIT 7. Fast reboot, observations below > teamd goes off first ( **confirmed swss don't exit here** ) > swss goes off next > syncd goes away at the end of the FR process > dockers comes back up fine. > there is a traffic HIT as per fast-reboot 8. Verified in multi-asic platform, the tests above other than WR/FB scenarios
2020-10-23 02:41:16 -05:00
ALL_DEPS_RUNNING=true
for dep in ${MULTI_INST_DEPENDENT}; do
if [[ ! -z $DEV ]]; then
DEP_RUNNING=$(docker inspect -f '{{.State.Running}}' ${dep}$DEV)
else
DEP_RUNNING=$(docker inspect -f '{{.State.Running}}' ${dep})
fi
if [[ x"$DEP_RUNNING" != x"true" ]]; then
ALL_DEPS_RUNNING=false
break
fi
done
if [[ x"$RUNNING" == x"true" && x"$ALL_DEPS_RUNNING" == x"true" ]]; then
break
else
sleep 1
fi
done
# NOTE: This assumes Docker containers share the same names as their
# corresponding services
[docker-teamd]: Add teamd as a depedent service to swss (#5628) **- Why I did it** On teamd docker restart, the swss and syncd needs to be restarted as there are dependent resources present. **- How I did it** Add the teamd as a dependent service for swss Updated the docker-wait script to handle service and dependent services separately. Handle the case of warm-restart for the dependent service **- How to verify it** Verified the following scenario's with the following testbed VM1 ----------------------------[DUT 6100] -----------------------VM2, ping traffic continuous between VMs 1. Stop teamd docker alone > swss, syncd dockers seen going away > The LAG reference count error messages seen for a while till swss docker stops. > Dockers back up. 2. Enable WR mode for teamd. Stop teamd docker alone > swss, syncd dockers not removed. > The LAG reference count error messages not seen > Repeated stop teamd docker test - same result, no effect on swss/syncd. 3. Stop swss docker. > swss, teamd, syncd goes off - dockers comes back correctly, interfaces up 4. Enable WR mode for swss . Stop swss docker > swss goes off not affecting syncd/teamd dockers. 5. Config reload > no reference counter error seen, dockers comes back correctly, with interfaces up 6. Warm reboot, observations below > swss docker goes off first > teamd + syncd goes off to the end of WR process. > dockers comes back up fine. > ping traffic between VM's was NOT HIT 7. Fast reboot, observations below > teamd goes off first ( **confirmed swss don't exit here** ) > swss goes off next > syncd goes away at the end of the FR process > dockers comes back up fine. > there is a traffic HIT as per fast-reboot 8. Verified in multi-asic platform, the tests above other than WR/FB scenarios
2020-10-23 02:41:16 -05:00
for dep in ${MULTI_INST_DEPENDENT}; do
if [[ ! -z $DEV ]]; then
ALL_DEPS="$ALL_DEPS ${dep}$DEV"
else
ALL_DEPS="$ALL_DEPS ${dep}"
fi
done
if [[ ! -z $DEV ]]; then
[docker-teamd]: Add teamd as a depedent service to swss (#5628) **- Why I did it** On teamd docker restart, the swss and syncd needs to be restarted as there are dependent resources present. **- How I did it** Add the teamd as a dependent service for swss Updated the docker-wait script to handle service and dependent services separately. Handle the case of warm-restart for the dependent service **- How to verify it** Verified the following scenario's with the following testbed VM1 ----------------------------[DUT 6100] -----------------------VM2, ping traffic continuous between VMs 1. Stop teamd docker alone > swss, syncd dockers seen going away > The LAG reference count error messages seen for a while till swss docker stops. > Dockers back up. 2. Enable WR mode for teamd. Stop teamd docker alone > swss, syncd dockers not removed. > The LAG reference count error messages not seen > Repeated stop teamd docker test - same result, no effect on swss/syncd. 3. Stop swss docker. > swss, teamd, syncd goes off - dockers comes back correctly, interfaces up 4. Enable WR mode for swss . Stop swss docker > swss goes off not affecting syncd/teamd dockers. 5. Config reload > no reference counter error seen, dockers comes back correctly, with interfaces up 6. Warm reboot, observations below > swss docker goes off first > teamd + syncd goes off to the end of WR process. > dockers comes back up fine. > ping traffic between VM's was NOT HIT 7. Fast reboot, observations below > teamd goes off first ( **confirmed swss don't exit here** ) > swss goes off next > syncd goes away at the end of the FR process > dockers comes back up fine. > there is a traffic HIT as per fast-reboot 8. Verified in multi-asic platform, the tests above other than WR/FB scenarios
2020-10-23 02:41:16 -05:00
/usr/bin/docker-wait-any -s ${SERVICE}$DEV -d ${PEER}$DEV ${ALL_DEPS}
else
[docker-teamd]: Add teamd as a depedent service to swss (#5628) **- Why I did it** On teamd docker restart, the swss and syncd needs to be restarted as there are dependent resources present. **- How I did it** Add the teamd as a dependent service for swss Updated the docker-wait script to handle service and dependent services separately. Handle the case of warm-restart for the dependent service **- How to verify it** Verified the following scenario's with the following testbed VM1 ----------------------------[DUT 6100] -----------------------VM2, ping traffic continuous between VMs 1. Stop teamd docker alone > swss, syncd dockers seen going away > The LAG reference count error messages seen for a while till swss docker stops. > Dockers back up. 2. Enable WR mode for teamd. Stop teamd docker alone > swss, syncd dockers not removed. > The LAG reference count error messages not seen > Repeated stop teamd docker test - same result, no effect on swss/syncd. 3. Stop swss docker. > swss, teamd, syncd goes off - dockers comes back correctly, interfaces up 4. Enable WR mode for swss . Stop swss docker > swss goes off not affecting syncd/teamd dockers. 5. Config reload > no reference counter error seen, dockers comes back correctly, with interfaces up 6. Warm reboot, observations below > swss docker goes off first > teamd + syncd goes off to the end of WR process. > dockers comes back up fine. > ping traffic between VM's was NOT HIT 7. Fast reboot, observations below > teamd goes off first ( **confirmed swss don't exit here** ) > swss goes off next > syncd goes away at the end of the FR process > dockers comes back up fine. > there is a traffic HIT as per fast-reboot 8. Verified in multi-asic platform, the tests above other than WR/FB scenarios
2020-10-23 02:41:16 -05:00
/usr/bin/docker-wait-any -s ${SERVICE} -d ${PEER} ${ALL_DEPS}
fi
}
stop() {
debug "Stopping ${SERVICE}$DEV service..."
[[ -f ${LOCKFILE} ]] || /usr/bin/touch ${LOCKFILE}
lock_service_state_change
check_warm_boot
debug "Warm boot flag: ${SERVICE}$DEV ${WARM_BOOT}."
check_fast_boot
debug "Fast boot flag: ${SERVICE}$DEV ${FAST_BOOT}."
# For WARM/FAST boot do not perform service stop
if [[ x"$WARM_BOOT" != x"true" ]] && [[ x"$FAST_BOOT" != x"true" ]]; then
/usr/bin/${SERVICE}.sh stop $DEV
debug "Stopped ${SERVICE}$DEV service..."
else
debug "Killing Docker swss..."
/usr/bin/docker kill swss &> /dev/null || debug "Docker swss is not running ($?) ..."
fi
# Flush FAST_REBOOT table when swss needs to stop. The only
# time when this would take effect is when fast-reboot
# encountered error, e.g. syncd crashed. And swss needs to
# be restarted.
if [[ x"$FAST_BOOT" != x"true" ]]; then
debug "Clearing FAST_REBOOT flag..."
clean_up_tables STATE_DB "'FAST_REBOOT*'"
fi
# Unlock has to happen before reaching out to peer service
unlock_service_state_change
stop_peer_and_dependent_services
}
DEV=$2
SERVICE="swss"
PEER="syncd"
DEBUGLOG="/tmp/swss-syncd-debug$DEV.log"
LOCKFILE="/tmp/swss-syncd-lock$DEV"
NAMESPACE_PREFIX="asic"
if [ "$DEV" ]; then
NET_NS="$NAMESPACE_PREFIX$DEV" #name of the network namespace
SONIC_DB_CLI="sonic-db-cli -n $NET_NS"
else
NET_NS=""
SONIC_DB_CLI="sonic-db-cli"
fi
case "$1" in
start|wait|stop)
$1
;;
*)
echo "Usage: $0 {start|wait|stop}"
exit 1
;;
esac