Finalize fast-reboot in warmboot finalizer (#14238)
- Why I did it To solve an issue with upgrade with fast-reboot including FW upgrade which has been introduced since moving to fast-reboot over warm-reboot infrastructure. As well, this introduces fast-reboot finalizing logic to determine fast-reboot is done. - How I did it Added logic to finalize-warmboot script to handle fast-reboot as well, this makes sense as using fast-reboot over warm-reboot this script will be invoked. The script will clear fast-reboot entry from state-db instead of previous implementation that relied on timer. The timer could expire in some scenarios between fast-reboot finished causing fallback to cold-reboot and possible crashes. As well this PR updates all services/scripts reading fast-reboot state-db entry to look for the updated value representing fast-reboot is active. - How to verify it Run fast-reboot and check that fast-reboot entry exists in state-db right after startup and being cleared as warm-reboot is finalized and not due to a timer.
This commit is contained in:
parent
e32624d362
commit
41a9813018
@ -8,11 +8,11 @@ reboot_type='cold'
|
||||
function get_database_reboot_type()
|
||||
{
|
||||
SYSTEM_WARM_START=`sonic-db-cli STATE_DB hget "WARM_RESTART_ENABLE_TABLE|system" enable`
|
||||
SYSTEM_FAST_START=`sonic-db-cli STATE_DB get "FAST_REBOOT|system"`
|
||||
SYSTEM_FAST_START=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
|
||||
if [[ x"${SYSTEM_WARM_START}" == x"true" ]]; then
|
||||
reboot_type='warm'
|
||||
elif [[ x"${SYSTEM_FAST_START}" == x"1" ]]; then
|
||||
elif [[ x"${SYSTEM_FAST_START}" == x"true" ]]; then
|
||||
reboot_type='fast'
|
||||
fi
|
||||
}
|
||||
|
@ -52,6 +52,17 @@ function check_warm_boot()
|
||||
WARM_BOOT=`sonic-db-cli STATE_DB hget "WARM_RESTART_ENABLE_TABLE|system" enable`
|
||||
}
|
||||
|
||||
function check_fast_reboot()
|
||||
{
|
||||
debug "Checking if fast-reboot is enabled..."
|
||||
FAST_REBOOT=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
if [[ x"${FAST_REBOOT}" == x"true" ]]; then
|
||||
debug "Fast-reboot is enabled..."
|
||||
else
|
||||
debug "Fast-reboot is disabled..."
|
||||
fi
|
||||
}
|
||||
|
||||
|
||||
function wait_for_database_service()
|
||||
{
|
||||
@ -97,6 +108,12 @@ function finalize_warm_boot()
|
||||
sudo config warm_restart disable
|
||||
}
|
||||
|
||||
function finalize_fast_reboot()
|
||||
{
|
||||
debug "Finalizing fast-reboot..."
|
||||
sonic-db-cli STATE_DB hset "FAST_RESTART_ENABLE_TABLE|system" "enable" "false" &>/dev/null
|
||||
}
|
||||
|
||||
function stop_control_plane_assistant()
|
||||
{
|
||||
if [[ -x ${ASSISTANT_SCRIPT} ]]; then
|
||||
@ -119,14 +136,20 @@ function restore_counters_folder()
|
||||
|
||||
wait_for_database_service
|
||||
|
||||
check_fast_reboot
|
||||
check_warm_boot
|
||||
|
||||
if [[ x"${WARM_BOOT}" != x"true" ]]; then
|
||||
debug "warmboot is not enabled ..."
|
||||
exit 0
|
||||
if [[ x"${FAST_REBOOT}" != x"true" ]]; then
|
||||
debug "fastboot is not enabled ..."
|
||||
exit 0
|
||||
fi
|
||||
fi
|
||||
|
||||
restore_counters_folder
|
||||
if [[ (x"${WARM_BOOT}" == x"true") && (x"${FAST_REBOOT}" != x"true") ]]; then
|
||||
restore_counters_folder
|
||||
fi
|
||||
|
||||
get_component_list
|
||||
|
||||
@ -143,14 +166,22 @@ for i in `seq 60`; do
|
||||
sleep 5
|
||||
done
|
||||
|
||||
stop_control_plane_assistant
|
||||
if [[ (x"${WARM_BOOT}" == x"true") && (x"${FAST_REBOOT}" != x"true") ]]; then
|
||||
stop_control_plane_assistant
|
||||
fi
|
||||
|
||||
# Save DB after stopped control plane assistant to avoid extra entries
|
||||
debug "Save in-memory database after warm reboot ..."
|
||||
debug "Save in-memory database after warm/fast reboot ..."
|
||||
config save -y
|
||||
|
||||
if [[ -n "${list}" ]]; then
|
||||
debug "Some components didn't finish reconcile: ${list} ..."
|
||||
fi
|
||||
|
||||
finalize_warm_boot
|
||||
if [ x"${FAST_REBOOT}" == x"true" ]; then
|
||||
finalize_fast_reboot
|
||||
fi
|
||||
|
||||
if [ x"${WARM_BOOT}" == x"true" ]; then
|
||||
finalize_warm_boot
|
||||
fi
|
@ -30,7 +30,8 @@ function validate_restore_count()
|
||||
|
||||
function check_fast_boot ()
|
||||
{
|
||||
if [[ $($SONIC_DB_CLI STATE_DB GET "FAST_REBOOT|system") == "1" ]]; then
|
||||
SYSTEM_FAST_REBOOT=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
if [[ x"${SYSTEM_FAST_REBOOT}" == x"true" ]]; then
|
||||
FAST_BOOT="true"
|
||||
else
|
||||
FAST_BOOT="false"
|
||||
|
@ -19,7 +19,8 @@ function check_warm_boot()
|
||||
|
||||
function check_fast_boot ()
|
||||
{
|
||||
if [[ $($SONIC_DB_CLI STATE_DB GET "FAST_REBOOT|system") == "1" ]]; then
|
||||
SYSTEM_FAST_REBOOT=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
if [[ x"${SYSTEM_FAST_REBOOT}" == x"true" ]]; then
|
||||
FAST_BOOT="true"
|
||||
else
|
||||
FAST_BOOT="false"
|
||||
|
@ -60,7 +60,8 @@ function check_warm_boot()
|
||||
|
||||
function check_fast_boot()
|
||||
{
|
||||
if [[ $($SONIC_DB_CLI STATE_DB GET "FAST_REBOOT|system") == "1" ]]; then
|
||||
SYSTEM_FAST_REBOOT=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
if [[ x"${SYSTEM_FAST_REBOOT}" == x"true" ]]; then
|
||||
FAST_BOOT="true"
|
||||
else
|
||||
FAST_BOOT="false"
|
||||
@ -284,8 +285,8 @@ stop() {
|
||||
# encountered error, e.g. syncd crashed. And swss needs to
|
||||
# be restarted.
|
||||
if [[ x"$FAST_BOOT" != x"true" ]]; then
|
||||
debug "Clearing FAST_REBOOT flag..."
|
||||
clean_up_tables STATE_DB "'FAST_REBOOT*'"
|
||||
debug "Clearing FAST_RESTART_ENABLE_TABLE flag..."
|
||||
sonic-db-cli STATE_DB hset "FAST_RESTART_ENABLE_TABLE|system" "enable" "false"
|
||||
fi
|
||||
# Unlock has to happen before reaching out to peer service
|
||||
unlock_service_state_change
|
||||
|
@ -50,7 +50,8 @@ function check_warm_boot()
|
||||
|
||||
function check_fast_boot()
|
||||
{
|
||||
if [[ $($SONIC_DB_CLI STATE_DB GET "FAST_REBOOT|system") == "1" ]]; then
|
||||
SYSTEM_FAST_REBOOT=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
if [[ x"${SYSTEM_FAST_REBOOT}" == x"true" ]]; then
|
||||
FAST_BOOT="true"
|
||||
else
|
||||
FAST_BOOT="false"
|
||||
@ -82,7 +83,8 @@ function getBootType()
|
||||
;;
|
||||
*SONIC_BOOT_TYPE=fast*|*fast-reboot*)
|
||||
# check that the key exists
|
||||
if [[ $($SONIC_DB_CLI STATE_DB GET "FAST_REBOOT|system") == "1" ]]; then
|
||||
SYSTEM_FAST_REBOOT=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
if [[ x"${SYSTEM_FAST_REBOOT}" == x"true" ]]; then
|
||||
TYPE='fast'
|
||||
else
|
||||
TYPE='cold'
|
||||
|
@ -32,7 +32,8 @@ function validate_restore_count()
|
||||
|
||||
function check_fast_boot ()
|
||||
{
|
||||
if [[ $($SONIC_DB_CLI STATE_DB GET "FAST_REBOOT|system") == "1" ]]; then
|
||||
SYSTEM_FAST_REBOOT=`sonic-db-cli STATE_DB hget "FAST_RESTART_ENABLE_TABLE|system" enable`
|
||||
if [[ x"${SYSTEM_FAST_REBOOT}" == x"true" ]]; then
|
||||
FAST_BOOT="true"
|
||||
else
|
||||
FAST_BOOT="false"
|
||||
|
@ -699,14 +699,16 @@ def is_warm_restart_enabled(container_name):
|
||||
|
||||
# Check if System fast reboot is enabled.
|
||||
def is_fast_reboot_enabled():
|
||||
fb_system_state = 0
|
||||
cmd = ['sonic-db-cli', 'STATE_DB', 'get', "FAST_REBOOT|system"]
|
||||
proc = subprocess.Popen(cmd, universal_newlines=True, stdout=subprocess.PIPE)
|
||||
(stdout, stderr) = proc.communicate()
|
||||
state_db = SonicV2Connector(host='127.0.0.1')
|
||||
state_db.connect(state_db.STATE_DB, False)
|
||||
|
||||
TABLE_NAME_SEPARATOR = '|'
|
||||
prefix = 'FAST_RESTART_ENABLE_TABLE' + TABLE_NAME_SEPARATOR
|
||||
|
||||
# Get the system warm reboot enable state
|
||||
_hash = '{}{}'.format(prefix, 'system')
|
||||
fb_system_state = state_db.get(state_db.STATE_DB, _hash, "enable")
|
||||
fb_enable_state = True if fb_system_state == "true" else False
|
||||
|
||||
if proc.returncode != 0:
|
||||
log.log_error("Error running command '{}'".format(cmd))
|
||||
elif stdout:
|
||||
fb_system_state = stdout.rstrip('\n')
|
||||
|
||||
return fb_system_state
|
||||
state_db.close(state_db.STATE_DB)
|
||||
return fb_enable_state
|
||||
|
Loading…
Reference in New Issue
Block a user