openstack
/
tripleo-upgrade
Code Issues Proposed changes

Make a workload_launch script more robust 

Add more error detection in workload_launch script to fail script early
when the error occurs.

Also, make ssh test to run by default to be sure created vm is
accessible via floating ip, before saving its floating ip to a file. The
file is used in ping test and we need to make sure it is not present on
undercloud when vm fails to boot or is unreachable.

Change-Id: I1057de8dde62fef7e2e00880704d7f3bb3bf6b19
This commit is contained in:
mciecier 2022-10-03 13:16:32 +02:00
parent 06888b1bd8
commit f78db9fbc6
1 changed files with 35 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
templates/workload_launch.sh.j2
View File

@ -271,6 +271,13 @@ function workload_launch {
echo "Assign FIP[${INSTANCE_FIP}] to server ${INSTANCE_NAME}"
openstack server add floating ip ${INSTANCE_NAME} ${INSTANCE_FIP}
if [ $? -ne 0 ]; then
echo "Network related error detected while attaching FIP to VM. Exiting with non-zero code"
if [[ "${MODE}" == "sanity" ]]; then
sanity_teardown
fi
exit 1
fi
VM_IP=${INSTANCE_FIP}
{%- endif %}
@ -278,32 +285,38 @@ function workload_launch {
CINDER_VOL_ID=$(openstack volume create --size 1 vol_${SUFFIX} -f json | jq -r .id)
echo "Attach volume vol_${SUFFIX} to instance ${INSTANCE_NAME}"
openstack server add volume ${INSTANCE_NAME} ${CINDER_VOL_ID}
if [ $? -ne 0 ]; then
echo "Storage related error detected while attaching VOLUME to VM. Exiting with non-zero code"
if [[ "${MODE}" == "sanity" ]]; then
sanity_teardown
fi
exit 1
fi
## SSH to VM through it's floating ip or external ip
if [[ "${MODE}" == "sanity" ]]; then
timeout_seconds=180
elapsed_seconds=0
while true; do
# assert instance is reachable via ssh
echo " [$(date)] Trying to ssh to ${VM_IP}"
ssh -q -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null \
${INSTANCE_USER}@${VM_IP} 'whoami'
if [[ ${?} -eq 0 ]]; then
echo "Instance ${INSTANCE_NAME} is reachable via ${VM_IP}"
break
fi
sleep 3
elapsed_seconds=$(expr $elapsed_seconds + 3)
if [ $elapsed_seconds -ge $timeout_seconds ]; then
echo "FAILURE: Instance failed to boot."
timeout_seconds=180
elapsed_seconds=0
while true; do
# assert instance is reachable via ssh
echo " [$(date)] Trying to ssh to ${VM_IP}"
ssh -q -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null \
${INSTANCE_USER}@${VM_IP} 'whoami'
if [[ ${?} -eq 0 ]]; then
echo "Instance ${INSTANCE_NAME} is reachable via ${VM_IP}"
echo "Write VM_IP ${VM_IP} to file"
echo "vm-ip: ${VM_IP}" > ~/${INSTANCE_NAME}
break
fi
sleep 3
elapsed_seconds=$(expr $elapsed_seconds + 3)
if [ $elapsed_seconds -ge $timeout_seconds ]; then
echo "FAILURE: Instance failed to boot."
if [[ "${MODE}" == "sanity" ]]; then
sanity_teardown
exit 1
fi
done
fi
echo "vm-ip: ${VM_IP}" > ~/${INSTANCE_NAME}
exit 1
fi
done
}
if [[ "${MODE}" == "workload" ]]; then