#! /bin/bash
################################################################################
#
# Dunuins Vzdump Hook Script for Voyager
#
# This script for PVE 7.3 will enable storages when a backup starts and disable
# them after the backup has finsihed. This is useful in case your backup
# storages aren't online 24/7, as the webUI will get unresponsive or even
# totally unusable when there are unreachable PBS, NFS or SMB storages.
#
# To install it, create a new file at the location of your choice and edit it.
# For example:
# $ nano /var/lib/vz/snippets/vzdump_hook.sh
# Paste all of this code there and save it with CTRL+X, Y.
# Make that script owned by root:
# $ chown root:root /var/lib/vz/snippets/vzdump_hook.sh
# Make the script executable by root:
# $ chmod 750 /var/lib/vz/snippets/vzdump_hook.sh
# Add hook script to /etc/vzdump.conf:
# $ echo 'script: /var/lib/vz/snippets/vzdump_hook.sh' >> /etc/vzdump.conf
#
# Last edit: 2023.05.21 03:12
###############################################################################
# You might want to edit the following parameters:
# Define which storageIDs should be allowed to be enabled/disabled by this
# script. When the array is empty, it will allow all storages. If you only want
# to allow specific storages, add a new storageID by creating a new line like
# this below "incl_storids=()":
# incl_storids+=("MyStorageID")
declare -a incl_storids
incl_storids=()
#incl_storids+=("YourStorageID")
# Definde which storageIDs should not allowed to be enabled/disabled by this
# script. When the array is empty, it won't prevent enabling/disabling of any
# storages. If you want to exclude a storage from enabling/disabling add a new
# line like this below "excl_storids()":
# excl_storids+=("MyStorageID")
declare -a excl_storids
excl_storids=()
#excl_storids+=("YourStorageID")
# set the VMIDs here of the VMs that can't be run at the same time
declare -a vmids_sharing_device1
vmids_sharing_device1=()
#vmids_sharing_device1+=(YourVMID)
# where to store config files
conf_dir="/tmp"
# if VMs that got shutdown because they were part of a group sharing a device
# should be started again when the backup job ends
resume_vmids_sharing_device="false"
# how many seconds to wait between retries
retry_timeout=60
# how many seconds to wait for a VM to shutdown
shutdown_timeout=600
# how often to retry
retry_amount=3
# how many seconds to wait for pvesm commands to finish
check_interval=10
# how many seconds need to be passed since booting the server before backup jobs are allowed to run.
# might be useful in case you virtualize a PBS or NAS that needs to be started first after boot
# in order for the backup storage to get available
boot_delay=300
# End of Config
phase=$1
case "${phase}" in
job-init \
| job-start \
| job-end \
| job-abort)
# undef for Proxmox Backup Server storages
# undef in phase 'job-init' except when --dumpdir is used directly
dumpdir=$(printenv DUMPDIR)
# undef when --dumpdir is used directly
storeid=$(printenv STOREID)
case "${phase}" in
job-init)
# pause backup job if uptime is below boot_delay
# calculate uptime in seconds
uptimesec=$(($(date +%s)-$(date +%s --date="$(uptime -s)")))
while [ ${uptimesec} -lt ${boot_delay} ]; do
sleep 10
# calculate uptime in seconds
uptimesec=$(($(date +%s)-$(date +%s --date="$(uptime -s)")))
done
# remove files that store the last running VM of a group
if [ -f "${conf_dir}/vzdump_resume_vmid1" ]; then
rm "${conf_dir}/vzdump_resume_vmid1"
fi
# enable storage
if [ ! -z "${storeid}" ]; then
storid_allowed=0
if [ ${#incl_storids[@]} -gt 0 ]; then
for stid in "${incl_storids[@]}"; do
if [ "${stid}" = "${storeid}" ]; then
storid_allowed=1
break
fi
done
else
storid_allowed=1
fi
if [ ${#excl_storids[@]} -gt 0 ]; then
for stid in "${excl_storids[@]}"; do
if [ "${stid}" = "${storeid}" ]; then
storid_allowed=0
break
fi
done
fi
if [ ${storid_allowed} -eq 1 ]; then
storestatus=$(pvesm status --storage ${storeid} | grep -E "^${storeid}[[:space:]]" | tr -s ' ' | cut -d ' ' -f3)
if [ "${storestatus}" = "disabled" ]; then
# enable storage and wait for it to become active
retries=0
while [ ${retries} -lt ${retry_amount} ]; do
/usr/sbin/pvesm set "${storeid}" --disable 0
timeoutcounter=0
while [ ${timeoutcounter} -lt ${retry_timeout} ]; do
sleep ${check_interval}
timeoutcounter+=${check_interval}
storestatus=$(pvesm status --storage ${storeid} | grep -E "^${storeid}[[:space:]]" | tr -s ' ' | cut -d ' ' -f3)
if [ "${storestatus}" = "active" ]; then
echo "$(date '+%Y-%m-%d %H:%M:%S') - Storage '${storeid}' successfully enabled " >> /tmp/hook.log
break 2
fi
done
retries+=1
done
if [ ${retries} -ge ${retry_amount} ]; then
# fail because storage couldn't be successfully enabled
/usr/sbin/pvesm set "${storeid}" --disable 1
echo "$(date '+%Y-%m-%d %H:%M:%S') - Error: failed to enable storage '${storeid}'" >> /tmp/hook.log
exit 1
fi
fi
fi
fi
;;
job-end)
# disable storage
if [ ! -z "${storeid}" ]; then
storid_allowed=0
if [ ${#incl_storids[@]} -gt 0 ]; then
for stid in "${incl_storids[@]}"; do
if [ "${stid}" = "${storeid}" ]; then
storid_allowed=1
break
fi
done
else
storid_allowed=1
fi
if [ ${#excl_storids[@]} -gt 0 ]; then
for stid in "${excl_storids[@]}"; do
if [ "${stid}" = "${storeid}" ]; then
storid_allowed=0
break
fi
done
fi
if [ ${storid_allowed} -eq 1 ]; then
storestatus=$(pvesm status --storage ${storeid} | grep -E "^${storeid}[[:space:]]" | tr -s ' ' | cut -d ' ' -f3)
if [ "${storestatus}" != "disabled" ]; then
# disable storage and wait for it to become disabled
retries=0
while [ ${retries} -lt ${retry_amount} ]; do
/usr/sbin/pvesm set "${storeid}" --disable 1
timeoutcounter=0
while [ ${timeoutcounter} -lt ${retry_timeout} ]; do
sleep ${check_interval}
timeoutcounter+=${check_interval}
storestatus=$(pvesm status --storage ${storeid} | grep -E "^${storeid}[[:space:]]" | tr -s ' ' | cut -d ' ' -f3)
if [ "${storestatus}" = "disabled" ]; then
echo "$(date '+%Y-%m-%d %H:%M:%S') - Storage '${storeid}' successfully disabled " >> /tmp/hook.log
break 2
fi
done
retries+=1
done
if [ ${retries} -ge ${retry_amount} ]; then
# fail because storage couldn't be successfully disabled
echo "$(date '+%Y-%m-%d %H:%M:%S') - Error: failed to disable storage '${storeid}'" >> /tmp/hook.log
exit 1
fi
fi
fi
fi
# start VMs again that got shutdown for the backup
if [ "${resume_vmids_sharing_device}" = "true" ]; then
if [ -f "${conf_dir}/vzdump_resume_vmid1" ]; then
retries=0
start_vmid=$(<"${conf_dir}/vzdump_resume_vmid1")
# wait until VM is running
while [ ${retries} -lt ${retry_amount} ]; do
qm start ${start_vmid}
timeoutcounter=0
while [ ${timeoutcounter} -lt ${retry_timeout} ]; do
sleep ${check_interval}
timeoutcounter+=${check_interval}
vmstatus=$(qm status ${start_vmid} | grep status | sed 's/^status: \(.*\)/\1/')
if [ "${vmstatus}" = "running" ]; then
echo "$(date '+%Y-%m-%d %H:%M:%S') - VM with VMID ${start_vmid} successfully started again" >> /tmp/hook.log
break 2
fi
done
retries+=1
done
# remove file that store the last running VM of a group
rm "${conf_dir}/vzdump_resume_vmid1"
fi
fi
;;
esac
;;
backup-start \
| backup-end \
| backup-abort \
| log-end \
| pre-stop \
| pre-restart \
| post-restart)
mode=$2
vmid=$3
# shutdown VMs sharing the GPU before doing a backup
if [ "${phase}" = "backup-start" ]; then
if [ ${#vmids_sharing_device1[@]} -gt 0 ]; then
# find out position in the array
this_vmid_position=-1
for (( i=0; i<${#vmids_sharing_device1[@]}; i++ )); do
if [ "${vmids_sharing_device1[${i}]}" = "${vmid}" ]; then
this_vmid_position=${i}
break
fi
done
if [ ${this_vmid_position} -ge 0 ]; then
# find out which VMs are running
declare -a vmids_state
vmids_state=()
for (( i=0; i<${#vmids_sharing_device1[@]}; i++ )); do
# find out state of VM
vmids_state+=($(qm status ${vmids_sharing_device1[${i}]} | grep status | sed 's/^status: \(.*\)/\1/'))
done
# shutdown running VM
for (( i=0; i<${#vmids_state[@]}; i++ )); do
if [ "${vmids_state[${i}]}" = "running" ]; then
echo "$(date '+%Y-%m-%d %H:%M:%S') - Stutting down VM with VMID '${vmids_sharing_device1[${i}]}'" >> /tmp/hook.log
qm shutdown ${vmids_sharing_device1[${i}]} && qm wait ${vmids_sharing_device1[${i}]} -timeout ${shutdown_timeout}
if [ "${resume_vmids_sharing_device}" = "true" ]; then
echo "${vmids_sharing_device1[${i}]}" > "${conf_dir}/vzdump_resume_vmid1"
fi
fi
done
fi
fi
fi
;;
*)
echo "$(date '+%Y-%m-%d %H:%M:%S') - Error: Phase '${phase}' unknown" >> /tmp/hook.log
exit 1
;;
esac
exit 0
) I'm successfully using on 4 nodes for some months. But all my PVE nodes are unclustered, so might be problematic if you are running a cluster as I didn't cared about that. I started rewriting all that some weeks ago but then never finished it.
) i think that may be workable as well - thanks again!