mirror of
https://github.com/community-scripts/ProxmoxVE.git
synced 2026-07-14 01:45:08 +02:00
feat(build.func): smart error recovery menu for failed installations
Replace simple Y/n removal prompt with interactive recovery menu: - Option 1: Remove container and exit (default, auto after 60s timeout) - Option 2: Keep container for debugging - Option 3: Retry installation with verbose mode enabled - Option 4: Retry with 1.5x RAM and +1 CPU core (OOM errors only) Improvements: - Detect OOM errors (exit codes 137, 243) and offer resource increase - Show human-readable error explanation using explain_exit_code() - Recursive rebuild preserves ALL settings from advanced/app.vars/default.vars - Settings preserved: Network (IP, Gateway, VLAN, MTU, Bridge), Features (Nesting, FUSE, TUN, GPU), Storage, SSH keys, Tags, Hostname, etc. - Show rebuild summary before retry (old→new CTID, resources, network) - New container ID generated automatically for rebuilds This helps users recover from transient failures without re-running the entire script manually.
This commit is contained in:
MickLesk
+118
-21
@@ -3970,30 +3970,127 @@ EOF'
|
||||
|
||||
# Prompt user for cleanup with 60s timeout (plain echo - no msg_info to avoid spinner)
|
||||
echo ""
|
||||
echo -en "${YW}Remove broken container ${CTID}? (Y/n) [auto-remove in 60s]: ${CL}"
|
||||
|
||||
# Detect error type for smart recovery options
|
||||
local is_oom=false
|
||||
local error_explanation=""
|
||||
if declare -f explain_exit_code >/dev/null 2>&1; then
|
||||
error_explanation="$(explain_exit_code "$install_exit_code")"
|
||||
fi
|
||||
|
||||
# OOM detection: exit codes 137 (SIGKILL/OOM) and 243 (Node.js heap)
|
||||
if [[ $install_exit_code -eq 137 || $install_exit_code -eq 243 ]]; then
|
||||
is_oom=true
|
||||
fi
|
||||
|
||||
# Show error explanation if available
|
||||
if [[ -n "$error_explanation" ]]; then
|
||||
echo -e "${TAB}${RD}Error: ${error_explanation}${CL}"
|
||||
echo ""
|
||||
fi
|
||||
|
||||
# Build recovery menu based on error type
|
||||
echo -e "${YW}What would you like to do?${CL}"
|
||||
echo ""
|
||||
echo -e " ${GN}1)${CL} Remove container and exit"
|
||||
echo -e " ${GN}2)${CL} Keep container for debugging"
|
||||
echo -e " ${GN}3)${CL} Retry with verbose mode"
|
||||
if [[ "$is_oom" == true ]]; then
|
||||
local new_ram=$((RAM_SIZE * 3 / 2))
|
||||
local new_cpu=$((CORE_COUNT + 1))
|
||||
echo -e " ${GN}4)${CL} Retry with more resources (RAM: ${RAM_SIZE}→${new_ram} MiB, CPU: ${CORE_COUNT}→${new_cpu} cores)"
|
||||
fi
|
||||
echo ""
|
||||
echo -en "${YW}Select option [1-$([[ "$is_oom" == true ]] && echo "4" || echo "3")] (default: 1, auto-remove in 60s): ${CL}"
|
||||
|
||||
if read -t 60 -r response; then
|
||||
if [[ -z "$response" || "$response" =~ ^[Yy]$ ]]; then
|
||||
# Remove container
|
||||
echo -e "\n${TAB}${HOLD}${YW}Removing container ${CTID}${CL}"
|
||||
pct stop "$CTID" &>/dev/null || true
|
||||
pct destroy "$CTID" &>/dev/null || true
|
||||
echo -e "${BFR}${CM}${GN}Container ${CTID} removed${CL}"
|
||||
elif [[ "$response" =~ ^[Nn]$ ]]; then
|
||||
echo -e "\n${TAB}${YW}Container ${CTID} kept for debugging${CL}"
|
||||
|
||||
# Dev mode: Setup MOTD/SSH for debugging access to broken container
|
||||
if [[ "${DEV_MODE_MOTD:-false}" == "true" ]]; then
|
||||
echo -e "${TAB}${HOLD}${DGN}Setting up MOTD and SSH for debugging...${CL}"
|
||||
if pct exec "$CTID" -- bash -c "
|
||||
source <(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVE/main/misc/install.func)
|
||||
declare -f motd_ssh >/dev/null 2>&1 && motd_ssh || true
|
||||
" >/dev/null 2>&1; then
|
||||
local ct_ip=$(pct exec "$CTID" ip a s dev eth0 2>/dev/null | awk '/inet / {print $2}' | cut -d/ -f1)
|
||||
echo -e "${BFR}${CM}${GN}MOTD/SSH ready - SSH into container: ssh root@${ct_ip}${CL}"
|
||||
case "${response:-1}" in
|
||||
1)
|
||||
# Remove container
|
||||
echo -e "\n${TAB}${HOLD}${YW}Removing container ${CTID}${CL}"
|
||||
pct stop "$CTID" &>/dev/null || true
|
||||
pct destroy "$CTID" &>/dev/null || true
|
||||
echo -e "${BFR}${CM}${GN}Container ${CTID} removed${CL}"
|
||||
;;
|
||||
2)
|
||||
echo -e "\n${TAB}${YW}Container ${CTID} kept for debugging${CL}"
|
||||
# Dev mode: Setup MOTD/SSH for debugging access to broken container
|
||||
if [[ "${DEV_MODE_MOTD:-false}" == "true" ]]; then
|
||||
echo -e "${TAB}${HOLD}${DGN}Setting up MOTD and SSH for debugging...${CL}"
|
||||
if pct exec "$CTID" -- bash -c "
|
||||
source <(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVE/main/misc/install.func)
|
||||
declare -f motd_ssh >/dev/null 2>&1 && motd_ssh || true
|
||||
" >/dev/null 2>&1; then
|
||||
local ct_ip=$(pct exec "$CTID" ip a s dev eth0 2>/dev/null | awk '/inet / {print $2}' | cut -d/ -f1)
|
||||
echo -e "${BFR}${CM}${GN}MOTD/SSH ready - SSH into container: ssh root@${ct_ip}${CL}"
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
exit $install_exit_code
|
||||
;;
|
||||
3)
|
||||
# Retry with verbose mode
|
||||
echo -e "\n${TAB}${HOLD}${YW}Removing container ${CTID} for rebuild...${CL}"
|
||||
pct stop "$CTID" &>/dev/null || true
|
||||
pct destroy "$CTID" &>/dev/null || true
|
||||
echo -e "${BFR}${CM}${GN}Container ${CTID} removed${CL}"
|
||||
echo ""
|
||||
# Get new container ID
|
||||
local old_ctid="$CTID"
|
||||
export CTID=$(get_valid_container_id "$CTID")
|
||||
export VERBOSE="yes"
|
||||
export var_verbose="yes"
|
||||
|
||||
# Show rebuild summary
|
||||
echo -e "${YW}Rebuilding with preserved settings:${CL}"
|
||||
echo -e " Container ID: ${old_ctid} → ${CTID}"
|
||||
echo -e " RAM: ${RAM_SIZE} MiB | CPU: ${CORE_COUNT} cores | Disk: ${DISK_SIZE} GB"
|
||||
echo -e " Network: ${NET:-dhcp} | Bridge: ${BRG:-vmbr0}"
|
||||
echo -e " Verbose: ${GN}enabled${CL}"
|
||||
echo ""
|
||||
msg_info "Restarting installation..."
|
||||
# Re-run build_container
|
||||
build_container
|
||||
return $?
|
||||
;;
|
||||
4)
|
||||
if [[ "$is_oom" == true ]]; then
|
||||
# Retry with more resources
|
||||
echo -e "\n${TAB}${HOLD}${YW}Removing container ${CTID} for rebuild with more resources...${CL}"
|
||||
pct stop "$CTID" &>/dev/null || true
|
||||
pct destroy "$CTID" &>/dev/null || true
|
||||
echo -e "${BFR}${CM}${GN}Container ${CTID} removed${CL}"
|
||||
echo ""
|
||||
# Get new container ID and increase resources
|
||||
local old_ctid="$CTID"
|
||||
local old_ram="$RAM_SIZE"
|
||||
local old_cpu="$CORE_COUNT"
|
||||
export CTID=$(get_valid_container_id "$CTID")
|
||||
export RAM_SIZE=$((RAM_SIZE * 3 / 2))
|
||||
export CORE_COUNT=$((CORE_COUNT + 1))
|
||||
export var_ram="$RAM_SIZE"
|
||||
export var_cpu="$CORE_COUNT"
|
||||
|
||||
# Show rebuild summary
|
||||
echo -e "${YW}Rebuilding with increased resources:${CL}"
|
||||
echo -e " Container ID: ${old_ctid} → ${CTID}"
|
||||
echo -e " RAM: ${old_ram} → ${GN}${RAM_SIZE}${CL} MiB (+50%)"
|
||||
echo -e " CPU: ${old_cpu} → ${GN}${CORE_COUNT}${CL} cores (+1)"
|
||||
echo -e " Disk: ${DISK_SIZE} GB | Network: ${NET:-dhcp} | Bridge: ${BRG:-vmbr0}"
|
||||
echo ""
|
||||
msg_info "Restarting installation..."
|
||||
# Re-run build_container
|
||||
build_container
|
||||
return $?
|
||||
else
|
||||
echo -e "\n${TAB}${YW}Invalid option. Container ${CTID} kept.${CL}"
|
||||
exit $install_exit_code
|
||||
fi
|
||||
;;
|
||||
*)
|
||||
echo -e "\n${TAB}${YW}Invalid option. Container ${CTID} kept.${CL}"
|
||||
exit $install_exit_code
|
||||
;;
|
||||
esac
|
||||
else
|
||||
# Timeout - auto-remove
|
||||
echo -e "\n${YW}No response - auto-removing container${CL}"
|
||||
|
||||
Reference in New Issue
Block a user