Start install timer and refine error reporting

Call start_install_timer during build startup and overhaul exit/error reporting.

Changes:
- Invoke start_install_timer early in misc/build.func to track install duration.
- Update api_exit_script comments to reference PocketBase/api.func and adjust ERR/SIGINT/SIGTERM traps to post numeric exit codes (use $? / 130 / 143) instead of command strings.
- Replace the previous explain_exit_code implementation with a conditional fallback: only define explain_exit_code if not already provided (api.func is the canonical source). Expanded and reorganized exit code mappings (curl, timeout, systemd, Node/Python/Postgres/MySQL/MongoDB, Proxmox, etc.).
- In error_handler: stop echoing the container log path (host shows combined log), and post a "failed" update to the API with the exit code before offering container cleanup.

Rationale: these changes make telemetry more consistent and robust (numeric codes), provide a safe fallback for exit descriptions when api.func isn't loaded, and ensure failures are reported to the API prior to any automatic cleanup.
This commit is contained in:
CanbiZ (MickLesk)
2026-02-12 11:21:40 +01:00
parent 29171d2e27
commit af83d3d428
2 changed files with 98 additions and 105 deletions

View File

@@ -4010,6 +4010,9 @@ EOF'
# Install SSH keys
install_ssh_keys_into_ct
# Start timer for duration tracking
start_install_timer
# Run application installer
# Disable error trap - container errors are handled internally via flag file
set +Eeuo pipefail # Disable ALL error handling temporarily
@@ -5123,9 +5126,9 @@ EOF
# api_exit_script()
#
# - Exit trap handler for reporting to API telemetry
# - Captures exit code and reports to API using centralized error descriptions
# - Uses explain_exit_code() from error_handler.func for consistent error messages
# - Posts failure status with exit code to API (error description added automatically)
# - Captures exit code and reports to PocketBase using centralized error descriptions
# - Uses explain_exit_code() from api.func for consistent error messages
# - Posts failure status with exit code to API (error description resolved automatically)
# - Only executes on non-zero exit codes
# ------------------------------------------------------------------------------
api_exit_script() {
@@ -5138,6 +5141,6 @@ api_exit_script() {
if command -v pveversion >/dev/null 2>&1; then
trap 'api_exit_script' EXIT
fi
trap 'post_update_to_api "failed" "$BASH_COMMAND"' ERR
trap 'post_update_to_api "failed" "INTERRUPTED"' SIGINT
trap 'post_update_to_api "failed" "TERMINATED"' SIGTERM
trap 'post_update_to_api "failed" "$?"' ERR
trap 'post_update_to_api "failed" "130"' SIGINT
trap 'post_update_to_api "failed" "143"' SIGTERM

View File

@@ -27,100 +27,90 @@
# ------------------------------------------------------------------------------
# explain_exit_code()
#
# - Maps numeric exit codes to human-readable error descriptions
# - Supports:
# * Generic/Shell errors (1, 2, 126, 127, 128, 130, 137, 139, 143)
# * Package manager errors (APT, DPKG: 100, 101, 255)
# * Node.js/npm errors (243-249, 254)
# * Python/pip/uv errors (210-212)
# * PostgreSQL errors (231-234)
# * MySQL/MariaDB errors (241-244)
# * MongoDB errors (251-254)
# * Proxmox custom codes (200-231)
# - Returns description string for given exit code
# - Canonical version is defined in api.func (sourced before this file)
# - This section only provides a fallback if api.func was not loaded
# - See api.func SECTION 1 for the authoritative exit code mappings
# ------------------------------------------------------------------------------
explain_exit_code() {
local code="$1"
case "$code" in
# --- Generic / Shell ---
1) echo "General error / Operation not permitted" ;;
2) echo "Misuse of shell builtins (e.g. syntax error)" ;;
126) echo "Command invoked cannot execute (permission problem?)" ;;
127) echo "Command not found" ;;
128) echo "Invalid argument to exit" ;;
130) echo "Terminated by Ctrl+C (SIGINT)" ;;
137) echo "Killed (SIGKILL / Out of memory?)" ;;
139) echo "Segmentation fault (core dumped)" ;;
143) echo "Terminated (SIGTERM)" ;;
# --- Package manager / APT / DPKG ---
100) echo "APT: Package manager error (broken packages / dependency problems)" ;;
101) echo "APT: Configuration error (bad sources.list, malformed config)" ;;
255) echo "DPKG: Fatal internal error" ;;
# --- Node.js / npm / pnpm / yarn ---
243) echo "Node.js: Out of memory (JavaScript heap out of memory)" ;;
245) echo "Node.js: Invalid command-line option" ;;
246) echo "Node.js: Internal JavaScript Parse Error" ;;
247) echo "Node.js: Fatal internal error" ;;
248) echo "Node.js: Invalid C++ addon / N-API failure" ;;
249) echo "Node.js: Inspector error" ;;
254) echo "npm/pnpm/yarn: Unknown fatal error" ;;
# --- Python / pip / uv ---
210) echo "Python: Virtualenv / uv environment missing or broken" ;;
211) echo "Python: Dependency resolution failed" ;;
212) echo "Python: Installation aborted (permissions or EXTERNALLY-MANAGED)" ;;
# --- PostgreSQL ---
231) echo "PostgreSQL: Connection failed (server not running / wrong socket)" ;;
232) echo "PostgreSQL: Authentication failed (bad user/password)" ;;
233) echo "PostgreSQL: Database does not exist" ;;
234) echo "PostgreSQL: Fatal error in query / syntax" ;;
# --- MySQL / MariaDB ---
241) echo "MySQL/MariaDB: Connection failed (server not running / wrong socket)" ;;
242) echo "MySQL/MariaDB: Authentication failed (bad user/password)" ;;
243) echo "MySQL/MariaDB: Database does not exist" ;;
244) echo "MySQL/MariaDB: Fatal error in query / syntax" ;;
# --- MongoDB ---
251) echo "MongoDB: Connection failed (server not running)" ;;
252) echo "MongoDB: Authentication failed (bad user/password)" ;;
253) echo "MongoDB: Database not found" ;;
254) echo "MongoDB: Fatal query error" ;;
# --- Proxmox Custom Codes ---
200) echo "Proxmox: Failed to create lock file" ;;
203) echo "Proxmox: Missing CTID variable" ;;
204) echo "Proxmox: Missing PCT_OSTYPE variable" ;;
205) echo "Proxmox: Invalid CTID (<100)" ;;
206) echo "Proxmox: CTID already in use" ;;
207) echo "Proxmox: Password contains unescaped special characters" ;;
208) echo "Proxmox: Invalid configuration (DNS/MAC/Network format)" ;;
209) echo "Proxmox: Container creation failed" ;;
210) echo "Proxmox: Cluster not quorate" ;;
211) echo "Proxmox: Timeout waiting for template lock" ;;
212) echo "Proxmox: Storage type 'iscsidirect' does not support containers (VMs only)" ;;
213) echo "Proxmox: Storage type does not support 'rootdir' content" ;;
214) echo "Proxmox: Not enough storage space" ;;
215) echo "Proxmox: Container created but not listed (ghost state)" ;;
216) echo "Proxmox: RootFS entry missing in config" ;;
217) echo "Proxmox: Storage not accessible" ;;
219) echo "Proxmox: CephFS does not support containers - use RBD" ;;
224) echo "Proxmox: PBS storage is for backups only" ;;
218) echo "Proxmox: Template file corrupted or incomplete" ;;
220) echo "Proxmox: Unable to resolve template path" ;;
221) echo "Proxmox: Template file not readable" ;;
222) echo "Proxmox: Template download failed" ;;
223) echo "Proxmox: Template not available after download" ;;
225) echo "Proxmox: No template available for OS/Version" ;;
231) echo "Proxmox: LXC stack upgrade failed" ;;
# --- Default ---
*) echo "Unknown error" ;;
esac
}
if ! declare -f explain_exit_code &>/dev/null; then
explain_exit_code() {
local code="$1"
case "$code" in
1) echo "General error / Operation not permitted" ;;
2) echo "Misuse of shell builtins (e.g. syntax error)" ;;
6) echo "curl: DNS resolution failed (could not resolve host)" ;;
7) echo "curl: Failed to connect (network unreachable / host down)" ;;
22) echo "curl: HTTP error returned (404, 429, 500+)" ;;
28) echo "curl: Operation timeout (network slow or server not responding)" ;;
35) echo "curl: SSL/TLS handshake failed (certificate error)" ;;
100) echo "APT: Package manager error (broken packages / dependency problems)" ;;
101) echo "APT: Configuration error (bad sources.list, malformed config)" ;;
102) echo "APT: Lock held by another process (dpkg/apt still running)" ;;
124) echo "Command timed out (timeout command)" ;;
126) echo "Command invoked cannot execute (permission problem?)" ;;
127) echo "Command not found" ;;
128) echo "Invalid argument to exit" ;;
130) echo "Terminated by Ctrl+C (SIGINT)" ;;
134) echo "Process aborted (SIGABRT - possibly Node.js heap overflow)" ;;
137) echo "Killed (SIGKILL / Out of memory?)" ;;
139) echo "Segmentation fault (core dumped)" ;;
141) echo "Broken pipe (SIGPIPE - output closed prematurely)" ;;
143) echo "Terminated (SIGTERM)" ;;
150) echo "Systemd: Service failed to start" ;;
151) echo "Systemd: Service unit not found" ;;
152) echo "Permission denied (EACCES)" ;;
153) echo "Build/compile failed (make/gcc/cmake)" ;;
154) echo "Node.js: Native addon build failed (node-gyp)" ;;
160) echo "Python: Virtualenv / uv environment missing or broken" ;;
161) echo "Python: Dependency resolution failed" ;;
162) echo "Python: Installation aborted (permissions or EXTERNALLY-MANAGED)" ;;
170) echo "PostgreSQL: Connection failed (server not running / wrong socket)" ;;
171) echo "PostgreSQL: Authentication failed (bad user/password)" ;;
172) echo "PostgreSQL: Database does not exist" ;;
173) echo "PostgreSQL: Fatal error in query / syntax" ;;
180) echo "MySQL/MariaDB: Connection failed (server not running / wrong socket)" ;;
181) echo "MySQL/MariaDB: Authentication failed (bad user/password)" ;;
182) echo "MySQL/MariaDB: Database does not exist" ;;
183) echo "MySQL/MariaDB: Fatal error in query / syntax" ;;
190) echo "MongoDB: Connection failed (server not running)" ;;
191) echo "MongoDB: Authentication failed (bad user/password)" ;;
192) echo "MongoDB: Database not found" ;;
193) echo "MongoDB: Fatal query error" ;;
200) echo "Proxmox: Failed to create lock file" ;;
203) echo "Proxmox: Missing CTID variable" ;;
204) echo "Proxmox: Missing PCT_OSTYPE variable" ;;
205) echo "Proxmox: Invalid CTID (<100)" ;;
206) echo "Proxmox: CTID already in use" ;;
207) echo "Proxmox: Password contains unescaped special characters" ;;
208) echo "Proxmox: Invalid configuration (DNS/MAC/Network format)" ;;
209) echo "Proxmox: Container creation failed" ;;
210) echo "Proxmox: Cluster not quorate" ;;
211) echo "Proxmox: Timeout waiting for template lock" ;;
212) echo "Proxmox: Storage type 'iscsidirect' does not support containers (VMs only)" ;;
213) echo "Proxmox: Storage type does not support 'rootdir' content" ;;
214) echo "Proxmox: Not enough storage space" ;;
215) echo "Proxmox: Container created but not listed (ghost state)" ;;
216) echo "Proxmox: RootFS entry missing in config" ;;
217) echo "Proxmox: Storage not accessible" ;;
218) echo "Proxmox: Template file corrupted or incomplete" ;;
219) echo "Proxmox: CephFS does not support containers - use RBD" ;;
220) echo "Proxmox: Unable to resolve template path" ;;
221) echo "Proxmox: Template file not readable" ;;
222) echo "Proxmox: Template download failed" ;;
223) echo "Proxmox: Template not available after download" ;;
224) echo "Proxmox: PBS storage is for backups only" ;;
225) echo "Proxmox: No template available for OS/Version" ;;
231) echo "Proxmox: LXC stack upgrade failed" ;;
243) echo "Node.js: Out of memory (JavaScript heap out of memory)" ;;
245) echo "Node.js: Invalid command-line option" ;;
246) echo "Node.js: Internal JavaScript Parse Error" ;;
247) echo "Node.js: Fatal internal error" ;;
248) echo "Node.js: Invalid C++ addon / N-API failure" ;;
249) echo "npm/pnpm/yarn: Unknown fatal error" ;;
255) echo "DPKG: Fatal internal error" ;;
*) echo "Unknown error" ;;
esac
}
fi
# ==============================================================================
# SECTION 2: ERROR HANDLERS
@@ -197,12 +187,7 @@ error_handler() {
# Create error flag file with exit code for host detection
echo "$exit_code" >"/root/.install-${SESSION_ID:-error}.failed" 2>/dev/null || true
if declare -f msg_custom >/dev/null 2>&1; then
msg_custom "📋" "${YW}" "Log saved to: ${container_log}"
else
echo -e "${YW}Log saved to:${CL} ${BL}${container_log}${CL}"
fi
# Log path is shown by host as combined log - no need to show container path
else
# HOST CONTEXT: Show local log path and offer container cleanup
if declare -f msg_custom >/dev/null 2>&1; then
@@ -213,6 +198,11 @@ error_handler() {
# Offer to remove container if it exists (build errors after container creation)
if [[ -n "${CTID:-}" ]] && command -v pct &>/dev/null && pct status "$CTID" &>/dev/null; then
# Report failure to API before container cleanup
if declare -f post_update_to_api &>/dev/null; then
post_update_to_api "failed" "$exit_code"
fi
echo ""
echo -en "${YW}Remove broken container ${CTID}? (Y/n) [auto-remove in 60s]: ${CL}"