mirror of
https://github.com/community-scripts/ProxmoxVE.git
synced 2026-07-11 00:22:13 +02:00
fix(telemetry): improve error reporting with structured error strings and better categorization
- Add build_error_string() that creates structured format:
'exit_code=N | description\n---\n<last 20 log lines>'
- Fix categorize_error() to map ALL known exit codes:
- Added: shell(1,2), proxmox(200-231), service(150-154),
database(170-193), runtime(243-249), signal(139,141,143)
- Split timeout from network (28 was in both)
- Added DPKG(255) to dependency category
- Update all API functions to use build_error_string():
post_update_to_api, post_update_to_api_extended,
post_tool_to_api, post_addon_to_api
- Add ensure_log_on_host() calls to on_exit, on_interrupt,
on_terminate handlers to prevent race condition where
telemetry reports before container log is pulled to host
This commit is contained in:
CanbiZ (MickLesk)
+73
-33
@@ -287,6 +287,32 @@ get_error_text() {
|
||||
fi
|
||||
}
|
||||
|
||||
# ------------------------------------------------------------------------------
|
||||
# build_error_string()
|
||||
#
|
||||
# - Builds a structured error string for telemetry reporting
|
||||
# - Format: "exit_code=<N> | <explanation>\n---\n<last 20 log lines>"
|
||||
# - If no log lines available, returns just the explanation
|
||||
# - Arguments:
|
||||
# * $1: exit_code (numeric)
|
||||
# * $2: log_text (optional, output from get_error_text)
|
||||
# - Returns structured error string via stdout
|
||||
# ------------------------------------------------------------------------------
|
||||
build_error_string() {
|
||||
local exit_code="${1:-1}"
|
||||
local log_text="${2:-}"
|
||||
local explanation
|
||||
explanation=$(explain_exit_code "$exit_code")
|
||||
|
||||
if [[ -n "$log_text" ]]; then
|
||||
# Structured format: header + separator + log lines
|
||||
printf 'exit_code=%s | %s\n---\n%s' "$exit_code" "$explanation" "$log_text"
|
||||
else
|
||||
# No log available - just the explanation with exit code
|
||||
printf 'exit_code=%s | %s' "$exit_code" "$explanation"
|
||||
fi
|
||||
}
|
||||
|
||||
# ==============================================================================
|
||||
# SECTION 2: TELEMETRY FUNCTIONS
|
||||
# ==============================================================================
|
||||
@@ -665,13 +691,12 @@ post_update_to_api() {
|
||||
else
|
||||
exit_code=1
|
||||
fi
|
||||
# Get log lines and build structured error string
|
||||
local error_text=""
|
||||
error_text=$(get_error_text)
|
||||
if [[ -n "$error_text" ]]; then
|
||||
error=$(json_escape "$error_text")
|
||||
else
|
||||
error=$(json_escape "$(explain_exit_code "$exit_code")")
|
||||
fi
|
||||
local full_error
|
||||
full_error=$(build_error_string "$exit_code" "$error_text")
|
||||
error=$(json_escape "$full_error")
|
||||
short_error=$(json_escape "$(explain_exit_code "$exit_code")")
|
||||
error_category=$(categorize_error "$exit_code")
|
||||
[[ -z "$error" ]] && error="Unknown error"
|
||||
@@ -814,31 +839,52 @@ EOF
|
||||
categorize_error() {
|
||||
local code="$1"
|
||||
case "$code" in
|
||||
# Network errors
|
||||
6 | 7 | 22 | 28 | 35) echo "network" ;;
|
||||
# Network errors (curl/wget)
|
||||
6 | 7 | 22 | 35) echo "network" ;;
|
||||
|
||||
# Storage errors
|
||||
214 | 217 | 219) echo "storage" ;;
|
||||
# Timeout errors
|
||||
28 | 124 | 211) echo "timeout" ;;
|
||||
|
||||
# Dependency/Package errors
|
||||
100 | 101 | 102 | 127 | 160 | 161 | 162) echo "dependency" ;;
|
||||
# Storage errors (Proxmox storage)
|
||||
214 | 217 | 219 | 224) echo "storage" ;;
|
||||
|
||||
# Dependency/Package errors (APT, DPKG, pip, commands)
|
||||
100 | 101 | 102 | 127 | 160 | 161 | 162 | 255) echo "dependency" ;;
|
||||
|
||||
# Permission errors
|
||||
126 | 152) echo "permission" ;;
|
||||
|
||||
# Timeout errors
|
||||
124 | 28 | 211) echo "timeout" ;;
|
||||
# Configuration errors (Proxmox config, invalid args)
|
||||
128 | 203 | 204 | 205 | 206 | 207 | 208) echo "config" ;;
|
||||
|
||||
# Configuration errors
|
||||
203 | 204 | 205 | 206 | 207 | 208) echo "config" ;;
|
||||
# Proxmox container/template errors
|
||||
200 | 209 | 210 | 212 | 213 | 215 | 216 | 218 | 220 | 221 | 222 | 223 | 225 | 231) echo "proxmox" ;;
|
||||
|
||||
# Service/Systemd errors
|
||||
150 | 151 | 153 | 154) echo "service" ;;
|
||||
|
||||
# Database errors (PostgreSQL, MySQL, MongoDB)
|
||||
170 | 171 | 172 | 173 | 180 | 181 | 182 | 183 | 190 | 191 | 192 | 193) echo "database" ;;
|
||||
|
||||
# Node.js / JavaScript runtime errors
|
||||
243 | 245 | 246 | 247 | 248 | 249) echo "runtime" ;;
|
||||
|
||||
# Python environment errors
|
||||
# (already covered: 160-162 under dependency)
|
||||
|
||||
# Aborted by user
|
||||
130) echo "aborted" ;;
|
||||
|
||||
# Resource errors (OOM, etc)
|
||||
137 | 134) echo "resource" ;;
|
||||
# Resource errors (OOM, SIGKILL, SIGABRT)
|
||||
134 | 137) echo "resource" ;;
|
||||
|
||||
# Default
|
||||
# Signal/Process errors (SIGTERM, SIGPIPE, SIGSEGV)
|
||||
139 | 141 | 143) echo "signal" ;;
|
||||
|
||||
# Shell errors (general error, syntax error)
|
||||
1 | 2) echo "shell" ;;
|
||||
|
||||
# Default - truly unknown
|
||||
*) echo "unknown" ;;
|
||||
esac
|
||||
}
|
||||
@@ -901,11 +947,9 @@ post_tool_to_api() {
|
||||
[[ ! "$exit_code" =~ ^[0-9]+$ ]] && exit_code=1
|
||||
local error_text=""
|
||||
error_text=$(get_error_text)
|
||||
if [[ -n "$error_text" ]]; then
|
||||
error=$(json_escape "$error_text")
|
||||
else
|
||||
error=$(json_escape "$(explain_exit_code "$exit_code")")
|
||||
fi
|
||||
local full_error
|
||||
full_error=$(build_error_string "$exit_code" "$error_text")
|
||||
error=$(json_escape "$full_error")
|
||||
error_category=$(categorize_error "$exit_code")
|
||||
fi
|
||||
|
||||
@@ -968,11 +1012,9 @@ post_addon_to_api() {
|
||||
[[ ! "$exit_code" =~ ^[0-9]+$ ]] && exit_code=1
|
||||
local error_text=""
|
||||
error_text=$(get_error_text)
|
||||
if [[ -n "$error_text" ]]; then
|
||||
error=$(json_escape "$error_text")
|
||||
else
|
||||
error=$(json_escape "$(explain_exit_code "$exit_code")")
|
||||
fi
|
||||
local full_error
|
||||
full_error=$(build_error_string "$exit_code" "$error_text")
|
||||
error=$(json_escape "$full_error")
|
||||
error_category=$(categorize_error "$exit_code")
|
||||
fi
|
||||
|
||||
@@ -1067,11 +1109,9 @@ post_update_to_api_extended() {
|
||||
fi
|
||||
local error_text=""
|
||||
error_text=$(get_error_text)
|
||||
if [[ -n "$error_text" ]]; then
|
||||
error=$(json_escape "$error_text")
|
||||
else
|
||||
error=$(json_escape "$(explain_exit_code "$exit_code")")
|
||||
fi
|
||||
local full_error
|
||||
full_error=$(build_error_string "$exit_code" "$error_text")
|
||||
error=$(json_escape "$full_error")
|
||||
error_category=$(categorize_error "$exit_code")
|
||||
[[ -z "$error" ]] && error="Unknown error"
|
||||
fi
|
||||
|
||||
@@ -254,6 +254,10 @@ on_exit() {
|
||||
# post_to_api was called ("installing" sent) but post_update_to_api was never called
|
||||
if [[ "${POST_TO_API_DONE:-}" == "true" && "${POST_UPDATE_DONE:-}" != "true" ]]; then
|
||||
if declare -f post_update_to_api >/dev/null 2>&1; then
|
||||
# Ensure log is accessible on host before reporting
|
||||
if declare -f ensure_log_on_host >/dev/null 2>&1; then
|
||||
ensure_log_on_host
|
||||
fi
|
||||
if [[ $exit_code -ne 0 ]]; then
|
||||
post_update_to_api "failed" "$exit_code"
|
||||
else
|
||||
@@ -273,6 +277,10 @@ on_exit() {
|
||||
# - Exits with code 130 (128 + SIGINT=2)
|
||||
# ------------------------------------------------------------------------------
|
||||
on_interrupt() {
|
||||
# Ensure log is accessible on host before reporting
|
||||
if declare -f ensure_log_on_host >/dev/null 2>&1; then
|
||||
ensure_log_on_host
|
||||
fi
|
||||
# Report interruption to telemetry API (prevents stuck "installing" records)
|
||||
if declare -f post_update_to_api >/dev/null 2>&1; then
|
||||
post_update_to_api "failed" "130"
|
||||
@@ -294,6 +302,10 @@ on_interrupt() {
|
||||
# - Triggered by external process termination
|
||||
# ------------------------------------------------------------------------------
|
||||
on_terminate() {
|
||||
# Ensure log is accessible on host before reporting
|
||||
if declare -f ensure_log_on_host >/dev/null 2>&1; then
|
||||
ensure_log_on_host
|
||||
fi
|
||||
# Report termination to telemetry API (prevents stuck "installing" records)
|
||||
if declare -f post_update_to_api >/dev/null 2>&1; then
|
||||
post_update_to_api "failed" "143"
|
||||
|
||||
Reference in New Issue
Block a user