core: Enhance signal handling, reported "status" and logs (#12216)
* Enhance telemetry, signal handling, and logs Improve failure telemetry and signal handling across the installer: add get_full_log() to collect/strip/truncate install logs and include them in API payloads with a truncated retry; add CONTAINER_INSTALLING flag around lxc-attach and stop containers on abort to avoid orphaned "installing/configuring" records; introduce _send_abort_telemetry() (curl fallback for container context) and _stop_container_if_installing() helpers; centralize and simplify EXIT/ERR/INT/TERM/HUP traps and handlers (including a new on_hangup handler) and update VM scripts to report numeric exit codes. Also ensure best-effort log collection is performed and tweak error categorization for certain signals. * Include full log in error telemetry Use get_full_log (up to 120KB) to populate the error telemetry field so the API receives the full installation trace; fall back to get_error_text (last ~20 lines) if the full log is empty. Removed collection and inclusion of a separate install_log field from the JSON payloads and simplified the retry payloads/comments accordingly. The change ensures error reports contain the complete trace while avoiding duplicate large log fields and keeps graceful failure handling (get_full_log || true). * Anonymize IP addresses in get_full_log Mask IPv4 addresses in logs when collecting full log output: added a sed step that replaces the last two octets with "x.x" to avoid exposing full IPs (GDPR). Also updated the comment to reflect anonymization; existing steps that strip carriage returns and ANSI escape sequences remain in place before truncating with head -c.
This commit is contained in:
CanbiZ (MickLesk)
committed by
GitHub
GitHub
parent
c1ec478269
commit
691cec80ab
@@ -350,6 +350,55 @@ get_error_text() {
|
||||
fi
|
||||
}
|
||||
|
||||
# ------------------------------------------------------------------------------
|
||||
# get_full_log()
|
||||
#
|
||||
# - Returns the FULL installation log (build + install combined)
|
||||
# - Calls ensure_log_on_host() to pull container log if needed
|
||||
# - Strips ANSI escape codes and carriage returns
|
||||
# - Truncates to max_bytes (default: 120KB) to stay within API limits
|
||||
# - Used for the error telemetry field (full trace instead of 20 lines)
|
||||
# ------------------------------------------------------------------------------
|
||||
get_full_log() {
|
||||
local max_bytes="${1:-122880}" # 120KB default
|
||||
local logfile=""
|
||||
|
||||
# Ensure logs are available on host (pulls from container if needed)
|
||||
if declare -f ensure_log_on_host >/dev/null 2>&1; then
|
||||
ensure_log_on_host
|
||||
fi
|
||||
|
||||
# Try combined log first (most complete)
|
||||
if [[ -n "${CTID:-}" && -n "${SESSION_ID:-}" ]]; then
|
||||
local combined_log="/tmp/${NSAPP:-lxc}-${CTID}-${SESSION_ID}.log"
|
||||
if [[ -s "$combined_log" ]]; then
|
||||
logfile="$combined_log"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Fall back to INSTALL_LOG
|
||||
if [[ -z "$logfile" || ! -s "$logfile" ]]; then
|
||||
if [[ -n "${INSTALL_LOG:-}" && -s "${INSTALL_LOG}" ]]; then
|
||||
logfile="$INSTALL_LOG"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Fall back to BUILD_LOG
|
||||
if [[ -z "$logfile" || ! -s "$logfile" ]]; then
|
||||
if [[ -n "${BUILD_LOG:-}" && -s "${BUILD_LOG}" ]]; then
|
||||
logfile="$BUILD_LOG"
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ -n "$logfile" && -s "$logfile" ]]; then
|
||||
# Strip ANSI codes, carriage returns, and anonymize IP addresses (GDPR)
|
||||
sed 's/\r$//' "$logfile" 2>/dev/null |
|
||||
sed 's/\x1b\[[0-9;]*[a-zA-Z]//g' |
|
||||
sed -E 's/([0-9]{1,3}\.)[0-9]{1,3}\.[0-9]{1,3}/\1x.x/g' |
|
||||
head -c "$max_bytes"
|
||||
fi
|
||||
}
|
||||
|
||||
# ------------------------------------------------------------------------------
|
||||
# build_error_string()
|
||||
#
|
||||
@@ -782,11 +831,15 @@ post_update_to_api() {
|
||||
else
|
||||
exit_code=1
|
||||
fi
|
||||
# Get log lines and build structured error string
|
||||
local error_text=""
|
||||
error_text=$(get_error_text)
|
||||
# Get full installation log for error field
|
||||
local log_text=""
|
||||
log_text=$(get_full_log 122880) || true # 120KB max
|
||||
if [[ -z "$log_text" ]]; then
|
||||
# Fallback to last 20 lines
|
||||
log_text=$(get_error_text)
|
||||
fi
|
||||
local full_error
|
||||
full_error=$(build_error_string "$exit_code" "$error_text")
|
||||
full_error=$(build_error_string "$exit_code" "$log_text")
|
||||
error=$(json_escape "$full_error")
|
||||
short_error=$(json_escape "$(explain_exit_code "$exit_code")")
|
||||
error_category=$(categorize_error "$exit_code")
|
||||
@@ -807,7 +860,7 @@ post_update_to_api() {
|
||||
|
||||
local http_code=""
|
||||
|
||||
# ── Attempt 1: Full payload with complete error text ──
|
||||
# ── Attempt 1: Full payload with complete error text (includes full log) ──
|
||||
local JSON_PAYLOAD
|
||||
JSON_PAYLOAD=$(
|
||||
cat <<EOF
|
||||
@@ -969,16 +1022,16 @@ categorize_error() {
|
||||
# Python environment errors
|
||||
# (already covered: 160-162 under dependency)
|
||||
|
||||
# Aborted by user
|
||||
130) echo "aborted" ;;
|
||||
# Aborted by user (SIGHUP=terminal closed, SIGINT=Ctrl+C, SIGTERM=killed)
|
||||
129 | 130 | 143) echo "user_aborted" ;;
|
||||
|
||||
# Resource errors (OOM, SIGKILL, SIGABRT)
|
||||
134 | 137) echo "resource" ;;
|
||||
|
||||
# Signal/Process errors (SIGTERM, SIGPIPE, SIGSEGV)
|
||||
139 | 141 | 143) echo "signal" ;;
|
||||
# Signal/Process errors (SIGPIPE, SIGSEGV)
|
||||
139 | 141) echo "signal" ;;
|
||||
|
||||
# Shell errors (general error, syntax error)
|
||||
# Shell errors (general error, syntax error)
|
||||
1 | 2) echo "shell" ;;
|
||||
|
||||
# Default - truly unknown
|
||||
|
||||
Reference in New Issue
Block a user