community-scripts/ProxmoxVE
1
0
Fork 0
mirror of https://github.com/community-scripts/ProxmoxVE.git synced 2026-03-03 17:35:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add timeouts and prioritize telemetry on exit

Browse Source 
Prevent hangs when pulling logs from containers by wrapping pct pull calls with timeout (8s) and running ensure_log_on_host under timeout (10s). Always send telemetry (post_update_to_api) before attempting best-effort log collection so status is reported even if log retrieval blocks. Update EXIT/ERR/SIGHUP/SIGINT/SIGTERM traps and consolidate error/interrupt handlers to use the new timeouted log collection. Changes in misc/build.func and misc/error_handler.func.
This commit is contained in:
CanbiZ (MickLesk)
2026-02-18 13:14:59 +01:00
parent 845b89f975
commit 6cc8877852
2 changed files with 30 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
misc/error_handler.func
View File

@@ -339,24 +339,17 @@ 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
if [[ $exit_code -gt 128 ]]; then
# Signal exit: send telemetry IMMEDIATELY (container may be dying, pct pull could hang)
# ALWAYS send telemetry FIRST - ensure status is reported even if
# ensure_log_on_host hangs (e.g. pct pull on dead/unresponsive container)
if [[ $exit_code -ne 0 ]]; then
post_update_to_api "failed" "$exit_code" 2>/dev/null || true
# Then try log collection (non-critical, best-effort)
if declare -f ensure_log_on_host >/dev/null 2>&1; then
ensure_log_on_host 2>/dev/null || true
fi
else
# Normal exit: collect logs first for better error details
if declare -f ensure_log_on_host >/dev/null 2>&1; then
ensure_log_on_host 2>/dev/null || true
fi
if [[ $exit_code -ne 0 ]]; then
post_update_to_api "failed" "$exit_code"
else
# exit_code=0 is never an error — report as success
post_update_to_api "done" "0"
fi
# exit_code=0 is never an error — report as success
post_update_to_api "done" "0" 2>/dev/null || true
fi
# Best-effort log collection with timeout (non-critical after telemetry is sent)
if declare -f ensure_log_on_host >/dev/null 2>&1; then
timeout 10 bash -c 'ensure_log_on_host' 2>/dev/null || true
fi
fi
fi
@@ -380,9 +373,9 @@ on_interrupt() {
if declare -f post_update_to_api >/dev/null 2>&1; then
post_update_to_api "failed" "130" 2>/dev/null || true
fi
# Best-effort log collection (non-critical after telemetry is sent)
# Best-effort log collection with timeout (non-critical after telemetry is sent)
if declare -f ensure_log_on_host >/dev/null 2>&1; then
ensure_log_on_host 2>/dev/null || true
timeout 10 bash -c 'ensure_log_on_host' 2>/dev/null || true
fi
if declare -f msg_error >/dev/null 2>&1; then
msg_error "Interrupted by user (SIGINT)" 2>/dev/null || true
@@ -409,9 +402,9 @@ on_terminate() {
if declare -f post_update_to_api >/dev/null 2>&1; then
post_update_to_api "failed" "143" 2>/dev/null || true
fi
# Best-effort log collection (non-critical after telemetry is sent)
# Best-effort log collection with timeout (non-critical after telemetry is sent)
if declare -f ensure_log_on_host >/dev/null 2>&1; then
ensure_log_on_host 2>/dev/null || true
timeout 10 bash -c 'ensure_log_on_host' 2>/dev/null || true
fi
if declare -f msg_error >/dev/null 2>&1; then
msg_error "Terminated by signal (SIGTERM)" 2>/dev/null || true