fix: serialize concurrent tran session opens

2026-05-25 16:18:05 +00:00
parent 964cc7e984
commit fcc3ce125a
4 changed files with 120 additions and 4 deletions
@@ -13,8 +13,63 @@ if [ -n "${CODE_QUEUE_SERVICE_ROLE:-}" ] || [ -n "${CODE_QUEUE_INSTANCE_ID:-}" ]
  runner_env=1
 fi

-if [ "$runner_env" = 1 ] && [ -n "$host" ] && [ "${UNIDESK_TRAN_LOCAL:-}" != "1" ]; then
-  exec bun "$repo/scripts/cli.ts" --main-server-ip "$host" ssh "$@"
+tran_lock_scope() {
+  [ "$#" -ge 2 ] || return 1
+  case "${UNIDESK_TRAN_SESSION_LOCK:-1}" in
+    0|false|FALSE|no|NO|off|OFF) return 1 ;;
+  esac
+  route=$1
+  case "$route" in
+    ""|-*) return 1 ;;
+  esac
+  provider=${route%%:*}
+  [ -n "$provider" ] || return 1
+  plane=host
+  case "$route" in
+    *:k3s*) plane=k3s ;;
+  esac
+  printf '%s\n' "$provider-$plane"
+}
+
+tran_acquire_lock() {
+  scope=$1
+  lock_root=${UNIDESK_TRAN_LOCK_DIR:-/tmp/unidesk-tran-locks}
+  lock_name=$(printf '%s' "$scope" | tr -c 'A-Za-z0-9_.-' '_')
+  lock_path=$lock_root/$lock_name.lock
+  notice_seconds=${UNIDESK_TRAN_LOCK_NOTICE_SECONDS:-3}
+  warning_seconds=${UNIDESK_TRAN_LOCK_WARNING_SECONDS:-10}
+  timeout_seconds=${UNIDESK_TRAN_LOCK_TIMEOUT_SECONDS:-120}
+  mkdir -p "$lock_root"
+  started=$(date +%s)
+  noticed=0
+  warned=0
+  while ! mkdir "$lock_path" 2>/dev/null; do
+    now=$(date +%s)
+    waited=$((now - started))
+    if [ "$noticed" = 0 ] && [ "$waited" -ge "$notice_seconds" ]; then
+      printf 'tran provider session lock waiting scope=%s waited=%ss; serializing concurrent opens to avoid provider session allocation timeouts\n' "$scope" "$waited" >&2
+      noticed=1
+    fi
+    if [ "$warned" = 0 ] && [ "$waited" -ge "$warning_seconds" ]; then
+      printf 'tran provider session lock warning scope=%s waited=%ss; high-frequency distributed calls are queued behind another tran, consider batching reads or checking stuck sessions if this repeats\n' "$scope" "$waited" >&2
+      warned=1
+    fi
+    if [ "$waited" -ge "$timeout_seconds" ]; then
+      printf 'tran provider session lock timeout scope=%s waited=%ss lock=%s\n' "$scope" "$waited" "$lock_path" >&2
+      exit 255
+    fi
+    sleep 1
+  done
+  trap 'rmdir "$lock_path" 2>/dev/null || true' EXIT
+}
+
+if scope=$(tran_lock_scope "$@"); then
+  tran_acquire_lock "$scope"
 fi

-exec bun "$repo/scripts/cli.ts" ssh "$@"
+if [ "$runner_env" = 1 ] && [ -n "$host" ] && [ "${UNIDESK_TRAN_LOCAL:-}" != "1" ]; then
+  bun "$repo/scripts/cli.ts" --main-server-ip "$host" ssh "$@"
+  exit $?
+fi
+
+bun "$repo/scripts/cli.ts" ssh "$@"