增强(08-23-isolated-backup-restore-drill): 固化八阶段RTO合同

scripts/qa/run-offhost-shadow-restore-runner-contract.sh

@@ -432,14 +432,17 @@ finish = re.search(r"\nfinish\(\) \{(?P<body>.*?)\n\}\ntrap finish", text, re.S)
 if not finish:
     raise SystemExit("finish function not found")
 body = finish.group("body")
+finalize_position = body.find("\n  if ! rto_finalize; then")
 emit_position = body.find("\n  emit_restore_diagnostics")
 cleanup_position = body.find("\n    cleanup_runtime ||")
+if finalize_position == -1:
+    raise SystemExit("RTO finalization missing")
 if emit_position == -1:
     raise SystemExit("diagnostic emission missing")
 if cleanup_position == -1:
     raise SystemExit("runtime cleanup call missing")
-if emit_position > cleanup_position:
-    raise SystemExit("diagnostics are emitted after cleanup")
+if not (finalize_position < emit_position < cleanup_position):
+    raise SystemExit("RTO/stage diagnostics are not finalized before cleanup")
 required = {
     'echo "dump_list=$DUMP_LIST_STATUS"',
     'echo "target_confirmation=$TARGET_CONFIRMATION_STATUS"',
@@ -452,14 +455,41 @@ required = {
     'echo "pg_restore_exit_code=$PG_RESTORE_EXIT_CODE"',
     'echo "pg_restore_error_count=$PG_RESTORE_ERROR_COUNT"',
     'echo "restore_error_category=$RESTORE_ERROR_CATEGORY"',
+    'echo "rto_batch_copy_seconds=$RTO_BATCH_COPY_SECONDS"',
+    'echo "rto_postgres_container_start_seconds=$RTO_POSTGRES_CONTAINER_START_SECONDS"',
+    'echo "rto_dump_list_seconds=$RTO_DUMP_LIST_SECONDS"',
+    'echo "rto_target_confirmation_seconds=$RTO_TARGET_CONFIRMATION_SECONDS"',
+    'echo "rto_restore_apply_seconds=$RTO_RESTORE_APPLY_SECONDS"',
+    'echo "rto_database_verify_seconds=$RTO_DATABASE_VERIFY_SECONDS"',
+    'echo "rto_storage_attachment_verify_seconds=$RTO_STORAGE_ATTACHMENT_VERIFY_SECONDS"',
+    'echo "rto_final_integrity_seconds=$RTO_FINAL_INTEGRITY_SECONDS"',
+    'echo "data_restore_rto_seconds=$RTO_SECONDS"',
 }
 missing = sorted(value for value in required if value not in text)
 if missing:
     raise SystemExit(f"diagnostic fields missing: {missing}")
 if 'RESTORE_ERROR_CATEGORY="RESTORE_APPLY_NONZERO"' not in text:
     raise SystemExit("non-zero apply classification missing")
+transitions = [
+    "rto_begin batch_copy",
+    "rto_transition batch_copy postgres_container_start",
+    "rto_transition postgres_container_start dump_list",
+    "rto_transition dump_list target_confirmation",
+    "rto_transition target_confirmation restore_apply",
+    "rto_transition restore_apply database_verify",
+    "rto_transition database_verify storage_attachment_verify",
+    "rto_transition storage_attachment_verify final_integrity",
+]
+positions = [text.find(value) for value in transitions]
+if any(position == -1 for position in positions) or positions != sorted(positions):
+    raise SystemExit("RTO stage transitions missing or out of order")
+target_call_position = text.find("if ! confirm_postgres_target; then")
+if not positions[3] < target_call_position < positions[4]:
+    raise SystemExit("TCP target confirmation is outside its RTO stage boundary")
+if text.count('echo "data_restore_rto_seconds=$RTO_SECONDS"') != 1:
+    raise SystemExit("data restore RTO must be emitted exactly once")
 PY
-pass "diagnostics precede finally-equivalent cleanup and use allowlisted fields"
+pass "eight-stage RTO and restore diagnostics precede cleanup with one vocabulary"
 
 cat >"$TEST_DIR/mock-target-docker" <<'MOCK_DOCKER'
 #!/usr/bin/env bash
@@ -738,6 +768,107 @@ CONTAINER_NAME=""
 sed -n '1,/^trap finish EXIT HUP INT TERM$/p' "$RUNNER" \
   | sed '$d' >"$TEST_DIR/runner-finalization-functions.sh"
 
+(
+  # shellcheck disable=SC1090
+  source "$TEST_DIR/runner-finalization-functions.sh"
+  RTO_TEST_NOW=100
+  rto_now() {
+    printf '%s\n' "$RTO_TEST_NOW"
+  }
+  rto_begin batch_copy
+  RTO_TEST_NOW=103
+  rto_transition batch_copy postgres_container_start
+  RTO_TEST_NOW=108
+  rto_transition postgres_container_start dump_list
+  RTO_TEST_NOW=110
+  rto_transition dump_list target_confirmation
+  RTO_TEST_NOW=121
+  rto_transition target_confirmation restore_apply
+  RTO_TEST_NOW=128
+  rto_transition restore_apply database_verify
+  RTO_TEST_NOW=141
+  rto_transition database_verify storage_attachment_verify
+  RTO_TEST_NOW=158
+  rto_transition storage_attachment_verify final_integrity
+  RTO_TEST_NOW=161
+  rto_finalize
+  emit_restore_diagnostics
+) >"$TEST_DIR/captured-rto-success" 2>&1
+for expected in \
+  'rto_batch_copy_seconds=3' \
+  'rto_postgres_container_start_seconds=5' \
+  'rto_dump_list_seconds=2' \
+  'rto_target_confirmation_seconds=11' \
+  'rto_restore_apply_seconds=7' \
+  'rto_database_verify_seconds=13' \
+  'rto_storage_attachment_verify_seconds=17' \
+  'rto_final_integrity_seconds=3' \
+  'data_restore_rto_seconds=61'; do
+  grep -Fxq "$expected" "$TEST_DIR/captured-rto-success" \
+    || fail "successful eight-stage RTO total or boundary mismatch"
+done
+[[ "$(grep -c '^data_restore_rto_seconds=' "$TEST_DIR/captured-rto-success")" -eq 1 ]] \
+  || fail "successful RTO total was not emitted exactly once"
+pass "rendered runner measures eight contiguous stages with an exact total"
+
+set +e
+(
+  # shellcheck disable=SC1090
+  source "$TEST_DIR/runner-finalization-functions.sh"
+  cleanup_runtime() {
+    echo "cleanup_marker=runtime"
+    return 0
+  }
+  cleanup_access() {
+    echo "cleanup_marker=access"
+    return 0
+  }
+  RTO_BATCH_COPY_SECONDS="2"
+  RTO_POSTGRES_CONTAINER_START_SECONDS="4"
+  RTO_DUMP_LIST_SECONDS="1"
+  RTO_ACTIVE_STAGE="target_confirmation"
+  RTO_STAGE_STARTED_EPOCH="200"
+  RTO_TEST_NOW=209
+  rto_now() {
+    printf '%s\n' "$RTO_TEST_NOW"
+  }
+  FAILURE_CATEGORY="restore_target_confirmation_failed"
+  DUMP_LIST_STATUS="PASS"
+  DUMP_LIST_EXIT_CODE="0"
+  TARGET_CONFIRMATION_STATUS="FAIL"
+  TARGET_CONFIRMATION_EXIT_CODE="1"
+  TARGET_CONFIRMATION_ATTEMPT_COUNT="60"
+  RESTORE_EXECUTION_PATH="DOCKER_STDIN"
+  RESTORE_ERROR_CATEGORY="TARGET_QUERY_NONZERO"
+  trap finish EXIT
+  exit 23
+) >"$TEST_DIR/captured-rto-target-failure" 2>&1
+rto_target_failure_exit="$?"
+set -e
+[[ "$rto_target_failure_exit" -eq 23 ]] \
+  || fail "target-confirmation timing failure did not preserve exit code"
+for expected in \
+  'rto_batch_copy_seconds=2' \
+  'rto_postgres_container_start_seconds=4' \
+  'rto_dump_list_seconds=1' \
+  'rto_target_confirmation_seconds=9' \
+  'rto_restore_apply_seconds=NOT_RUN' \
+  'rto_database_verify_seconds=NOT_RUN' \
+  'rto_storage_attachment_verify_seconds=NOT_RUN' \
+  'rto_final_integrity_seconds=NOT_RUN' \
+  'data_restore_rto_seconds=16'; do
+  grep -Fxq "$expected" "$TEST_DIR/captured-rto-target-failure" \
+    || fail "target-confirmation failure RTO boundary mismatch"
+done
+rto_line="$(grep -n '^rto_target_confirmation_seconds=9$' \
+  "$TEST_DIR/captured-rto-target-failure" | cut -d: -f1)"
+rto_cleanup_line="$(grep -n '^cleanup_marker=runtime$' \
+  "$TEST_DIR/captured-rto-target-failure" | cut -d: -f1)"
+[[ "$rto_line" =~ ^[0-9]+$ && "$rto_cleanup_line" =~ ^[0-9]+$ \
+  && "$rto_line" -lt "$rto_cleanup_line" ]] \
+  || fail "failed-stage RTO was not emitted before teardown"
+pass "target-confirmation failure preserves elapsed stages and later NOT_RUN before cleanup"
+
 capture_finalization_case() {
   local output_file="$1"
   local failure_category="$2"
@@ -805,7 +936,13 @@ grep -Fxq 'target_confirmation=NOT_RUN' \
   || fail "target stage ran after dump-list failure"
 grep -Fxq 'restore_apply=NOT_RUN' "$TEST_DIR/captured-dump-list-failure" \
   || fail "apply stage ran after dump-list failure"
-pass "dump-list failure keeps target and apply stages NOT_RUN"
+grep -Fxq 'rto_batch_copy_seconds=NOT_RUN' \
+  "$TEST_DIR/captured-dump-list-failure" \
+  || fail "pre-RTO failure unexpectedly reported a measured stage"
+grep -Fxq 'data_restore_rto_seconds=NOT_RUN' \
+  "$TEST_DIR/captured-dump-list-failure" \
+  || fail "pre-RTO failure unexpectedly reported a measured total"
+pass "pre-RTO failure keeps timing, target and apply fields NOT_RUN"
 
 capture_finalization_case \
   "$TEST_DIR/captured-target-failure" \
@@ -849,6 +986,16 @@ set +e
   PG_RESTORE_EXIT_CODE="23"
   PG_RESTORE_ERROR_COUNT="UNKNOWN"
   RESTORE_ERROR_CATEGORY="RESTORE_APPLY_NONZERO"
+  RTO_BATCH_COPY_SECONDS="2"
+  RTO_POSTGRES_CONTAINER_START_SECONDS="4"
+  RTO_DUMP_LIST_SECONDS="1"
+  RTO_TARGET_CONFIRMATION_SECONDS="9"
+  RTO_ACTIVE_STAGE="restore_apply"
+  RTO_STAGE_STARTED_EPOCH="300"
+  RTO_TEST_NOW=312
+  rto_now() {
+    printf '%s\n' "$RTO_TEST_NOW"
+  }
   trap finish EXIT
   exit 23
 ) >"$TEST_DIR/captured-finalization" 2>&1
@@ -869,7 +1016,13 @@ grep -Fxq 'temporary_access_cleanup=PASS' "$TEST_DIR/captured-finalization" \
   || fail "access teardown result was not retained"
 grep -Fxq 'pg_restore_exit_code=23' "$TEST_DIR/captured-finalization" \
   || fail "pg_restore exit code disappeared after teardown"
-pass "injected failure emits readable stages before finally-equivalent teardown"
+grep -Fxq 'rto_restore_apply_seconds=12' "$TEST_DIR/captured-finalization" \
+  || fail "restore-apply failure duration missing"
+grep -Fxq 'rto_database_verify_seconds=NOT_RUN' "$TEST_DIR/captured-finalization" \
+  || fail "database verification ran after restore-apply failure"
+grep -Fxq 'data_restore_rto_seconds=28' "$TEST_DIR/captured-finalization" \
+  || fail "restore-apply failure RTO total mismatch"
+pass "injected restore-apply failure preserves diagnostics and RTO before teardown"
 
 if grep -Eiq 'postgresql://|SELECT[[:space:]]|/tmp/|local_fixture_password' \
   "$TEST_DIR/captured-dump-list-failure" \