fix(backup): make Host110 runtime receipt durable

This commit is contained in:
Your Name
2026-07-18 23:37:52 +08:00
parent 0b9c028400
commit 8f11ef3362
3 changed files with 767 additions and 44 deletions

View File

@@ -44,13 +44,19 @@ EXECUTOR_DIGEST=""
VERIFIER_DIGEST=""
STAGE_DIR=""
ROLLBACK_DIR=""
RECEIPT_PATH=""
APPLY_STARTED=0
APPLY_COMPLETE=0
ROLLBACK_ATTEMPTED=0
ROLLBACK_PERFORMED=0
ROLLBACK_VERIFIED=0
RUN_TEMP_RESIDUE_VERIFIED=0
FAULT_INJECTION_ENABLED=0
declare -A FILE_EXISTED=()
declare -A PREVIOUS_DIGEST=()
declare -A PREVIOUS_METADATA=()
declare -A EXPECTED_DIGEST=()
declare -A RUN_OWNED_TEMP_PATHS=()
usage() {
printf '%s\n' \
@@ -96,6 +102,11 @@ case "$MODE" in check|apply|verify) ;; *) fail "invalid_mode" ;; esac
[[ "$RUN_ID" =~ ^[A-Za-z0-9][A-Za-z0-9._-]{0,95}$ ]] || fail "invalid_run_id"
expected_source_stage="/tmp/agent99-host110-backup-runtime-${RUN_ID}"
[ "$SOURCE_STAGE" = "$expected_source_stage" ] || fail "invalid_source_stage"
RECEIPT_PATH="$STATUS_ROOT/agent99-backup-runtime-deploy-${RUN_ID}.json"
if [ "${HOST110_BACKUP_RUNTIME_ENABLE_TEST_FAULTS:-}" = "1" ] \
&& [ "$DEST_ROOT" != "/backup/scripts" ]; then
FAULT_INJECTION_ENABLED=1
fi
for command_name in awk bash cp dirname flock grep hostname id install mv pgrep python3 readlink rm sha256sum stat timeout tr; do
command -v "$command_name" >/dev/null 2>&1 || fail "required_command_missing_${command_name}"
@@ -174,10 +185,10 @@ working_digest() {
|| fail "verifier_identity_failed"
validate_file() {
local path="$1"
case "$path" in
*.sh) bash -n "$path" ;;
*.py) python3 -c 'import ast, pathlib, sys; ast.parse(pathlib.Path(sys.argv[1]).read_text(encoding="utf-8"))' "$path" ;;
local validation_path="$1"
case "$validation_path" in
*.sh) bash -n "$validation_path" ;;
*.py) python3 -c 'import ast, pathlib, sys; ast.parse(pathlib.Path(sys.argv[1]).read_text(encoding="utf-8"))' "$validation_path" ;;
*) return 64 ;;
esac
}
@@ -222,12 +233,75 @@ verify_destination() {
done
}
fsync_paths_and_parents() {
python3 - "$@" <<'PY'
import os
import stat
import sys
from pathlib import Path
parents = set()
for raw_path in sys.argv[1:]:
path = Path(raw_path)
parents.add(path.parent)
if not os.path.lexists(path):
continue
if path.is_symlink() or not path.is_file():
raise SystemExit(76)
flags = os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0)
descriptor = os.open(path, flags)
try:
if not stat.S_ISREG(os.fstat(descriptor).st_mode):
raise SystemExit(76)
os.fsync(descriptor)
finally:
os.close(descriptor)
for parent in sorted(parents, key=str):
if parent.is_symlink() or not parent.is_dir():
raise SystemExit(76)
flags = os.O_RDONLY | getattr(os, "O_DIRECTORY", 0) | getattr(os, "O_NOFOLLOW", 0)
descriptor = os.open(parent, flags)
try:
os.fsync(descriptor)
finally:
os.close(descriptor)
PY
}
fsync_destination_state() {
local name dest_path
local -a fsync_targets=()
for name in "${PAYLOAD_FILES[@]}"; do
dest_path="$(destination_path "$name")"
fsync_targets+=("$dest_path")
done
fsync_paths_and_parents "${fsync_targets[@]}"
}
fsync_rollback_prestate() {
local name
local -a fsync_targets=("$ROLLBACK_DIR/prestate.tsv")
for name in "${PAYLOAD_FILES[@]}"; do
if [ "${FILE_EXISTED[$name]:-}" = "1" ]; then
fsync_targets+=("$ROLLBACK_DIR/$name")
fi
done
fsync_paths_and_parents "${fsync_targets[@]}"
}
write_receipt() {
local status="$1"
local rollback_verified="$2"
local receipt_path="$STATUS_ROOT/agent99-backup-runtime-deploy-${RUN_ID}.json"
install -d -m 700 "$STATUS_ROOT"
python3 - "$receipt_path" "$status" "$SOURCE_REVISION" "$SOURCE_HEAD" "$RUN_ID" "$rollback_verified" "$VERIFIER_DIGEST" <<'PY'
local receipt_status="$1"
local rollback_attempted="$2"
local rollback_performed="$3"
local rollback_verified="$4"
local zero_residue_verified="$5"
install -d -m 700 "$STATUS_ROOT" || return 1
[ -d "$STATUS_ROOT" ] && [ ! -L "$STATUS_ROOT" ] || return 1
[ "$(stat -c '%U:%G:%a' "$STATUS_ROOT")" = "wooo:wooo:700" ] || return 1
if ! python3 - "$RECEIPT_PATH" "$receipt_status" "$SOURCE_REVISION" "$SOURCE_HEAD" "$RUN_ID" \
"$rollback_attempted" "$rollback_performed" "$rollback_verified" \
"$zero_residue_verified" "$VERIFIER_DIGEST" "$FAULT_INJECTION_ENABLED" <<'PY'
import hashlib
import json
import os
import sys
@@ -235,64 +309,176 @@ import time
from pathlib import Path
path = Path(sys.argv[1])
status = sys.argv[2]
rollback_attempted = sys.argv[6] == "1"
rollback_performed = sys.argv[7] == "1"
rollback_verified = sys.argv[8] == "1"
zero_residue_verified = sys.argv[9] == "1"
if status not in {"verified", "failed_rolled_back", "rollback_unverified"}:
raise SystemExit(78)
if status == "verified" and (rollback_attempted or rollback_performed or rollback_verified or not zero_residue_verified):
raise SystemExit(78)
if status == "failed_rolled_back" and not (
rollback_attempted and rollback_performed and rollback_verified and zero_residue_verified
):
raise SystemExit(78)
if status == "rollback_unverified" and (not rollback_attempted or rollback_verified):
raise SystemExit(78)
document = {
"schemaVersion": "agent99_host110_backup_runtime_deploy_receipt_v1",
"status": sys.argv[2],
"schemaVersion": "agent99_host110_backup_runtime_deploy_receipt_v2",
"status": status,
"sourceRevision": sys.argv[3],
"sourceHead": sys.argv[4],
"runId": sys.argv[5],
"fileCount": 18,
"backupScriptFileCount": 17,
"backupHealthExporterIncluded": True,
"rollbackPerformed": sys.argv[6] == "1",
"rollbackVerified": sys.argv[6] == "1",
"verifierSha256": sys.argv[7],
"rollbackAttempted": rollback_attempted,
"rollbackPerformed": rollback_performed,
"rollbackVerified": rollback_verified,
"zeroResidueVerified": zero_residue_verified,
"verifierSha256": sys.argv[10],
"executorHost": "192.168.0.110",
"productionServiceRestarted": False,
"secretValuesRead": False,
"writtenAt": int(time.time()),
}
payload = (json.dumps(document, ensure_ascii=True, sort_keys=True, separators=(",", ":")) + "\n").encode("utf-8")
expected_digest = hashlib.sha256(payload).hexdigest()
temporary = path.with_name(f".{path.name}.tmp-{os.getpid()}")
temporary.write_text(json.dumps(document, ensure_ascii=True, sort_keys=True) + "\n", encoding="utf-8")
os.chmod(temporary, 0o600)
fault_enabled = sys.argv[11] == "1"
fault = (
os.environ.get("HOST110_BACKUP_RUNTIME_TEST_RECEIPT_FAULT", "")
if status == "verified" and fault_enabled
else ""
)
if fault not in {"", "write", "link", "fsync", "readback"}:
raise SystemExit(78)
created_final = False
directory_fd = None
try:
if os.path.lexists(path) or os.path.lexists(temporary):
raise FileExistsError(path)
if fault == "write":
raise OSError("fault_injected_receipt_write")
descriptor = os.open(temporary, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
with os.fdopen(descriptor, "wb") as handle:
if handle.write(payload) != len(payload):
raise OSError("receipt_short_write")
handle.flush()
if fault == "fsync":
raise OSError("fault_injected_receipt_fsync")
os.fsync(handle.fileno())
os.chmod(temporary, 0o600)
temporary_readback = temporary.read_bytes()
if temporary_readback != payload or hashlib.sha256(temporary_readback).hexdigest() != expected_digest:
raise OSError("receipt_temporary_readback_failed")
if fault == "link":
raise OSError("fault_injected_receipt_link")
os.link(temporary, path)
created_final = True
directory_flags = os.O_RDONLY | getattr(os, "O_DIRECTORY", 0)
directory_fd = os.open(path.parent, directory_flags)
os.fsync(directory_fd)
if fault == "readback":
raise OSError("fault_injected_receipt_readback")
readback = path.read_bytes()
if readback != payload or hashlib.sha256(readback).hexdigest() != expected_digest:
raise OSError("receipt_final_readback_failed")
if json.loads(readback.decode("utf-8")) != document:
raise OSError("receipt_document_readback_failed")
temporary.unlink()
os.fsync(directory_fd)
except BaseException:
try:
if created_final:
path.unlink(missing_ok=True)
temporary.unlink(missing_ok=True)
if directory_fd is None and path.parent.is_dir():
directory_flags = os.O_RDONLY | getattr(os, "O_DIRECTORY", 0)
directory_fd = os.open(path.parent, directory_flags)
if directory_fd is not None:
os.fsync(directory_fd)
finally:
raise
finally:
temporary.unlink(missing_ok=True)
if directory_fd is not None:
os.close(directory_fd)
PY
printf '%s' "$receipt_path"
then
return 1
fi
[ -f "$RECEIPT_PATH" ] && [ ! -L "$RECEIPT_PATH" ] || return 1
return 0
}
record_prestate() {
local name dest_path digest metadata
: > "$ROLLBACK_DIR/prestate.tsv"
chmod 600 "$ROLLBACK_DIR/prestate.tsv"
: > "$ROLLBACK_DIR/prestate.tsv" || return 74
chmod 600 "$ROLLBACK_DIR/prestate.tsv" || return 74
for name in "${PAYLOAD_FILES[@]}"; do
dest_path="$(destination_path "$name")"
if [ -f "$dest_path" ] && [ ! -L "$dest_path" ]; then
[ "$(stat -c '%U:%G' "$dest_path")" = "wooo:wooo" ] || return 71
FILE_EXISTED[$name]=1
digest="$(working_digest "$dest_path")"
metadata="$(stat -c '%u:%g:%a' "$dest_path")"
digest="$(working_digest "$dest_path")" || return 72
metadata="$(stat -c '%u:%g:%a' "$dest_path")" || return 72
PREVIOUS_DIGEST[$name]="$digest"
PREVIOUS_METADATA[$name]="$metadata"
printf '%s\t1\t%s\t%s\n' "$name" "$digest" "$metadata" >> "$ROLLBACK_DIR/prestate.tsv"
cp -p -- "$dest_path" "$ROLLBACK_DIR/$name"
printf '%s\t1\t%s\t%s\n' "$name" "$digest" "$metadata" >> "$ROLLBACK_DIR/prestate.tsv" || return 72
cp -p -- "$dest_path" "$ROLLBACK_DIR/$name" || return 72
[ "$(working_digest "$ROLLBACK_DIR/$name")" = "$digest" ] || return 72
elif [ ! -e "$dest_path" ]; then
FILE_EXISTED[$name]=0
PREVIOUS_DIGEST[$name]="-"
PREVIOUS_METADATA[$name]="-"
printf '%s\t0\t-\t-\n' "$name" >> "$ROLLBACK_DIR/prestate.tsv"
printf '%s\t0\t-\t-\n' "$name" >> "$ROLLBACK_DIR/prestate.tsv" || return 72
else
return 73
fi
done
fsync_rollback_prestate || return 75
}
register_run_owned_temp() {
RUN_OWNED_TEMP_PATHS["$1"]=1
}
verify_run_owned_temp_absence() {
local temporary
for temporary in "${!RUN_OWNED_TEMP_PATHS[@]}"; do
[ ! -e "$temporary" ] && [ ! -L "$temporary" ] || return 1
done
}
cleanup_run_owned_temps() {
local temporary failed=0 preserved=0
local fault=""
if [ "$FAULT_INJECTION_ENABLED" -eq 1 ]; then
fault="${HOST110_BACKUP_RUNTIME_TEST_ROLLBACK_FAULT:-}"
fi
for temporary in "${!RUN_OWNED_TEMP_PATHS[@]}"; do
if [ "$fault" = "preserve_first_temp" ] \
&& [ "$preserved" -eq 0 ] \
&& { [ -e "$temporary" ] || [ -L "$temporary" ]; }; then
preserved=1
failed=1
continue
fi
rm -f -- "$temporary" || failed=1
done
verify_run_owned_temp_absence || failed=1
[ "$failed" -eq 0 ]
}
rollback_transaction() {
local name dest_path destination_parent backup_path temporary failed=0
ROLLBACK_ATTEMPTED=1
ROLLBACK_PERFORMED=0
ROLLBACK_VERIFIED=0
RUN_TEMP_RESIDUE_VERIFIED=0
set +e
cleanup_run_owned_temps || failed=1
for name in "${PAYLOAD_FILES[@]}"; do
[ -n "${FILE_EXISTED[$name]+x}" ] || { failed=1; continue; }
dest_path="$(destination_path "$name")"
@@ -300,13 +486,22 @@ rollback_transaction() {
backup_path="$ROLLBACK_DIR/$name"
destination_parent="$(dirname "$dest_path")"
temporary="$destination_parent/.${name}.agent99-rollback-${RUN_ID}"
cp -p -- "$backup_path" "$temporary" \
&& mv -f -- "$temporary" "$dest_path" \
|| failed=1
register_run_owned_temp "$temporary"
if cp -p -- "$backup_path" "$temporary" && mv -f -- "$temporary" "$dest_path"; then
ROLLBACK_PERFORMED=1
else
failed=1
fi
else
rm -f -- "$dest_path" || failed=1
if rm -f -- "$dest_path"; then
ROLLBACK_PERFORMED=1
else
failed=1
fi
fi
done
cleanup_run_owned_temps || failed=1
fsync_destination_state || failed=1
for name in "${PAYLOAD_FILES[@]}"; do
dest_path="$(destination_path "$name")"
if [ "${FILE_EXISTED[$name]:-}" = "1" ]; then
@@ -320,8 +515,14 @@ rollback_transaction() {
failed=1
fi
done
if verify_run_owned_temp_absence; then
RUN_TEMP_RESIDUE_VERIFIED=1
else
failed=1
RUN_TEMP_RESIDUE_VERIFIED=0
fi
set -e
if [ "$failed" -eq 0 ]; then
if [ "$failed" -eq 0 ] && [ "$ROLLBACK_PERFORMED" -eq 1 ] && [ "$RUN_TEMP_RESIDUE_VERIFIED" -eq 1 ]; then
ROLLBACK_VERIFIED=1
return 0
fi
@@ -330,20 +531,28 @@ rollback_transaction() {
}
cleanup() {
local status=$?
local exit_status=$?
local rollback_status="rollback_unverified"
local failure_receipt_written=0
trap - EXIT HUP INT TERM
if [ "$APPLY_STARTED" -eq 1 ] && [ "$APPLY_COMPLETE" -ne 1 ]; then
if rollback_transaction; then
rollback_status="failed_rolled_back"
fi
write_receipt "$rollback_status" "$ROLLBACK_VERIFIED" >/dev/null || true
if write_receipt "$rollback_status" "$ROLLBACK_ATTEMPTED" "$ROLLBACK_PERFORMED" \
"$ROLLBACK_VERIFIED" "$RUN_TEMP_RESIDUE_VERIFIED"; then
failure_receipt_written=1
fi
fi
[ -z "$STAGE_DIR" ] || rm -rf -- "$STAGE_DIR"
if [ "$ROLLBACK_VERIFIED" -eq 1 ]; then
[ -z "$ROLLBACK_DIR" ] || rm -rf -- "$ROLLBACK_DIR"
if [ -n "$STAGE_DIR" ]; then
rm -rf -- "$STAGE_DIR" || true
fi
exit "$status"
if [ "$ROLLBACK_VERIFIED" -eq 1 ] && [ "$failure_receipt_written" -eq 1 ]; then
if [ -n "$ROLLBACK_DIR" ]; then
rm -rf -- "$ROLLBACK_DIR" || true
fi
fi
exit "$exit_status"
}
validate_source || fail "source_validation_failed"
@@ -359,7 +568,7 @@ if [ "$MODE" = "verify" ]; then
exit 0
fi
[ ! -e "$STATUS_ROOT/agent99-backup-runtime-deploy-${RUN_ID}.json" ] || fail "run_identity_receipt_exists"
[ ! -e "$RECEIPT_PATH" ] && [ ! -L "$RECEIPT_PATH" ] || fail "run_identity_receipt_exists"
STAGE_DIR="$STAGE_ROOT/$RUN_ID"
ROLLBACK_DIR="$ROLLBACK_ROOT/$RUN_ID"
[ ! -e "$STAGE_DIR" ] || fail "run_identity_stage_exists"
@@ -399,10 +608,17 @@ for name in "${PAYLOAD_FILES[@]}"; do
dest_path="$(destination_path "$name")"
destination_parent="$(dirname "$dest_path")"
temporary="$destination_parent/.${name}.agent99-${RUN_ID}"
register_run_owned_temp "$temporary"
install -m 755 "$STAGE_DIR/$name" "$temporary"
if [ "$FAULT_INJECTION_ENABLED" -eq 1 ] \
&& [ "${HOST110_BACKUP_RUNTIME_TEST_APPLY_FAULT:-}" = "after_temp_install" ] \
&& [ "$name" = "${PAYLOAD_FILES[0]}" ]; then
fail "fault_injected_after_temp_install"
fi
mv -f -- "$temporary" "$dest_path"
done
fsync_destination_state || fail "post_apply_durability_failed"
verify_destination || fail "post_apply_verification_failed"
verifier_result="$(BACKUP_RUNTIME_DEPLOY_CONTEXT=1 python3 "$SOURCE_STAGE/verify-host110-backup-runtime.py" \
--manifest "$SOURCE_STAGE/manifest.json" \
@@ -433,13 +649,26 @@ if not (
raise SystemExit(1)
PY
verify_run_owned_temp_absence || fail "post_apply_temp_residue_detected"
RUN_TEMP_RESIDUE_VERIFIED=1
if ! write_receipt "verified" 0 0 0 "$RUN_TEMP_RESIDUE_VERIFIED"; then
fail "durable_receipt_failed"
fi
receipt_path="$RECEIPT_PATH"
APPLY_COMPLETE=1
receipt_path="$(write_receipt "verified" 0)"
rm -rf -- "$STAGE_DIR" "$ROLLBACK_DIR"
trap - EXIT HUP INT TERM
stage_cleanup_verified=0
rollback_prestate_cleanup_verified=0
if rm -rf -- "$STAGE_DIR" && [ ! -e "$STAGE_DIR" ] && [ ! -L "$STAGE_DIR" ]; then
stage_cleanup_verified=1
fi
if rm -rf -- "$ROLLBACK_DIR" && [ ! -e "$ROLLBACK_DIR" ] && [ ! -L "$ROLLBACK_DIR" ]; then
rollback_prestate_cleanup_verified=1
fi
STAGE_DIR=""
ROLLBACK_DIR=""
trap - EXIT HUP INT TERM
python3 - "$SOURCE_REVISION" "$SOURCE_HEAD" "$receipt_path" "$verifier_result" <<'PY'
python3 - "$SOURCE_REVISION" "$SOURCE_HEAD" "$receipt_path" "$verifier_result" \
"$stage_cleanup_verified" "$rollback_prestate_cleanup_verified" <<'PY'
import json
import sys
@@ -452,7 +681,12 @@ print(json.dumps({
"fileCount": 18,
"backupScriptFileCount": 17,
"backupHealthExporterIncluded": True,
"rollbackAttempted": False,
"rollbackPerformed": False,
"rollbackVerified": False,
"zeroResidueVerified": True,
"stageCleanupVerified": sys.argv[5] == "1",
"rollbackPrestateCleanupVerified": sys.argv[6] == "1",
"receipt": sys.argv[3],
"verifier": json.loads(sys.argv[4]),
}, ensure_ascii=True, sort_keys=True))