Files
rustfs/crates/ecstore/tests/minio_generated_read_test.rs
houseme ea2e24ac13 test/ci(ecstore): fix MinIO SSE interop size assertion + nightly dockerized interop check (#4809)
* test(ecstore): assert decrypted_size for MinIO SSE interop round-trip

The ignored MinIO interop round-trip tests asserted `ObjectInfo.size`
against the plaintext length. For SSE objects `size` is the on-disk
DARE-encrypted size (plaintext + 32 bytes per 64 KiB block), so the
assertion can never hold once real fixtures are present — the two
`#[ignore]` tests failed the moment a real MinIO-written fixture was fed
in, even though the decoded data was byte-identical.

The client-visible object size comes from `decrypted_size()` /
`get_actual_size()`, which correctly reads MinIO's
`x-*-internal-actual-size` metadata (verified: both SSE-S3 and SSE-KMS
8 MiB multipart fixtures now report 8388608). Assert against that
instead and keep the plaintext length and SHA-256 data checks.

With real 4-drive MinIO fixtures (RELEASE.2025-09-07) all four tests
pass, confirming RustFS reads MinIO erasure-coded SSE objects with
byte-identical data and correct logical size.

Co-Authored-By: heihutu <heihutu@gmail.com>

* ci(ecstore): nightly MinIO interop check + dockerized fixture capture

Wire the ignored MinIO on-disk interop reader tests into a nightly,
non-required CI job, and make their fixtures reproducible without a host
MinIO install.

- Dockerfile + capture_via_docker.sh: build a throwaway image carrying
  the official MinIO server binary (pinned RELEASE.2025-09-07) plus the
  fixture lab on a small Python base, then run `lab.py capture-matrix` to
  write the SSE-S3 / SSE-KMS multipart fixtures the tests consume. lab.py
  drives MinIO's S3 API directly, so no `mc` is needed.
- .github/workflows/minio-interop.yml: nightly + manual workflow on
  GitHub-hosted ubuntu-latest (reliable Docker + Python, unlike the
  self-hosted fleet — see e2e-s3tests.yml infra note). Regenerates the
  gitignored fixtures each run and executes the #[ignore] reader tests.
  Not a PR gate.
- README: document the Docker capture path.

Validated end to end: the script builds the image, captures the two
multipart cases, and `cargo nextest run --run-ignored ignored-only`
passes all four interop tests.

Co-Authored-By: heihutu <heihutu@gmail.com>

---------

Co-authored-by: heihutu <heihutu@gmail.com>
2026-07-14 15:08:14 +00:00

300 lines
11 KiB
Rust

#![cfg(feature = "rio-v2")]
use std::fs;
use std::io::Cursor;
use std::path::{Path, PathBuf};
mod storage_api;
use rustfs_filemeta::{FileInfo, FileInfoOpts, get_file_info};
use serde::Deserialize;
use sha2::{Digest, Sha256};
use storage_api::minio_generated_read::{
DiskAPI as _, DiskOption, Endpoint, Erasure, GetObjectReader, ObjectInfo, ObjectOptions, create_bitrot_reader, new_disk,
};
use temp_env::async_with_vars;
use tokio::io::{AsyncReadExt, AsyncWrite};
#[derive(Debug, Deserialize)]
struct ManifestRecord {
bucket: String,
object: String,
backend_files: Vec<String>,
}
#[derive(Default)]
struct VecAsyncWriter {
bytes: Vec<u8>,
}
impl AsyncWrite for VecAsyncWriter {
fn poll_write(
mut self: std::pin::Pin<&mut Self>,
_cx: &mut std::task::Context<'_>,
buf: &[u8],
) -> std::task::Poll<std::io::Result<usize>> {
self.bytes.extend_from_slice(buf);
std::task::Poll::Ready(Ok(buf.len()))
}
fn poll_flush(self: std::pin::Pin<&mut Self>, _cx: &mut std::task::Context<'_>) -> std::task::Poll<std::io::Result<()>> {
std::task::Poll::Ready(Ok(()))
}
fn poll_shutdown(self: std::pin::Pin<&mut Self>, _cx: &mut std::task::Context<'_>) -> std::task::Poll<std::io::Result<()>> {
std::task::Poll::Ready(Ok(()))
}
}
fn fixture_root() -> PathBuf {
std::env::var_os("RUSTFS_MINIO_FIXTURE_ROOT")
.map(PathBuf::from)
.unwrap_or_else(|| PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("../rio-v2/tests/fixtures/minio-generated"))
}
fn case_dir(case_id: &str) -> PathBuf {
fixture_root().join("cases").join(case_id)
}
fn read_json<T: for<'de> Deserialize<'de>>(path: &Path) -> T {
let text = fs::read_to_string(path).unwrap_or_else(|err| panic!("read {}: {err}", path.display()));
serde_json::from_str(&text).unwrap_or_else(|err| panic!("parse {}: {err}", path.display()))
}
fn require_fixture_case(case_id: &str) -> PathBuf {
let path = case_dir(case_id);
assert!(
path.is_dir(),
"fixture case missing: {}. Run scripts/minio_fixture_lab/lab.py capture-matrix first.",
path.display()
);
path
}
fn read_plaintext_sha256(case_dir: &Path) -> String {
fs::read_to_string(case_dir.join("plaintext.sha256"))
.unwrap_or_else(|err| panic!("read plaintext.sha256 under {}: {err}", case_dir.display()))
.trim()
.to_string()
}
fn minio_static_kms_key_b64() -> String {
std::env::var("RUSTFS_MINIO_STATIC_KMS_KEY_B64")
.unwrap_or_else(|_| panic!("RUSTFS_MINIO_STATIC_KMS_KEY_B64 must point to the 32-byte static MinIO KMS key"))
}
fn object_xl_meta_path(case_dir: &Path, manifest: &ManifestRecord) -> PathBuf {
let expected = format!("disk1/{}/{}/xl.meta", manifest.bucket, manifest.object);
let relative = manifest
.backend_files
.iter()
.find(|entry| entry.as_str() == expected)
.unwrap_or_else(|| panic!("object xl.meta missing from manifest backend_files: {expected}"));
case_dir.join("backend").join(relative)
}
fn load_file_info(case_dir: &Path, manifest: &ManifestRecord) -> FileInfo {
let xl_meta_path = object_xl_meta_path(case_dir, manifest);
let xl_meta = fs::read(&xl_meta_path).unwrap_or_else(|err| panic!("read {}: {err}", xl_meta_path.display()));
get_file_info(
&xl_meta,
&manifest.bucket,
&manifest.object,
"",
FileInfoOpts {
data: true,
include_free_versions: true,
},
)
.unwrap_or_else(|err| panic!("decode {}: {err}", xl_meta_path.display()))
}
fn load_object_info(file_info: &FileInfo, manifest: &ManifestRecord) -> ObjectInfo {
ObjectInfo::from_file_info(file_info, &manifest.bucket, &manifest.object, false)
}
fn sha256_hex(bytes: &[u8]) -> String {
hex_simd::encode_to_string(Sha256::digest(bytes), hex_simd::AsciiCase::Lower)
}
async fn load_fixture_reader_input(case_id: &str) -> (ObjectInfo, Vec<u8>, String) {
let case_dir = require_fixture_case(case_id);
let manifest: ManifestRecord = read_json(&case_dir.join("manifest.json"));
let expected_sha256 = read_plaintext_sha256(&case_dir);
let file_info = load_file_info(&case_dir, &manifest);
let encrypted = encrypted_fixture_bytes(&case_dir, &manifest, &file_info).await;
let object_info = load_object_info(&file_info, &manifest);
(object_info, encrypted, expected_sha256)
}
async fn read_fixture_plaintext(encrypted: Vec<u8>, object_info: ObjectInfo, kms_key_b64: String) -> Result<Vec<u8>, String> {
let object_size = object_info.size;
async_with_vars(
[
("__RUSTFS_SSE_SIMPLE_CMK", Some(kms_key_b64)),
("RUSTFS_SSE_S3_MASTER_KEY", None::<String>),
],
async move {
let (mut reader, offset, length) = GetObjectReader::new(
Box::new(Cursor::new(encrypted)),
None,
&object_info,
&ObjectOptions::default(),
&http::HeaderMap::new(),
)
.await
.map_err(|err| format!("construct GetObjectReader from MinIO raw fixture: {err:?}"))?;
if offset != 0 || length != object_size {
return Err(format!("unexpected fixture range offset={offset} length={length} size={object_size}"));
}
let mut plaintext = Vec::new();
reader
.read_to_end(&mut plaintext)
.await
.map_err(|err| format!("read plaintext from MinIO raw fixture: {err}"))?;
Ok(plaintext)
},
)
.await
}
async fn encrypted_fixture_bytes(case_dir: &Path, manifest: &ManifestRecord, file_info: &FileInfo) -> Vec<u8> {
let mut disks = Vec::with_capacity(file_info.erasure.distribution.len());
for disk_number in 1..=file_info.erasure.distribution.len() {
let disk_root = case_dir.join("backend").join(format!("disk{disk_number}"));
let disk_root_str = disk_root
.to_str()
.unwrap_or_else(|| panic!("non-utf8 disk root {}", disk_root.display()));
let mut endpoint = Endpoint::try_from(disk_root_str).expect("fixture disk endpoint");
endpoint.set_pool_index(0);
endpoint.set_set_index(0);
endpoint.set_disk_index(disk_number - 1);
let disk = new_disk(
&endpoint,
&DiskOption {
cleanup: false,
health_check: false,
},
)
.await
.unwrap_or_else(|err| panic!("open fixture disk {disk_number}: {err}"));
disks.push(disk);
}
let mut disk_order = vec![None; disks.len()];
for (idx, disk) in disks.iter().enumerate() {
let block_index = file_info.erasure.distribution[idx];
disk_order[block_index - 1] = Some(disk);
}
let data_dir = file_info
.data_dir
.as_ref()
.unwrap_or_else(|| panic!("fixture {} is missing data_dir", manifest.object));
let mut encrypted = Vec::new();
for part in &file_info.parts {
let checksum_info = file_info.erasure.get_checksum_info(part.number);
let path = format!("{}/{}/part.{}", manifest.object, data_dir, part.number);
let shard_read_len = file_info.erasure.shard_file_size(part.size as i64);
let mut readers = Vec::with_capacity(disks.len());
for (idx, disk) in disk_order.iter().enumerate() {
let reader = create_bitrot_reader(
None,
*disk,
&manifest.bucket,
&path,
0,
shard_read_len as usize,
file_info.erasure.shard_size(),
checksum_info.algorithm.clone(),
false,
false,
)
.await
.unwrap_or_else(|err| panic!("create bitrot reader for disk{} {path}: {err:?}", idx + 1));
readers.push(reader);
}
let erasure = Erasure::new(
file_info.erasure.data_blocks,
file_info.erasure.parity_blocks,
file_info.erasure.block_size,
);
let mut writer = VecAsyncWriter::default();
let (written, err) = erasure.decode(&mut writer, readers, 0, part.size, part.size).await;
if let Some(err) = err {
panic!("decode erasure shards for {path}: {err}");
}
assert_eq!(written, part.size, "decoded part size should match xl.meta part size");
encrypted.extend_from_slice(&writer.bytes);
}
for disk in disks {
disk.close().await.expect("close fixture disk");
}
encrypted
}
#[tokio::test]
#[ignore = "requires generated MinIO fixture data and a local static KMS key"]
async fn reads_minio_generated_sse_s3_multipart_fixture() {
assert_fixture_round_trip("sse-s3-multipart-8m", 8 * 1024 * 1024).await;
}
#[tokio::test]
#[ignore = "requires generated MinIO fixture data and a local static KMS key"]
async fn reads_minio_generated_sse_kms_multipart_fixture() {
assert_fixture_round_trip("sse-kms-multipart-8m", 8 * 1024 * 1024).await;
}
#[tokio::test]
#[ignore = "requires generated MinIO fixture data and a local static KMS key"]
async fn rejects_minio_generated_sse_s3_fixture_with_wrong_kms_key() {
let (object_info, encrypted, _) = load_fixture_reader_input("sse-s3-multipart-8m").await;
let wrong_key_b64 = "AQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQE=".to_string();
let result = read_fixture_plaintext(encrypted, object_info, wrong_key_b64).await;
assert!(result.is_err(), "wrong KMS key must fail closed");
}
#[tokio::test]
#[ignore = "requires generated MinIO fixture data and a local static KMS key"]
async fn rejects_minio_generated_sse_s3_fixture_with_truncated_ciphertext() {
let (object_info, mut encrypted, expected_sha256) = load_fixture_reader_input("sse-s3-multipart-8m").await;
encrypted.truncate(encrypted.len() / 2);
let result = read_fixture_plaintext(encrypted, object_info, minio_static_kms_key_b64()).await;
if let Ok(plaintext) = result {
assert_ne!(
sha256_hex(&plaintext),
expected_sha256,
"truncated ciphertext must not restore the original plaintext"
);
}
}
async fn assert_fixture_round_trip(case_id: &str, expected_size: i64) {
let (object_info, encrypted, expected_sha256) = load_fixture_reader_input(case_id).await;
// `ObjectInfo.size` is the on-disk size. For SSE objects that is the
// DARE-encrypted size (plaintext + 32 bytes per 64 KiB block), which is
// deliberately larger than the logical object size. The size a client sees
// (and what MinIO records via `x-*-internal-actual-size`) comes from
// `decrypted_size()`/`get_actual_size()`, so assert against that — the raw
// `size` field would never equal the plaintext length for encrypted objects.
let decrypted_size = object_info.decrypted_size().expect("decrypted size from MinIO metadata");
let kms_key_b64 = minio_static_kms_key_b64();
let plaintext = read_fixture_plaintext(encrypted, object_info, kms_key_b64)
.await
.expect("fixture must restore with the configured KMS key");
assert_eq!(decrypted_size, expected_size);
assert_eq!(plaintext.len(), expected_size as usize);
assert_eq!(sha256_hex(&plaintext), expected_sha256);
}