Compare commits

..

2 Commits

Author SHA1 Message Date
overtrue 3aab93bdff chore: merge main after ECStore compile repair 2026-09-05 18:46:53 +08:00
overtrue ea993d482c fix(ci): preserve reported functional suite failures 2026-09-05 18:33:42 +08:00
23 changed files with 255 additions and 821 deletions
-3
View File
@@ -54,9 +54,6 @@ env:
jobs:
heal-test:
runs-on: smoke-testing
# Requirement: a failing suite must not fail the workflow; failures
# are filed to rustfs/backlog and the chain continues.
continue-on-error: true
timeout-minutes: 480
# Standalone manual run, or one link of the nightly functional chain
# (storage -> heal -> pool). Pool expansion no longer re-runs heal.
-2
View File
@@ -49,7 +49,6 @@ env:
jobs:
kms-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 420
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -109,7 +108,6 @@ jobs:
- name: Run KMS suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-kms.log
run: |
@@ -84,9 +84,6 @@ env:
jobs:
performance-test:
runs-on: pf-testing
# Requirement: a failing benchmark must not fail the workflow;
# failures are filed to rustfs/backlog.
continue-on-error: true
timeout-minutes: 900
# Run on manual dispatch, or when the nightly build completed successfully.
# Skipped when nightly failed.
@@ -76,9 +76,6 @@ jobs:
pool-expansion-test:
name: Pool expansion / decommission test
runs-on: smoke-testing
# Requirement: a failing suite must not fail the workflow; failures
# are filed to rustfs/backlog and the chain continues.
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
env:
@@ -62,9 +62,6 @@ env:
jobs:
replication-test:
runs-on: smoke-testing
# A failed replication run must not break the chain or the workflow: the
# failure is reported to rustfs/backlog instead (see the issue step).
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -116,7 +113,6 @@ jobs:
- name: Run replication suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-replication.log
run: |
@@ -37,7 +37,6 @@ env:
jobs:
s3-compat-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -88,7 +87,6 @@ jobs:
- name: Run S3 compatibility suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-s3-compat.log
run: |
@@ -46,7 +46,6 @@ env:
jobs:
storage-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -97,7 +96,6 @@ jobs:
- name: Run storage engine suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-storage.log
run: |
-3
View File
@@ -61,9 +61,6 @@ env:
jobs:
tier-test:
runs-on: smoke-testing
# Requirement: a failing suite must not fail the workflow; failures
# are filed to rustfs/backlog and the chain continues.
continue-on-error: true
timeout-minutes: 420
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -79,7 +79,6 @@ env:
jobs:
upgrade-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 420
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -142,7 +141,6 @@ jobs:
- name: Run upgrade compatibility suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-upgrade.log
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
-15
View File
@@ -130,21 +130,6 @@ Scanner cycle budget controls:
- timeout returns S3 `SlowDown`, so clients should use normal SDK retry handling.
- this is not a fdatasync or group-commit switch. Track fdatasync batching separately with `rustfs_s3_put_object_rename_fdatasync_batch_files`.
## Remote tier timeout environment variables
- `RUSTFS_TIER_REMOTE_CONNECT_TIMEOUT_SECS`
- remote tier TCP connect timeout.
- default is `10`.
- must be positive; zero fails tier client initialization, while an invalid integer is logged and falls back to the default.
- `RUSTFS_TIER_REMOTE_REQUEST_TIMEOUT_SECS`
- remote tier request timeout through response headers.
- default is `86400` so large transition uploads keep a production-safe budget.
- must be positive; zero fails tier client initialization, while an invalid integer is logged and falls back to the default. Very large values are accepted and act as a correspondingly long budget.
- `RUSTFS_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS`
- maximum idle time between remote tier response-body chunks.
- default is `60`; the timer resets only when non-empty body data keeps progressing.
- must be positive; zero fails tier client initialization, while an invalid integer is logged and falls back to the default.
## Drive timeout environment variables
- `RUSTFS_DRIVE_METADATA_TIMEOUT_SECS`
-32
View File
@@ -137,28 +137,6 @@ pub const DEFAULT_TIER_REMOTE_VERSION_STATE_FLEET_CONFIRMED: bool = false;
const _: () = assert!(!DEFAULT_TIER_REMOTE_VERSION_STATE_WRITE);
const _: () = assert!(!DEFAULT_TIER_REMOTE_VERSION_STATE_FLEET_CONFIRMED);
/// Environment variable for remote tier TCP connect timeout in seconds.
pub const ENV_TIER_REMOTE_CONNECT_TIMEOUT_SECS: &str = "RUSTFS_TIER_REMOTE_CONNECT_TIMEOUT_SECS";
/// Default remote tier TCP connect timeout in seconds.
pub const DEFAULT_TIER_REMOTE_CONNECT_TIMEOUT_SECS: u64 = 10;
/// Environment variable for the remote tier request timeout in seconds.
///
/// This bounds upload/download request progress through response headers. The
/// default is intentionally large so multi-TiB transition uploads keep their
/// previous production budget while black-hole remotes no longer wait forever.
pub const ENV_TIER_REMOTE_REQUEST_TIMEOUT_SECS: &str = "RUSTFS_TIER_REMOTE_REQUEST_TIMEOUT_SECS";
/// Default remote tier request timeout in seconds.
pub const DEFAULT_TIER_REMOTE_REQUEST_TIMEOUT_SECS: u64 = 24 * 60 * 60;
/// Environment variable for remote tier response-body idle timeout in seconds.
///
/// The timer is re-armed on every non-empty response-body chunk, so slow but
/// progressing remotes can continue while silent response bodies are cancelled.
pub const ENV_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS: &str = "RUSTFS_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS";
/// Default remote tier response-body idle timeout in seconds.
pub const DEFAULT_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS: u64 = 60;
/// Request the object-transaction fencing contract used by storage-owned
/// cleanup receipts and lock-window optimizations.
///
@@ -834,16 +812,6 @@ mod remote_version_state_tests {
);
}
#[test]
fn remote_tier_timeout_env_names_are_stable() {
assert_eq!(super::ENV_TIER_REMOTE_CONNECT_TIMEOUT_SECS, "RUSTFS_TIER_REMOTE_CONNECT_TIMEOUT_SECS");
assert_eq!(super::ENV_TIER_REMOTE_REQUEST_TIMEOUT_SECS, "RUSTFS_TIER_REMOTE_REQUEST_TIMEOUT_SECS");
assert_eq!(
super::ENV_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS,
"RUSTFS_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS"
);
}
#[test]
fn data_movement_part_checksum_gate_uses_stable_environment_names() {
assert_eq!(super::ENV_DATA_MOVEMENT_PART_CHECKSUMS_WRITE, "RUSTFS_DATA_MOVEMENT_PART_CHECKSUMS_WRITE");
@@ -37,7 +37,7 @@ use crate::services::tier::{
use bytes::Bytes;
use http::StatusCode;
use rustfs_s3_client::credentials::{Credentials, SignatureType, Static, Value};
use rustfs_s3_client::transition_api::{BucketLookupType, Options, TransitionClient, TransitionClientTimeouts, TransitionCore};
use rustfs_s3_client::transition_api::{BucketLookupType, Options, TransitionClient, TransitionCore};
use rustfs_s3_client::{
admin_handler_utils::AdminError,
api_error_response::to_error_response,
@@ -320,27 +320,6 @@ pub(crate) fn endpoint_authority(url: &url::Url) -> Result<String, std::io::Erro
}
}
fn transition_timeout_from_env(env_key: &str, default_secs: u64) -> Duration {
Duration::from_secs(rustfs_utils::get_env_u64(env_key, default_secs))
}
pub(crate) fn transition_client_timeouts_from_env() -> TransitionClientTimeouts {
TransitionClientTimeouts::new(
transition_timeout_from_env(
rustfs_config::ENV_TIER_REMOTE_CONNECT_TIMEOUT_SECS,
rustfs_config::DEFAULT_TIER_REMOTE_CONNECT_TIMEOUT_SECS,
),
transition_timeout_from_env(
rustfs_config::ENV_TIER_REMOTE_REQUEST_TIMEOUT_SECS,
rustfs_config::DEFAULT_TIER_REMOTE_REQUEST_TIMEOUT_SECS,
),
transition_timeout_from_env(
rustfs_config::ENV_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS,
rustfs_config::DEFAULT_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS,
),
)
}
/// Build the [`WarmBackendS3`] shared by the S3-compatible warm backend providers.
///
/// Credential, bucket, and endpoint validation run in this order because the
@@ -371,7 +350,6 @@ pub(crate) async fn new_s3_compatible_warm_backend(
signer_type: SignatureType::SignatureV4,
..Default::default()
}));
let timeouts = transition_client_timeouts_from_env();
let opts = Options {
creds,
secure: u.scheme() == "https",
@@ -384,7 +362,7 @@ pub(crate) async fn new_s3_compatible_warm_backend(
// Run the SSRF guard after the host-presence check so a host-less endpoint
// keeps this constructor's stable error text.
(params.validate_endpoint)(&u).map_err(|err| std::io::Error::other(format!("tier endpoint is not allowed: {err}")))?;
let client = TransitionClient::new_with_timeouts(&endpoint, opts, params.provider_tag, timeouts).await?;
let client = TransitionClient::new(&endpoint, opts, params.provider_tag).await?;
let client = Arc::new(client);
let core = TransitionCore(Arc::clone(&client));
@@ -26,7 +26,7 @@ use crate::services::tier::{
tier_config::TierS3,
warm_backend::{
TransitionCandidateIdentity, TransitionCandidateProbe, TransitionCandidateReconciler, WarmBackend, WarmBackendGetOpts,
build_transition_put_options, endpoint_authority, transition_client_timeouts_from_env,
build_transition_put_options, endpoint_authority,
},
};
use http::HeaderMap;
@@ -139,7 +139,6 @@ impl WarmBackendS3 {
} else {
return Err(std::io::Error::other("insufficient parameters for S3 backend authentication"));
}
let timeouts = transition_client_timeouts_from_env();
let opts = Options {
creds,
secure: u.scheme() == "https",
@@ -148,7 +147,7 @@ impl WarmBackendS3 {
..Default::default()
};
let endpoint = endpoint_authority(&u)?;
let client = TransitionClient::new_with_timeouts(&endpoint, opts, tier_type, timeouts).await?;
let client = TransitionClient::new(&endpoint, opts, tier_type).await?;
let client = Arc::new(client);
let core = TransitionCore(Arc::clone(&client));
+48 -204
View File
@@ -120,10 +120,18 @@ impl TransitionClient {
let h = resp.headers().clone();
let mut body = resp.into_body();
let body_vec = if let Some(limit) = max_response_bytes {
self.collect_response_body(resp.into_body(), limit).await?
collect_response_body(body, limit).await?
} else {
self.collect_response_body_unbounded(resp.into_body()).await?
let mut body_vec = Vec::new();
while let Some(frame) = body.frame().await {
let frame = frame.map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e.to_string()))?;
if let Some(data) = frame.data_ref() {
body_vec.extend_from_slice(data);
}
}
body_vec
};
Ok((object_stat, h, BufReader::new(Cursor::new(body_vec))))
}
@@ -135,7 +143,7 @@ mod bounded_response_tests {
use crate::{
api_get_options::GetObjectOptions,
credentials::{Credentials, SignatureType, Static, Value},
transition_api::{BucketLookupType, Options, TransitionClient, TransitionClientTimeouts, collect_response_body},
transition_api::{BucketLookupType, Options, TransitionClient, collect_response_body},
};
use http_body_util::Full;
use hyper::body::Bytes;
@@ -167,31 +175,7 @@ mod bounded_response_tests {
assert_eq!(err.kind(), std::io::ErrorKind::InvalidData);
}
fn test_options() -> Options {
Options {
creds: Credentials::new(Static(Value {
access_key_id: "access-key".to_string(),
secret_access_key: "secret-key".to_string(),
signer_type: SignatureType::SignatureV4,
..Default::default()
})),
region: "us-east-1".to_string(),
bucket_lookup: BucketLookupType::BucketLookupPath,
max_retries: 1,
..Default::default()
}
}
async fn client_for_endpoint(endpoint: &str, timeouts: TransitionClientTimeouts) -> TransitionClient {
TransitionClient::new_with_timeouts(endpoint, test_options(), "", timeouts)
.await
.expect("fixture client should build")
}
async fn bounded_get_fixture_with_timeouts(
body: &'static [u8],
timeouts: TransitionClientTimeouts,
) -> Option<(TransitionClient, tokio::task::JoinHandle<String>)> {
async fn bounded_get_fixture(body: &'static [u8]) -> Option<(TransitionClient, tokio::task::JoinHandle<String>)> {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return None,
@@ -225,14 +209,27 @@ mod bounded_response_tests {
stream.write_all(body).await.expect("fixture should write response body");
request
});
let client = client_for_endpoint(&endpoint, timeouts).await;
let client = TransitionClient::new(
&endpoint,
Options {
creds: Credentials::new(Static(Value {
access_key_id: "access-key".to_string(),
secret_access_key: "secret-key".to_string(),
signer_type: SignatureType::SignatureV4,
..Default::default()
})),
region: "us-east-1".to_string(),
bucket_lookup: BucketLookupType::BucketLookupPath,
max_retries: 1,
..Default::default()
},
"",
)
.await
.expect("fixture client should build");
Some((client, request))
}
async fn bounded_get_fixture(body: &'static [u8]) -> Option<(TransitionClient, tokio::task::JoinHandle<String>)> {
bounded_get_fixture_with_timeouts(body, TransitionClientTimeouts::default()).await
}
#[tokio::test]
async fn real_transport_accepts_the_exact_closed_range_length() {
let Some((client, request)) = bounded_get_fixture(b"RustFS!").await else {
@@ -295,7 +292,24 @@ mod bounded_response_tests {
.local_addr()
.expect("listener local address should be available")
.to_string();
let client = client_for_endpoint(&endpoint, TransitionClientTimeouts::default()).await;
let client = TransitionClient::new(
&endpoint,
Options {
creds: Credentials::new(Static(Value {
access_key_id: "access-key".to_string(),
secret_access_key: "secret-key".to_string(),
signer_type: SignatureType::SignatureV4,
..Default::default()
})),
region: "us-east-1".to_string(),
bucket_lookup: BucketLookupType::BucketLookupPath,
max_retries: 1,
..Default::default()
},
"",
)
.await
.expect("fixture client should build");
let mut opts = GetObjectOptions::default();
opts.headers
.insert("range".to_string(), "bytes=0-18446744073709551615".to_string());
@@ -312,176 +326,6 @@ mod bounded_response_tests {
.is_err()
);
}
#[tokio::test]
async fn connection_refused_returns_without_waiting_for_the_request_timeout() {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return,
Err(err) => panic!("test listener should bind: {err}"),
};
let endpoint = listener
.local_addr()
.expect("listener local address should be available")
.to_string();
drop(listener);
let client = client_for_endpoint(
&endpoint,
TransitionClientTimeouts::new(Duration::from_secs(1), Duration::from_secs(5), Duration::from_secs(1)),
)
.await;
let mut opts = GetObjectOptions::default();
opts.set_range(0, 6).expect("the probe range should be valid");
let result = tokio::time::timeout(Duration::from_secs(2), client.get_object_inner("bucket", "probe", &opts))
.await
.expect("connection refused should return before the broader request timeout");
assert!(result.is_err(), "connection refused must fail instead of hanging");
}
#[tokio::test]
async fn response_header_stall_returns_timed_out() {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return,
Err(err) => panic!("test listener should bind: {err}"),
};
let endpoint = listener
.local_addr()
.expect("listener local address should be available")
.to_string();
let fixture = tokio::spawn(async move {
let (mut stream, _) = listener.accept().await.expect("fixture should accept one GET");
let mut request = Vec::new();
let mut buffer = [0; 1024];
loop {
let read = stream.read(&mut buffer).await.expect("fixture should read request headers");
assert_ne!(read, 0, "connection closed before request headers were received");
request.extend_from_slice(&buffer[..read]);
if request.windows(4).any(|window| window == b"\r\n\r\n") {
break;
}
}
tokio::time::sleep(Duration::from_millis(200)).await;
});
let client = client_for_endpoint(
&endpoint,
TransitionClientTimeouts::new(Duration::from_secs(1), Duration::from_millis(50), Duration::from_secs(1)),
)
.await;
let mut opts = GetObjectOptions::default();
opts.set_range(0, 6).expect("the probe range should be valid");
let err = client
.get_object_inner("bucket", "probe", &opts)
.await
.expect_err("response header stalls must be bounded");
assert_eq!(err.kind(), std::io::ErrorKind::TimedOut);
fixture.await.expect("fixture should join");
}
#[tokio::test]
async fn response_body_idle_stall_returns_timed_out() {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return,
Err(err) => panic!("test listener should bind: {err}"),
};
let endpoint = listener
.local_addr()
.expect("listener local address should be available")
.to_string();
let fixture = tokio::spawn(async move {
let (mut stream, _) = listener.accept().await.expect("fixture should accept one GET");
let mut request = Vec::new();
let mut buffer = [0; 1024];
loop {
let read = stream.read(&mut buffer).await.expect("fixture should read request headers");
assert_ne!(read, 0, "connection closed before request headers were received");
request.extend_from_slice(&buffer[..read]);
if request.windows(4).any(|window| window == b"\r\n\r\n") {
break;
}
}
stream
.write_all(b"HTTP/1.1 206 Partial Content\r\nContent-Length: 7\r\nConnection: close\r\n\r\nRu")
.await
.expect("fixture should write the first body chunk");
tokio::time::sleep(Duration::from_millis(200)).await;
});
let client = client_for_endpoint(
&endpoint,
TransitionClientTimeouts::new(Duration::from_secs(1), Duration::from_secs(1), Duration::from_millis(50)),
)
.await;
let mut opts = GetObjectOptions::default();
opts.set_range(0, 6).expect("the probe range should be valid");
let err = client
.get_object_inner("bucket", "probe", &opts)
.await
.expect_err("body stalls after partial progress must be bounded");
assert_eq!(err.kind(), std::io::ErrorKind::TimedOut);
fixture.await.expect("fixture should join");
}
#[tokio::test]
async fn response_body_idle_timer_resets_on_progress() {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return,
Err(err) => panic!("test listener should bind: {err}"),
};
let endpoint = listener
.local_addr()
.expect("listener local address should be available")
.to_string();
let fixture = tokio::spawn(async move {
let (mut stream, _) = listener.accept().await.expect("fixture should accept one GET");
let mut request = Vec::new();
let mut buffer = [0; 1024];
loop {
let read = stream.read(&mut buffer).await.expect("fixture should read request headers");
assert_ne!(read, 0, "connection closed before request headers were received");
request.extend_from_slice(&buffer[..read]);
if request.windows(4).any(|window| window == b"\r\n\r\n") {
break;
}
}
stream
.write_all(b"HTTP/1.1 206 Partial Content\r\nContent-Length: 7\r\nConnection: close\r\n\r\n")
.await
.expect("fixture should write response headers");
for byte in b"RustFS!" {
stream.write_all(&[*byte]).await.expect("fixture should write body progress");
tokio::time::sleep(Duration::from_millis(20)).await;
}
});
let client = client_for_endpoint(
&endpoint,
TransitionClientTimeouts::new(Duration::from_millis(10), Duration::from_secs(1), Duration::from_millis(100)),
)
.await;
let mut opts = GetObjectOptions::default();
opts.set_range(0, 6).expect("the probe range should be valid");
let (_, _, mut reader) = client
.get_object_inner("bucket", "probe", &opts)
.await
.expect("continuous body progress must not be killed by the idle timer");
let mut body = Vec::new();
reader
.read_to_end(&mut body)
.await
.expect("bounded response should be readable");
assert_eq!(body, b"RustFS!");
fixture.await.expect("fixture should join");
}
}
#[derive(Default)]
+10 -82
View File
@@ -27,6 +27,7 @@ use crate::{
transition_api::{ReaderImpl, RequestMetadata, TransitionClient, collect_response_body},
};
use http::{HeaderMap, StatusCode};
use http_body_util::BodyExt;
use hyper::body::Body;
use hyper::body::Bytes;
use rustfs_config::MAX_S3_CLIENT_RESPONSE_SIZE;
@@ -123,9 +124,14 @@ impl TransitionClient {
}
//let mut list_bucket_result = ListBucketV2Result::default();
let body_vec = self
.collect_response_body(resp.into_body(), MAX_S3_CLIENT_RESPONSE_SIZE)
.await?;
let mut body_vec = Vec::new();
let mut body = resp.into_body();
while let Some(frame) = body.frame().await {
let frame = frame.map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e.to_string()))?;
if let Some(data) = frame.data_ref() {
body_vec.extend_from_slice(data);
}
}
let mut list_bucket_result = match quick_xml::de::from_str::<ListBucketV2Result>(&String::from_utf8_lossy(&body_vec)) {
Ok(result) => result,
Err(err) => {
@@ -208,9 +214,7 @@ impl TransitionClient {
let resp_status = resp.status();
let headers = resp.headers().clone();
let body = self
.collect_response_body(resp.into_body(), MAX_S3_CLIENT_RESPONSE_SIZE)
.await?;
let body = collect_response_body(resp.into_body(), MAX_S3_CLIENT_RESPONSE_SIZE).await?;
if resp_status != StatusCode::OK {
return Err(std::io::Error::other(http_resp_to_error_response(
resp_status,
@@ -424,30 +428,6 @@ fn decode_s3_name(name: &str, encoding_type: &str) -> Result<String, std::io::Er
#[cfg(test)]
mod tests {
use super::*;
use crate::{
credentials::{Credentials, SignatureType, Static, Value},
transition_api::{BucketLookupType, Options, TransitionClientTimeouts},
};
use std::time::Duration;
use tokio::{
io::{AsyncReadExt, AsyncWriteExt},
net::TcpListener,
};
fn timeout_test_options() -> Options {
Options {
creds: Credentials::new(Static(Value {
access_key_id: "access-key".to_string(),
secret_access_key: "secret-key".to_string(),
signer_type: SignatureType::SignatureV4,
..Default::default()
})),
region: "us-east-1".to_string(),
bucket_lookup: BucketLookupType::BucketLookupPath,
max_retries: 1,
..Default::default()
}
}
#[test]
fn list_versions_xml_preserves_versions_and_delete_markers() {
@@ -545,56 +525,4 @@ mod tests {
assert_eq!(parsed.common_prefixes.len(), 1);
assert_eq!(parsed.common_prefixes[0].prefix, "subdir/");
}
#[tokio::test]
async fn list_objects_v2_body_stall_returns_timed_out() {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return,
Err(err) => panic!("test listener should bind: {err}"),
};
let endpoint = listener
.local_addr()
.expect("listener local address should be available")
.to_string();
let fixture = tokio::spawn(async move {
let (mut stream, _) = listener.accept().await.expect("fixture should accept one list request");
let mut request = Vec::new();
let mut buffer = [0; 1024];
loop {
let read = stream.read(&mut buffer).await.expect("fixture should read request headers");
assert_ne!(read, 0, "connection closed before request headers were received");
request.extend_from_slice(&buffer[..read]);
if request.windows(4).any(|window| window == b"\r\n\r\n") {
break;
}
}
stream
.write_all(b"HTTP/1.1 200 OK\r\nContent-Length: 512\r\nConnection: close\r\n\r\n<ListBucketResult><Name>warm")
.await
.expect("fixture should write a partial list response");
tokio::time::sleep(Duration::from_millis(200)).await;
});
let client = TransitionClient::new_with_timeouts(
&endpoint,
timeout_test_options(),
"",
TransitionClientTimeouts::new(Duration::from_secs(1), Duration::from_secs(1), Duration::from_millis(50)),
)
.await
.expect("fixture client should build");
client
.bucket_loc_cache
.lock()
.expect("location cache should lock")
.set("bucket", "us-east-1");
let err = client
.list_objects_v2_query("bucket", "", "", false, false, "", "", 1, HeaderMap::new())
.await
.expect_err("a stalled ListObjectsV2 body must be bounded");
assert_eq!(err.kind(), std::io::ErrorKind::TimedOut);
fixture.await.expect("fixture should join");
}
}
@@ -18,6 +18,7 @@
#![allow(clippy::all)]
use http::{HeaderMap, HeaderName, StatusCode};
use http_body_util::BodyExt;
use hyper::body::Bytes;
use s3s::S3ErrorCode;
use std::collections::HashMap;
@@ -246,9 +247,14 @@ impl TransitionClient {
// Parse the CreateMultipartUpload response for the UploadId. Returning a
// default (empty) result here made every multipart transition fail at the
// first UploadPart with "UploadID cannot be empty" (rustfs/rustfs#4811).
let body_vec = self
.collect_response_body(resp.into_body(), rustfs_config::MAX_S3_CLIENT_RESPONSE_SIZE)
.await?;
let mut body_vec = Vec::new();
let mut body = resp.into_body();
while let Some(frame) = body.frame().await {
let frame = frame.map_err(|e| std::io::Error::other(e.to_string()))?;
if let Some(data) = frame.data_ref() {
body_vec.extend_from_slice(data);
}
}
let initiate_multipart_upload_result =
quick_xml::de::from_str::<InitiateMultipartUploadResult>(&String::from_utf8_lossy(&body_vec))
.map_err(|e| std::io::Error::other(format!("failed to parse CreateMultipartUpload response: {e}")))?;
+9 -3
View File
@@ -19,6 +19,7 @@
#![allow(clippy::all)]
use http::{HeaderMap, HeaderValue, Method, StatusCode};
use http_body_util::BodyExt;
use hyper::body::Body;
use hyper::body::Bytes;
use rustfs_utils::HashAlgorithm;
@@ -350,9 +351,14 @@ impl TransitionClient {
)
.await?;
let body_vec = self
.collect_response_body(resp.into_body(), rustfs_config::MAX_S3_CLIENT_RESPONSE_SIZE)
.await?;
let mut body_vec = Vec::new();
let mut body = resp.into_body();
while let Some(frame) = body.frame().await {
let frame = frame.map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e.to_string()))?;
if let Some(data) = frame.data_ref() {
body_vec.extend_from_slice(data);
}
}
process_remove_multi_objects_response(
ReaderImpl::Body(Bytes::from(body_vec)),
bucket_name,
+11 -72
View File
@@ -19,6 +19,7 @@
#![allow(clippy::all)]
use http::{HeaderMap, HeaderValue, StatusCode};
use http_body_util::BodyExt;
use hyper::body::Body;
use hyper::body::Bytes;
use rustfs_utils::EMPTY_STRING_SHA256_HASH;
@@ -118,9 +119,14 @@ impl TransitionClient {
let resp_status = resp.status();
let h = resp.headers().clone();
let body_vec = self
.collect_response_body(resp.into_body(), rustfs_config::MAX_S3_CLIENT_RESPONSE_SIZE)
.await?;
let mut body_vec = Vec::new();
let mut body = resp.into_body();
while let Some(frame) = body.frame().await {
let frame = frame.map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e.to_string()))?;
if let Some(data) = frame.data_ref() {
body_vec.extend_from_slice(data);
}
}
let resperr = http_resp_to_error_response(resp_status, &h, body_vec, bucket_name, "");
warn!("bucket exists, resperr: {:?}", resperr);
@@ -164,13 +170,11 @@ impl TransitionClient {
let resp_status = resp.status();
let h = resp.headers().clone();
let body_vec = self
.collect_response_body(resp.into_body(), rustfs_config::MAX_S3_CLIENT_RESPONSE_SIZE)
.await?;
let body_vec = collect_response_body(resp.into_body(), rustfs_config::MAX_S3_CLIENT_RESPONSE_SIZE).await?;
parse_bucket_versioning_response(resp_status, &h, body_vec, bucket_name)
}
Err(err) => Err(err),
Err(err) => Err(std::io::Error::other(err)),
}
}
@@ -270,14 +274,8 @@ impl TransitionClient {
#[cfg(test)]
mod tests {
use super::parse_bucket_versioning_response;
use crate::{
credentials::{Credentials, SignatureType, Static, Value},
transition_api::{BucketLookupType, Options, TransitionClient, TransitionClientTimeouts},
};
use http::{HeaderMap, StatusCode};
use s3s::dto::BucketVersioningStatus;
use std::time::Duration;
use tokio::{io::AsyncReadExt, net::TcpListener};
#[test]
fn parses_bucket_versioning_statuses_mfa_delete_and_unversioned_state() {
@@ -340,63 +338,4 @@ mod tests {
assert_eq!(strict_err.kind(), std::io::ErrorKind::InvalidData);
}
}
#[tokio::test]
async fn get_bucket_versioning_preserves_request_timeout_kind() {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return,
Err(err) => panic!("test listener should bind: {err}"),
};
let endpoint = listener
.local_addr()
.expect("listener local address should be available")
.to_string();
let fixture = tokio::spawn(async move {
let (mut stream, _) = listener.accept().await.expect("fixture should accept one versioning request");
let mut request = Vec::new();
let mut buffer = [0; 1024];
loop {
let read = stream.read(&mut buffer).await.expect("fixture should read request headers");
assert_ne!(read, 0, "connection closed before request headers were received");
request.extend_from_slice(&buffer[..read]);
if request.windows(4).any(|window| window == b"\r\n\r\n") {
break;
}
}
tokio::time::sleep(Duration::from_millis(200)).await;
});
let client = TransitionClient::new_with_timeouts(
&endpoint,
Options {
creds: Credentials::new(Static(Value {
access_key_id: "access-key".to_string(),
secret_access_key: "secret-key".to_string(),
signer_type: SignatureType::SignatureV4,
..Default::default()
})),
region: "us-east-1".to_string(),
bucket_lookup: BucketLookupType::BucketLookupPath,
max_retries: 1,
..Default::default()
},
"",
TransitionClientTimeouts::new(Duration::from_secs(1), Duration::from_millis(50), Duration::from_secs(1)),
)
.await
.expect("fixture client should build");
client
.bucket_loc_cache
.lock()
.expect("location cache should lock")
.set("bucket", "us-east-1");
let err = client
.get_bucket_versioning("bucket")
.await
.expect_err("a stalled versioning request must time out");
assert_eq!(err.kind(), std::io::ErrorKind::TimedOut);
fixture.await.expect("fixture should join");
}
}
+10 -5
View File
@@ -26,6 +26,7 @@ use crate::{
transition_api::{CreateBucketConfiguration, LocationConstraint, TransitionClient},
};
use http::Request;
use http_body_util::BodyExt;
use hyper::StatusCode;
use hyper::body::Body;
use hyper::body::Bytes;
@@ -85,7 +86,7 @@ impl TransitionClient {
let req = self.get_bucket_location_request(bucket_name)?;
let mut resp = self.doit(req).await?;
location = process_bucket_location_response(self, resp, bucket_name, &self.tier_type).await?;
location = process_bucket_location_response(resp, bucket_name, &self.tier_type).await?;
{
if let Ok(mut bucket_loc_cache) = self.bucket_loc_cache.lock() {
bucket_loc_cache.set(bucket_name, &location);
@@ -197,7 +198,6 @@ impl TransitionClient {
}
async fn process_bucket_location_response(
client: &TransitionClient,
mut resp: http::Response<Incoming>,
bucket_name: &str,
tier_type: &str,
@@ -237,9 +237,14 @@ async fn process_bucket_location_response(
}
//}
let body_vec = client
.collect_response_body(resp.into_body(), MAX_S3_CLIENT_RESPONSE_SIZE)
.await?;
let mut body_vec = Vec::new();
let mut body = resp.into_body();
while let Some(frame) = body.frame().await {
let frame = frame.map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e.to_string()))?;
if let Some(data) = frame.data_ref() {
body_vec.extend_from_slice(data);
}
}
let mut location = "".to_string();
if tier_type == "huaweicloud" {
if let Ok(body_str) = String::from_utf8(body_vec) {
+41 -328
View File
@@ -41,7 +41,7 @@ use http::{
request::{Builder, Request},
};
use http_body::Body;
use http_body_util::BodyExt;
use http_body_util::{BodyExt, LengthLimitError, Limited};
use hyper::body::Bytes;
use hyper::body::Incoming;
use hyper_rustls::{ConfigBuilderExt, HttpsConnector};
@@ -67,12 +67,10 @@ use s3s::dto::Owner;
use s3s::dto::ReplicationStatus;
use serde::{Deserialize, Serialize};
use sha2::Sha256;
use std::error::Error as StdError;
use std::io::Cursor;
use std::pin::Pin;
use std::sync::atomic::{AtomicI32, Ordering};
use std::task::{Context, Poll};
use std::time::Duration as StdDuration;
use std::{
collections::HashMap,
sync::{Arc, Mutex},
@@ -81,108 +79,28 @@ use time::Duration;
use time::OffsetDateTime;
use tokio::io::BufReader;
use tokio::io::{AsyncRead, AsyncReadExt};
use tracing::{debug, error, trace, warn};
use tracing::{debug, error, warn};
use url::{Url, form_urlencoded};
use uuid::Uuid;
const C_USER_AGENT: &str = "RustFS (linux; x86)";
pub const MAX_S3_ERROR_RESPONSE_SIZE: usize = 64 * 1024;
const EVENT_TIER_REMOTE_TRANSPORT: &str = "tier_remote_transport";
const LOG_COMPONENT_S3_CLIENT: &str = "s3_client";
const LOG_SUBSYSTEM_TIER: &str = "tier";
const SUCCESS_STATUS: [StatusCode; 3] = [StatusCode::OK, StatusCode::NO_CONTENT, StatusCode::PARTIAL_CONTENT];
fn response_body_exceeds_limit_error() -> std::io::Error {
std::io::Error::new(std::io::ErrorKind::InvalidData, "remote tier response body exceeds limit")
}
fn remote_tier_timeout_error(message: &'static str) -> std::io::Error {
std::io::Error::new(std::io::ErrorKind::TimedOut, message)
}
fn source_chain_has_io_kind(error: &(dyn StdError + 'static), kind: std::io::ErrorKind) -> bool {
let mut current = Some(error);
while let Some(error) = current {
if error
.downcast_ref::<std::io::Error>()
.is_some_and(|io_error| io_error.kind() == kind)
{
return true;
}
current = error.source();
}
false
}
fn transition_transport_error(err: hyper_util::client::legacy::Error) -> std::io::Error {
if source_chain_has_io_kind(&err, std::io::ErrorKind::TimedOut) {
return remote_tier_timeout_error("remote tier connection timed out");
}
std::io::Error::other(err)
}
async fn next_response_body_data<B>(
mut body: Pin<&mut B>,
idle_timeout: Option<StdDuration>,
) -> Result<Option<Bytes>, std::io::Error>
where
B: Body<Data = Bytes>,
B::Error: Into<Box<dyn StdError + Send + Sync>>,
{
let next_nonempty_data = async {
loop {
let Some(frame) = std::future::poll_fn(|cx| body.as_mut().poll_frame(cx)).await else {
return Ok(None);
};
let frame = frame.map_err(std::io::Error::other)?;
let Ok(data) = frame.into_data() else {
continue;
};
if !data.is_empty() {
return Ok(Some(data));
}
}
};
if let Some(idle_timeout) = idle_timeout {
tokio::time::timeout(idle_timeout, next_nonempty_data)
.await
.map_err(|_| remote_tier_timeout_error("remote tier response body stalled"))?
} else {
next_nonempty_data.await
}
}
async fn collect_response_body_inner<B>(
body: B,
limit: Option<usize>,
idle_timeout: Option<StdDuration>,
) -> Result<Vec<u8>, std::io::Error>
where
B: Body<Data = Bytes>,
B::Error: Into<Box<dyn StdError + Send + Sync>>,
{
let mut body_vec = Vec::new();
let mut body = std::pin::pin!(body);
while let Some(data) = next_response_body_data(body.as_mut(), idle_timeout).await? {
let Some(new_len) = body_vec.len().checked_add(data.len()) else {
return Err(response_body_exceeds_limit_error());
};
if limit.is_some_and(|limit| new_len > limit) {
return Err(response_body_exceeds_limit_error());
}
body_vec.extend_from_slice(&data);
}
Ok(body_vec)
}
pub async fn collect_response_body<B>(body: B, limit: usize) -> Result<Vec<u8>, std::io::Error>
where
B: Body<Data = Bytes>,
B::Error: Into<Box<dyn StdError + Send + Sync>>,
B::Error: Into<Box<dyn std::error::Error + Send + Sync>>,
{
collect_response_body_inner(body, Some(limit), None).await
let body = Limited::new(body, limit).collect().await.map_err(|err| {
if err.is::<LengthLimitError>() {
std::io::Error::new(std::io::ErrorKind::InvalidData, "remote tier response body exceeds limit")
} else {
std::io::Error::other(err)
}
})?;
Ok(body.to_bytes().to_vec())
}
const C_UNKNOWN: i32 = -1;
@@ -278,62 +196,6 @@ pub struct TransitionClient {
pub trailing_header_support: bool,
pub max_retries: i64,
pub tier_type: String,
pub timeouts: TransitionClientTimeouts,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct TransitionClientTimeouts {
pub connect_timeout: StdDuration,
pub request_timeout: StdDuration,
pub response_body_idle_timeout: StdDuration,
}
impl TransitionClientTimeouts {
pub const fn new(
connect_timeout: StdDuration,
request_timeout: StdDuration,
response_body_idle_timeout: StdDuration,
) -> Self {
Self {
connect_timeout,
request_timeout,
response_body_idle_timeout,
}
}
fn validate(self) -> Result<Self, std::io::Error> {
if self.connect_timeout.is_zero() {
return Err(std::io::Error::new(
std::io::ErrorKind::InvalidInput,
"remote tier connect timeout must be greater than zero",
));
}
if self.request_timeout.is_zero() {
return Err(std::io::Error::new(
std::io::ErrorKind::InvalidInput,
"remote tier request timeout must be greater than zero",
));
}
if self.response_body_idle_timeout.is_zero() {
return Err(std::io::Error::new(
std::io::ErrorKind::InvalidInput,
"remote tier response body idle timeout must be greater than zero",
));
}
Ok(self)
}
}
impl Default for TransitionClientTimeouts {
fn default() -> Self {
Self {
connect_timeout: StdDuration::from_secs(rustfs_config::DEFAULT_TIER_REMOTE_CONNECT_TIMEOUT_SECS),
request_timeout: StdDuration::from_secs(rustfs_config::DEFAULT_TIER_REMOTE_REQUEST_TIMEOUT_SECS),
response_body_idle_timeout: StdDuration::from_secs(
rustfs_config::DEFAULT_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS,
),
}
}
}
#[derive(Debug, Default)]
@@ -426,28 +288,12 @@ async fn build_tls_config() -> Result<rustls::ClientConfig, std::io::Error> {
impl TransitionClient {
pub async fn new(endpoint: &str, opts: Options, tier_type: &str) -> Result<TransitionClient, std::io::Error> {
Self::private_new(endpoint, opts, tier_type, TransitionClientTimeouts::default()).await
let client = Self::private_new(endpoint, opts, tier_type).await?;
Ok(client)
}
/// Builds a transition client with explicit transport timeout budgets.
///
/// [`Self::new`] keeps the historical constructor surface and uses the
/// production defaults from [`TransitionClientTimeouts::default`].
pub async fn new_with_timeouts(
endpoint: &str,
opts: Options,
tier_type: &str,
timeouts: TransitionClientTimeouts,
) -> Result<TransitionClient, std::io::Error> {
Self::private_new(endpoint, opts, tier_type, timeouts).await
}
async fn private_new(
endpoint: &str,
opts: Options,
tier_type: &str,
timeouts: TransitionClientTimeouts,
) -> Result<TransitionClient, std::io::Error> {
async fn private_new(endpoint: &str, opts: Options, tier_type: &str) -> Result<TransitionClient, std::io::Error> {
if rustls::crypto::CryptoProvider::get_default().is_none() {
// No default provider is set yet; try to install aws-lc-rs.
// `install_default` can only fail if another thread races us and installs a provider
@@ -460,19 +306,15 @@ impl TransitionClient {
}
let endpoint_url = get_endpoint_url(endpoint, opts.secure)?;
let timeouts = timeouts.validate()?;
let tls = build_tls_config().await?;
let mut http = HttpConnector::new();
http.enforce_http(false);
http.set_connect_timeout(Some(timeouts.connect_timeout));
let https = hyper_rustls::HttpsConnectorBuilder::new()
.with_tls_config(tls)
.https_or_http()
.enable_http1()
.enable_http2()
.wrap_connector(http);
.build();
let http_client = Client::builder(TokioExecutor::new()).build(https);
let mut client = TransitionClient {
@@ -495,7 +337,6 @@ impl TransitionClient {
trailing_header_support: opts.trailing_headers,
max_retries: opts.max_retries,
tier_type: tier_type.to_string(),
timeouts,
};
{
@@ -660,43 +501,29 @@ impl TransitionClient {
}
pub async fn doit(&self, req: Request<s3s::Body>) -> Result<Response<Incoming>, std::io::Error> {
let req_method;
let req_uri;
let resp;
let http_client = self.http_client.clone();
let req_method = req.method().clone();
let resp = tokio::time::timeout(self.timeouts.request_timeout, http_client.request(req)).await;
{
req_method = req.method().clone();
req_uri = req.uri().clone();
debug!("endpoint_url: {}", self.endpoint_url.as_str().to_string());
resp = http_client.request(req);
}
let resp = resp.await;
debug!("http_client url: {} {}", req_method, req_uri);
if let Err(err) = resp {
error!("http_client call error: {:?}", err);
return Err(std::io::Error::other(err));
}
let resp = match resp {
Ok(Ok(resp)) => resp,
Ok(Err(err)) => {
let err = transition_transport_error(err);
error!(
event = EVENT_TIER_REMOTE_TRANSPORT,
component = LOG_COMPONENT_S3_CLIENT,
subsystem = LOG_SUBSYSTEM_TIER,
method = %req_method,
error_kind = ?err.kind(),
"remote tier request failed"
);
return Err(err);
}
Err(_) => {
warn!(
event = EVENT_TIER_REMOTE_TRANSPORT,
component = LOG_COMPONENT_S3_CLIENT,
subsystem = LOG_SUBSYSTEM_TIER,
method = %req_method,
timeout_ms = self.timeouts.request_timeout.as_millis(),
"remote tier request timed out before response headers"
);
return Err(remote_tier_timeout_error("remote tier request timed out before response headers"));
}
Ok(r) => r,
Err(_) => return Err(std::io::Error::other("Unexpected error in response")),
};
trace!(
event = EVENT_TIER_REMOTE_TRANSPORT,
component = LOG_COMPONENT_S3_CLIENT,
subsystem = LOG_SUBSYSTEM_TIER,
method = %req_method,
status = %resp.status(),
"remote tier response received"
);
debug!(status = %resp.status(), "remote tier response received");
//let b = resp.body_mut().store_all_unlimited().await.unwrap().to_vec();
//debug!("http_resp_body: {}", String::from_utf8(b).unwrap());
@@ -710,15 +537,7 @@ impl TransitionClient {
.and_then(|value| value.to_str().ok())
.unwrap_or_default()
.to_string();
warn!(
event = EVENT_TIER_REMOTE_TRANSPORT,
component = LOG_COMPONENT_S3_CLIENT,
subsystem = LOG_SUBSYSTEM_TIER,
method = %req_method,
status = %status,
request_id,
"remote tier request rejected"
);
warn!(status = %status, request_id, "remote tier request rejected");
}
Ok(resp)
}
@@ -762,9 +581,7 @@ impl TransitionClient {
let resp_status = resp.status();
let h = resp.headers().clone();
let body_vec = self
.collect_response_body(resp.into_body(), MAX_S3_ERROR_RESPONSE_SIZE)
.await?;
let body_vec = collect_response_body(resp.into_body(), MAX_S3_ERROR_RESPONSE_SIZE).await?;
let parsed_error =
http_resp_to_error_response(resp_status, &h, body_vec, &metadata.bucket_name, &metadata.object_name);
let routing_region = parsed_error.region;
@@ -818,22 +635,6 @@ impl TransitionClient {
Err(std::io::Error::other("remote tier request did not produce a response"))
}
pub async fn collect_response_body<B>(&self, body: B, limit: usize) -> Result<Vec<u8>, std::io::Error>
where
B: Body<Data = Bytes>,
B::Error: Into<Box<dyn StdError + Send + Sync>>,
{
collect_response_body_inner(body, Some(limit), Some(self.timeouts.response_body_idle_timeout)).await
}
pub async fn collect_response_body_unbounded<B>(&self, body: B) -> Result<Vec<u8>, std::io::Error>
where
B: Body<Data = Bytes>,
B::Error: Into<Box<dyn StdError + Send + Sync>>,
{
collect_response_body_inner(body, None, Some(self.timeouts.response_body_idle_timeout)).await
}
async fn new_request(
&self,
method: &http::Method,
@@ -1703,17 +1504,12 @@ pub struct CreateBucketConfiguration {
mod tests {
use super::{
MAX_S3_CLIENT_RESPONSE_SIZE, MAX_S3_ERROR_RESPONSE_SIZE, SignatureType, build_tls_config, collect_response_body,
collect_response_body_inner, signer_error_to_io_error, to_object_info_for_provider, validate_header_values,
with_rustls_init_guard,
signer_error_to_io_error, to_object_info_for_provider, validate_header_values, with_rustls_init_guard,
};
use crate::provider_versions::{BucketVersioningState, ProviderVersionCapabilities, RemoteVersion};
use futures::stream;
use http::{HeaderMap, HeaderValue, Request};
use http_body::Frame;
use http_body_util::{Full, StreamBody};
use http::{HeaderMap, HeaderValue};
use http_body_util::Full;
use hyper::body::Bytes;
use std::time::Duration as StdDuration;
use tokio::net::TcpListener;
use uuid::Uuid;
#[tokio::test]
@@ -1744,77 +1540,6 @@ mod tests {
assert_eq!(err.kind(), std::io::ErrorKind::InvalidData);
}
#[tokio::test]
async fn empty_data_frames_do_not_reset_the_body_idle_timeout() {
let frames = stream::unfold((), |_| async {
tokio::time::sleep(StdDuration::from_millis(10)).await;
Some((Ok::<_, std::io::Error>(Frame::data(Bytes::new())), ()))
});
let body = StreamBody::new(Box::pin(frames));
let err = tokio::time::timeout(
StdDuration::from_millis(200),
collect_response_body_inner(body, Some(1), Some(StdDuration::from_millis(50))),
)
.await
.expect("the collector should enforce its own body idle timeout")
.expect_err("empty frames must not count as body progress");
assert_eq!(err.kind(), std::io::ErrorKind::TimedOut);
}
#[tokio::test]
async fn public_body_collector_accepts_non_unpin_bodies() {
let body = StreamBody::new(stream::once(async { Ok::<_, std::io::Error>(Frame::data(Bytes::from_static(b"ok"))) }));
let collected = collect_response_body(body, 2)
.await
.expect("the public collector should pin non-Unpin bodies internally");
assert_eq!(collected, b"ok");
}
#[tokio::test]
async fn https_endpoints_reach_the_transport_connector() {
let listener = match TcpListener::bind("127.0.0.1:0").await {
Ok(listener) => listener,
Err(err) if err.kind() == std::io::ErrorKind::PermissionDenied => return,
Err(err) => panic!("test listener should bind: {err}"),
};
let endpoint = listener
.local_addr()
.expect("listener local address should be available")
.to_string();
let accepted = tokio::spawn(async move {
let (stream, _) = tokio::time::timeout(StdDuration::from_secs(1), listener.accept())
.await
.expect("HTTPS connector should reach the TCP listener")
.expect("fixture should accept the HTTPS connection");
drop(stream);
});
let client = super::TransitionClient::new_with_timeouts(
&endpoint,
super::Options {
secure: true,
..Default::default()
},
"",
super::TransitionClientTimeouts::new(StdDuration::from_secs(1), StdDuration::from_secs(1), StdDuration::from_secs(1)),
)
.await
.expect("fixture client should build");
let request = Request::builder()
.uri(format!("https://{endpoint}/"))
.body(s3s::Body::empty())
.expect("fixture request should build");
client
.doit(request)
.await
.expect_err("the fixture closes before completing the TLS handshake");
accepted.await.expect("fixture should join");
}
#[test]
fn rustls_guard_converts_panics_to_io_errors() {
let err = with_rustls_init_guard(|| -> Result<(), std::io::Error> { panic!("missing provider") })
@@ -1848,18 +1573,6 @@ mod tests {
assert!(outcome.is_ok(), "provider install guard must not panic when a provider is already set");
}
#[test]
fn transition_timeouts_reject_zero_budgets() {
for timeouts in [
super::TransitionClientTimeouts::new(StdDuration::ZERO, StdDuration::from_secs(1), StdDuration::from_secs(1)),
super::TransitionClientTimeouts::new(StdDuration::from_secs(1), StdDuration::ZERO, StdDuration::from_secs(1)),
super::TransitionClientTimeouts::new(StdDuration::from_secs(1), StdDuration::from_secs(1), StdDuration::ZERO),
] {
let err = timeouts.validate().expect_err("zero timeout budgets must fail closed");
assert_eq!(err.kind(), std::io::ErrorKind::InvalidInput);
}
}
#[test]
fn validate_header_values_returns_header_name_for_non_utf8_values() {
let mut headers = HeaderMap::new();
@@ -29,18 +29,6 @@
Both knobs are read by the RustFS process that owns the replication target, at client build time; restart the server after changing them.
### Remote tier transport timeouts
Remote tier S3-compatible clients use separate transport budgets. These settings do not change bucket or site replication clients.
| Variable | Default | Meaning |
| --- | --- | --- |
| `RUSTFS_TIER_REMOTE_CONNECT_TIMEOUT_SECS` | `10` | Maximum time to establish the remote tier TCP connection. |
| `RUSTFS_TIER_REMOTE_REQUEST_TIMEOUT_SECS` | `86400` | Maximum time for a remote tier request to reach response headers. The long default preserves large transition-upload headroom. |
| `RUSTFS_TIER_REMOTE_RESPONSE_BODY_IDLE_TIMEOUT_SECS` | `60` | Maximum time without a non-empty response-body chunk. Empty HTTP/2 frames do not count as progress. |
All three values must be positive integers. Zero fails tier client initialization instead of silently disabling the boundary. An invalid integer is logged and falls back to the default; very large values are accepted and provide a correspondingly long effective budget. The values are read when the tier client is built; recreate or reload the tier configuration after changing them.
## Before changing any of this
Follow the SOP in `docs/postmortems/2026-09-03-replication-checksum-default-regression.md`: inventory the target-side rules the current default satisfies, run the outbound target matrix, and document any new knob here in the same PR.
+6
View File
@@ -91,6 +91,12 @@ Scheduled lanes never block a PR. Their workflow-local gate fails the run, sched
Manual `workflow_dispatch` runs are debugging evidence and do not open scheduled-failure issues. A manual performance run may explicitly allow a known regression; that override is not a passing baseline.
## Packaged functional acceptance
`rustfs-functional-chain.yml` dispatches the packaged-build suites in `rustfs-*-test.yml` on the shared lab runners. A failing suite step or job must fail its workflow. Report collection, cleanup, and dispatch of the next suite can still run with `always()`; continuing diagnostics does not make the failed suite successful.
Workflow status preserves errors that the test scripts report. It does not establish complete execution or a common package identity across the chain: inspect the current run's case results, package identity, and test-script revision as well. A script that returns zero after a failed tool invocation needs its own result check.
## Release validation
Post-merge and tag-driven; not a substitute for a PR gate.
+107 -14
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env python3
"""Run the security workflow's evidence and result steps without remote VMs."""
"""Exercise functional workflow failures and security evidence without remote VMs."""
from __future__ import annotations
@@ -18,16 +18,32 @@ WORKFLOW = ROOT / ".github/workflows/rustfs-security-test.yml"
CASE_ROW = "| IAM-101 | user CRUD lifecycle | PASS |"
def named_steps(job: list[str]) -> dict[str, list[str]]:
starts = [i for i, line in enumerate(job) if line.startswith(" - name: ")]
return {
job[start].split(": ", 1)[1].strip('"'): job[start:end]
for start, end in zip(starts, starts[1:] + [len(job)])
}
def shell_body(lines: list[str]) -> str:
start = lines.index(" run: |") + 1
shell_lines = []
for line in lines[start:]:
if line.strip() and not line.startswith(" "):
break
shell_lines.append(line[10:])
if not shell_lines:
raise ValueError("missing literal shell body")
return "\n".join(shell_lines)
class SecurityWorkflowTests(unittest.TestCase):
def setUp(self) -> None:
self.source = WORKFLOW.read_text()
self.job = yaml_block(self.source.splitlines(), "security-test", 2)
self.assertIsNotNone(self.job)
starts = [i for i, line in enumerate(self.job) if line.startswith(" - name: ")]
self.steps = {
self.job[start].split(": ", 1)[1].strip('"'): self.job[start:end]
for start, end in zip(starts, starts[1:] + [len(self.job)])
}
self.steps = named_steps(self.job)
self.temp = tempfile.TemporaryDirectory()
self.addCleanup(self.temp.cleanup)
self.directory = Path(self.temp.name)
@@ -83,15 +99,8 @@ class SecurityWorkflowTests(unittest.TestCase):
def run_step(self, name: str) -> subprocess.CompletedProcess[str]:
lines = self.steps[name]
start = lines.index(" run: |") + 1
shell_lines = []
for line in lines[start:]:
if line.strip() and not line.startswith(" "):
break
shell_lines.append(line[10:])
self.assertTrue(shell_lines, f"missing literal shell body: {name}")
result = subprocess.run(
["bash", "--noprofile", "--norc", "-e", "-o", "pipefail", "-c", self.render("\n".join(shell_lines))],
["bash", "--noprofile", "--norc", "-e", "-o", "pipefail", "-c", self.render(shell_body(lines))],
cwd=self.directory, env={**self.env, **self.step_env(lines)}, capture_output=True, text=True,
)
for line in lines:
@@ -193,5 +202,89 @@ class SecurityWorkflowTests(unittest.TestCase):
self.assertIn("https://github.com/rustfs/rustfs/actions/runs/314159", body.read_text())
class FunctionalWorkflowTests(unittest.TestCase):
JOBS = {
"kms": "kms-test", "storage": "storage-test", "s3-compat": "s3-compat-test",
"upgrade": "upgrade-test", "replication": "replication-test", "heal": "heal-test",
"tier": "tier-test", "pool-expand": "pool-expansion-test", "performance": "performance-test",
}
DIRECT_TESTS = {
"kms": "Run KMS suite", "storage": "Run storage engine suite",
"s3-compat": "Run S3 compatibility suite", "upgrade": "Run upgrade compatibility suite",
"replication": "Run replication suite",
}
def test_failure_and_always_step_wiring(self) -> None:
for suite, job_id in self.JOBS.items():
with self.subTest(suite=suite):
source = (ROOT / f".github/workflows/rustfs-{suite}-test.yml").read_text()
job = yaml_block(source.splitlines(), job_id, 2)
self.assertIsNotNone(job)
self.assertNotRegex("\n".join(job), r'''(?m)^ ["']?continue-on-error["']?\s*:''')
steps = named_steps(job)
if suite in self.DIRECT_TESTS:
test = steps[self.DIRECT_TESTS[suite]]
self.assertNotRegex("\n".join(test), r'''(?m)^ ["']?continue-on-error["']?\s*:''')
self.assertIn(" if: always()", steps["Generate report"])
cleanup = steps["Reset test environment (after)" if suite == "performance" else "Cleanup environment (after)"]
condition = next(line.strip() for line in cleanup if line.startswith(" if:"))
self.assertIn(condition, (
"if: always()",
"if: ${{ always() && inputs.cleanup_after != 'false' }}",
"if: ${{ always() && (inputs.cleanup_after != 'false' || github.event_name != 'workflow_dispatch') }}",
))
if suite != "performance":
handoff = steps["Chain complete"] if suite == "replication" else next(
value for name, value in steps.items() if name.startswith("Continue functional chain")
)
self.assertIn(" if: ${{ always() && github.event_name == 'repository_dispatch' }}", handoff)
def test_failed_suite_preserves_exit_and_cleanup_and_dispatch_execute(self) -> None:
for suite, test_name in self.DIRECT_TESTS.items():
with self.subTest(suite=suite), tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "auto-testing").mkdir()
script = root / f"auto-testing/rustfs-{suite}-test.sh"
script.write_text('#!/bin/sh\nprintf "partial suite diagnostics\\n"\nexit 17\n')
script.chmod(0o755)
fake_bin = root / "bin"
fake_bin.mkdir()
for command, marker in (("ssh", "cleanup"), ("gh", "dispatch")):
fake = fake_bin / command
fake.write_text(f'#!/bin/sh\nprintf "{marker}\\n" >> "$EXECUTED"\n')
fake.chmod(0o755)
env = {
**os.environ, "PATH": f"{fake_bin}{os.pathsep}{os.environ['PATH']}",
"EXECUTED": str(root / "executed"), "RUSTFS_NODES": "fixture-node",
"RUSTFS_SSH_USER": "fixture-user", "RUSTFS_NIGHTLY_PACKAGE_URL": "https://example.invalid/package.deb",
"GH_TOKEN": "local-fixture", "GITHUB_EVENT_NAME": "repository_dispatch", "GITHUB_RUN_ID": "314159",
}
source = (ROOT / f".github/workflows/rustfs-{suite}-test.yml").read_text()
steps = named_steps(yaml_block(source.splitlines(), self.JOBS[suite], 2))
context = {"github.event_name": "repository_dispatch", "steps.test.outcome": "failure"}
for expression in re.findall(r"\$\{\{\s*(.*?)\s*\}\}", source):
if expression.startswith("inputs.") and re.fullmatch(r"inputs\.\w+", expression):
context[expression] = ""
def execute(name):
lines = steps[name]
rendered = re.sub(r"\$\{\{\s*(.*?)\s*\}\}", lambda match: context[match[1]], shell_body(lines))
return subprocess.run(
["bash", "--noprofile", "--norc", "-e", "-o", "pipefail", "-c", rendered],
cwd=root, env={**env, "LOG_FILE": str(root / "suite.log")}, capture_output=True, text=True,
)
failed = execute(test_name)
self.assertEqual(failed.returncode, 17, failed.stderr)
self.assertIn("partial suite diagnostics", failed.stdout)
cleanup = execute("Cleanup environment (after)")
self.assertEqual(cleanup.returncode, 0, cleanup.stderr)
handoff_name = "Chain complete" if suite == "replication" else next(
name for name in steps if name.startswith("Continue functional chain")
)
handoff = execute(handoff_name)
self.assertEqual(handoff.returncode, 0, handoff.stderr)
markers = (root / "executed").read_text().splitlines()
self.assertEqual(markers, ["cleanup"] if suite == "replication" else ["cleanup", "dispatch"])
if __name__ == "__main__":
unittest.main()