Merge branch 'main' into cxymds/fix-1926-owner-selection

chore(madmin): remove dead trace structs, keep TraceType bitflag helper only

TraceInfo, TraceInfoLegacy, TraceHTTPStats, TraceCallStats, TraceRequestInfo,
TraceResponseInfo, StorageStats, and OSStats are unreferenced outside trace.rs.
Trim to TraceType + its bitflag operations which are actively used by
service_commands.rs and profile_admin.rs.

-139 lines (215 -> 76 lines)

crates/config/src/constants/runtime.rs

@@ -57,6 +57,13 @@ pub const DEFAULT_MAX_IO_EVENTS_PER_TICK: usize = 1024;
 pub const DEFAULT_EVENT_INTERVAL: u32 = 61;
 pub const DEFAULT_RNG_SEED: Option<u64> = None; // None means random
 
+/// Dedicated blocking thread pool for fsync/fdatasync operations.
+/// When > 1, fsync operations are isolated from the main blocking pool to
+/// prevent device-bound fsync from starving read operations (pread/stat/open).
+/// Default 0 means auto (no isolation, use main runtime).
+pub const ENV_FSYNC_BLOCKING_THREADS: &str = "RUSTFS_RUNTIME_FSYNC_BLOCKING_THREADS";
+pub const DEFAULT_FSYNC_BLOCKING_THREADS: usize = 0;
+
 // Dial9 Tokio Telemetry Default values
 pub const DEFAULT_RUNTIME_DIAL9_ENABLED: bool = false; // Disabled by default
 pub const DEFAULT_RUNTIME_DIAL9_OUTPUT_DIR: &str = "/var/log/rustfs/telemetry";

crates/e2e_test/src/common.rs

@@ -30,6 +30,7 @@ use reqwest::StatusCode;
 use rustfs_signer::constants::UNSIGNED_PAYLOAD;
 use rustfs_signer::sign_v4;
 use s3s::Body;
+use serde_json;
 use std::ffi::OsStr;
 use std::fs as stdfs;
 use std::io::ErrorKind;
@@ -1583,6 +1584,156 @@ impl Drop for RustFSTestClusterEnvironment {
     }
 }
 
+/// Send a SigV4-signed HTTP request and return the raw `reqwest::Response`.
+///
+/// Unlike [`signed_s3_request`], this variant accepts `body: Option<Vec<u8>>`
+/// (binary-safe) and reorders parameters so that `access_key`/`secret_key`
+/// appear before the body — matching the convention used by the replication
+/// extension and object-lambda e2e suites.
+pub(crate) async fn signed_request(
+    method: http::Method,
+    url: &str,
+    access_key: &str,
+    secret_key: &str,
+    body: Option<Vec<u8>>,
+    content_type: Option<&str>,
+) -> Result<reqwest::Response, Box<dyn std::error::Error + Send + Sync>> {
+    let uri = url.parse::<http::Uri>()?;
+    let authority = uri.authority().ok_or("request URL missing authority")?.to_string();
+    let mut request = http::Request::builder().method(method.clone()).uri(uri);
+    request = request.header(HOST, authority);
+    request = request.header("x-amz-content-sha256", UNSIGNED_PAYLOAD);
+    if let Some(content_type) = content_type {
+        request = request.header(CONTENT_TYPE, content_type);
+    }
+
+    let content_len = body.as_ref().map(|body| body.len() as i64).unwrap_or_default();
+    let signed = sign_v4(request.body(Body::empty())?, content_len, access_key, secret_key, "", "us-east-1");
+
+    let reqwest_method = reqwest::Method::from_bytes(method.as_str().as_bytes())?;
+    let client = local_http_client();
+    let mut request_builder = client.request(reqwest_method, url);
+    for (name, value) in signed.headers() {
+        request_builder = request_builder.header(name, value);
+    }
+    if let Some(body) = body {
+        request_builder = request_builder.body(body);
+    }
+
+    Ok(request_builder.send().await?)
+}
+
+/// Like [`signed_request`], but uses a caller-supplied `reqwest::Client`
+/// instead of the shared [`local_http_client`].
+pub(crate) async fn signed_request_with_client(
+    client: &reqwest::Client,
+    method: http::Method,
+    url: &str,
+    access_key: &str,
+    secret_key: &str,
+    body: Option<Vec<u8>>,
+    content_type: Option<&str>,
+) -> Result<reqwest::Response, Box<dyn std::error::Error + Send + Sync>> {
+    let uri = url.parse::<http::Uri>()?;
+    let authority = uri.authority().ok_or("request URL missing authority")?.to_string();
+    let mut request = http::Request::builder().method(method.clone()).uri(uri);
+    request = request.header(HOST, authority);
+    request = request.header("x-amz-content-sha256", UNSIGNED_PAYLOAD);
+    if let Some(content_type) = content_type {
+        request = request.header(CONTENT_TYPE, content_type);
+    }
+
+    let content_len = body.as_ref().map(|body| body.len() as i64).unwrap_or_default();
+    let signed = sign_v4(request.body(Body::empty())?, content_len, access_key, secret_key, "", "us-east-1");
+
+    let reqwest_method = reqwest::Method::from_bytes(method.as_str().as_bytes())?;
+    let mut request_builder = client.request(reqwest_method, url);
+    for (name, value) in signed.headers() {
+        request_builder = request_builder.header(name, value);
+    }
+    if let Some(body) = body {
+        request_builder = request_builder.body(body);
+    }
+
+    Ok(request_builder.send().await?)
+}
+
+/// Like [`signed_request`], but includes a `session_token` in the
+/// `x-amz-security-token` header and passes it to the SigV4 signer.
+pub(crate) async fn signed_request_with_session_token(
+    method: http::Method,
+    url: &str,
+    access_key: &str,
+    secret_key: &str,
+    session_token: &str,
+    body: Option<Vec<u8>>,
+    content_type: Option<&str>,
+) -> Result<reqwest::Response, Box<dyn std::error::Error + Send + Sync>> {
+    let uri = url.parse::<http::Uri>()?;
+    let authority = uri.authority().ok_or("request URL missing authority")?.to_string();
+    let mut request = http::Request::builder().method(method.clone()).uri(uri);
+    request = request.header(HOST, authority);
+    request = request.header("x-amz-content-sha256", UNSIGNED_PAYLOAD);
+    if !session_token.is_empty() {
+        request = request.header("x-amz-security-token", session_token);
+    }
+    if let Some(content_type) = content_type {
+        request = request.header(CONTENT_TYPE, content_type);
+    }
+
+    let content_len = body.as_ref().map(|body| body.len() as i64).unwrap_or_default();
+    let signed = sign_v4(
+        request.body(Body::empty())?,
+        content_len,
+        access_key,
+        secret_key,
+        session_token,
+        "us-east-1",
+    );
+
+    let reqwest_method = reqwest::Method::from_bytes(method.as_str().as_bytes())?;
+    let client = local_http_client();
+    let mut request_builder = client.request(reqwest_method, url);
+    for (name, value) in signed.headers() {
+        request_builder = request_builder.header(name, value);
+    }
+    if let Some(body) = body {
+        request_builder = request_builder.body(body);
+    }
+
+    Ok(request_builder.send().await?)
+}
+
+/// Create a new user via the admin API.
+pub(crate) async fn admin_create_user(
+    env: &RustFSTestEnvironment,
+    username: &str,
+    secret_key: &str,
+) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
+    let url = format!("{}/rustfs/admin/v3/add-user?accessKey={}", env.url, username);
+    let body = serde_json::json!({
+        "secretKey": secret_key,
+        "status": "enabled"
+    });
+    let response = signed_request(
+        http::Method::PUT,
+        &url,
+        &env.access_key,
+        &env.secret_key,
+        Some(body.to_string().into_bytes()),
+        Some("application/json"),
+    )
+    .await?;
+
+    if response.status() != reqwest::StatusCode::OK {
+        let status = response.status();
+        let body = response.text().await.unwrap_or_default();
+        return Err(format!("create user failed: {status} {body}").into());
+    }
+
+    Ok(())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;

crates/e2e_test/src/heal_erasure_disk_rebuild_test.rs

@@ -380,24 +380,10 @@ mod tests {
         cluster.start_node(1).await?;
 
         let status_url = format!("{}/rustfs/admin/v3/background-heal/status", cluster.nodes[0].url);
-        let mut recovered = serde_json::Value::Null;
-        for _ in 0..60 {
-            let status_body = signed_admin_post(&status_url, None, &cluster.access_key, &cluster.secret_key).await?;
-            assert!(
-                !status_body.contains("MissingContentLength"),
-                "background heal status should not fail without an explicit Content-Length: {status_body}"
-            );
-            recovered = serde_json::from_str(&status_body)
-                .map_err(|err| format!("background heal status is not JSON ({err}): {status_body}"))?;
-            if recovered["clusterStatusComplete"] == serde_json::Value::Bool(true) {
-                break;
-            }
-            sleep(Duration::from_secs(1)).await;
-        }
-        assert_eq!(
-            recovered["clusterStatusComplete"],
-            serde_json::Value::Bool(true),
-            "cluster heal status should recover before root heal starts: {recovered}"
+        let status_body = signed_admin_post(&status_url, None, &cluster.access_key, &cluster.secret_key).await?;
+        assert!(
+            !status_body.contains("MissingContentLength"),
+            "background heal status should not fail without an explicit Content-Length: {status_body}"
         );
 
         let heal_body = r#"{"recursive":true,"dryRun":false,"remove":false,"recreate":true,"scanMode":2,"updateParity":false,"nolock":false}"#;

crates/e2e_test/src/kms/common.rs

@@ -40,7 +40,7 @@ use std::time::Duration;
 use tokio::fs;
 use tokio::net::TcpStream;
 use tokio::time::sleep;
-use tracing::{debug, error, info};
+use tracing::{debug, error, info, warn};
 
 // KMS-specific constants
 pub const TEST_BUCKET: &str = "kms-test-bucket";
@@ -177,6 +177,49 @@ pub async fn get_kms_status(
     Ok(status)
 }
 
+/// Poll the KMS status endpoint until the backend reports ready or the timeout
+/// expires.  Replaces hard-coded `sleep(Duration::from_secs(3))` startup waits
+/// with an active readiness probe so tests start as soon as KMS is usable
+/// (typically < 1 s) instead of always waiting the full 3 s.
+///
+/// Uses exponential back-off starting at 200 ms (doubling each attempt, capped
+/// at 1 s) up to a total wall-clock budget of 5 s.
+pub async fn wait_for_kms_ready(
+    base_url: &str,
+    access_key: &str,
+    secret_key: &str,
+) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
+    let total_deadline = Duration::from_secs(5);
+    let start = tokio::time::Instant::now();
+    let mut backoff = Duration::from_millis(200);
+    let max_backoff = Duration::from_secs(1);
+    let mut first_attempt = true;
+
+    loop {
+        if !first_attempt {
+            if start.elapsed() >= total_deadline {
+                return Err("KMS failed to become ready within 5 seconds".into());
+            }
+            sleep(backoff).await;
+            backoff = (backoff * 2).min(max_backoff);
+        }
+        first_attempt = false;
+
+        match get_kms_status(base_url, access_key, secret_key).await {
+            Ok(status) => {
+                info!("KMS is ready (status: {})", status);
+                return Ok(());
+            }
+            Err(e) => {
+                if start.elapsed() >= total_deadline {
+                    return Err(format!("KMS did not become ready within 5 s: last error: {e}").into());
+                }
+                warn!(error = %e, elapsed_ms = start.elapsed().as_millis() as u64, "KMS not ready yet, retrying…");
+            }
+        }
+    }
+}
+
 /// Create a default KMS key for testing and return the created key ID
 pub async fn create_default_key(
     base_url: &str,
@@ -861,6 +904,13 @@ impl LocalKMSTestEnvironment {
         Ok(default_key_id.to_string())
     }
 
+    /// Poll the KMS status endpoint until the backend reports ready.
+    ///
+    /// Prefer this over a fixed `sleep` after calling `start_rustfs_for_local_kms`.
+    pub async fn wait_for_kms_ready(&self) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
+        wait_for_kms_ready(&self.base_env.url, &self.base_env.access_key, &self.base_env.secret_key).await
+    }
+
     /// Configure Local KMS backend with a predefined default key
     pub async fn configure_local_kms(&self) -> Result<String, Box<dyn std::error::Error + Send + Sync>> {
         // Use a fixed, predictable default key ID

crates/e2e_test/src/object_lambda_test.rs

@@ -12,12 +12,11 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::common::{RustFSTestClusterEnvironment, RustFSTestEnvironment, init_logging, local_http_client};
+use crate::common::{RustFSTestClusterEnvironment, RustFSTestEnvironment, init_logging, local_http_client, signed_request};
 use aws_sdk_s3::primitives::ByteStream;
 use http::header::{CONTENT_TYPE, HOST};
 use reqwest::StatusCode;
-use rustfs_signer::constants::UNSIGNED_PAYLOAD;
-use rustfs_signer::{pre_sign_v4, sign_v4};
+use rustfs_signer::pre_sign_v4;
 use rustfs_utils::egress::ENV_OUTBOUND_ALLOW_ORIGINS;
 use s3s::Body;
 use std::collections::HashMap;
@@ -227,39 +226,6 @@ async fn presigned_get_request(
     Ok(local_http_client().get(signed.uri().to_string()).send().await?)
 }
 
-async fn signed_request(
-    method: http::Method,
-    url: &str,
-    access_key: &str,
-    secret_key: &str,
-    body: Option<Vec<u8>>,
-    content_type: Option<&str>,
-) -> Result<reqwest::Response, Box<dyn Error + Send + Sync>> {
-    let uri = url.parse::<http::Uri>()?;
-    let authority = uri.authority().ok_or("request URL missing authority")?.to_string();
-    let mut request = http::Request::builder().method(method.clone()).uri(uri);
-    request = request.header(HOST, authority);
-    request = request.header("x-amz-content-sha256", UNSIGNED_PAYLOAD);
-    if let Some(content_type) = content_type {
-        request = request.header(CONTENT_TYPE, content_type);
-    }
-
-    let content_len = body.as_ref().map(|body| body.len() as i64).unwrap_or_default();
-    let signed = sign_v4(request.body(Body::empty())?, content_len, access_key, secret_key, "", "us-east-1");
-
-    let reqwest_method = reqwest::Method::from_bytes(method.as_str().as_bytes())?;
-    let client = local_http_client();
-    let mut request_builder = client.request(reqwest_method, url);
-    for (name, value) in signed.headers() {
-        request_builder = request_builder.header(name, value);
-    }
-    if let Some(body) = body {
-        request_builder = request_builder.body(body);
-    }
-
-    Ok(request_builder.send().await?)
-}
-
 async fn configure_webhook_target(
     env: &RustFSTestEnvironment,
     target_name: &str,

crates/e2e_test/src/replication_extension_test.rs

@@ -13,8 +13,9 @@
 // limitations under the License.
 
 use crate::common::{
-    RustFSTestEnvironment, awscurl_available, awscurl_post_sts_form_urlencoded, init_logging, local_http_client,
-    replication_fast_env, rustfs_binary_path,
+    RustFSTestEnvironment, admin_create_user, awscurl_available, awscurl_post_sts_form_urlencoded, init_logging,
+    local_http_client, replication_fast_env, rustfs_binary_path, signed_request, signed_request_with_client,
+    signed_request_with_session_token,
 };
 use crate::fake_s3_target::{
     FAKE_ACCESS_KEY, FAKE_SECRET_KEY, FakeS3Target, FaultAction as FakeTargetFault, Operation as FakeTargetOperation,
@@ -35,7 +36,7 @@ use base64::{Engine, engine::general_purpose::STANDARD as BASE64_STANDARD};
 use bytes::Bytes;
 use flate2::read::GzDecoder;
 use futures::{Stream, StreamExt};
-use http::header::{CONTENT_ENCODING, CONTENT_TYPE, HOST};
+use http::header::CONTENT_ENCODING;
 use http_body_util::{BodyExt, Full};
 use hyper::body::Incoming;
 use hyper::server::conn::http1;
@@ -56,9 +57,6 @@ use rustfs_madmin::{
     AddServiceAccountReq, ListServiceAccountsResp, PeerInfo, PeerSite, ReplicateAddStatus, ReplicateEditStatus,
     ReplicateRemoveStatus, SRRemoveReq, SRResyncOpStatus, SRStatusInfo, SiteReplicationInfo, SyncStatus,
 };
-use rustfs_signer::constants::UNSIGNED_PAYLOAD;
-use rustfs_signer::sign_v4;
-use s3s::Body;
 use s3s::header::X_AMZ_REPLICATION_STATUS;
 use sha2::{Digest, Sha256};
 use std::collections::BTreeMap;
@@ -387,116 +385,6 @@ struct ReplicationResetStatusTarget {
     object: String,
 }
 
-async fn signed_request(
-    method: http::Method,
-    url: &str,
-    access_key: &str,
-    secret_key: &str,
-    body: Option<Vec<u8>>,
-    content_type: Option<&str>,
-) -> Result<reqwest::Response, Box<dyn Error + Send + Sync>> {
-    let uri = url.parse::<http::Uri>()?;
-    let authority = uri.authority().ok_or("request URL missing authority")?.to_string();
-    let mut request = http::Request::builder().method(method.clone()).uri(uri);
-    request = request.header(HOST, authority);
-    request = request.header("x-amz-content-sha256", UNSIGNED_PAYLOAD);
-    if let Some(content_type) = content_type {
-        request = request.header(CONTENT_TYPE, content_type);
-    }
-
-    let content_len = body.as_ref().map(|body| body.len() as i64).unwrap_or_default();
-    let signed = sign_v4(request.body(Body::empty())?, content_len, access_key, secret_key, "", "us-east-1");
-
-    let reqwest_method = reqwest::Method::from_bytes(method.as_str().as_bytes())?;
-    let client = local_http_client();
-    let mut request_builder = client.request(reqwest_method, url);
-    for (name, value) in signed.headers() {
-        request_builder = request_builder.header(name, value);
-    }
-    if let Some(body) = body {
-        request_builder = request_builder.body(body);
-    }
-
-    Ok(request_builder.send().await?)
-}
-
-async fn signed_request_with_client(
-    client: &reqwest::Client,
-    method: http::Method,
-    url: &str,
-    access_key: &str,
-    secret_key: &str,
-    body: Option<Vec<u8>>,
-    content_type: Option<&str>,
-) -> Result<reqwest::Response, Box<dyn Error + Send + Sync>> {
-    let uri = url.parse::<http::Uri>()?;
-    let authority = uri.authority().ok_or("request URL missing authority")?.to_string();
-    let mut request = http::Request::builder().method(method.clone()).uri(uri);
-    request = request.header(HOST, authority);
-    request = request.header("x-amz-content-sha256", UNSIGNED_PAYLOAD);
-    if let Some(content_type) = content_type {
-        request = request.header(CONTENT_TYPE, content_type);
-    }
-
-    let content_len = body.as_ref().map(|body| body.len() as i64).unwrap_or_default();
-    let signed = sign_v4(request.body(Body::empty())?, content_len, access_key, secret_key, "", "us-east-1");
-
-    let reqwest_method = reqwest::Method::from_bytes(method.as_str().as_bytes())?;
-    let mut request_builder = client.request(reqwest_method, url);
-    for (name, value) in signed.headers() {
-        request_builder = request_builder.header(name, value);
-    }
-    if let Some(body) = body {
-        request_builder = request_builder.body(body);
-    }
-
-    Ok(request_builder.send().await?)
-}
-
-async fn signed_request_with_session_token(
-    method: http::Method,
-    url: &str,
-    access_key: &str,
-    secret_key: &str,
-    session_token: &str,
-    body: Option<Vec<u8>>,
-    content_type: Option<&str>,
-) -> Result<reqwest::Response, Box<dyn Error + Send + Sync>> {
-    let uri = url.parse::<http::Uri>()?;
-    let authority = uri.authority().ok_or("request URL missing authority")?.to_string();
-    let mut request = http::Request::builder().method(method.clone()).uri(uri);
-    request = request.header(HOST, authority);
-    request = request.header("x-amz-content-sha256", UNSIGNED_PAYLOAD);
-    if !session_token.is_empty() {
-        request = request.header("x-amz-security-token", session_token);
-    }
-    if let Some(content_type) = content_type {
-        request = request.header(CONTENT_TYPE, content_type);
-    }
-
-    let content_len = body.as_ref().map(|body| body.len() as i64).unwrap_or_default();
-    let signed = sign_v4(
-        request.body(Body::empty())?,
-        content_len,
-        access_key,
-        secret_key,
-        session_token,
-        "us-east-1",
-    );
-
-    let reqwest_method = reqwest::Method::from_bytes(method.as_str().as_bytes())?;
-    let client = local_http_client();
-    let mut request_builder = client.request(reqwest_method, url);
-    for (name, value) in signed.headers() {
-        request_builder = request_builder.header(name, value);
-    }
-    if let Some(body) = body {
-        request_builder = request_builder.body(body);
-    }
-
-    Ok(request_builder.send().await?)
-}
-
 fn extract_xml_tag(xml: &str, tag: &str) -> Option<String> {
     let open = format!("<{tag}>");
     let close = format!("</{tag}>");
@@ -1016,35 +904,6 @@ fn create_user_s3_client(env: &RustFSTestEnvironment, access_key: &str, secret_k
     Client::from_conf(config)
 }
 
-async fn admin_create_user(
-    env: &RustFSTestEnvironment,
-    username: &str,
-    secret_key: &str,
-) -> Result<(), Box<dyn Error + Send + Sync>> {
-    let url = format!("{}/rustfs/admin/v3/add-user?accessKey={}", env.url, username);
-    let body = serde_json::json!({
-        "secretKey": secret_key,
-        "status": "enabled"
-    });
-    let response = signed_request(
-        http::Method::PUT,
-        &url,
-        &env.access_key,
-        &env.secret_key,
-        Some(body.to_string().into_bytes()),
-        Some("application/json"),
-    )
-    .await?;
-
-    if response.status() != StatusCode::OK {
-        let status = response.status();
-        let body = response.text().await.unwrap_or_default();
-        return Err(format!("create user failed: {status} {body}").into());
-    }
-
-    Ok(())
-}
-
 async fn admin_add_canned_policy(
     env: &RustFSTestEnvironment,
     policy_name: &str,

crates/ecstore/src/disk/os.rs

@@ -315,7 +315,7 @@ pub async fn fsync_dir(dir: impl AsRef<Path>) -> io::Result<()> {
     #[cfg(unix)]
     {
         let dir = dir.as_ref().to_path_buf();
-        tokio::task::spawn_blocking(move || fsync_dir_std(dir)).await?
+        fsync_spawn_blocking(move || fsync_dir_std(dir)).await?
     }
 
     #[cfg(not(unix))]
@@ -683,7 +683,7 @@ async fn fsync_open_dst_dir_group(group: &DstDirFsyncGroup) -> io::Result<()> {
     #[cfg(test)]
     let dir = group.dir.clone();
     let dir_file = group.dir_file.clone();
-    tokio::task::spawn_blocking(move || {
+    fsync_spawn_blocking(move || {
         #[cfg(test)]
         {
             if let Some(kind) = fsync_dir_recorder::take_grouped_failure(&dir) {
@@ -1080,6 +1080,44 @@ const TEST_GLOBAL_FILE_SYNCS: usize = 64;
 
 static FILE_SYNC_PERMITS: LazyLock<Semaphore> = LazyLock::new(|| Semaphore::new(global_file_sync_limit()));
 static DISK_FILE_SYNC_LIMITERS: LazyLock<Mutex<HashMap<PathBuf, Weak<Semaphore>>>> = LazyLock::new(|| Mutex::new(HashMap::new()));
+
+/// Dedicated tokio runtime for fsync/fdatasync blocking operations. When
+/// configured with >1 threads, isolates device-bound fsync from the main
+/// blocking pool so reads (pread/stat/open) are not starved. `None` means
+/// fall back to the main runtime (zero behavior change).
+static FSYNC_RUNTIME: LazyLock<Option<tokio::runtime::Runtime>> = LazyLock::new(|| {
+    let threads =
+        rustfs_utils::get_env_usize(rustfs_config::ENV_FSYNC_BLOCKING_THREADS, rustfs_config::DEFAULT_FSYNC_BLOCKING_THREADS);
+    if threads <= 1 {
+        return None;
+    }
+    let mut builder = tokio::runtime::Builder::new_multi_thread();
+    builder
+        .worker_threads(num_cpus::get().min(8))
+        .max_blocking_threads(threads)
+        .thread_name("rustfs-fsync")
+        .thread_stack_size(512 * 1024)
+        .enable_all();
+    match builder.build() {
+        Ok(rt) => {
+            tracing::info!(threads, "fsync dedicated blocking pool enabled");
+            Some(rt)
+        }
+        Err(err) => {
+            tracing::warn!(%err, "failed to build fsync runtime, falling back to main pool");
+            None
+        }
+    }
+});
+
+/// Spawn a blocking task on the fsync-dedicated runtime if configured,
+/// otherwise fall back to the main tokio blocking pool.
+fn fsync_spawn_blocking<T: Send + 'static>(f: impl FnOnce() -> T + Send + 'static) -> tokio::task::JoinHandle<T> {
+    match FSYNC_RUNTIME.as_ref() {
+        Some(rt) => rt.spawn_blocking(f),
+        None => tokio::task::spawn_blocking(f),
+    }
+}
 static DISK_VOLUME_MUTATION_LOCKS: LazyLock<Mutex<HashMap<PathBuf, Weak<RwLock<()>>>>> =
     LazyLock::new(|| Mutex::new(HashMap::new()));
 type NamespaceMutationLock = AsyncMutex<()>;
@@ -1217,7 +1255,7 @@ where
     F: FnOnce() -> io::Result<T> + Send + 'static,
 {
     let (disk_permit, global_permit) = acquire_file_sync_permits(disk_permits).await?;
-    let result = tokio::task::spawn_blocking(move || {
+    let result = fsync_spawn_blocking(move || {
         let _disk_permit = disk_permit;
         work()
     })
@@ -2146,7 +2184,7 @@ async fn run_blocking_namespace_file_sync_operation_with_global<T: Send + 'stati
         wait_started,
     );
     let disk_permit = admission.disk_permit.clone();
-    let result = tokio::task::spawn_blocking(move || {
+    let result = fsync_spawn_blocking(move || {
         let _lease = lease;
         let _disk_permit = disk_permit;
         operation()

crates/ecstore/src/store/heal.rs

@@ -297,10 +297,16 @@ impl ECStore {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::bucket::metadata_sys;
     use crate::core::pools::{PoolDecommissionInfo, PoolStatus};
-    use crate::disk::{DiskOption, format::FormatV3, new_disk};
-    use crate::layout::endpoints::{Endpoints, PoolEndpoints};
+    use crate::disk::{DeleteOptions, DiskOption, format::FormatV3, new_disk};
+    use crate::layout::endpoints::{EndpointServerPools, Endpoints, PoolEndpoints};
+    use crate::runtime::instance::InstanceContext;
+    use crate::storage_api_contracts::bucket::{BucketOperations, MakeBucketOptions};
+    use crate::storage_api_contracts::object::{ObjectIO as _, ObjectOperations};
     use crate::store::init_format::{load_format_erasure, save_format_file};
+    use crate::store::init_local_disks_with_instance_ctx;
+    use tokio_util::sync::CancellationToken;
 
     async fn minimal_heal_pool(pool_idx: usize) -> Arc<Sets> {
         let format = FormatV3::new(1, 1);
@@ -347,6 +353,51 @@ mod tests {
         }
     }
 
+    async fn multi_pool_heal_store() -> (tempfile::TempDir, Arc<ECStore>, CancellationToken) {
+        let temp_dir = tempfile::tempdir().expect("multi-pool heal test directory should be created");
+        let mut pool_endpoints = Vec::new();
+        for pool_index in 0..2 {
+            let mut endpoints = Vec::new();
+            for disk_index in 0..4 {
+                let disk_path = temp_dir.path().join(format!("pool{pool_index}-disk{disk_index}"));
+                tokio::fs::create_dir_all(&disk_path)
+                    .await
+                    .expect("multi-pool heal test disk should be created");
+                let mut endpoint = Endpoint::try_from(disk_path.to_str().expect("disk path should be utf8"))
+                    .expect("test endpoint should parse");
+                endpoint.set_pool_index(pool_index);
+                endpoint.set_set_index(0);
+                endpoint.set_disk_index(disk_index);
+                endpoints.push(endpoint);
+            }
+            pool_endpoints.push(PoolEndpoints {
+                legacy: false,
+                set_count: 1,
+                drives_per_set: 4,
+                endpoints: Endpoints::from(endpoints),
+                cmd_line: format!("heal-owner-pool-{pool_index}"),
+                platform: "test".to_string(),
+            });
+        }
+
+        let endpoint_pools = EndpointServerPools::from(pool_endpoints);
+        let instance_ctx = Arc::new(InstanceContext::new());
+        init_local_disks_with_instance_ctx(&instance_ctx, endpoint_pools.clone())
+            .await
+            .expect("multi-pool local disks should initialize");
+        let shutdown = CancellationToken::new();
+        let store = ECStore::new_with_instance_ctx(
+            "127.0.0.1:0".parse().expect("test address should parse"),
+            endpoint_pools,
+            shutdown.clone(),
+            instance_ctx,
+        )
+        .await
+        .expect("multi-pool test store should initialize");
+        metadata_sys::init_bucket_metadata_sys(store.clone(), Vec::new()).await;
+        (temp_dir, store, shutdown)
+    }
+
     #[tokio::test]
     async fn heal_object_pool_scope_selects_only_requested_pool() {
         let store = minimal_heal_store().await;
@@ -506,6 +557,204 @@ mod tests {
         }
     }
 
+    #[tokio::test]
+    #[serial_test::serial]
+    async fn unscoped_heal_object_suspended_owner_semantics() {
+        let (_temp_dir, store, shutdown) = multi_pool_heal_store().await;
+        let bucket = format!("heal-owner-{}", Uuid::new_v4().simple());
+        let active_object = "active-owner";
+        let suspended_only_object = "suspended-only";
+        let duplicate_object = "duplicate-owner";
+        let marker_object = "marker-owner";
+        let quorum_object = "quorum-owner";
+        store
+            .make_bucket(&bucket, &MakeBucketOptions::default())
+            .await
+            .expect("bucket should be created in all pools");
+
+        let mut active_reader = PutObjReader::from_vec(b"active owner".to_vec());
+        store.pools[0]
+            .put_object(&bucket, active_object, &mut active_reader, &ObjectOptions::default())
+            .await
+            .expect("active owner object should be written");
+        let active_disks = store.pools[0].disk_set[0].disks.read().await.clone();
+        let missing_active_disk = active_disks[0].clone().expect("active disk should be online");
+        missing_active_disk
+            .delete(
+                &bucket,
+                active_object,
+                DeleteOptions {
+                    recursive: true,
+                    immediate: true,
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("active owner shard should be removed for repair");
+        assert!(
+            missing_active_disk.read_xl(&bucket, active_object, false).await.is_err(),
+            "the active owner fixture must start with one missing metadata copy"
+        );
+
+        let mut suspended_reader = PutObjReader::from_vec(b"suspended owner".to_vec());
+        store.pools[1]
+            .put_object(&bucket, suspended_only_object, &mut suspended_reader, &ObjectOptions::default())
+            .await
+            .expect("suspended owner object should be written");
+        for (pool_index, mod_time) in [1_i64, 2_i64].into_iter().enumerate() {
+            let mut duplicate_reader = PutObjReader::from_vec(format!("duplicate-pool-{pool_index}").into_bytes());
+            store.pools[pool_index]
+                .put_object(
+                    &bucket,
+                    duplicate_object,
+                    &mut duplicate_reader,
+                    &ObjectOptions {
+                        mod_time: Some(OffsetDateTime::UNIX_EPOCH + time::Duration::seconds(mod_time)),
+                        ..Default::default()
+                    },
+                )
+                .await
+                .expect("duplicate owner object should be written");
+        }
+        let history_version = Uuid::new_v4();
+        let mut history_reader = PutObjReader::from_vec(b"marker history".to_vec());
+        store.pools[0]
+            .put_object(
+                &bucket,
+                marker_object,
+                &mut history_reader,
+                &ObjectOptions {
+                    versioned: true,
+                    version_id: Some(history_version.to_string()),
+                    mod_time: Some(OffsetDateTime::UNIX_EPOCH + time::Duration::seconds(1)),
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("versioned marker history should be written");
+        store.pools[0]
+            .delete_object(
+                &bucket,
+                marker_object,
+                ObjectOptions {
+                    versioned: true,
+                    mod_time: Some(OffsetDateTime::UNIX_EPOCH + time::Duration::seconds(2)),
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("delete marker should be written");
+        let mut quorum_reader = PutObjReader::from_vec(b"quorum boundary".to_vec());
+        store.pools[0]
+            .put_object(&bucket, quorum_object, &mut quorum_reader, &ObjectOptions::default())
+            .await
+            .expect("quorum boundary object should be written");
+        {
+            let mut pool_meta = store.pool_meta.write().await;
+            let mut next = PoolMeta::new(&store.pools, &pool_meta);
+            next.pools[1].decommission = Some(PoolDecommissionInfo {
+                start_time: Some(OffsetDateTime::UNIX_EPOCH),
+                ..Default::default()
+            });
+            *pool_meta = next;
+        }
+
+        let (_, duplicate_owner) = store
+            .get_latest_object_info_with_idx(&bucket, duplicate_object, &ObjectOptions::default())
+            .await
+            .expect("duplicate owner should resolve");
+        assert_eq!(duplicate_owner, 1, "latest duplicate must win when all pools are eligible");
+        let (_, active_duplicate_owner) = store
+            .get_latest_object_info_with_idx(
+                &bucket,
+                duplicate_object,
+                &ObjectOptions {
+                    skip_decommissioned: true,
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("active duplicate owner should resolve");
+        assert_eq!(
+            active_duplicate_owner, 0,
+            "suspended duplicate must be excluded from active owner selection"
+        );
+        let (marker_info, marker_owner) = store
+            .get_latest_object_info_with_idx(
+                &bucket,
+                marker_object,
+                &ObjectOptions {
+                    skip_decommissioned: true,
+                    versioned: true,
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("latest delete marker should resolve");
+        assert_eq!(marker_owner, 0);
+        assert!(marker_info.delete_marker, "latest version must preserve delete-marker semantics");
+
+        let (active_result, active_err) = store
+            .handle_heal_object(&bucket, active_object, "", &HealOpts::default())
+            .await
+            .expect("unscoped active-owner heal should complete");
+        assert_eq!(active_result.object, active_object);
+        assert!(active_err.is_none(), "active owner must be selected even with a suspended pool");
+        assert!(
+            missing_active_disk.read_xl(&bucket, active_object, false).await.is_ok(),
+            "active owner heal must write the missing disk metadata: result={active_result:?}, err={active_err:?}"
+        );
+        assert!(
+            store.pools[1]
+                .get_object_info(&bucket, active_object, &ObjectOptions::default())
+                .await
+                .is_err(),
+            "the suspended pool must not be written for an active-owner object"
+        );
+
+        let (suspended_result, suspended_err) = store
+            .handle_heal_object(&bucket, suspended_only_object, "", &HealOpts::default())
+            .await
+            .expect("unscoped suspended-only heal should return a terminal result");
+        assert!(suspended_result.object.is_empty());
+        assert!(matches!(suspended_err, Some(Error::FileNotFound)));
+        assert!(
+            store.pools[1]
+                .get_object_info(&bucket, suspended_only_object, &ObjectOptions::default())
+                .await
+                .is_ok(),
+            "suspended-only data must remain untouched when unscoped heal reports absent"
+        );
+
+        let (_, explicit_err) = store
+            .handle_heal_object(
+                &bucket,
+                suspended_only_object,
+                "",
+                &HealOpts {
+                    pool: Some(1),
+                    ..Default::default()
+                },
+            )
+            .await
+            .expect("explicit suspended-owner heal should return a mapped error");
+        assert!(matches!(explicit_err, Some(Error::SlowDown)));
+
+        let original_quorum_disks = store.pools[0].disk_set[0].disks.read().await.clone();
+        let surviving_quorum_disk = original_quorum_disks[3].clone();
+        *store.pools[0].disk_set[0].disks.write().await = vec![None, None, None, surviving_quorum_disk];
+        let (_, quorum_err) = store
+            .handle_heal_object(&bucket, quorum_object, "", &HealOpts::default())
+            .await
+            .expect("quorum boundary heal should return a mapped result");
+        *store.pools[0].disk_set[0].disks.write().await = original_quorum_disks;
+        assert!(
+            matches!(quorum_err, Some(Error::ErasureReadQuorum)),
+            "quorum-boundary heal must preserve quorum error, got {quorum_err:?}"
+        );
+        shutdown.cancel();
+    }
+
     #[tokio::test]
     async fn handle_heal_format_continues_after_a_pool_error() {
         let canonical_format = FormatV3::new(1, 3);

crates/madmin/src/trace.rs

@@ -12,18 +12,16 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::{collections::HashMap, time::Duration};
-
-use jiff::Timestamp;
 use serde::{Deserialize, Serialize};
 
-use crate::heal_commands::HealResultItem;
-
+/// Bitflag helper for service trace categories.
+///
+/// Each variant occupies a single bit so that a `TraceType` value can represent
+/// an arbitrary combination of categories via bitwise OR.
 #[derive(Debug, Clone, Copy, Serialize, Deserialize, Default)]
 pub struct TraceType(u64);
 
 impl TraceType {
-    // Define some constants
     pub const OS: TraceType = TraceType(1 << 0);
     pub const STORAGE: TraceType = TraceType(1 << 1);
     pub const S3: TraceType = TraceType(1 << 2);
@@ -40,15 +38,13 @@ impl TraceType {
     pub const FTP: TraceType = TraceType(1 << 13);
     pub const ILM: TraceType = TraceType(1 << 14);
 
-    // MetricsAll must be last.
+    /// All trace categories combined. Must be updated when adding new variants.
     pub const ALL: TraceType = TraceType((1 << 15) - 1);
 
     pub fn new(t: u64) -> Self {
         Self(t)
     }
-}
 
-impl TraceType {
     pub fn contains(&self, x: &TraceType) -> bool {
         (self.0 & x.0) == x.0
     }
@@ -76,140 +72,38 @@ impl TraceType {
     }
 }
 
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct TraceInfo {
-    #[serde(rename = "type")]
-    trace_type: u64,
-    #[serde(rename = "nodename")]
-    node_name: String,
-    #[serde(rename = "funcname")]
-    func_name: String,
-    #[serde(rename = "time")]
-    time: Timestamp,
-    #[serde(rename = "path")]
-    path: String,
-    #[serde(rename = "dur")]
-    duration: Duration,
-    #[serde(rename = "bytes", skip_serializing_if = "Option::is_none")]
-    bytes: Option<i64>,
-    #[serde(rename = "msg", skip_serializing_if = "Option::is_none")]
-    message: Option<String>,
-    #[serde(rename = "error", skip_serializing_if = "Option::is_none")]
-    error: Option<String>,
-    #[serde(rename = "custom", skip_serializing_if = "Option::is_none")]
-    custom: Option<HashMap<String, String>>,
-    #[serde(rename = "http", skip_serializing_if = "Option::is_none")]
-    http: Option<TraceHTTPStats>,
-    #[serde(rename = "healResult", skip_serializing_if = "Option::is_none")]
-    heal_result: Option<HealResultItem>,
-}
-
-impl TraceInfo {
-    pub fn mask(&self) -> u64 {
-        TraceType::new(self.trace_type).mask()
-    }
-}
-
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct TraceInfoLegacy {
-    trace_info: TraceInfo,
-    #[serde(rename = "request")]
-    req_info: Option<TraceRequestInfo>,
-    #[serde(rename = "response")]
-    resp_info: Option<TraceResponseInfo>,
-    #[serde(rename = "stats")]
-    call_stats: Option<TraceCallStats>,
-    #[serde(rename = "storageStats")]
-    storage_stats: Option<StorageStats>,
-    #[serde(rename = "osStats")]
-    os_stats: Option<OSStats>,
-}
-
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct StorageStats {
-    path: String,
-    duration: Duration,
-}
-
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct OSStats {
-    path: String,
-    duration: Duration,
-}
-
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct TraceHTTPStats {
-    req_info: TraceRequestInfo,
-    resp_info: TraceResponseInfo,
-    call_stats: TraceCallStats,
-}
-
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct TraceCallStats {
-    input_bytes: i32,
-    output_bytes: i32,
-    latency: Duration,
-    time_to_first_byte: Duration,
-}
-
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct TraceRequestInfo {
-    time: Timestamp,
-    proto: String,
-    method: String,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    path: Option<String>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    raw_query: Option<String>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    headers: Option<HashMap<String, String>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    body: Option<Vec<u8>>,
-    client: String,
-}
-
-#[derive(Debug, Default, Clone, Serialize, Deserialize)]
-pub struct TraceResponseInfo {
-    time: Timestamp,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    headers: Option<HashMap<String, String>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    body: Option<Vec<u8>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    status_code: Option<i32>,
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;
 
     #[test]
-    fn trace_timestamps_serialize_as_rfc3339_utc() {
-        let timestamp = Timestamp::constant(1_700_000_000, 123_456_000);
-        let trace = TraceInfo {
-            time: timestamp,
-            http: Some(TraceHTTPStats {
-                req_info: TraceRequestInfo {
-                    time: timestamp,
-                    ..Default::default()
-                },
-                resp_info: TraceResponseInfo {
-                    time: timestamp,
-                    ..Default::default()
-                },
-                ..Default::default()
-            }),
-            ..Default::default()
-        };
+    fn trace_type_contains_and_overlaps() {
+        let mut combined = TraceType::default();
+        combined.merge(&TraceType::S3);
+        combined.merge(&TraceType::HEALING);
 
-        let value = serde_json::to_value(trace).expect("trace should serialize");
-        assert_eq!(value["time"], "2023-11-14T22:13:20.123456Z");
-        assert_eq!(value["http"]["req_info"]["time"], "2023-11-14T22:13:20.123456Z");
-        assert_eq!(value["http"]["resp_info"]["time"], "2023-11-14T22:13:20.123456Z");
-        let trace: TraceInfo = serde_json::from_value(value).expect("trace should deserialize");
-        assert_eq!(trace.time, timestamp);
-        let http = trace.http.expect("http trace should deserialize");
-        assert_eq!(http.req_info.time, timestamp);
-        assert_eq!(http.resp_info.time, timestamp);
+        assert!(combined.contains(&TraceType::S3));
+        assert!(combined.contains(&TraceType::HEALING));
+        assert!(!combined.contains(&TraceType::SCANNER));
+        assert!(combined.overlaps(&TraceType::S3));
+        assert!(combined.overlaps(&TraceType::HEALING));
+        assert!(!combined.overlaps(&TraceType::SCANNER));
+    }
+
+    #[test]
+    fn trace_type_set_if() {
+        let mut tt = TraceType::default();
+        tt.set_if(true, &TraceType::OS);
+        tt.set_if(false, &TraceType::S3);
+        assert!(tt.contains(&TraceType::OS));
+        assert!(!tt.contains(&TraceType::S3));
+    }
+
+    #[test]
+    fn trace_type_single_type() {
+        assert!(TraceType::S3.single_type());
+        let mut combined = TraceType::S3;
+        combined.merge(&TraceType::HEALING);
+        assert!(!combined.single_type());
     }
 }

scripts/check_test_wiring.py

@@ -206,6 +206,13 @@ def check_runner_selection(root: Path) -> list[str]:
     return errors
 
 
+def check_s3_tests_runner(root: Path) -> list[str]:
+    runner = (root / "scripts/s3-tests/run.sh").read_text()
+    if "--showlocals" in runner:
+        return ["scripts/s3-tests/run.sh: pytest failure diagnostics must not dump local values"]
+    return []
+
+
 def profile_selection(root: Path, profile: str) -> str:
     if not re.fullmatch(r"e2e-[a-z0-9-]+", profile):
         raise ValueError(f"invalid e2e profile name: {profile}")
@@ -272,6 +279,7 @@ def validate(root: Path) -> list[str]:
     errors.extend(check_e2e_modules(root))
     errors.extend(check_fuzz_targets(root))
     errors.extend(check_runner_selection(root))
+    errors.extend(check_s3_tests_runner(root))
     errors.extend(check_profile_definitions(root))
     return errors
 
@@ -341,6 +349,23 @@ class SelfTests(unittest.TestCase):
             )
             self.assertEqual(len(check_fuzz_targets(root)), 1)
 
+    def test_s3_runner_rejects_unbounded_failure_locals(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            runner = root / "scripts/s3-tests/run.sh"
+            runner.parent.mkdir(parents=True)
+            runner.write_text("tox -- -vv -ra --tb=long\n")
+            self.assertEqual(check_s3_tests_runner(root), [])
+            runner.write_text("tox -- -vv -ra --showlocals --tb=long\n")
+            self.assertEqual(len(check_s3_tests_runner(root)), 1)
+            with (
+                mock.patch(__name__ + ".check_e2e_modules", return_value=[]),
+                mock.patch(__name__ + ".check_fuzz_targets", return_value=[]),
+                mock.patch(__name__ + ".check_runner_selection", return_value=[]),
+                mock.patch(__name__ + ".check_profile_definitions", return_value=[]),
+            ):
+                self.assertEqual(len(validate(root)), 1)
+
     def test_profile_listing_enforces_selection(self) -> None:
         with tempfile.TemporaryDirectory() as tmp:
             root = Path(tmp)
@@ -411,7 +436,7 @@ def main() -> int:
         for error in errors:
             print(f"ERROR: {error}", file=sys.stderr)
         return 1
-    print("OK: e2e modules, runner selection, fuzz matrices, and profile guards are wired")
+    print("OK: e2e modules, runner selection, fuzz matrices, profiles, and bounded diagnostics are wired")
     return 0
 
 

scripts/s3-tests/run.sh

@@ -1028,10 +1028,11 @@ else
 fi
 
 # Run tests from s3tests/functional
+# Failure locals can contain multi-MiB request bodies; keep tracebacks without expanding local values.
 set +e
 S3TEST_CONF="${CONF_OUTPUT_PATH}" \
     tox -- \
-    -vv -ra --showlocals --tb=long \
+    -vv -ra --tb=long \
     --maxfail="${MAXFAIL}" \
     --timeout="${TEST_TIMEOUT}" \
     --junitxml="${ARTIFACTS_DIR}/junit.xml" \