Merge branch 'main' into cxymds/fix-decommission-listing-failclosed

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/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/core/pools.rs

@@ -36,7 +36,8 @@ use crate::disk::error::DiskError;
 use crate::disk::{BUCKET_META_PREFIX, RUSTFS_META_BUCKET};
 use crate::error::{Error, Result};
 use crate::error::{
-    StorageError, is_err_bucket_exists, is_err_bucket_not_found, is_err_object_not_found, is_err_version_not_found,
+    StorageError, is_err_bucket_exists, is_err_bucket_not_found, is_err_object_not_found, is_err_operation_canceled,
+    is_err_version_not_found,
 };
 use crate::layout::endpoints::EndpointServerPools;
 use crate::object_api::{GetObjectReader, ObjectOptions};
@@ -773,7 +774,76 @@ async fn load_decommission_entry_exact_versions(
 }
 
 fn resolve_decommission_check_after_list_result(list_result: Result<()>, entry_error: Option<Error>) -> Result<()> {
-    if let Some(err) = entry_error { Err(err) } else { list_result }
+    match list_result {
+        Ok(()) => entry_error.map_or(Ok(()), Err),
+        Err(list_err) => resolve_decommission_listing_error(Some(list_err), entry_error).map_or(Ok(()), Err),
+    }
+}
+
+fn resolve_decommission_listing_error(listing_error: Option<Error>, entry_error: Option<Error>) -> Option<Error> {
+    match (listing_error, entry_error) {
+        (Some(listing_error), Some(entry_error)) if is_err_operation_canceled(&listing_error) => Some(entry_error),
+        (Some(listing_error), Some(entry_error)) if is_err_operation_canceled(&entry_error) => Some(listing_error),
+        (Some(listing_error), _) => Some(listing_error),
+        (None, entry_error) => entry_error,
+    }
+}
+
+fn decommission_unresolved_listing_error(
+    bucket: &str,
+    prefix: &str,
+    candidate: Option<&str>,
+    candidate_count: usize,
+    disk_error_count: usize,
+    pool_index: usize,
+    set_index: usize,
+) -> Error {
+    let location = candidate.unwrap_or(prefix);
+    Error::other(format!(
+        "decommission listing could not resolve metadata for {bucket}/{location} on pool {pool_index} set {set_index} ({candidate_count} candidate(s), {disk_error_count} disk error(s))"
+    ))
+}
+
+fn resolve_decommission_partial_listing_entry(
+    entries: MetaCacheEntries,
+    resolver: MetadataResolutionParams,
+    bucket: &str,
+    prefix: &str,
+    disk_error_count: usize,
+    pool_index: usize,
+    set_index: usize,
+) -> Result<MetaCacheEntry> {
+    let candidate_count = entries.as_ref().iter().flatten().count();
+    if let Some(entry) = entries.resolve(resolver) {
+        return Ok(entry);
+    }
+
+    let candidate = entries.as_ref().iter().flatten().map(|entry| entry.name.as_str()).next();
+    Err(decommission_unresolved_listing_error(
+        bucket,
+        prefix,
+        candidate,
+        candidate_count,
+        disk_error_count,
+        pool_index,
+        set_index,
+    ))
+}
+
+async fn record_decommission_entry_error(
+    entry_error: &Arc<tokio::sync::Mutex<Option<Error>>>,
+    rx: &CancellationToken,
+    err: Error,
+) {
+    if rx.is_cancelled() {
+        return;
+    }
+
+    let mut first_err = entry_error.lock().await;
+    if first_err.is_none() && !rx.is_cancelled() {
+        *first_err = Some(err);
+        rx.cancel();
+    }
 }
 
 fn resolve_decommission_pool_meta_reload_result(result: Result<()>, stage: &str) -> Result<()> {
@@ -3538,6 +3608,7 @@ impl ECStore {
             let rx_clone = rx.clone();
             let bi = bi.clone();
             let set_id = set_idx;
+            let listing_entry_error = entry_error.clone();
             let worker = tokio::spawn(async move {
                 let _listing_permit = listing_permit;
                 run_decommission_listing_with_retry(
@@ -3551,7 +3622,11 @@ impl ECStore {
                         let set = set.clone();
                         let rx = rx_clone.clone();
                         let bucket = bi.clone();
-                        async move { set.list_objects_to_decommission(rx, bucket, callback).await }
+                        let entry_error = listing_entry_error.clone();
+                        async move {
+                            set.list_objects_to_decommission(rx, bucket, callback, entry_error.clone(), idx, set_id)
+                                .await
+                        }
                     },
                 )
                 .await
@@ -3581,11 +3656,7 @@ impl ECStore {
 
         wait_decommission_worker_drain(&workers, worker_limit).await?;
 
-        if let Some(err) = listing_worker_error {
-            return Err(err);
-        }
-
-        if let Some(err) = entry_error.lock().await.clone() {
+        if let Some(err) = resolve_decommission_listing_error(listing_worker_error, entry_error.lock().await.clone()) {
             return Err(err);
         }
 
@@ -4191,7 +4262,7 @@ impl ECStore {
         let buckets = self.get_buckets_to_decommission().await?;
         let pool = self.pools[idx].clone();
 
-        for set in &pool.disk_set {
+        for (set_index, set) in pool.disk_set.iter().enumerate() {
             for bucket_info in &buckets {
                 let mut lifecycle_config = None;
                 let mut object_lock_config = None;
@@ -4286,7 +4357,7 @@ impl ECStore {
                 });
 
                 let list_result = set
-                    .list_objects_to_decommission(callback_rx, bucket_info.clone(), callback)
+                    .list_objects_to_decommission(callback_rx, bucket_info.clone(), callback, entry_error.clone(), idx, set_index)
                     .await;
                 let entry_error = entry_error.lock().await.clone();
                 resolve_decommission_check_after_list_result(list_result, entry_error)?;
@@ -5021,12 +5092,15 @@ mod tests {
 pub type ListCallback = Arc<dyn Fn(MetaCacheEntry) -> BoxFuture<'static, ()> + Send + Sync + 'static>;
 
 impl SetDisks {
-    #[tracing::instrument(skip(self, rx, cb_func))]
+    #[tracing::instrument(skip(self, rx, cb_func, entry_error))]
     async fn list_objects_to_decommission(
         self: &Arc<Self>,
         rx: CancellationToken,
         bucket_info: DecomBucketInfo,
         cb_func: ListCallback,
+        entry_error: Arc<tokio::sync::Mutex<Option<Error>>>,
+        pool_index: usize,
+        set_index: usize,
     ) -> Result<()> {
         let (disks, _) = self.get_online_disks_with_healing(false).await;
         ensure_decommission_listing_disks_available(!disks.is_empty(), &bucket_info.name)?;
@@ -5041,6 +5115,12 @@ impl SetDisks {
         };
 
         let cb1 = cb_func.clone();
+        let unresolved_error = entry_error.clone();
+        let unresolved_rx = rx.clone();
+        let unresolved_bucket = bucket_info.name.clone();
+        let unresolved_prefix = bucket_info.prefix.clone();
+        let unresolved_pool_index = pool_index;
+        let unresolved_set_index = set_index;
 
         list_path_raw(
             rx,
@@ -5053,20 +5133,51 @@ impl SetDisks {
                 skip_walkdir_total_timeout: true,
                 walkdir_stall_timeout: Some(DECOMMISSION_BACKGROUND_WALKDIR_STALL_TIMEOUT),
                 agreed: Some(Box::new(move |entry: MetaCacheEntry| Box::pin(cb1(entry)))),
-                partial: Some(Box::new(move |entries: MetaCacheEntries, _: &[Option<DiskError>]| {
+                partial: Some(Box::new(move |entries: MetaCacheEntries, errs: &[Option<DiskError>]| {
                     let resolver = resolver.clone();
                     let cb_func = cb_func.clone();
-                    match entries.resolve(resolver) {
-                        Some(entry) => {
+                    let bucket = unresolved_bucket.clone();
+                    let prefix = unresolved_prefix.clone();
+                    let unresolved_error = unresolved_error.clone();
+                    let unresolved_rx = unresolved_rx.clone();
+                    let pool_index = unresolved_pool_index;
+                    let set_index = unresolved_set_index;
+                    let disk_error_count = errs.iter().flatten().count();
+                    if unresolved_rx.is_cancelled() {
+                        return Box::pin(async {});
+                    }
+
+                    match resolve_decommission_partial_listing_entry(
+                        entries,
+                        resolver,
+                        &bucket,
+                        &prefix,
+                        disk_error_count,
+                        pool_index,
+                        set_index,
+                    ) {
+                        Ok(entry) => {
                             warn!("decommission_pool: list_objects_to_decommission get {}", &entry.name);
                             Box::pin(async move {
                                 cb_func(entry).await;
                             })
                         }
-                        None => {
-                            warn!("decommission_pool: list_objects_to_decommission get none");
-                            Box::pin(async {})
-                        }
+                        Err(err) => Box::pin(async move {
+                            if unresolved_rx.is_cancelled() {
+                                return;
+                            }
+                            warn!(
+                                event = EVENT_DECOMMISSION_BUCKET,
+                                component = LOG_COMPONENT_ECSTORE,
+                                subsystem = LOG_SUBSYSTEM_POOLS,
+                                bucket = %bucket,
+                                prefix = %prefix,
+                                state = "unresolved_entry",
+                                error = %err,
+                                "Decommission listing failed closed on unresolved metadata"
+                            );
+                            record_decommission_entry_error(&unresolved_error, &unresolved_rx, err).await;
+                        }),
                     }
                 })),
                 ..Default::default()
@@ -5074,6 +5185,10 @@ impl SetDisks {
         )
         .await?;
 
+        if let Some(err) = entry_error.lock().await.clone() {
+            return Err(err);
+        }
+
         Ok(())
     }
 }
@@ -5279,11 +5394,12 @@ mod pools_tests {
         has_active_decommission_canceler, is_decommission_active, is_decommission_cancel_requested,
         load_decommission_entry_versions, local_decommission_queue_prefix, mark_decommission_bucket_done,
         merge_pool_status_refresh, missing_decommission_worker_prefix, observe_decommission_terminal_reload_result,
-        pool_meta_has_active_decommission, require_decommission_store, resolve_decommission_bucket_done_save_result,
-        resolve_decommission_bucket_state, resolve_decommission_check_after_list_result,
-        resolve_decommission_entry_cleanup_delete_result, resolve_decommission_entry_exact_versions,
-        resolve_decommission_entry_reload_result, resolve_decommission_listing_worker_result,
-        resolve_decommission_optional_bucket_config_result, resolve_decommission_pool_meta_reload_result,
+        pool_meta_has_active_decommission, record_decommission_entry_error, require_decommission_store,
+        resolve_decommission_bucket_done_save_result, resolve_decommission_bucket_state,
+        resolve_decommission_check_after_list_result, resolve_decommission_entry_cleanup_delete_result,
+        resolve_decommission_entry_exact_versions, resolve_decommission_entry_reload_result, resolve_decommission_listing_error,
+        resolve_decommission_listing_worker_result, resolve_decommission_optional_bucket_config_result,
+        resolve_decommission_partial_listing_entry, resolve_decommission_pool_meta_reload_result,
         resolve_decommission_preflight_heal_result, resolve_decommission_progress_save_result,
         resolve_decommission_spawn_failure_result, resolve_decommission_terminal_mark_after_error_result,
         resolve_decommission_terminal_mark_result, resolve_decommission_update_after_result,
@@ -5302,7 +5418,9 @@ mod pools_tests {
     use crate::error::{Error, StorageError};
     use crate::layout::endpoints::{EndpointServerPools, Endpoints, PoolEndpoints};
     use crate::services::rebalance::{RebalStatus, RebalanceInfo, RebalanceMeta, RebalanceStats};
-    use rustfs_filemeta::{FileInfo, FileInfoVersions, MetaCacheEntry, ObjectPartInfo};
+    use rustfs_filemeta::{
+        FileInfo, FileInfoVersions, MetaCacheEntries, MetaCacheEntry, MetadataResolutionParams, ObjectPartInfo,
+    };
     use rustfs_rio::Index;
     use std::sync::{
         Arc,
@@ -6321,6 +6439,65 @@ mod pools_tests {
         assert!(matches!(err, Error::SlowDown));
     }
 
+    #[test]
+    fn test_resolve_decommission_partial_listing_entry_rejects_unresolved_metadata() {
+        let err = resolve_decommission_partial_listing_entry(
+            MetaCacheEntries(vec![None]),
+            MetadataResolutionParams {
+                dir_quorum: 2,
+                obj_quorum: 2,
+                bucket: "bucket-a".to_string(),
+                ..Default::default()
+            },
+            "bucket-a",
+            "prefix/",
+            1,
+            2,
+            3,
+        )
+        .expect_err("unresolved partial listing must fail closed");
+
+        let message = err.to_string();
+        assert!(message.contains("decommission listing could not resolve metadata"));
+        assert!(message.contains("bucket-a/prefix/"));
+        assert!(message.contains("pool 2 set 3"));
+        assert!(message.contains("1 disk error(s)"));
+    }
+
+    #[tokio::test]
+    async fn test_record_decommission_entry_error_cancels_listing_and_preserves_first_error() {
+        let entry_error = Arc::new(tokio::sync::Mutex::new(None));
+        let rx = CancellationToken::new();
+
+        record_decommission_entry_error(&entry_error, &rx, Error::SlowDown).await;
+        record_decommission_entry_error(&entry_error, &rx, Error::OperationCanceled).await;
+
+        assert!(rx.is_cancelled());
+        assert!(matches!(*entry_error.lock().await, Some(Error::SlowDown)));
+    }
+
+    #[tokio::test]
+    async fn test_record_decommission_entry_error_ignores_already_canceled_listing() {
+        let entry_error = Arc::new(tokio::sync::Mutex::new(None));
+        let rx = CancellationToken::new();
+        rx.cancel();
+
+        record_decommission_entry_error(&entry_error, &rx, Error::SlowDown).await;
+
+        assert!(entry_error.lock().await.is_none());
+    }
+
+    #[test]
+    fn test_resolve_decommission_listing_error_preserves_real_listing_failure() {
+        let err = resolve_decommission_listing_error(Some(Error::SlowDown), Some(Error::OperationCanceled))
+            .expect("listing failure should be returned");
+        assert!(matches!(err, Error::SlowDown));
+
+        let err = resolve_decommission_listing_error(Some(Error::OperationCanceled), Some(Error::SlowDown))
+            .expect("entry failure should be returned");
+        assert!(matches!(err, Error::SlowDown));
+    }
+
     #[test]
     fn test_resolve_decommission_check_after_list_result_returns_list_result_without_entry_error() {
         let err = resolve_decommission_check_after_list_result(Err(Error::OperationCanceled), None)

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" \