Merge branch 'main' into overtrue/require-mc-e2e

* test(kms): bound Vault failover progress wait

* ci(nightly): honor manual dispatch ref

* test(kms): preserve Vault worker failures

* test(kms): validate Vault circuit recovery

.config/nextest.toml

@@ -325,8 +325,8 @@ slow-timeout = { period = "60s", terminate-after = 2, grace-period = "10s" }
 #
 # Wired by .github/workflows/e2e-replication-nightly.yml (schedule +
 # workflow_dispatch), which builds the rustfs binary once, installs awscurl so
-# the STS dual-node test actually exercises its path (it skips gracefully with
+# the STS dual-node test actually exercises its path (the test fails when
-# a visible log line when awscurl is absent), and routes scheduled failures
+# awscurl is absent), and routes scheduled failures
 # through .github/actions/schedule-failure-issue (ci-8). Explicit division of
 # labor with e2e-full: these tests run only in the consolidated nightly
 # workflow, not in the merge/main lane.

.github/workflows/ci.yml

@@ -681,6 +681,19 @@ jobs:
           cache-save-if: 'false'
           install-build-packaging-tools: 'false'
 
+      - name: Set up Python
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        with:
+          python-version: "3.12"
+
+      - name: Install awscurl
+        run: |
+          python3 -m pip install --user --upgrade pip "awscurl==0.44"
+          echo "AWSCURL_PATH=$HOME/.local/bin/awscurl" >> "$GITHUB_ENV"
+
+      - name: Verify awscurl
+        run: test -x "$AWSCURL_PATH"
+
       # Download after the cache restore so the freshly built binary from the
       # build job always wins over anything restored into target/debug.
       - name: Download debug binary
@@ -803,6 +816,20 @@ jobs:
       - name: Verify awscurl
         run: test -x "$AWSCURL_PATH"
 
+      - name: Install mc
+        env:
+          MC_VERSION: RELEASE.2025-08-13T08-35-41Z
+          MC_SHA256: 01f866e9c5f9b87c2b09116fa5d7c06695b106242d829a8bb32990c00312e891
+        run: |
+          MC_BINARY="mc.linux-amd64.${MC_VERSION}"
+          curl -fsSLo "$RUNNER_TEMP/mc" "https://github.com/minio/mc/releases/download/${MC_VERSION}/${MC_BINARY}"
+          echo "${MC_SHA256}  $RUNNER_TEMP/mc" | sha256sum --check --status
+          chmod +x "$RUNNER_TEMP/mc"
+          echo "$RUNNER_TEMP" >> "$GITHUB_PATH"
+
+      - name: Verify mc
+        run: mc --version
+
       - name: Install Vault
         run: |
           VAULT_VERSION="1.17.6"

.github/workflows/e2e-replication-nightly.yml

@@ -75,11 +75,7 @@ jobs:
           cache-save-if: ${{ github.ref == 'refs/heads/main' }}
           install-build-packaging-tools: 'false'
 
-      # awscurl lets the STS dual-node test actually exercise its path. Without
+      # The STS dual-node test requires awscurl and fails if it is unavailable.
-      # it the test skips gracefully with a visible log line
-      # (`awscurl_available()` in crates/e2e_test/src/common.rs), so the lane
-      # still passes — installing it just upgrades that one test from skip to
-      # real coverage.
       - name: Set up Python
         uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
         with:
@@ -87,7 +83,7 @@ jobs:
 
       - name: Install awscurl
         run: |
-          python3 -m pip install --user --upgrade pip awscurl
+          python3 -m pip install --user --upgrade pip "awscurl==0.44"
           echo "AWSCURL_PATH=$HOME/.local/bin/awscurl" >> "$GITHUB_ENV"
 
       - name: Verify awscurl

.github/workflows/nightly-gnu.yml

@@ -39,11 +39,10 @@ jobs:
     env:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
     steps:
-      - name: Checkout main branch
+      - name: Checkout repository
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
         with:
           persist-credentials: false
-          ref: main
 
       - name: Setup Rust environment
         uses: ./.github/actions/setup
@@ -89,11 +88,10 @@ jobs:
       # either casing.
       NO_PROXY: 127.0.0.1,localhost
     steps:
-      - name: Checkout main branch
+      - name: Checkout repository
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
         with:
           persist-credentials: false
-          ref: main
 
       - name: Setup Rust environment
         uses: ./.github/actions/setup
@@ -178,11 +176,10 @@ jobs:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
       NO_PROXY: 127.0.0.1,localhost
     steps:
-      - name: Checkout main branch
+      - name: Checkout repository
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
         with:
           persist-credentials: false
-          ref: main
 
       - name: Setup Rust environment
         uses: ./.github/actions/setup

crates/e2e_test/README.md

@@ -123,7 +123,7 @@ via `create_s3_client(idx)` / `create_all_clients()`. See
 | `find_available_port` | Random free port (isolation primitive) |
 | `rustfs_binary_path` / `_with_features` | Locate/build the binary; honors `RUSTFS_BUILD_FEATURES` |
 | `requested_rustfs_build_features` / `rustfs_build_feature_enabled` | Feature-gate a test to what the binary was built with |
-| `awscurl_available` + `execute_awscurl` / `awscurl_post` / `_get` / `_put` / `_delete` / `awscurl_post_sts_form_urlencoded` | Admin/STS API calls via `awscurl` (skip gracefully when absent) |
+| `execute_awscurl` / `awscurl_post` / `_get` / `_put` / `_delete` / `awscurl_post_sts_form_urlencoded` | Admin/STS API calls via `awscurl`; missing binaries are test failures |
 | `replication_fast_env` | Env vars that shrink replication timers (from repl-4); pass to `start_rustfs_server_with_env` |
 | `local_http_client` / `init_logging` | Loopback HTTP client; idempotent tracing init |
 | `RustFSTestClusterEnvironment` (`new`/`start`/`start_node`/`stop_node`/`create_all_clients`) | Multi-node harness |
@@ -189,7 +189,7 @@ cargo nextest run --profile e2e-smoke -p e2e_test
 cargo nextest run --profile e2e-full -p e2e_test
 # Cluster fault nightly lane
 cargo nextest run --profile e2e-nightly -p e2e_test
-# Replication nightly lane; install awscurl so STS paths do not skip
+# Replication nightly lane; awscurl is required for STS paths
 cargo nextest run --profile e2e-repl-nightly -p e2e_test
 # Fixed-port protocol nightly lane
 RUSTFS_BUILD_FEATURES=ftps,webdav,sftp \
@@ -221,9 +221,8 @@ The `s3s-e2e` CI job selects a random `RUSTFS_TEST_PORT` (see the `e2e-tests`
 job) to dodge this; local single-node tests already use random ports, so a
 lingering orphan is usually the cause of a spurious bind failure.
 
-**`awscurl` not found.** `awscurl`-dependent tests skip gracefully with a
+**`awscurl` not found.** `awscurl`-dependent tests fail closed with a process
-visible log line (`awscurl_available()`); install `awscurl` to actually run
+spawn error. Install the pinned CI version before running their profiles.
-them.
 
 ## Related
 
@@ -258,10 +257,9 @@ A test module may join the smoke filter only if every test in it is:
 2. **Single-node** — spawns its own server via
    `RustFSTestEnvironment`/`start_rustfs_server` on a random port with an
    isolated temp dir. No `RustFSTestClusterEnvironment`, no fixed ports.
-3. **Dependency-free** — no pre-started server at `localhost:9000`, no Vault,
+3. **Hermetic dependencies** — no pre-started server at `localhost:9000`, no
-   no fixed protocol ports. Tools that may be absent on the runner (e.g.
+   Vault, and no fixed protocol ports. Any required CLI must be pinned and
-   `awscurl`) are acceptable only when the test skips gracefully with a
+   installed by the workflow; a missing CLI must fail the test.
-   visible log line (see `bucket_policy_check_test.rs`).
 4. **Not `#[ignore]`** — ignored tests are activation work (backlog#1149
    ci-13 / backlog#1148 ilm-3), not smoke candidates.
 

crates/e2e_test/src/bucket_policy_check_test.rs

@@ -52,10 +52,6 @@ fn create_user_client(env: &RustFSTestEnvironment, access_key: &str, secret_key:
 #[tokio::test]
 async fn test_bucket_policy_authenticated_user() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !crate::common::awscurl_available() {
-        info!("Skipping test_bucket_policy_authenticated_user because awscurl is not available");
-        return Ok(());
-    }
     info!("Starting test_bucket_policy_authenticated_user...");
 
     let mut env = RustFSTestEnvironment::new().await?;

crates/e2e_test/src/common.rs

@@ -494,17 +494,6 @@ fn awscurl_binary_path() -> PathBuf {
         .unwrap_or_else(|| PathBuf::from("awscurl"))
 }
 
-pub fn awscurl_available() -> bool {
-    let path = awscurl_binary_path();
-    if path.components().count() > 1 || path.is_absolute() {
-        return path.is_file();
-    }
-
-    std::env::var_os("PATH")
-        .map(|paths| std::env::split_paths(&paths).any(|dir| dir.join(&path).is_file()))
-        .unwrap_or(false)
-}
-
 // Global initialization
 static INIT: Once = Once::new();
 

crates/e2e_test/src/existing_object_tag_policy_test.rs

@@ -16,9 +16,7 @@
 //! session policy** (`Policy` parameter) via `awscurl --service sts` with explicit
 //! `Content-Type: application/x-www-form-urlencoded` on `POST /`.
 
-use crate::common::{
+use crate::common::{RustFSTestEnvironment, awscurl_delete, awscurl_post_sts_form_urlencoded, awscurl_put, init_logging};
-    RustFSTestEnvironment, awscurl_available, awscurl_delete, awscurl_post_sts_form_urlencoded, awscurl_put, init_logging,
-};
 use aws_sdk_s3::config::{Credentials, Region};
 use aws_sdk_s3::primitives::ByteStream;
 use aws_sdk_s3::types::{Delete, ObjectIdentifier, Tag, Tagging};
@@ -175,11 +173,6 @@ async fn cleanup_bucket_and_object(admin: &Client, bucket: &str, key: &str) {
 #[tokio::test]
 async fn test_e2e_iam_policy_existing_object_tag_get_object() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_iam_policy_existing_object_tag_get_object: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let user = format!("e2eiamtag-{suffix}");
     let user_secret = "longSecretKeyForTest123!";
@@ -233,11 +226,6 @@ async fn test_e2e_iam_policy_existing_object_tag_get_object() -> Result<(), Box<
 #[tokio::test]
 async fn test_e2e_bucket_policy_existing_object_tag_get_object() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_bucket_policy_existing_object_tag_get_object: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let user = format!("e2ebptag-{suffix}");
     let user_secret = "longSecretKeyForTest456!";
@@ -294,11 +282,6 @@ async fn test_e2e_bucket_policy_existing_object_tag_get_object() -> Result<(), B
 #[tokio::test]
 async fn test_e2e_sts_assume_role_session_policy_existing_object_tag() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_sts_assume_role_session_policy_existing_object_tag: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let parent = format!("e2e-sts-par-{suffix}");
     let parent_secret = "longSecretKeyForParentSts99!";
@@ -370,11 +353,6 @@ async fn test_e2e_sts_assume_role_session_policy_existing_object_tag() -> Result
 #[tokio::test]
 async fn test_e2e_sts_session_policy_delete_objects_object_prefix_only() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_sts_session_policy_delete_objects_object_prefix_only: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let parent = format!("e2e-sts-del-par-{suffix}");
     let parent_secret = "longSecretKeyForParentDelete99!";

crates/e2e_test/src/kms/common.rs

@@ -22,9 +22,7 @@
 //! - KMS backend configuration (Local and Vault)
 //! - SSE encryption testing utilities
 
-use crate::common::{
+use crate::common::{RustFSTestEnvironment, awscurl_get, awscurl_post, init_logging as common_init_logging, local_http_client};
-    RustFSTestEnvironment, awscurl_available, awscurl_get, awscurl_post, init_logging as common_init_logging, local_http_client,
-};
 use aws_sdk_s3::Client;
 use aws_sdk_s3::primitives::ByteStream;
 use aws_sdk_s3::types::ServerSideEncryption;
@@ -59,15 +57,6 @@ pub fn init_logging() {
     // Additional KMS-specific logging configuration can be added here if needed
 }
 
-pub fn skip_if_kms_admin_tool_unavailable(test_name: &str) -> bool {
-    if awscurl_available() {
-        return false;
-    }
-
-    info!("Skipping {} because awscurl is not available in PATH", test_name);
-    true
-}
-
 pub fn sse_customer_key_md5_base64(key: &str) -> String {
     let mut hasher = Md5::new();
     hasher.update(key.as_bytes());
@@ -490,10 +479,6 @@ pub async fn test_kms_key_management(
     access_key: &str,
     secret_key: &str,
 ) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
-    if skip_if_kms_admin_tool_unavailable("test_kms_key_management") {
-        return Ok(());
-    }
-
     info!("Testing KMS key management APIs");
 
     // Test CreateKey

crates/e2e_test/src/kms/kms_local_test.rs

@@ -20,8 +20,7 @@
 //! - Complete encryption/decryption lifecycle
 
 use super::common::{
-    LocalKMSTestEnvironment, get_kms_status, skip_if_kms_admin_tool_unavailable, sse_customer_key_md5_base64,
+    LocalKMSTestEnvironment, get_kms_status, sse_customer_key_md5_base64, test_kms_key_management, test_sse_c_encryption,
-    test_kms_key_management, test_sse_c_encryption,
 };
 use crate::common::{TEST_BUCKET, init_logging};
 use tracing::{error, info};
@@ -29,9 +28,6 @@ use tracing::{error, info};
 #[tokio::test]
 async fn test_local_kms_end_to_end() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_local_kms_end_to_end") {
-        return Ok(());
-    }
     info!("Starting Local KMS End-to-End Test");
 
     // Create LocalKMS test environment

crates/e2e_test/src/kms/kms_vault_test.rs

@@ -22,8 +22,8 @@ use crate::common::{TEST_BUCKET, init_logging};
 use tracing::{error, info};
 
 use super::common::{
-    VAULT_KEY_NAME, VaultTestEnvironment, get_kms_status, skip_if_kms_admin_tool_unavailable, sse_customer_key_md5_base64,
+    VAULT_KEY_NAME, VaultTestEnvironment, get_kms_status, sse_customer_key_md5_base64, start_kms,
-    start_kms, test_all_multipart_encryption_types, test_error_scenarios, test_kms_key_management, test_sse_c_encryption,
+    test_all_multipart_encryption_types, test_error_scenarios, test_kms_key_management, test_sse_c_encryption,
     test_sse_kms_encryption, test_sse_s3_encryption,
 };
 
@@ -62,9 +62,6 @@ impl VaultKmsTestContext {
 #[tokio::test]
 async fn test_vault_kms_end_to_end() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_end_to_end") {
-        return Ok(());
-    }
     info!("Starting Vault KMS End-to-End Test with default key {}", VAULT_KEY_NAME);
 
     let context = VaultKmsTestContext::new().await?;
@@ -117,9 +114,6 @@ async fn test_vault_kms_end_to_end() -> Result<(), Box<dyn std::error::Error + S
 #[tokio::test]
 async fn test_vault_kms_key_isolation() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_key_isolation") {
-        return Ok(());
-    }
     info!("Starting Vault KMS SSE-C key isolation test");
 
     let context = VaultKmsTestContext::new().await?;
@@ -203,9 +197,6 @@ async fn test_vault_kms_key_isolation() -> Result<(), Box<dyn std::error::Error
 #[tokio::test]
 async fn test_vault_kms_large_file() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_large_file") {
-        return Ok(());
-    }
     info!("Starting Vault KMS large file SSE-S3 test");
 
     let context = VaultKmsTestContext::new().await?;
@@ -267,9 +258,6 @@ async fn test_vault_kms_large_file() -> Result<(), Box<dyn std::error::Error + S
 #[tokio::test]
 async fn test_vault_kms_multipart_upload() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_multipart_upload") {
-        return Ok(());
-    }
     info!("Starting Vault KMS multipart upload encryption suite");
 
     let context = VaultKmsTestContext::new().await?;
@@ -297,9 +285,6 @@ async fn test_vault_kms_multipart_upload() -> Result<(), Box<dyn std::error::Err
 #[tokio::test]
 async fn test_vault_kms_key_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_key_operations") {
-        return Ok(());
-    }
     info!("Starting Vault KMS key operations test (CRUD)");
 
     let context = VaultKmsTestContext::new().await?;

crates/e2e_test/src/mc_mirror_small_bucket_test.rs

@@ -41,13 +41,6 @@ async fn create_issue_3107_fixture(root: &Path) -> TestResult {
     Ok(())
 }
 
-fn mc_available() -> bool {
-    Command::new("mc")
-        .arg("--version")
-        .output()
-        .is_ok_and(|output| output.status.success())
-}
-
 fn run_mc(args: &[&str]) -> TestResult {
     let output = Command::new("mc").args(args).output()?;
     if !output.status.success() {
@@ -75,10 +68,7 @@ fn count_files(root: &Path) -> usize {
 async fn test_mc_mirror_small_bucket_completes_without_list_timeout() -> TestResult {
     crate::common::init_logging();
     info!("Starting issue #3107 mc mirror regression test");
-    if !mc_available() {
+    run_mc(&["--version"])?;
-        info!("Skipping issue #3107 mc mirror regression test because mc is not installed");
-        return Ok(());
-    }
 
     let mut env = RustFSTestEnvironment::new().await?;
     env.start_rustfs_server(vec![]).await?;

crates/e2e_test/src/multipart_auth_test.rs

@@ -4278,10 +4278,6 @@ async fn test_signed_put_object_extract_preserves_pax_metadata_and_version_id()
 async fn test_signed_put_object_extract_authorizes_each_pax_privilege_and_retention_conditions()
 -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !crate::common::awscurl_available() {
-        return Ok(());
-    }
-
     let mut env = RustFSTestEnvironment::new().await?;
     env.start_rustfs_server(vec![]).await?;
 

crates/e2e_test/src/quota_test.rs

@@ -18,15 +18,6 @@ use http::{Method, StatusCode};
 use tokio::time::{Duration, sleep, timeout};
 use tracing::{debug, info};
 
-fn skip_without_awscurl() -> bool {
-    if crate::common::awscurl_available() {
-        return false;
-    }
-
-    info!("Skipping quota test because awscurl is not available");
-    true
-}
-
 /// Test environment setup for quota tests
 pub struct QuotaTestEnv {
     pub env: RustFSTestEnvironment,
@@ -276,9 +267,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_basic_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         // Create test bucket
@@ -320,9 +308,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_admission_aws_chunked_declared_encoding() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
         env.create_bucket().await?;
 
@@ -371,9 +356,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_update_and_clear() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -406,9 +388,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_delete_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -442,9 +421,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_usage_tracking() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -480,9 +456,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_statistics() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -513,9 +486,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_check_api() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -553,9 +523,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_multiple_buckets() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         // Create two buckets in the same environment
@@ -593,9 +560,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_error_handling() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -628,9 +592,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_http_endpoints() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -689,9 +650,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_normal_user_permissions() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
         env.create_bucket().await?;
 
@@ -744,9 +702,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_copy_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -789,9 +744,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_batch_delete() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -847,9 +799,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_multipart_upload() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;

crates/e2e_test/src/replication_extension_test.rs

@@ -13,9 +13,8 @@
 // limitations under the License.
 
 use crate::common::{
-    RustFSTestEnvironment, admin_create_user, awscurl_available, awscurl_post_sts_form_urlencoded, init_logging,
+    RustFSTestEnvironment, admin_create_user, awscurl_post_sts_form_urlencoded, init_logging, local_http_client,
-    local_http_client, replication_fast_env, rustfs_binary_path, signed_request, signed_request_with_client,
+    replication_fast_env, rustfs_binary_path, signed_request, signed_request_with_client, signed_request_with_session_token,
-    signed_request_with_session_token,
 };
 use crate::fake_s3_target::{
     FAKE_ACCESS_KEY, FAKE_SECRET_KEY, FakeS3Target, FaultAction as FakeTargetFault, Operation as FakeTargetOperation,
@@ -7281,11 +7280,6 @@ async fn test_site_replication_replicates_multiple_service_accounts_real_dual_no
 async fn test_site_replication_replicates_service_accounts_created_from_sts_session_real_dual_node() -> TestResult {
     init_logging();
 
-    if !awscurl_available() {
-        eprintln!("Skipping STS site replication service-account test because awscurl is unavailable");
-        return Ok(());
-    }
-
     let mut source_env = RustFSTestEnvironment::new().await?;
     source_env
         .start_rustfs_server_with_env(vec![], LOOPBACK_REPLICATION_TARGET_ENV)

crates/e2e_test/src/security_boundary_test.rs

@@ -21,7 +21,7 @@
 //! - SSRF prevention (internal/private endpoints rejected for tiering)
 //! - Race condition handling (concurrent writes converge without corruption)
 
-use crate::common::{RustFSTestEnvironment, awscurl_available, awscurl_put, init_logging};
+use crate::common::{RustFSTestEnvironment, awscurl_put, init_logging};
 use aws_sdk_s3::error::ProvideErrorMetadata;
 use aws_sdk_s3::primitives::ByteStream;
 use aws_sdk_s3::types::{CompletedMultipartUpload, CompletedPart, Tag, Tagging};
@@ -225,16 +225,11 @@ async fn test_concurrent_object_operations() -> Result<(), Box<dyn Error + Send
 /// outcome — the internal endpoint is not accepted — is asserted here.
 ///
 /// The admin API is exercised via signed `awscurl` requests, matching the
-/// pattern used by the other admin-API E2E tests in this crate; the test is
+/// pattern used by the other admin-API E2E tests in this crate. The full E2E
-/// skipped when `awscurl` is not installed.
+/// lane installs and verifies the pinned `awscurl` prerequisite.
 #[tokio::test]
 async fn test_tiering_url_validation() -> Result<(), Box<dyn Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping tiering URL validation test because awscurl is not available");
-        return Ok(());
-    }
-
     let mut env = RustFSTestEnvironment::new().await?;
     env.start_rustfs_server(vec![]).await?;
 

crates/ecstore/src/io_support/bitrot.rs

@@ -784,6 +784,24 @@ pub(crate) fn create_deferred_bitrot_reader_with_stripe_handle(
 ///
 /// # Returns
 /// A Result containing the BitrotWriterWrapper or an error
+/// Size hint handed to `DiskAPI::create_file` for a bitrot-wrapped shard.
+///
+/// A known length is grown by one checksum per shard so the on-disk file size
+/// matches what the bitrot writer emits. A negative length is the
+/// unknown-size sentinel (`HashReader::SIZE_PRESERVE_LAYER`, used by SSE and
+/// compression) and must be preserved: `RemoteDisk::create_file` forwards it
+/// in the `put_file_stream` query, and the receiver only treats `size > 0` as
+/// a fixed body length when locating the authenticated trailer. Clamping it
+/// to `0` would claim an empty body and misframe the stream. `0` stays `0`
+/// because a genuinely empty object still means an empty body.
+fn bitrot_create_file_size(length: i64, shard_size: usize, checksum_algo: &HashAlgorithm) -> i64 {
+    if length <= 0 {
+        return length;
+    }
+    let length = length as usize;
+    (length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
+}
+
 pub async fn create_bitrot_writer(
     is_inline_buffer: bool,
     disk: Option<&DiskStore>,
@@ -796,12 +814,7 @@ pub async fn create_bitrot_writer(
     let writer = if is_inline_buffer {
         CustomWriter::new_inline_buffer()
     } else if let Some(disk) = disk {
-        let length = if length > 0 {
+        let length = bitrot_create_file_size(length, shard_size, &checksum_algo);
-            let length = length as usize;
-            (length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
-        } else {
-            0
-        };
 
         let file = disk.create_file("", volume, path, length).await?;
         #[cfg(feature = "hotpath")]
@@ -820,6 +833,25 @@ mod tests {
     use rustfs_rio::ChunkReader;
     use std::collections::VecDeque;
 
+    #[test]
+    fn bitrot_create_file_size_grows_known_length_by_checksums() {
+        // 10 bytes over 4-byte shards = 3 shards, each followed by a 32-byte hash.
+        assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::HighwayHash256), 10 + 3 * 32);
+        assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::None), 10);
+    }
+
+    #[test]
+    fn bitrot_create_file_size_keeps_empty_and_unknown_distinct() {
+        assert_eq!(bitrot_create_file_size(0, 4, &HashAlgorithm::HighwayHash256), 0);
+        // SSE/compression streams advertise SIZE_PRESERVE_LAYER (-1); the remote
+        // put_file_stream receiver relies on a non-positive size to parse the auth
+        // trailer from the stream tail, so the sentinel must survive untouched.
+        assert_eq!(
+            bitrot_create_file_size(rustfs_rio::HashReader::SIZE_PRESERVE_LAYER, 4, &HashAlgorithm::HighwayHash256),
+            rustfs_rio::HashReader::SIZE_PRESERVE_LAYER
+        );
+    }
+
     struct TestChunkReader {
         chunks: VecDeque<Bytes>,
     }

crates/kms/tests/vault_ha_failover_live.rs

@@ -16,14 +16,14 @@
 //!
 //! `scripts/test/vault_ha_kms_live.sh` owns the official Vault containers and
 //! kills the active node while this test continuously decrypts through a
-//! surviving standby. KV2 and Transit requests must remain successful, use a
+//! surviving standby. KV2 and Transit must recover after the bounded circuit
-//! bounded number of attempts, and leave the circuit and in-flight gauges at
+//! interval, use a bounded number of attempts, and leave the circuit and
-//! zero after a new leader is elected.
+//! in-flight gauges at zero after a new leader is elected.
 
 use std::collections::HashMap;
 use std::path::{Path, PathBuf};
-use std::sync::Arc;
 use std::sync::atomic::{AtomicBool, AtomicU64, Ordering};
+use std::sync::{Arc, Mutex};
 use std::time::Duration;
 
 use metrics_util::MetricKind;
@@ -43,6 +43,11 @@ const OPERATION_ATTEMPTS: &str = "rustfs_kms_backend_operation_attempts";
 const IN_FLIGHT: &str = "rustfs_kms_backend_in_flight";
 const CIRCUIT_OPEN: &str = "rustfs_kms_backend_circuit_open";
 const MAX_ATTEMPTS: u32 = 10;
+const ATTEMPT_TIMEOUT: Duration = Duration::from_secs(2);
+const HEALTHY_PROGRESS_TIMEOUT: Duration = Duration::from_secs(20);
+// The circuit remains open for 30s after five failed attempts.
+const POST_FAILOVER_PROGRESS_TIMEOUT: Duration = Duration::from_secs(35);
+const FAILOVER_ERROR_POLL_INTERVAL: Duration = Duration::from_millis(100);
 
 type MetricEntry = (
     metrics_util::CompositeKey,
@@ -64,7 +69,7 @@ fn config(backend: KmsBackend, backend_config: BackendConfig) -> KmsConfig {
         backend,
         backend_config,
         allow_insecure_dev_defaults: true,
-        timeout: Duration::from_secs(2),
+        timeout: ATTEMPT_TIMEOUT,
         retry_attempts: MAX_ATTEMPTS,
         enable_cache: false,
         ..KmsConfig::default()
@@ -164,14 +169,31 @@ fn retryable_failures(snapshot: &[MetricEntry], operation: &str) -> u64 {
         .sum()
 }
 
-async fn wait_for_count(counter: &AtomicU64, minimum: u64, description: &str) {
+async fn wait_for_count(
-    tokio::time::timeout(Duration::from_secs(20), async {
+    counter: &AtomicU64,
+    failure: &Mutex<Option<String>>,
+    minimum: u64,
+    description: &str,
+    timeout: Duration,
+) {
+    tokio::time::timeout(timeout, async {
         while counter.load(Ordering::SeqCst) < minimum {
+            if let Some(error) = failure.lock().expect("decrypt failure lock poisoned").as_ref() {
+                panic!(
+                    "{description} worker failed after {} successful decrypts: {error}",
+                    counter.load(Ordering::SeqCst)
+                );
+            }
             tokio::time::sleep(Duration::from_millis(25)).await;
         }
     })
     .await
-    .unwrap_or_else(|_| panic!("timed out waiting for {description}"));
+    .unwrap_or_else(|_| {
+        panic!(
+            "timed out after {timeout:?} waiting for {description}: completed {}, expected {minimum}",
+            counter.load(Ordering::SeqCst)
+        )
+    });
 }
 
 async fn wait_for_file(path: &Path, description: &str) {
@@ -189,7 +211,8 @@ async fn decrypt_loop<B: KmsBackendTrait + Send + Sync + 'static>(
     request: DecryptRequest,
     expected: Vec<u8>,
     completed: Arc<AtomicU64>,
-    failed: Arc<AtomicBool>,
+    allow_failover_errors: Arc<AtomicBool>,
+    failure: Arc<Mutex<Option<String>>>,
     stop: CancellationToken,
 ) {
     while !stop.is_cancelled() {
@@ -197,8 +220,18 @@ async fn decrypt_loop<B: KmsBackendTrait + Send + Sync + 'static>(
             Ok(response) if response.plaintext == expected => {
                 completed.fetch_add(1, Ordering::SeqCst);
             }
-            Ok(_) | Err(_) => {
+            Ok(_) => {
-                failed.store(true, Ordering::SeqCst);
+                *failure.lock().expect("decrypt failure lock poisoned") =
+                    Some("decrypt returned unexpected plaintext".to_string());
+                return;
+            }
+            Err(rustfs_kms::KmsError::BackendError { .. } | rustfs_kms::KmsError::OperationTimedOut { .. })
+                if allow_failover_errors.load(Ordering::SeqCst) =>
+            {
+                tokio::time::sleep(FAILOVER_ERROR_POLL_INTERVAL).await;
+            }
+            Err(error) => {
+                *failure.lock().expect("decrypt failure lock poisoned") = Some(error.to_string());
                 return;
             }
         }
@@ -296,7 +329,9 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
     );
 
     let stop = CancellationToken::new();
-    let failed = Arc::new(AtomicBool::new(false));
+    let allow_failover_errors = Arc::new(AtomicBool::new(false));
+    let kv2_failure = Arc::new(Mutex::new(None));
+    let transit_failure = Arc::new(Mutex::new(None));
     let kv2_completed = Arc::new(AtomicU64::new(0));
     let transit_completed = Arc::new(AtomicU64::new(0));
     let kv2_worker = tokio::spawn(decrypt_loop(
@@ -304,7 +339,8 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
         kv2_request,
         kv2_data_key.plaintext_key,
         Arc::clone(&kv2_completed),
-        Arc::clone(&failed),
+        Arc::clone(&allow_failover_errors),
+        Arc::clone(&kv2_failure),
         stop.clone(),
     ));
     let transit_worker = tokio::spawn(decrypt_loop(
@@ -312,12 +348,21 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
         transit_request,
         transit_data_key.plaintext_key,
         Arc::clone(&transit_completed),
-        Arc::clone(&failed),
+        Arc::clone(&allow_failover_errors),
+        Arc::clone(&transit_failure),
         stop.clone(),
     ));
 
-    wait_for_count(&kv2_completed, 2, "two healthy KV2 decrypts").await;
+    wait_for_count(&kv2_completed, &kv2_failure, 2, "two healthy KV2 decrypts", HEALTHY_PROGRESS_TIMEOUT).await;
-    wait_for_count(&transit_completed, 2, "two healthy Transit decrypts").await;
+    wait_for_count(
+        &transit_completed,
+        &transit_failure,
+        2,
+        "two healthy Transit decrypts",
+        HEALTHY_PROGRESS_TIMEOUT,
+    )
+    .await;
+    allow_failover_errors.store(true, Ordering::SeqCst);
     std::fs::write(&marker, b"ready").expect("publish failover readiness marker");
 
     wait_for_file(&elected, "the replacement Vault leader").await;
@@ -326,18 +371,39 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
 
     let kv2_after_election = kv2_completed.load(Ordering::SeqCst) + 2;
     let transit_after_election = transit_completed.load(Ordering::SeqCst) + 2;
-    wait_for_count(&kv2_completed, kv2_after_election, "post-failover KV2 decrypts").await;
+    wait_for_count(
-    wait_for_count(&transit_completed, transit_after_election, "post-failover Transit decrypts").await;
+        &kv2_completed,
+        &kv2_failure,
+        kv2_after_election,
+        "post-failover KV2 decrypts",
+        POST_FAILOVER_PROGRESS_TIMEOUT,
+    )
+    .await;
+    wait_for_count(
+        &transit_completed,
+        &transit_failure,
+        transit_after_election,
+        "post-failover Transit decrypts",
+        POST_FAILOVER_PROGRESS_TIMEOUT,
+    )
+    .await;
 
     stop.cancel();
     kv2_worker.await.expect("KV2 decrypt worker must join");
     transit_worker.await.expect("Transit decrypt worker must join");
-    assert!(!failed.load(Ordering::SeqCst), "no decrypt may fail or return different plaintext");
+    assert!(
+        kv2_failure.lock().expect("KV2 failure lock poisoned").is_none(),
+        "no KV2 decrypt may fail or return different plaintext"
+    );
+    assert!(
+        transit_failure.lock().expect("Transit failure lock poisoned").is_none(),
+        "no Transit decrypt may fail or return different plaintext"
+    );
 }
 
 #[test]
 #[ignore = "requires a real three-node Vault Raft cluster; run scripts/test/vault_ha_kms_live.sh"]
-fn vault_raft_leader_failure_preserves_kv2_and_transit_decrypts() {
+fn vault_raft_leader_failure_recovers_kv2_and_transit_decrypts() {
     let recorder = DebuggingRecorder::new();
     let snapshotter = recorder.snapshotter();
     metrics::with_local_recorder(&recorder, || {
@@ -349,11 +415,6 @@ fn vault_raft_leader_failure_preserves_kv2_and_transit_decrypts() {
     });
     let snapshot = snapshotter.snapshot().into_vec();
 
-    assert_eq!(
-        counter_value(&snapshot, OPERATIONS_TOTAL, &[("outcome", "circuit_open")]),
-        0,
-        "a bounded leader election must not open the circuit"
-    );
     assert_eq!(
         counter_value(&snapshot, OPERATIONS_TOTAL, &[("outcome", "budget_exhausted")]),
         0,

scripts/test/vault_ha_kms_live.sh

@@ -241,7 +241,7 @@ env \
   RUSTFS_TEST_VAULT_FAILOVER_MARKER="$MARKER" \
   RUSTFS_TEST_VAULT_OLD_LEADER="$OLD_LEADER" \
   cargo test -p rustfs-kms --test vault_ha_failover_live \
-    vault_raft_leader_failure_preserves_kv2_and_transit_decrypts -- \
+    vault_raft_leader_failure_recovers_kv2_and_transit_decrypts -- \
     --ignored --nocapture --test-threads=1 &
 TEST_PID=$!