fix(ecstore): make transitioned cleanup crash-safe (#6978)

* fix(ecstore): fence transitioned object cleanup

* fix(ecstore): address ILM recovery review findings

* fix(ecstore): complete crash-safe tier cleanup recovery

* test(ecstore): avoid typo false positive

* fix(ecstore): stabilize decommission error buckets

* fix(ecstore): stabilize transition delete validation

* fix(ecstore): resume authorized tier delete dispatch

* fix(ecstore): satisfy feature clippy

crates/ecstore/src/error/conversion_roundtrip_tests.rs

@@ -278,3 +278,17 @@ fn reduce_errs_buckets_identical_other_messages_together() {
     assert_eq!(count, 3);
     assert_eq!(err, Some(DiskError::other("can not get client")));
 }
+
+#[test]
+fn stable_io_context_buckets_by_cause_and_preserves_diagnostic_source() {
+    let first = StorageError::other_with_context("tier mutation intent changed", "mutation-a");
+    let second = StorageError::other_with_context("tier mutation intent changed", "mutation-b");
+
+    assert_eq!(first, second, "diagnostic identity must not split quorum buckets");
+    let StorageError::Io(io_error) = first else {
+        panic!("stable context must remain an io error");
+    };
+    assert_eq!(io_error.to_string(), "tier mutation intent changed");
+    let context = io_error.get_ref().expect("stable context must remain downcastable");
+    assert_eq!(context.source().expect("diagnostic source must be retained").to_string(), "mutation-a");
+}

crates/ecstore/src/error/mod.rs

@@ -23,6 +23,36 @@ use s3s::S3ErrorCode;
 pub type Error = StorageError;
 pub type Result<T> = core::result::Result<T, Error>;
 
+/// Keeps high-cardinality diagnostic detail in the error source while making
+/// the rendered `io::Error` stable for quorum aggregation.
+#[derive(Debug)]
+struct StableIoContextError {
+    message: &'static str,
+    source: Box<dyn std::error::Error + Send + Sync>,
+}
+
+impl std::fmt::Display for StableIoContextError {
+    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        formatter.write_str(self.message)
+    }
+}
+
+impl std::error::Error for StableIoContextError {
+    fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
+        Some(self.source.as_ref())
+    }
+}
+
+pub(crate) fn stable_io_error<E>(message: &'static str, source: E) -> std::io::Error
+where
+    E: Into<Box<dyn std::error::Error + Send + Sync>>,
+{
+    std::io::Error::other(StableIoContextError {
+        message,
+        source: source.into(),
+    })
+}
+
 /// Storage layer error type covering disk, volume, bucket, object, multipart,
 /// erasure-coding, and operational error conditions.
 ///
@@ -264,6 +294,13 @@ impl StorageError {
         StorageError::Io(std::io::Error::other(error))
     }
 
+    pub(crate) fn other_with_context<E>(message: &'static str, source: E) -> Self
+    where
+        E: Into<Box<dyn std::error::Error + Send + Sync>>,
+    {
+        StorageError::Io(stable_io_error(message, source))
+    }
+
     pub fn is_not_found(&self) -> bool {
         matches!(
             self,