fix(ecstore): handle stalled recovery reads and listings (#3790)

* fix(ecstore): handle stalled recovery reads and listings

* fix(rio): start HTTP stall timeout on read

* fix(ecstore): handle stalled reads and partial lists

* fix(ecstore): retire stalled shards and list errors

* fix(ecstore): preserve list merge lookahead entries

* fix(ecstore): bound zero-copy shard reads

* fix(ecstore): hedge stalled shard reads

* fix(ecstore): retire abandoned shard reads

* fix(ecstore): include part identity in metadata quorum

* fix(ecstore): validate heal shard sources

* fix(ecstore): verify reconstructed read shards

* chore(ecstore): log slow object read stages

* fix(heal): throttle auto heal during recovery

* fix(scanner): yield to foreground reads

* fix(scanner): track streaming object reads

* fix(ecstore): avoid false read heal fanout

* fix(ecstore): verify codec streaming reconstruction sources

* fix(ecstore): preserve quorum progress on slow shards

* fix(storage): restore read timeout facade

* fix(ecstore): retain fallback readers after quorum

* chore: allow decode helper argument lists

---------

Co-authored-by: overtrue <anzhengchao@gmail.com>
This commit is contained in:
GatewayJ
2026-06-27 10:21:09 +08:00
committed by GitHub
parent 3fb4dcd52e
commit 675597ec16
28 changed files with 2991 additions and 486 deletions
+32
View File
@@ -366,6 +366,10 @@ fn scanner_concurrency_limit(configured: usize, available: usize) -> usize {
return 0;
}
if crate::current_foreground_read_activity() > 0 {
return 1;
}
if configured == 0 {
available
} else {
@@ -1656,25 +1660,53 @@ mod tests {
}
#[test]
#[serial]
fn scanner_concurrency_limit_preserves_available_when_unconfigured() {
crate::reset_foreground_read_activity_for_test();
assert_eq!(scanner_concurrency_limit(0, 4), 4);
}
#[test]
#[serial]
fn scanner_concurrency_limit_caps_to_configured_value() {
crate::reset_foreground_read_activity_for_test();
assert_eq!(scanner_concurrency_limit(2, 4), 2);
}
#[test]
#[serial]
fn scanner_concurrency_limit_never_exceeds_available_work() {
crate::reset_foreground_read_activity_for_test();
assert_eq!(scanner_concurrency_limit(8, 4), 4);
}
#[test]
#[serial]
fn scanner_concurrency_limit_handles_no_available_work() {
crate::reset_foreground_read_activity_for_test();
assert_eq!(scanner_concurrency_limit(2, 0), 0);
}
#[test]
#[serial]
fn scanner_concurrency_limit_yields_to_foreground_reads() {
crate::reset_foreground_read_activity_for_test();
crate::set_foreground_read_activity(8);
assert_eq!(scanner_concurrency_limit(0, 4), 1);
assert_eq!(scanner_concurrency_limit(3, 4), 1);
crate::reset_foreground_read_activity_for_test();
}
#[test]
#[serial]
fn scanner_concurrency_limit_yields_to_streaming_reads() {
crate::reset_foreground_read_activity_for_test();
let _guard = crate::ForegroundReadGuard::new();
assert_eq!(scanner_concurrency_limit(0, 4), 1);
assert_eq!(scanner_concurrency_limit(3, 4), 1);
}
#[test]
fn decrement_atomic_usize_saturates_at_zero() {
let counter = AtomicUsize::new(1);