fix(cluster): clarify peer health and listing timeouts (#5086)

* fix(cluster): surface observed peer health

Refs rustfs/backlog#1387

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(admin): distinguish unreported peer health

Refs rustfs/backlog#1388

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(ecstore): decouple metacache peek timeout

Refs rustfs/backlog#1389

Co-Authored-By: heihutu <heihutu@gmail.com>

* docs(ops): diagnose metacache listing timeouts

Refs rustfs/backlog#1390

Co-Authored-By: heihutu <heihutu@gmail.com>

* refactor(cluster): clarify observed peer health

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(ecstore): route capability state through contract

Co-Authored-By: heihutu <heihutu@gmail.com>

---------

Co-authored-by: heihutu <heihutu@gmail.com>
This commit is contained in:
houseme
2026-07-21 19:11:24 +08:00
committed by GitHub
parent bb7bba3237
commit 7805cf5ae6
10 changed files with 349 additions and 45 deletions
+5
View File
@@ -39,6 +39,11 @@ pub const DEFAULT_DRIVE_WALKDIR_TIMEOUT_SECS: u64 = 5;
pub const ENV_DRIVE_WALKDIR_STALL_TIMEOUT_SECS: &str = "RUSTFS_DRIVE_WALKDIR_STALL_TIMEOUT_SECS";
pub const DEFAULT_DRIVE_WALKDIR_STALL_TIMEOUT_SECS: u64 = 5;
/// Maximum time the metacache merge consumer waits for the next visible
/// `walk_dir()` entry from a reader before detaching it from the merge.
pub const ENV_DRIVE_WALKDIR_PEEK_TIMEOUT_SECS: &str = "RUSTFS_DRIVE_WALKDIR_PEEK_TIMEOUT_SECS";
pub const DEFAULT_DRIVE_WALKDIR_PEEK_TIMEOUT_SECS: u64 = 10;
/// Interval in seconds between active health probes for local and remote drives.
pub const ENV_DRIVE_ACTIVE_CHECK_INTERVAL_SECS: &str = "RUSTFS_DRIVE_ACTIVE_CHECK_INTERVAL_SECS";
pub const DEFAULT_DRIVE_ACTIVE_CHECK_INTERVAL_SECS: u64 = 15;