mirror of
https://github.com/rustfs/rustfs.git
synced 2026-07-26 16:28:15 +00:00
houseme
cb977c4c5a
fix(admin): report unreachable info members as `unknown` with balanced drive counts `GET /rustfs/admin/v3/info` synthesizes an entry for every peer, but a peer whose properties RPC failed below the offline threshold with no cached snapshot was reported as `initializing` with an empty drive list. That drive list being empty meant its drives disappeared from the backend summary entirely, so `onlineDisks + offlineDisks` no longer equaled `totalDrivesPerSet` (an operator sees `onlineDisks: 3, offlineDisks: 0` for a 4-drive set), and `initializing` is a misleading state for a member that has been running for hours — it reads like a node was ejected when nothing is wrong (upstream rustfs/rustfs#4566). Changes: - madmin: add `ItemState::Unknown` ("unknown") and an `unknownDisks` bucket on `ErasureBackend` (serde `default`, so older payloads still deserialize). - ecstore diagnostics: `get_online_offline_disks_stats` now returns a third `unknown` bucket instead of folding those drives into `offline`, keeping `online + offline + unknown == totalDrivesPerSet`. - ecstore notification_sys: a probe miss below the failure threshold with no cache is now reported as `unknown` (not `initializing`) and carries the host's drives from the pool topology (tagged `unknown`) so the summary stays balanced; drive synthesis is factored into `synthesized_disks(host, endpoints, state)`, shared by the offline and unknown paths. Tracked in rustfs/backlog#1049 (P1-A + P0-A). Co-authored-by: heihutu <heihutu@gmail.com>