Files
rustfs/crates/ecstore/src/store/heal_walk.rs
T
houseme 360bceafce feat(heal): add progress and trace observability (#6179)
* feat(heal): track erasure set progress baseline

Record erasure-set heal byte progress from per-object results and seed progress totals from complete usage-cache snapshots when available.

Keep usage-cache failures observational so heal execution continues without a baseline.

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

* feat(heal): skip filtered erasure set versions

Skip erasure-set versions written after the durable heal start time, and queue lifecycle-expired versions for expiry before skipping them.

Track new-version and ILM-expired skips separately so progress can explain completed baseline work without treating these skips as retry-blocking failures.

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

* feat(heal): wire abandoned data-dir cleanup check

Connect check_abandoned_parts through ECStore, pool, and set layers so heal can invoke the existing orphan data-dir reclaim path instead of returning NotImplemented.

Add dry-run support to the reclaim scan and cover dry-run plus scoped set behavior with regression tests.

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

* feat(obs): add heal scanner trace bus

Introduce an in-process broadcast trace bus with typed heal and scanner events, lazy event construction, and bounded lagged-subscriber behavior.

Cover zero-subscriber publishing, subscription delivery, drop accounting, and lagged receivers with focused common-crate tests.

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

* feat(obs): stream heal trace events from admin API

Wire the admin trace endpoint to the common trace bus for heal/scanner events, including kind, regex, and threshold filtering.

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

* feat(obs): emit heal trace events

Publish heal task lifecycle and abandoned-parts cleanup events through the common trace bus so the admin trace stream has live heal diagnostics.

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

* feat(obs): emit scanner trace events

Publish scanner folder, lifecycle action, and heal-candidate events through the common trace bus for live admin scanner diagnostics.

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

* fix(heal): route data usage loader through storage api

Keep ECStore data-usage facade access behind the heal storage_api boundary so architecture migration guards can validate the heal progress path.

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

* perf(heal): avoid lifecycle snapshots on ordinary heal pages

Only request lifecycle object snapshots when the heal pass has lifecycle expiry context. This keeps ordinary listing and disk-walk pages from cloning FileInfo/ObjectInfo payloads while preserving the skip path that queues expired versions.

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

* test(heal): update bug-fix mocks for lifecycle snapshots

Carry the lifecycle snapshot opt-in argument through the remaining heal bug-fix test mocks so all-targets clippy covers the updated storage trait.

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

* test(rustfs): sync heal storage mock signature

Update the rustfs storage RPC test mock for the lifecycle snapshot opt-in argument and cover it with rustfs all-targets clippy.

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

* test(e2e): allocate smoke ports across nextest processes

Serialize E2E port selection with a small /tmp allocator so nextest workers do not reuse the same just-released ephemeral port before RustFS binds it.

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

---------

Co-authored-by: heihutu <heihutu@gmail.com>
2026-08-18 08:29:29 +08:00

52 lines
2.1 KiB
Rust

// Copyright 2024 RustFS Team
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//! Store-level entry point for the per-erasure-set disk-walk UNION heal
//! enumerator (backlog#920). Bounds-checks `(pool_idx, set_idx)` (mirroring
//! `handle_get_disks`) and delegates to the target `SetDisks`.
use super::*;
pub use crate::set_disk::HealWalkVersion;
impl ECStore {
/// Walk a specific erasure set's disks and return one page of the cross-disk
/// UNION of versions (see `SetDisks::heal_walk_versions_page`). `pool_idx` and
/// `set_idx` are bounds-checked against the live pool topology.
#[instrument(level = "debug", skip(self))]
#[allow(clippy::too_many_arguments)]
pub async fn heal_walk_versions_page(
&self,
pool_idx: usize,
set_idx: usize,
bucket: &str,
prefix: &str,
forward_to: Option<&str>,
batch_objects: usize,
version_budget: usize,
include_lifecycle_object_info: bool,
) -> Result<(Vec<HealWalkVersion>, Option<String>, bool)> {
if pool_idx >= self.pools.len() || set_idx >= self.pools[pool_idx].disk_set.len() {
return Err(Error::other(format!(
"heal disk-walk: invalid erasure set (pool index {pool_idx}, set index {set_idx}, pool count {})",
self.pools.len()
)));
}
self.pools[pool_idx].disk_set[set_idx]
.heal_walk_versions_page(bucket, prefix, forward_to, batch_objects, version_budget, include_lifecycle_object_info)
.await
.map_err(Error::from)
}
}