mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-18 10:43:15 +00:00
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>
This commit is contained in:
@@ -176,7 +176,7 @@ async fn enumerate_all_versions(heal_storage: &Arc<ECStoreHealStorage>, bucket:
|
||||
let mut token: Option<String> = None;
|
||||
loop {
|
||||
let (page, next, truncated) = heal_storage
|
||||
.list_objects_for_heal_page(bucket, "", token.as_deref())
|
||||
.list_objects_for_heal_page(bucket, "", token.as_deref(), false)
|
||||
.await
|
||||
.expect("list_objects_for_heal_page failed");
|
||||
items.extend(page);
|
||||
|
||||
@@ -166,7 +166,7 @@ async fn enumerate_b5(heal_storage: &Arc<ECStoreHealStorage>, bucket: &str) -> V
|
||||
let mut token: Option<String> = None;
|
||||
loop {
|
||||
let (page, next, truncated) = heal_storage
|
||||
.list_objects_for_heal_page(bucket, "", token.as_deref())
|
||||
.list_objects_for_heal_page(bucket, "", token.as_deref(), false)
|
||||
.await
|
||||
.expect("b5 list page failed");
|
||||
items.extend(page);
|
||||
@@ -187,7 +187,7 @@ async fn enumerate_disk_walk(heal_storage: &Arc<ECStoreHealStorage>, bucket: &st
|
||||
let mut token: Option<String> = None;
|
||||
loop {
|
||||
let (page, next, truncated) = heal_storage
|
||||
.list_versions_for_heal_page_disk_walk(SET_DISK_ID, bucket, "", token.as_deref())
|
||||
.list_versions_for_heal_page_disk_walk(SET_DISK_ID, bucket, "", token.as_deref(), false)
|
||||
.await
|
||||
.expect("disk-walk list page failed");
|
||||
items.extend(page);
|
||||
@@ -418,7 +418,7 @@ mod serial_tests {
|
||||
let mut pages = 0usize;
|
||||
loop {
|
||||
let (versions, next_forward, truncated) = ecstore
|
||||
.heal_walk_versions_page(0, 0, bucket, "", forward.as_deref(), 2, 100_000)
|
||||
.heal_walk_versions_page(0, 0, bucket, "", forward.as_deref(), 2, 100_000, false)
|
||||
.await
|
||||
.expect("heal_walk_versions_page failed");
|
||||
pages += 1;
|
||||
|
||||
@@ -242,6 +242,7 @@ fn test_heal_task_status_atomic_update() {
|
||||
_bucket: &str,
|
||||
_prefix: &str,
|
||||
_continuation_token: Option<&str>,
|
||||
_include_lifecycle_object_info: bool,
|
||||
) -> rustfs_heal::Result<(Vec<HealListItem>, Option<String>, bool)> {
|
||||
Ok((vec![], None, false))
|
||||
}
|
||||
@@ -385,6 +386,7 @@ async fn test_heal_task_transient_object_exists_skip_avoids_recreate() {
|
||||
_bucket: &str,
|
||||
_prefix: &str,
|
||||
_continuation_token: Option<&str>,
|
||||
_include_lifecycle_object_info: bool,
|
||||
) -> rustfs_heal::Result<(Vec<HealListItem>, Option<String>, bool)> {
|
||||
Ok((Vec::new(), None, false))
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user