diff --git a/Cargo.lock b/Cargo.lock index 63e94b893..79a87afae 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -9486,8 +9486,6 @@ version = "1.0.0-rc.3" dependencies = [ "hotpath", "metrics", - "rustfs-heal-contracts", - "rustfs-scanner-contracts", "smallvec", "tokio", "tonic", diff --git a/crates/common/Cargo.toml b/crates/common/Cargo.toml index b78526088..1d610aed2 100644 --- a/crates/common/Cargo.toml +++ b/crates/common/Cargo.toml @@ -39,10 +39,6 @@ tokio = { workspace = true, features = ["fs", "rt-multi-thread"] } tonic = { workspace = true, features = ["gzip", "deflate"] } uuid = { workspace = true, features = ["v4", "fast-rng", "macro-diagnostics"] } metrics = { workspace = true } -# Transitional shim deps (backlog#1843): dropped with the re-export shims once -# every consumer imports the contracts crates directly. -rustfs-heal-contracts = { workspace = true } -rustfs-scanner-contracts = { workspace = true } smallvec = { workspace = true } tracing = { workspace = true } diff --git a/crates/common/src/globals.rs b/crates/common/src/globals.rs index d4fe349e2..e4cd89c88 100644 --- a/crates/common/src/globals.rs +++ b/crates/common/src/globals.rs @@ -27,10 +27,6 @@ pub static GLOBAL_ROOT_CERT: LazyLock>>> = LazyLock::new(| pub static GLOBAL_MTLS_IDENTITY: LazyLock>> = LazyLock::new(|| RwLock::new(None)); pub static GLOBAL_OUTBOUND_TLS_GENERATION: LazyLock = LazyLock::new(|| AtomicU64::new(0)); -// Transitional re-export shim (backlog#1843): the node init-time global moved -// to rustfs-scanner-contracts, whose metrics report reads it directly. -pub use rustfs_scanner_contracts::{GLOBAL_INIT_TIME, get_global_init_time, set_global_init_time_now}; - /// Log level to use when reporting cached gRPC connection eviction. #[derive(Clone, Copy, Debug, Eq, PartialEq)] pub enum ConnectionEvictionLogLevel { diff --git a/crates/common/src/lib.rs b/crates/common/src/lib.rs index 9cfc5bfea..4c7d8cfe3 100644 --- a/crates/common/src/lib.rs +++ b/crates/common/src/lib.rs @@ -19,13 +19,6 @@ mod readiness; pub mod table_catalog; pub mod trace_bus; -// Transitional re-export shims (backlog#1843): these modules moved to the -// rustfs-heal-contracts / rustfs-scanner-contracts crates. Consumers migrate -// to the new paths crate by crate; the shims are deleted once -// `rg 'rustfs_common::(metrics|heal_channel|last_minute)'` reports zero hits. -pub use rustfs_heal_contracts::heal_channel; -pub use rustfs_scanner_contracts::{last_minute, metrics}; - pub use globals::*; pub use readiness::{GlobalReadiness, SystemStage}; diff --git a/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16.md b/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16.md index 931d020e8..da7572639 100644 --- a/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16.md +++ b/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16.md @@ -3,7 +3,7 @@ > English | [中文版](rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16_zh.md) - Date: 2026-08-16 (based on that day's `main` code; audit HEAD ≈ `a118d7e4f`) -- Scope: `crates/heal` (src 19,560 lines + tests 2,274 lines), `crates/scanner` (src ~26,000 lines + tests), `crates/data-usage`, the heal/heal_walk/bitrot_self_verify and config parts of `crates/ecstore`, `crates/common/src/heal_channel.rs`, `crates/madmin` (heal/scanner wire types), `rustfs/src` (startup wiring, admin handlers, cluster RPC) +- Scope: `crates/heal` (src 19,560 lines + tests 2,274 lines), `crates/scanner` (src ~26,000 lines + tests), `crates/data-usage`, the heal/heal_walk/bitrot_self_verify and config parts of `crates/ecstore`, `crates/heal-contracts/src/heal_channel.rs`, `crates/madmin` (heal/scanner wire types), `rustfs/src` (startup wiring, admin handlers, cluster RPC) - Parity baseline: minio/minio master (HEAD `7aac2a2c5b`; the repo has entered maintenance mode with master frozen, i.e. its final state) - Method: four parallel audit tracks (heal crate / scanner crate / ecstore integration layer / MinIO source study), with key conclusions verified by hand one by one (points marked "verified first-hand" below were checked against the source directly) - This document supersedes `docs/rustfs-heal-scanner-vs-minio-parity-assessment.md` (2026-06-15, v1). Since v1 there have been more than 80 heal/scanner commits (the full automatic drive-replacement healing chain, the resume state machine, making usage convergence authoritative, cluster-level heal coordination, ILM restore semantics, etc.), so v1's feature inventory and gap judgments are comprehensively outdated; v1 conclusions such as "bloom filter missing" were verified this round to be **misjudgments** (see §5.4). @@ -31,7 +31,7 @@ RustFS splits the heal/scanner functionality that MinIO keeps inside the `cmd/` | Primitives layer | `crates/ecstore/src/set_disk/ops/heal.rs` (~3,240 lines), `ops/heal_walk.rs`, `ops/bitrot_self_verify.rs`; upper wrappers `store/heal.rs`, `store/heal_walk.rs`, `core/sets.rs` | Object/bucket/format/replacement-drive format repair, disk-walk union enumeration, write-path bitrot self-verification; the `rustfs_storage_api::HealOperations` contract is implemented by `SetDisks`/`Sets`/`ECStore` (`crates/storage-api/src/object.rs:503-519`) | | heal runtime | `crates/heal` | Process-level HealManager (priority queue/scheduler/auto disk scanner/resumable resume), HealChannelProcessor (consumes the global heal channel), drive-replacement recovery state machine | | scanner runtime | `crates/scanner` | Data usage scanning, ILM evaluation and enqueueing, heal candidate production, replication usage statistics, remote scanner RPC | -| Shared protocol | `crates/common/src/heal_channel.rs` (~776 lines) | Start/Query/Cancel command channel, `HealOpts`/`HealScanMode`/`HealRequestSource`/`HealAdmission*` shared types, `HealResultItem` (madmin) | +| Shared protocol | `crates/heal-contracts/src/heal_channel.rs` (~776 lines) | Start/Query/Cancel command channel, `HealOpts`/`HealScanMode`/`HealRequestSource`/`HealAdmission*` shared types, `HealResultItem` (madmin) | | Shared data | `crates/data-usage` | `DataUsageEntry/Info`, histograms, `hash_path`; produced by the scanner, consumed by ecstore/admin | Startup chain (wiring verified first-hand): @@ -214,7 +214,7 @@ Compared with MinIO master: MinIO's skip strategy is likewise hash-mod-16 cycles ### 3.5 ILM integration - Per object `ScannerItem::apply_actions` (`scanner_folder.rs:747-1032`): `Evaluator::new(lifecycle).with_lock_retention(...).with_replication_config(...).eval()` batch evaluation. -- Implemented actions (the full IlmAction set, `common/src/metrics.rs:34-45`): expiry deletes (Delete/DeleteRestored/DeleteRestoredVersion), all-versions deletes (DeleteAllVersions/DelMarkerDeleteAllVersions, stop further versions after handling), transition (Transition/TransitionVersion, tier list read at runtime), noncurrent batches (DeleteVersionAction → `enqueue_by_newer_noncurrent`), free-version cleanup (`enqueue_free_version`), object-lock retention constraints. **A one-to-one mapping onto MinIO's 9 ILM actions.** +- Implemented actions (the full IlmAction set, `scanner-contracts/src/metrics.rs:34-45`): expiry deletes (Delete/DeleteRestored/DeleteRestoredVersion), all-versions deletes (DeleteAllVersions/DelMarkerDeleteAllVersions, stop further versions after handling), transition (Transition/TransitionVersion, tier list read at runtime), noncurrent batches (DeleteVersionAction → `enqueue_by_newer_noncurrent`), free-version cleanup (`enqueue_free_version`), object-lock retention constraints. **A one-to-one mapping onto MinIO's 9 ILM actions.** - Execution model: the scanner is the "discover and enqueue" role (the expiry/transition queues live in ecstore `bucket_lifecycle_ops.rs`); actions are consumed by worker pools — the same shape as MinIO's globalExpiryState/globalTransitionState. - AbortIncompleteMultipartUpload is not executed inside scanner/ILM (MinIO likewise: `internal/bucket/lifecycle/rule.go` has a FIXME, and it is actually carried by the `erasureSets.cleanupStaleUploads` global routine); in RustFS it is an independent ecstore background task `init_background_stale_multipart_upload_cleanup` (`bucket_lifecycle_ops.rs:3289-3320`) + on-demand at bucket deletion. - Integration-test coverage: transition+restore, free-version, noncurrent, delete-marker, 0-day, background-scan expiry (`scanner/tests/lifecycle_integration_test.rs:1071-2095`). diff --git a/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16_zh.md b/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16_zh.md index a75971d1a..9d5cb9461 100644 --- a/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16_zh.md +++ b/docs/operations/rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16_zh.md @@ -3,7 +3,7 @@ > English version: [rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16.md](rustfs-heal-scanner-vs-minio-comprehensive-analysis-2026-08-16.md) - 日期：2026-08-16（基于 main 分支当日代码，审计时 HEAD ≈ `a118d7e4f`） -- 范围：`crates/heal`（src 19,560 行 + tests 2,274 行）、`crates/scanner`（src 约 26,000 行 + tests）、`crates/data-usage`、`crates/ecstore` 中 heal/heal_walk/bitrot_self_verify 与 config、`crates/common/src/heal_channel.rs`、`crates/madmin`（heal/scanner wire 类型）、`rustfs/src`（startup wiring、admin handlers、集群 RPC） +- 范围：`crates/heal`（src 19,560 行 + tests 2,274 行）、`crates/scanner`（src 约 26,000 行 + tests）、`crates/data-usage`、`crates/ecstore` 中 heal/heal_walk/bitrot_self_verify 与 config、`crates/heal-contracts/src/heal_channel.rs`、`crates/madmin`（heal/scanner wire 类型）、`rustfs/src`（startup wiring、admin handlers、集群 RPC） - 对标基线：minio/minio master（HEAD `7aac2a2c5b`，仓库已进入维护模式，master 冻结，即最终态） - 方法：四路并行审计（heal crate / scanner crate / ecstore 集成层 / MinIO 源码研究），关键结论逐条人工抽验（文内标注"已亲验"处为一手验证） - 本文档取代 `docs/rustfs-heal-scanner-vs-minio-parity-assessment.md`（2026-06-15 v1）。v1 之后 heal/scanner 相关提交超过 80 个（换盘自动修复全链路、resume 状态机、usage 收敛权威化、集群级 heal 协调、ILM restore 语义等），v1 的功能清单与差距判断已全面过时；v1 中"bloom filter 缺失"等结论经本次核实为**误判**（详见 §5.4）。 @@ -31,7 +31,7 @@ RustFS 把 MinIO 在 `cmd/` 内单体的 heal/scanner 拆成三层 + 两个独 | 原语层 | `crates/ecstore/src/set_disk/ops/heal.rs`（~3,240 行）、`ops/heal_walk.rs`、`ops/bitrot_self_verify.rs`；上层封装 `store/heal.rs`、`store/heal_walk.rs`、`core/sets.rs` | 对象/桶/format/替换盘格式修复、disk-walk 并集枚举、写入路径 bitrot 自校验；由 `SetDisks`/`Sets`/`ECStore` 实现 `rustfs_storage_api::HealOperations` 契约（`crates/storage-api/src/object.rs:503-519`） | | heal 运行时 | `crates/heal` | 进程级 HealManager（优先级队列/调度器/auto disk scanner/断点续传 resume）、HealChannelProcessor（消费全局 heal channel）、换盘替换恢复状态机 | | scanner 运行时 | `crates/scanner` | 数据使用扫描、ILM 评估与入队、heal 候选生产、复制用量统计、remote scanner RPC | -| 共享协议 | `crates/common/src/heal_channel.rs`（~776 行） | Start/Query/Cancel 命令通道、`HealOpts`/`HealScanMode`/`HealRequestSource`/`HealAdmission*` 共享类型、`HealResultItem`（madmin） | +| 共享协议 | `crates/heal-contracts/src/heal_channel.rs`（~776 行） | Start/Query/Cancel 命令通道、`HealOpts`/`HealScanMode`/`HealRequestSource`/`HealAdmission*` 共享类型、`HealResultItem`（madmin） | | 共享数据 | `crates/data-usage` | `DataUsageEntry/Info`、直方图、`hash_path`；scanner 产生、ecstore/admin 消费 | 启动链路（已亲验 wiring）： @@ -214,7 +214,7 @@ heal crate 侧包装（`task.rs:855-1146`）：存在性检查（瞬时错误转 ### 3.5 ILM 集成 - 每对象 `ScannerItem::apply_actions`（`scanner_folder.rs:747-1032`）：`Evaluator::new(lifecycle).with_lock_retention(...).with_replication_config(...).eval()` 批量评估。 -- 已实现动作（IlmAction 全集，`common/src/metrics.rs:34-45`）：expiry 删除（Delete/DeleteRestored/DeleteRestoredVersion）、全版本删除（DeleteAllVersions/DelMarkerDeleteAllVersions，处理后停止后续版本）、transition（Transition/TransitionVersion，tier 列表运行时读取）、noncurrent 批量（DeleteVersionAction → `enqueue_by_newer_noncurrent`）、free-version 清理（`enqueue_free_version`）、object-lock retention 约束。**与 MinIO 的 9 个 ILM 动作一一对应**。 +- 已实现动作（IlmAction 全集，`scanner-contracts/src/metrics.rs:34-45`）：expiry 删除（Delete/DeleteRestored/DeleteRestoredVersion）、全版本删除（DeleteAllVersions/DelMarkerDeleteAllVersions，处理后停止后续版本）、transition（Transition/TransitionVersion，tier 列表运行时读取）、noncurrent 批量（DeleteVersionAction → `enqueue_by_newer_noncurrent`）、free-version 清理（`enqueue_free_version`）、object-lock retention 约束。**与 MinIO 的 9 个 ILM 动作一一对应**。 - 执行模型：scanner 是"发现与入队"角色（expiry 队列/transition 队列在 ecstore `bucket_lifecycle_ops.rs`），动作由 worker 池消费——与 MinIO globalExpiryState/globalTransitionState 同型。 - AbortIncompleteMultipartUpload 不在 scanner/ILM 内执行（MinIO 同样不在：`internal/bucket/lifecycle/rule.go` 有 FIXME，实际由 `erasureSets.cleanupStaleUploads` 全局例程承担）；RustFS 由 ecstore 独立后台任务 `init_background_stale_multipart_upload_cleanup`（`bucket_lifecycle_ops.rs:3289-3320`）+ 桶删除时 on-demand。 - 集成测试覆盖：transition+restore、free-version、noncurrent、delete-marker、0-day、后台扫描过期（`scanner/tests/lifecycle_integration_test.rs:1071-2095`）。