Files
rustfs/crates/utils/src/os/mod.rs
T
houseme f17ea7f146 fix(heal): harden replacement rebuild tracking (#5892)
* fix(heal): gate auto replacement formatting

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

* fix(heal): require replacement target outcomes

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

* fix(heal): bind resumes to replacement targets

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

* fix(heal): fence healing marker ownership

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

* test(heal): cover replacement target completion

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

* docs(heal): clarify replacement recovery status

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

* fix(heal): canonicalize replacement target checks

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

* fix(heal): satisfy marker test module lint

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

* fix(heal): scope automatic replacement format

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

* fix(heal): require a mounted replacement target

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

* fix(ecstore): avoid cloned ref slice in test

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

* fix(heal): revalidate replacement before scanning

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

* fix(heal): reset stale resume checkpoints

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

* fix(heal): release scanner disk map before probing

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

* fix(heal): persist replacement intent before format

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

* fix(heal): fail closed on mountinfo read errors

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

* fix(heal): fence replacement target identity

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

* fix(heal): order replacement completion cleanup

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

* fix(heal): atomically seal replacement completion

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

* test(heal): census replacement target shards

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

* fix(heal): fence replacement recovery ownership

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

* fix(heal): preserve replacement recovery anchors

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

* fix(heal): satisfy replacement recovery lint gates

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

* fix(ecstore): bind replacement identity to mount lease

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

* test(heal): cover durable replacement recovery states

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

* fix(heal): validate persisted resume task identifiers

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

* fix(ecstore): avoid blocking replacement marker CAS

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

* fix(heal): report failed marker rollback

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

* test(heal): pin replacement resume schema compatibility

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

* fix(heal): preserve durable recovery anchors

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

* fix(ecstore): preserve public disk path semantics

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

* test(heal): use canonical replacement task ids

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

* test(heal): cover automatic replacement in 3x4 cluster

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

* fix(heal): verify replacement target commits

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

* fix(heal): persist replacement completion proof

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

* feat(heal): expose durable replacement status

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

* fix(heal): bound durable replacement discovery

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

* fix(heal): remove replacement readiness bypass

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

* fix(heal): retry terminal replacement cleanup

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

* fix(heal): isolate replacement intents from legacy resume

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

* fix(heal): migrate legacy replacement intents at startup

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

* style(heal): apply strict clippy fix

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

* fix(heal): prioritize active replacement recovery state

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

* fix(heal): bind readiness to the admitted mount lease

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

* fix(heal): atomically publish replacement intents

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

* fix(heal): isolate replacement recovery directory

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

* fix(heal): tolerate an empty recovery directory

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

* style(heal): remove redundant disk bytes conversion

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

* fix(heal): reconcile proof-first replacement recovery

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

* fix(heal): fence torn intent recovery

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

* test(heal): cover replacement migration conflicts

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

* fix(ecstore): fence replacement lease mount identity

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

* test(heal): cover missing replacement path admission

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

* fix(heal): reject conflicting legacy completion proof

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

* fix(ecstore): fall back to proc mount identity

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

* feat(admin): expose replacement recovery status

Surface the local durable replacement recovery snapshot in the background heal status response so operators can tell whether replacement cleanup is definitive or still pending.

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

* fix(heal): keep replacement status compatible

Keep the existing background heal status response wire-compatible while retaining the Linux mount lease cleanup needed for the replacement recovery branch.

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

* style(ecstore): match linux mount lease formatting

Keep Linux rustfmt output stable for the replacement mount lease comparison.

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

* fix(ecstore): qualify mount lease test constant

Use the disk module path for the format config constant in the Linux mount lease regression test.

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

* fix(ecstore): keep procfd mount roots directory-safe

Use a procfd path with an explicit directory component so Unix directory guards can open the replacement mount lease root with O_NOFOLLOW while preserving handle-relative I/O semantics.

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

* fix(ecstore): delete empty leased buckets via dirfd

Use the held mount lease fd as the parent for non-force empty bucket deletion on Linux so procfd-rooted paths do not get rejected as BucketNotEmpty. Also make the download-part OpenOptions truncate behavior explicit and keep fsync test recording stable across procfd canonicalization.

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

* fix(ecstore): scan leased bucket paths for emptiness

Use the local disk I/O root for bucket emptiness probes before non-force bucket deletion and table-bucket metadata checks. This keeps validation on the same mount instance as the subsequent local disk delete path.

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

* test(ecstore): align lease path test probes

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

* fix(heal): block unsafe replacement recovery restarts

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

* fix(heal): defer blocked replacement candidates

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

* fix(heal): retry transient replacement discovery

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

* fix(heal): keep transient recovery errors retryable

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

* fix(heal): block corrupt legacy replacement state

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

* fix(heal): classify flat replacement intent corruption

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

* fix(heal): keep transient resume loads retryable

Classify malformed legacy replacement state as blocking corruption while preserving disk and transient load failures for retry. This avoids permanently blocking replacement recovery on temporary storage errors.

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

* fix(heal): avoid latching transient legacy publishes

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

* fix(heal): retry blocked legacy migrations

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

* fix(heal): defer blocked startup recoveries

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

* fix(ecstore): preserve disk sync limiter across lease roots

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

---------

Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
2026-08-10 08:32:47 +08:00

144 lines
4.2 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.
#[cfg(any(target_os = "linux", test))]
mod fs_type;
#[cfg(target_os = "linux")]
mod linux;
#[cfg(all(unix, not(target_os = "linux")))]
mod unix;
#[cfg(target_os = "windows")]
mod windows;
#[cfg(target_os = "linux")]
pub use linux::{check_cross_device_mounts, get_drive_stats, get_info, get_physical_device_ids, is_mount_point, same_disk};
#[cfg(all(unix, not(target_os = "linux")))]
pub use unix::{check_cross_device_mounts, get_drive_stats, get_info, get_physical_device_ids, is_mount_point, same_disk};
#[cfg(target_os = "windows")]
pub use windows::{
check_cross_device_mounts, get_drive_stats, get_info, get_physical_device_ids, get_volume_serial_number, is_mount_point,
same_disk,
};
#[derive(Debug, Default, PartialEq)]
pub struct IOStats {
pub read_ios: u64,
pub read_merges: u64,
pub read_sectors: u64,
pub read_ticks: u64,
pub write_ios: u64,
pub write_merges: u64,
pub write_sectors: u64,
pub write_ticks: u64,
pub current_ios: u64,
pub total_ticks: u64,
pub req_ticks: u64,
pub discard_ios: u64,
pub discard_merges: u64,
pub discard_sectors: u64,
pub discard_ticks: u64,
pub flush_ios: u64,
pub flush_ticks: u64,
}
#[derive(Debug, Default, PartialEq)]
pub struct DiskInfo {
pub total: u64,
pub free: u64,
pub used: u64,
pub files: u64,
pub ffree: u64,
pub fstype: String,
pub major: u64,
pub minor: u64,
pub name: String,
pub rotational: bool,
pub nrrequests: u64,
}
#[cfg(test)]
mod tests {
use super::*;
use std::path::PathBuf;
#[test]
fn test_get_info_valid_path() {
let temp_dir = tempfile::tempdir().unwrap();
let info = get_info(temp_dir.path()).unwrap();
// Verify disk info is valid
assert!(info.total > 0);
assert!(info.free > 0);
assert!(info.used > 0);
// Files count might be 0 on some systems/filesystems or if empty
// assert!(info.files > 0);
// assert!(info.ffree > 0);
assert!(info.total >= info.free);
}
#[test]
fn test_get_info_invalid_path() {
#[cfg(unix)]
let invalid_path = PathBuf::from("/invalid/path");
#[cfg(windows)]
let invalid_path = PathBuf::from("Z:\\invalid\\path");
let result = get_info(&invalid_path);
assert!(result.is_err());
}
#[test]
fn test_same_disk_same_path() {
let temp_dir = tempfile::tempdir().unwrap();
let path = temp_dir.path().to_str().unwrap();
let result = same_disk(path, path).unwrap();
assert!(result);
}
#[test]
fn test_same_disk_different_paths() {
let temp_dir1 = tempfile::tempdir().unwrap();
let temp_dir2 = tempfile::tempdir().unwrap();
let path1 = temp_dir1.path().to_str().unwrap();
let path2 = temp_dir2.path().to_str().unwrap();
let _result = same_disk(path1, path2).unwrap();
// Since both temporary directories are created in the same file system,
// they should be on the same disk in most cases
// Test passes if the function doesn't panic - the actual result depends on test environment
}
#[test]
fn test_get_drive_stats_missing_device_or_default() {
#[cfg(target_os = "linux")]
{
let err = get_drive_stats(0, 0).expect_err("linux block device 0:0 should not exist");
assert_eq!(err.kind(), std::io::ErrorKind::NotFound);
}
#[cfg(not(target_os = "linux"))]
{
let stats = get_drive_stats(0, 0).expect("non-linux drive stats fallback should return defaults");
assert_eq!(stats, IOStats::default());
}
}
}