opensource/rustfs
3
0
Fork 0
mirror of https://github.com/rustfs/rustfs.git synced 2026-08-28 19:24:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor(heal): migrate mainline throttle to shared ForegroundPressure (#6780)

Browse Source 
The heal manager carried its own byte-identical copy of the foreground pressure type and threshold computation that ecstore's data-movement backpressure also carries, so every change to the admission-utilization rules had to be mirrored by hand across two crates. The shared `ForegroundPressure` and `foreground_pressure` added to `rustfs-concurrency` now own that logic, and heal already depends on that crate, so this removes the duplicate without adding a crate edge.

`mainline_throttle_active` keeps the parts that are specific to this call site: the `mainline_throttle_enable` and both-thresholds-zero short circuit that avoids touching the provider at all, the optional-provider unwrap, and the heal-side threshold fields. Everything downstream is untouched — the `reason()` labels `foreground_read_pressure`, `foreground_write_pressure`, and `foreground_pressure` are byte-identical to the removed implementation, so the `rustfs_heal_mainline_throttle_total` reason label and the `heal_mainline_throttle` log fields keep their observability contract.

Refs rustfs/backlog#2049

(cherry picked from commit ec491bcbd8939e5978cd94f9a44cffb70d09fade)
(cherry picked from commit e800f29d6806591689204b3712300800b480beae)

Co-authored-by: houseme <housemecn@gmail.com>
This commit is contained in:
Zhengchao An
2026-08-28 16:21:27 +08:00
committed by GitHub
parent 6f9adb3ad0
commit 028be4f604
2 changed files with 9 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/heal/src/heal/manager.rs
+9 -35
View File
@@ -20,7 +20,10 @@ use crate::heal::{
};
use crate::{Error, Result};
use metrics::{counter, gauge};
use rustfs_concurrency::{AdmissionState, WorkloadAdmissionSnapshotProvider, WorkloadClass};
use rustfs_concurrency::WorkloadAdmissionSnapshotProvider;
use rustfs_concurrency::workload::{ForegroundPressure, foreground_pressure};
#[cfg(test)]
use rustfs_concurrency::{AdmissionState, WorkloadClass};
use rustfs_heal_contracts::heal_channel::{
HealAdmissionDropReason, HealAdmissionReceipt, HealAdmissionResult, HealRequestSource,
};
@@ -813,40 +816,11 @@ impl HealManager {
}
let provider = provider.as_ref()?;
let snapshot = provider.workload_admission_snapshot();
[
(WorkloadClass::ForegroundRead, config.mainline_read_utilization_high_percent),
(WorkloadClass::ForegroundWrite, config.mainline_write_utilization_high_percent),
]
.into_iter()
.filter_map(|(class, threshold_pct)| {
if threshold_pct == 0 {
return None;
}
let entry = snapshot.get(class)?;
let usage_pct = if matches!(entry.state, AdmissionState::Saturated) {
100
} else {
let limit = entry.limit?;
if limit == 0 {
return None;
}
entry
.active
.unwrap_or(0)
.saturating_mul(100)
.checked_div(limit)
.unwrap_or(100)
};
(usage_pct >= threshold_pct).then_some(ForegroundPressure {
class,
usage_pct,
threshold_pct,
})
})
.max_by_key(|pressure| pressure.usage_pct)
foreground_pressure(
&provider.workload_admission_snapshot(),
config.mainline_read_utilization_high_percent,
config.mainline_write_utilization_high_percent,
)
}
fn schedule_mainline_throttle_recheck(notify: Arc<Notify>, delay: Duration) {
crates/heal/src/heal/manager/queue.rs
-17
View File
@@ -78,23 +78,6 @@ pub(super) enum QueuePushOutcome {
Merged,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(super) struct ForegroundPressure {
pub(super) class: WorkloadClass,
pub(super) usage_pct: usize,
pub(super) threshold_pct: usize,
}
impl ForegroundPressure {
pub(super) const fn reason(self) -> &'static str {
match self.class {
WorkloadClass::ForegroundRead => "foreground_read_pressure",
WorkloadClass::ForegroundWrite => "foreground_write_pressure",
_ => "foreground_pressure",
}
}
}
#[derive(Debug, Clone)]
pub(super) struct CompletedHealStatus {
pub(super) heal_type: HealType,