Files
rustfs/crates/object-data-cache/src/memory.rs
T
houseme eebd16d8a4 feat(cache): add object data cache engine and app flow (#4187)
* feat(cache): add object data cache engine

* feat(cache): wire app-layer object cache flow

* refactor(cache): streamline app-layer cache flow

* refactor(cache): tighten cache flow internals

* refactor: address final clippy cleanup

* chore(deps): update quick-xml to 0.41.0

* feat(cache): wire object data cache env config

* fix(cache): gate materialize fill by cache plan

* chore(cache): add object data cache benchmark gate

* fix(cache): guard object cache fill size mismatches

* refactor(cache): streamline object cache body planning

* fix(cache): align object cache rollout config

* test(cache): cover buffered object cache benchmark

* test(cache): isolate object cache benchmark metrics

* test(cache): mark materialize rollout experimental

* test(cache): tighten object cache benchmark gate

* fix(cache): address review findings for object data cache

- singleflight: clean up leader entry on cancellation (Drop impl) so a dropped GET future can no longer wedge all subsequent fills for the same key; switch the fill map to a std Mutex and add a regression test

- adapter: honor RUSTFS_OBJECT_DATA_CACHE_ENABLE=true by defaulting to hit_only when no explicit mode is set (explicit mode still wins)

- planner: treat nil version UUIDs as "no value" per repo convention so unversioned objects key under the canonical "null" instead of fragmenting the key space

- multipart: invalidate the object cache on the quota-exceeded rollback delete after complete-multipart, closing a stale-cache window

- layering: move the disabled-cache fallback into app::context and drop the new infra->app layer-dependency baseline entry

* fix(cache): close invalidation races and drop full-cache scan on writes

- index: make identity-index insert/remove/prune atomic via starshard compute_if_present/compute_if_absent so concurrent fills can no longer drop each other's keys (lost keys made entries unreachable to invalidation until TTL); add a concurrency regression test

- fill: register the key in the identity index before the entry becomes visible in the cache and re-check the index afterwards, undoing the fill when an invalidation raced in between (new skipped_invalidation_race fill result)

- invalidate: with the index now authoritative, remove the full-cache iter() fallback that made every PUT/DELETE of a never-cached object O(total cache entries) (two scans per PUT, 2N per batch delete)

- materialize-fill: fail the GET instead of falling back to the partially consumed stream after a mid-read error (the fallback would send a body missing its prefix under a full-length Content-Length), and log the same size-mismatch warning as the sibling buffering paths

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

* test(storage): fix media-dependent buffer clamp expectation

test_concurrency_manager_multi_factor_strategy_buffer_clamp asserted media_cap.min(MI_B), but the implementation's final safety clamp is [32KiB, media_cap.max(MI_B)] — deliberately so a media cap above 1MiB (NVMe's 2MiB default) stays effective. The test only passed on machines detected as SSD/Unknown (cap == 1MiB) and failed on NVMe-backed CI runners with 2MiB != 1MiB. Assert the media cap itself, which is what the strategy actually guarantees on every environment.

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

* test(storage): format buffer clamp assertion

* chore(logging): update tier guardrail path

---------

Signed-off-by: houseme <housemecn@gmail.com>
Co-authored-by: cxymds <cxymds@gmail.com>
Co-authored-by: overtrue <anzhengchao@gmail.com>
Co-authored-by: heihutu <heihutu@gmail.com>
2026-07-03 18:11:14 +08:00

185 lines
6.3 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.
use crate::config::ObjectDataCacheConfig;
use crate::metrics::record_memory_pressure;
use crate::stats::ObjectDataCacheStats;
use std::sync::atomic::{AtomicU64, Ordering};
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant};
use sysinfo::System;
const DEFAULT_REFRESH_INTERVAL: Duration = Duration::from_secs(5);
/// Immutable memory snapshot used by the cache fill gate.
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
pub struct ObjectDataCacheMemorySnapshot {
/// Total system memory in bytes.
pub total_bytes: u64,
/// Available system memory in bytes.
pub available_bytes: u64,
}
impl ObjectDataCacheMemorySnapshot {
/// Returns the available memory percentage.
pub fn available_percent(&self) -> u8 {
if self.total_bytes == 0 {
return 0;
}
let percent = self.available_bytes.saturating_mul(100) / self.total_bytes;
u8::try_from(percent.min(100)).unwrap_or(100)
}
}
/// Memory gate that keeps a cheap snapshot for fill-path checks.
#[derive(Debug)]
pub struct ObjectDataCacheMemoryGate {
system: Mutex<System>,
last_refresh: Mutex<Instant>,
snapshot_total_bytes: AtomicU64,
snapshot_available_bytes: AtomicU64,
min_free_memory_percent: u8,
refresh_interval: Duration,
stats: Arc<ObjectDataCacheStats>,
#[cfg(test)]
test_override: Mutex<Option<ObjectDataCacheMemorySnapshot>>,
}
impl ObjectDataCacheMemoryGate {
/// Creates a new memory gate.
pub fn new(config: &ObjectDataCacheConfig, stats: Arc<ObjectDataCacheStats>) -> Self {
let mut system = System::new();
system.refresh_memory();
let snapshot = ObjectDataCacheMemorySnapshot {
total_bytes: system.total_memory(),
available_bytes: system.available_memory(),
};
Self {
system: Mutex::new(system),
last_refresh: Mutex::new(Instant::now()),
snapshot_total_bytes: AtomicU64::new(snapshot.total_bytes),
snapshot_available_bytes: AtomicU64::new(snapshot.available_bytes),
min_free_memory_percent: config.min_free_memory_percent,
refresh_interval: DEFAULT_REFRESH_INTERVAL,
stats,
#[cfg(test)]
test_override: Mutex::new(None),
}
}
/// Returns the current atomic memory snapshot.
pub fn snapshot(&self) -> ObjectDataCacheMemorySnapshot {
#[cfg(test)]
{
if let Some(snapshot) = *lock_or_recover(&self.test_override) {
return snapshot;
}
}
ObjectDataCacheMemorySnapshot {
total_bytes: self.snapshot_total_bytes.load(Ordering::Relaxed),
available_bytes: self.snapshot_available_bytes.load(Ordering::Relaxed),
}
}
/// Refreshes the snapshot if it is stale.
pub fn refresh_if_stale(&self) {
{
let last_refresh = lock_or_recover(&self.last_refresh);
if last_refresh.elapsed() < self.refresh_interval {
return;
}
}
let mut system = lock_or_recover(&self.system);
system.refresh_memory();
let snapshot = ObjectDataCacheMemorySnapshot {
total_bytes: system.total_memory(),
available_bytes: system.available_memory(),
};
self.snapshot_total_bytes.store(snapshot.total_bytes, Ordering::Relaxed);
self.snapshot_available_bytes
.store(snapshot.available_bytes, Ordering::Relaxed);
*lock_or_recover(&self.last_refresh) = Instant::now();
}
/// Returns true when the fill path may proceed under current memory pressure.
pub fn allows_fill(&self, required_bytes: u64) -> bool {
self.refresh_if_stale();
let snapshot = self.snapshot();
if snapshot.total_bytes == 0 {
return true;
}
let min_free = u64::from(self.min_free_memory_percent);
let has_percent_budget = snapshot.available_bytes.saturating_mul(100) >= snapshot.total_bytes.saturating_mul(min_free);
let has_entry_budget = snapshot.available_bytes >= required_bytes;
let allowed = has_percent_budget && has_entry_budget;
if !allowed {
record_memory_pressure(&self.stats, "moka");
}
allowed
}
#[cfg(test)]
pub fn set_test_snapshot(&self, snapshot: Option<ObjectDataCacheMemorySnapshot>) {
*lock_or_recover(&self.test_override) = snapshot;
}
}
fn lock_or_recover<T>(mutex: &Mutex<T>) -> std::sync::MutexGuard<'_, T> {
match mutex.lock() {
Ok(guard) => guard,
Err(poisoned) => poisoned.into_inner(),
}
}
#[cfg(test)]
mod tests {
use super::{ObjectDataCacheMemoryGate, ObjectDataCacheMemorySnapshot};
use crate::config::ObjectDataCacheConfig;
use crate::stats::ObjectDataCacheStats;
use std::sync::Arc;
#[test]
fn allows_fill_when_memory_snapshot_has_headroom() {
let stats = Arc::new(ObjectDataCacheStats::default());
let gate = ObjectDataCacheMemoryGate::new(&ObjectDataCacheConfig::default(), Arc::clone(&stats));
gate.set_test_snapshot(Some(ObjectDataCacheMemorySnapshot {
total_bytes: 1_000,
available_bytes: 500,
}));
assert!(gate.allows_fill(100));
}
#[test]
fn blocks_fill_under_memory_pressure() {
let stats = Arc::new(ObjectDataCacheStats::default());
let gate = ObjectDataCacheMemoryGate::new(&ObjectDataCacheConfig::default(), Arc::clone(&stats));
gate.set_test_snapshot(Some(ObjectDataCacheMemorySnapshot {
total_bytes: 1_000,
available_bytes: 100,
}));
assert!(!gate.allows_fill(128));
assert_eq!(stats.snapshot().memory_pressure_events, 1);
}
}