mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-05 12:57:42 +00:00
eebd16d8a4
* 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>
114 lines
3.4 KiB
Rust
114 lines
3.4 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 bytes::Bytes;
|
|
use std::cmp;
|
|
use std::sync::Arc;
|
|
use std::time::Instant;
|
|
|
|
use crate::key::ObjectDataCacheKey;
|
|
|
|
const ENTRY_OVERHEAD_BYTES: usize = 64;
|
|
|
|
/// Cached object body entry.
|
|
#[derive(Debug, Clone)]
|
|
pub struct ObjectDataCacheEntry {
|
|
bytes: Bytes,
|
|
content_length: u64,
|
|
etag: Arc<str>,
|
|
inserted_at: Instant,
|
|
}
|
|
|
|
impl ObjectDataCacheEntry {
|
|
/// Creates a new cached entry.
|
|
pub fn new(bytes: Bytes, content_length: u64, etag: Arc<str>) -> Self {
|
|
Self {
|
|
bytes,
|
|
content_length,
|
|
etag,
|
|
inserted_at: Instant::now(),
|
|
}
|
|
}
|
|
|
|
/// Returns a clone of the cached body bytes.
|
|
pub fn bytes(&self) -> Bytes {
|
|
self.bytes.clone()
|
|
}
|
|
|
|
/// Returns the recorded content length.
|
|
pub const fn content_length(&self) -> u64 {
|
|
self.content_length
|
|
}
|
|
|
|
/// Returns the cached etag reference.
|
|
pub fn etag(&self) -> &Arc<str> {
|
|
&self.etag
|
|
}
|
|
|
|
/// Returns the insertion timestamp.
|
|
pub const fn inserted_at(&self) -> Instant {
|
|
self.inserted_at
|
|
}
|
|
|
|
/// Returns the estimated weighted size for capacity accounting.
|
|
pub fn estimated_weight(&self, key: &ObjectDataCacheKey) -> u32 {
|
|
let key_bytes = key.bucket.len() + key.object.len() + key.version_id.len() + key.etag.len();
|
|
let body_bytes = self.bytes.len();
|
|
let total = key_bytes.saturating_add(body_bytes).saturating_add(ENTRY_OVERHEAD_BYTES);
|
|
let clamped = cmp::min(total, u32::MAX as usize);
|
|
|
|
u32::try_from(clamped).unwrap_or(u32::MAX)
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::ObjectDataCacheEntry;
|
|
use crate::key::{ObjectDataCacheBodyVariant, ObjectDataCacheKey};
|
|
use bytes::Bytes;
|
|
use std::sync::Arc;
|
|
|
|
#[test]
|
|
fn estimated_weight_includes_body_and_key_bytes() {
|
|
let key =
|
|
ObjectDataCacheKey::new("bucket", "object", Some("vid"), "etag", 5, ObjectDataCacheBodyVariant::FullObjectPlainV1);
|
|
let entry = ObjectDataCacheEntry::new(Bytes::from_static(b"hello"), 5, Arc::<str>::from("etag"));
|
|
|
|
let weight = entry.estimated_weight(&key);
|
|
|
|
assert!(weight >= 5);
|
|
}
|
|
|
|
#[test]
|
|
fn estimated_weight_clamps_to_u32_max() {
|
|
let huge_bucket = "b".repeat(1024);
|
|
let huge_object = "o".repeat(1024);
|
|
let huge_etag = "e".repeat(1024);
|
|
let key = ObjectDataCacheKey::new(
|
|
huge_bucket.as_str(),
|
|
huge_object.as_str(),
|
|
Some("version"),
|
|
huge_etag.as_str(),
|
|
1,
|
|
ObjectDataCacheBodyVariant::FullObjectPlainV1,
|
|
);
|
|
let huge = vec![0u8; (u32::MAX as usize).saturating_add(1024)];
|
|
let entry = ObjectDataCacheEntry::new(Bytes::from(huge), 1, Arc::<str>::from("etag"));
|
|
|
|
let weight = entry.estimated_weight(&key);
|
|
|
|
assert_eq!(weight, u32::MAX);
|
|
}
|
|
}
|