Files
rustfs/crates/object-data-cache/src/metrics.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

157 lines
5.9 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::ObjectDataCacheMode;
use crate::stats::ObjectDataCacheStats;
use metrics::{counter, describe_counter, describe_gauge, describe_histogram, gauge, histogram};
use std::sync::{Arc, OnceLock};
const METRIC_REQUESTS_TOTAL: &str = "rustfs_object_data_cache_requests_total";
const METRIC_FILLS_TOTAL: &str = "rustfs_object_data_cache_fill_total";
const METRIC_FILL_DURATION_SECONDS: &str = "rustfs_object_data_cache_fill_duration_seconds";
const METRIC_FILL_BYTES_TOTAL: &str = "rustfs_object_data_cache_fill_bytes_total";
const METRIC_HIT_BYTES_TOTAL: &str = "rustfs_object_data_cache_hit_bytes_total";
const METRIC_ENTRIES: &str = "rustfs_object_data_cache_entries";
const METRIC_WEIGHTED_BYTES: &str = "rustfs_object_data_cache_weighted_bytes";
const METRIC_INFLIGHT_FILLS: &str = "rustfs_object_data_cache_inflight_fills";
const METRIC_INVALIDATIONS_TOTAL: &str = "rustfs_object_data_cache_invalidations_total";
const METRIC_MEMORY_PRESSURE_TOTAL: &str = "rustfs_object_data_cache_memory_pressure_total";
pub(crate) fn describe_metrics_once() {
static DESCRIBED: OnceLock<()> = OnceLock::new();
let _ = DESCRIBED.get_or_init(|| {
describe_counter!(
METRIC_REQUESTS_TOTAL,
"Object data cache request decisions labeled by backend, mode, decision, reason, and size class."
);
describe_counter!(
METRIC_FILLS_TOTAL,
"Object data cache fill outcomes by backend, mode, result, and size class."
);
describe_histogram!(METRIC_FILL_DURATION_SECONDS, "Object data cache fill duration in seconds.");
describe_counter!(METRIC_FILL_BYTES_TOTAL, "Total bytes submitted to object data cache fill operations.");
describe_counter!(METRIC_HIT_BYTES_TOTAL, "Total bytes served from object data cache hits.");
describe_gauge!(METRIC_ENTRIES, "Current object data cache entry count.");
describe_gauge!(METRIC_WEIGHTED_BYTES, "Approximate weighted bytes held by the object data cache.");
describe_gauge!(METRIC_INFLIGHT_FILLS, "Current number of in-flight object data cache fills.");
describe_counter!(
METRIC_INVALIDATIONS_TOTAL,
"Object data cache invalidation attempts by backend and reason."
);
describe_counter!(METRIC_MEMORY_PRESSURE_TOTAL, "Object data cache fill skips caused by memory pressure.");
});
}
pub(crate) const fn size_class(size_bytes: u64) -> &'static str {
if size_bytes <= 4 * 1024 {
"le_4k"
} else if size_bytes <= 64 * 1024 {
"le_64k"
} else if size_bytes <= 256 * 1024 {
"le_256k"
} else if size_bytes <= 1024 * 1024 {
"le_1m"
} else if size_bytes <= 4 * 1024 * 1024 {
"le_4m"
} else {
"gt_4m"
}
}
pub(crate) fn record_request_decision(
backend: &'static str,
mode: ObjectDataCacheMode,
decision: &'static str,
reason: &'static str,
size_bytes: u64,
) {
counter!(
METRIC_REQUESTS_TOTAL,
"backend" => backend,
"mode" => mode.as_metric_label(),
"decision" => decision,
"reason" => reason,
"size_class" => size_class(size_bytes),
)
.increment(1);
}
pub(crate) fn record_fill_result(
backend: &'static str,
mode: ObjectDataCacheMode,
result: &'static str,
size_bytes: u64,
duration_seconds: f64,
) {
let size_class = size_class(size_bytes);
counter!(
METRIC_FILLS_TOTAL,
"backend" => backend,
"mode" => mode.as_metric_label(),
"result" => result,
"size_class" => size_class,
)
.increment(1);
histogram!(
METRIC_FILL_DURATION_SECONDS,
"backend" => backend,
"mode" => mode.as_metric_label(),
"result" => result,
"size_class" => size_class,
)
.record(duration_seconds);
counter!(
METRIC_FILL_BYTES_TOTAL,
"backend" => backend,
"mode" => mode.as_metric_label(),
"result" => result,
"size_class" => size_class,
)
.increment(size_bytes);
}
pub(crate) fn record_hit_bytes(backend: &'static str, mode: ObjectDataCacheMode, size_bytes: u64) {
counter!(
METRIC_HIT_BYTES_TOTAL,
"backend" => backend,
"mode" => mode.as_metric_label(),
"size_class" => size_class(size_bytes),
)
.increment(size_bytes);
}
pub(crate) fn publish_cache_state(backend: &'static str, entries: u64, weighted_bytes: u64) {
gauge!(METRIC_ENTRIES, "backend" => backend).set(entries as f64);
gauge!(METRIC_WEIGHTED_BYTES, "backend" => backend).set(weighted_bytes as f64);
}
pub(crate) fn set_inflight_fills(stats: &Arc<ObjectDataCacheStats>, backend: &'static str, count: usize) {
stats.set_inflight_fills(count);
let count_u64 = u64::try_from(count).unwrap_or(u64::MAX);
gauge!(METRIC_INFLIGHT_FILLS, "backend" => backend).set(count_u64 as f64);
}
pub(crate) fn record_singleflight_join(stats: &Arc<ObjectDataCacheStats>) {
stats.record_singleflight_join();
}
pub(crate) fn record_memory_pressure(stats: &Arc<ObjectDataCacheStats>, backend: &'static str) {
stats.record_memory_pressure();
counter!(METRIC_MEMORY_PRESSURE_TOTAL, "backend" => backend).increment(1);
}
pub(crate) fn record_invalidation(backend: &'static str, reason: &'static str) {
counter!(METRIC_INVALIDATIONS_TOTAL, "backend" => backend, "reason" => reason).increment(1);
}