Files
rustfs/crates/obs/examples/dial9_smoke.rs
T
houseme 00536da80c refactor(obs): make dial9 telemetry opt-in and actually record events (#4663)
* refactor(obs): make dial9 telemetry opt-in and actually record events

The dial9 Tokio-runtime profiler was disabled by default, yet every build
paid for it, and enabling it produced trace files with no events in them.

Recorded empty traces
---------------------
`build_traced_runtime` called `TracedRuntime::builder()...build(..)`, but dial9
only starts recording in `build_and_start*`. `build` still returns a live guard
whose `is_enabled()` reports true, and still creates and seals segment files —
they just contain a header and no events. It also skipped `with_trace_path`, so
the background worker driving the segment pipeline was never spawned.

Measured on the new smoke example: 310 bytes of bare segment header, against
5640 bytes for the same workload once recording actually starts.

Switch to `with_trace_path(..).build_and_start(..)`.

Cost was unconditional
----------------------
`--cfg tokio_unstable` was a global `[build] rustflags` entry and `rustfs-obs`
depended on `dial9-tokio-telemetry` unconditionally, so all builds depended on
Tokio's non-semver API. Worse, an environment `RUSTFLAGS` replaces (never
appends to) the config-file value, so any caller exporting their own RUSTFLAGS
silently dropped the flag — the long comment in build.yml was a scar from that.

dial9 is now an opt-in feature (`dial9`, plus `dial9-s3` and `dial9-taskdump`),
the global rustflag is gone, and `crates/obs/build.rs` fails the compile if the
feature is on without the flag. Telemetry builds go through `make build-profiling`.

Metrics that could not lie
--------------------------
`rustfs_dial9_{events_total,bytes_written_total,rotations_total,cpu_overhead_percent}`
were hard-coded to zero — a Counter pinned at 0 reads as "nothing happened".
Removed. `rustfs_dial9_enabled` was sourced from the environment, so it read 1
even when the traced runtime failed and the process fell back to a standard
runtime; it is replaced by `rustfs_dial9_supported` (compile-time),
`rustfs_dial9_configured` (intent) and `rustfs_dial9_active_sessions` (reality).

No `writer_healthy` gauge is exported: dial9's `RotatingWriter` can enter its
`Finished` state and stop writing, but exposes no way to observe that, so the
gauge could only ever be hard-coded to 1. Documented as a known gap instead.

Final events were lost
----------------------
The `TelemetryGuard` lived in a `static OnceLock`, which is never dropped, so
buffered events were never flushed at exit. `build_tokio_runtime` now returns
the guard and `run_process` drops it before any exit path.

Also
----
- `disk_usage_bytes` was a `read_dir` + per-file `stat` on the metrics
  collection path. It is now sampled by a background task into an atomic.
- `SAMPLING_RATE`/`S3_BUCKET`/`S3_PREFIX` were parsed, warned about, and
  discarded. S3 upload is now wired to dial9's `with_s3_uploader` behind
  `dial9-s3`; `SAMPLING_RATE` has no upstream equivalent and is removed.
- Wire `with_task_dumps` (async backtraces of stalled tasks), configurable via
  `RUSTFS_RUNTIME_DIAL9_TASK_DUMP_{ENABLED,IDLE_THRESHOLD_MS}`.
- Split `telemetry/dial9.rs` into `config`/`state`/`enabled`/`disabled`; the
  stub keeps the public API identical so callers need no `#[cfg]`.
- Drop four print-only examples and the manual test bin that exercised the
  removed `init_session` scaffolding.

Verified: cargo check/clippy/test across default, `dial9`, and `dial9-s3`;
build.rs correctly rejects `dial9` without `--cfg tokio_unstable`;
`make pre-commit` passes.

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

* docs(obs): document dial9 as an on-demand profiler

scripts/run.sh advertised a `SAMPLING_RATE` knob that was never passed to dial9,
and claimed "CPU overhead < 5% (with sampling rate 1.0)" and "lower values reduce
CPU overhead" on the strength of it. The knob is gone; the guidance built on it
had to go too.

Replace it with what is actually true: dial9 needs a `make build-profiling`
binary, its disk budget evicts oldest-first (so a high poll rate can overwrite
the incident you are chasing), and it cannot be toggled without a restart.

Add docs/operations/dial9-runtime-profiling.md covering the build variants, an
investigation walkthrough, the configuration table, how to read the three
supported/configured/active_sessions gauges against each other, and the upstream
gap that makes writer death only indirectly observable.

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

* test(obs): add a dial9 smoke example that proves events are recorded

The bug this guards against is invisible to every existing signal: with
`build` instead of `build_and_start`, dial9 creates the trace file, seals
segments, and reports `TelemetryGuard::is_enabled() == true` — it simply
records no events. Only the segment's byte count tells the two apart.

Measured on this workload: 5640 bytes when recording, 310 bytes (a bare
segment header) when not. The example asserts >= 2048 bytes, and was verified
to fail with the `build` call restored.

Also correct the comment on the `is_enabled` check in `finish_traced_runtime`.
It claimed to catch "recording silently off"; it does not. It only rejects the
inert guard a lenient config yields after a build failure. Recording is
guaranteed by `build_and_start`, not by that check.

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

* test(rustfs): accept Unsupported runtime telemetry capability

A binary built without the `dial9` feature now reports the runtime-telemetry
capability as `Unsupported` rather than `Disabled`. The distinction matters to
operators: `Disabled` implies the capability can be switched on by setting an
environment variable, which is not true here — telemetry needs a rebuild.

Widen the assertion and pin the new semantics: when `dial9::is_supported()` is
false, the state must be exactly `Unsupported`.

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

* fix(obs): drop the dial9-s3 feature, its TLS stack is vulnerable

CI's Dependency Review and `cargo deny` both reject the branch: dial9's
`worker-s3` feature depends on aws-sdk-s3-transfer-manager 0.1.3, which pins
aws-smithy-http-client onto hyper-rustls 0.24 and rustls-webpki 0.101.7. That
webpki carries RUSTSEC-2026-0098, -0099 and -0104.

0.1.3 is the latest release of the transfer manager, and 1.2.0 the latest of the
smithy client, so there is nothing to upgrade to. Cargo's feature unification can
add features but cannot drop a transitive dependency, so it cannot be worked
around from here either — the rest of the workspace already resolves to the safe
rustls-webpki 0.103 / hyper-rustls 0.27.

Remove the `dial9-s3` feature and the `with_s3_uploader` wiring. The two S3
environment variables stay parsed and warned about, now naming the real reason
rather than a missing build feature. Trace segments are collected from the output
directory instead. Tracked as D9-14 in rustfs/backlog#1157.

With this, Cargo.lock is byte-identical to main: the PR no longer touches the
dependency graph at all.

Also correct the `dial9-taskdump` documentation. It claimed the feature "compiles
to a no-op elsewhere"; in fact `tokio/taskdump` raises a `compile_error!` on any
target other than linux/{aarch64,x86,x86_64}. Verified by trying to build it on
macOS, which is how the claim was found to be wrong.

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

---------

Co-authored-by: heihutu <heihutu@gmail.com>
2026-07-10 10:52:48 +00:00

111 lines
4.3 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.
//! End-to-end check that a traced runtime actually records events to disk.
//!
//! Guards against the regression where `TracedRuntime::builder()...build(..)`
//! was used instead of `build_and_start(..)`: that returns a guard with
//! recording disabled, so telemetry appeared healthy and produced empty traces.
//!
//! Configuration comes from the environment (the crate forbids `unsafe`, so this
//! cannot call `set_var`). Run with:
//!
//! ```bash
//! RUSTFLAGS="--cfg tokio_unstable" \
//! RUSTFS_RUNTIME_DIAL9_ENABLED=true \
//! RUSTFS_RUNTIME_DIAL9_OUTPUT_DIR=/tmp/rustfs-dial9-smoke \
//! RUSTFS_RUNTIME_DIAL9_MAX_FILE_SIZE=65536 \
//! RUSTFS_RUNTIME_DIAL9_ROTATION_COUNT=4 \
//! cargo run -p rustfs-obs --features dial9 --example dial9_smoke
//! ```
use rustfs_obs::dial9::{Dial9Config, build_traced_runtime};
use std::path::Path;
const USAGE: &str = "\
set RUSTFS_RUNTIME_DIAL9_ENABLED=true and RUSTFS_RUNTIME_DIAL9_OUTPUT_DIR=<dir> \
before running this example (see the module docs for a full command line)";
/// A segment that was opened but never recorded an event still carries a header
/// (~292 bytes when this was written). A workload like the one below produces
/// several KiB. Anything under this threshold means events are not being
/// recorded, even though the file exists and the guard looks healthy.
const MIN_EXPECTED_TRACE_BYTES: u64 = 2048;
fn segment_bytes(dir: &Path, prefix: &str) -> u64 {
let Ok(entries) = std::fs::read_dir(dir) else {
return 0;
};
entries
.filter_map(Result::ok)
.filter(|e| e.file_name().to_str().is_some_and(|n| n.starts_with(prefix)))
.filter_map(|e| e.metadata().ok())
.map(|m| m.len())
.sum()
}
fn main() {
let config = Dial9Config::from_env();
if !config.enabled {
eprintln!("{USAGE}");
std::process::exit(2);
}
let output_dir = std::path::PathBuf::from(&config.output_dir);
println!("output_dir = {}", config.output_dir);
println!("disk budget = {} bytes", config.total_disk_budget());
let mut builder = tokio::runtime::Builder::new_multi_thread();
builder.worker_threads(2).enable_all();
let (runtime, guard) = build_traced_runtime(builder).expect("traced runtime should build");
// Necessary but not sufficient: a guard built without `build_and_start` also
// reports active. Only the byte count below proves events were recorded.
assert!(guard.is_active(), "telemetry session must be live");
println!("session active = {}", guard.is_active());
// Generate poll/park/spawn traffic, including a deliberately long poll.
runtime.block_on(async {
let mut handles = Vec::new();
for i in 0..64_u64 {
handles.push(tokio::spawn(async move {
if i % 16 == 0 {
// Block the worker: exactly the fault dial9 exists to surface.
std::thread::sleep(std::time::Duration::from_millis(5));
}
tokio::time::sleep(std::time::Duration::from_millis(1)).await;
i * 2
}));
}
for h in handles {
h.await.expect("task should not panic");
}
});
// Dropping the guard flushes buffered events and seals the active segment.
drop(guard);
drop(runtime);
let bytes = segment_bytes(&output_dir, &config.file_prefix);
println!("trace bytes = {bytes}");
assert!(
bytes >= MIN_EXPECTED_TRACE_BYTES,
"dial9 wrote only {bytes} bytes to {} (expected >= {MIN_EXPECTED_TRACE_BYTES}); \
the segment holds a header but no events, so recording never started",
output_dir.display()
);
println!("\nOK: dial9 recorded {bytes} bytes of trace data.");
}