Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
351 changes: 266 additions & 85 deletions Cargo.lock

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions nativelink-scheduler/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,8 @@ bytes = { version = "1.10.1", default-features = false }
futures = { version = "0.3.31", default-features = false }
lru = { version = "0.16.0", default-features = false }
mock_instant = { version = "0.5.3", default-features = false }
opentelemetry = { version = "0.29.1", default-features = false }
opentelemetry-semantic-conventions = { version = "0.29.0", default-features = false, features = [
opentelemetry = { version = "0.30.0", default-features = false }
opentelemetry-semantic-conventions = { version = "0.30.0", default-features = false, features = [
"default",
"semconv_experimental",
] }
Expand Down
4 changes: 2 additions & 2 deletions nativelink-service/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,8 @@ bytes = { version = "1.10.1", default-features = false }
futures = { version = "0.3.31", default-features = false }
http-body-util = { version = "0.1.3", default-features = false }
hyper = { version = "1.6.0", default-features = false }
opentelemetry = { version = "0.29.1", default-features = false }
opentelemetry-semantic-conventions = { version = "0.29.0", default-features = false, features = [
opentelemetry = { version = "0.30.0", default-features = false }
opentelemetry-semantic-conventions = { version = "0.30.0", default-features = false, features = [
"default",
"semconv_experimental",
] }
Expand Down
2 changes: 1 addition & 1 deletion nativelink-store/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ mongodb = { version = "3", features = [
"compat-3-0-0",
"rustls-tls",
], default-features = false }
opentelemetry = { version = "0.29.1", default-features = false }
opentelemetry = { version = "0.30.0", default-features = false }
parking_lot = { version = "0.12.3", features = [
"arc_lock",
"send_guard",
Expand Down
2 changes: 2 additions & 0 deletions nativelink-util/BUILD.bazel
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@ rust_library(
"@crates//:blake3",
"@crates//:bytes",
"@crates//:futures",
"@crates//:ginepro",
"@crates//:hex",
"@crates//:humantime",
"@crates//:hyper-1.7.0",
Expand Down Expand Up @@ -84,6 +85,7 @@ rust_library(
"@crates//:tracing",
"@crates//:tracing-opentelemetry",
"@crates//:tracing-subscriber",
"@crates//:url",
"@crates//:uuid",
"@crates//:walkdir",
],
Expand Down
16 changes: 9 additions & 7 deletions nativelink-util/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -27,21 +27,21 @@ hyper-util = { version = "0.1.11", default-features = false }
libc = { version = "0.2.177", default-features = false }
lru = { version = "0.16.0", default-features = false }
mock_instant = { version = "0.5.3", default-features = false }
opentelemetry = { version = "0.29.0", default-features = false }
opentelemetry-appender-tracing = { version = "0.29.1", default-features = false }
opentelemetry-http = { version = "0.29.0", default-features = false }
opentelemetry-otlp = { version = "0.29.0", default-features = false, features = [
opentelemetry = { version = "0.30.0", default-features = false }
opentelemetry-appender-tracing = { version = "0.30.0", default-features = false }
opentelemetry-http = { version = "0.30.0", default-features = false }
opentelemetry-otlp = { version = "0.30.0", default-features = false, features = [
"grpc-tonic",
"logs",
"metrics",
"trace",
"zstd-tonic",
] }
opentelemetry-semantic-conventions = { version = "0.29.0", default-features = false, features = [
opentelemetry-semantic-conventions = { version = "0.30.0", default-features = false, features = [
"default",
"semconv_experimental",
] }
opentelemetry_sdk = { version = "0.29.0", default-features = false }
opentelemetry_sdk = { version = "0.30.0", default-features = false }
parking_lot = { version = "0.12.3", features = [
"arc_lock",
"send_guard",
Expand Down Expand Up @@ -77,7 +77,7 @@ tonic = { version = "0.13.0", features = [
], default-features = false }
tower = { version = "0.5.2", default-features = false }
tracing = { version = "0.1.41", default-features = false }
tracing-opentelemetry = { version = "0.30.0", default-features = false, features = [
tracing-opentelemetry = { version = "0.31.0", default-features = false, features = [
"metrics",
] }
tracing-subscriber = { version = "0.3.19", features = [
Expand All @@ -87,6 +87,8 @@ tracing-subscriber = { version = "0.3.19", features = [
], default-features = false }
tracing-test = { version = "0.2.5", default-features = false, features = [] }

ginepro = { version = "0.9.0", default-features = false }
url = { version = "2.5.7", default-features = false }
uuid = { version = "1.16.0", default-features = false, features = [
"serde",
"v4",
Expand Down
63 changes: 55 additions & 8 deletions nativelink-util/src/telemetry.rs
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ use std::sync::OnceLock;

use base64::Engine;
use base64::prelude::BASE64_STANDARD_NO_PAD;
use ginepro::LoadBalancedChannel;
use hyper::http::Response;
use nativelink_error::{Code, ResultExt, make_err};
use nativelink_proto::build::bazel::remote::execution::v2::RequestMetadata;
Expand All @@ -26,7 +27,9 @@ use opentelemetry::trace::{TraceContextExt, Tracer, TracerProvider};
use opentelemetry::{KeyValue, global};
use opentelemetry_appender_tracing::layer::OpenTelemetryTracingBridge;
use opentelemetry_http::HeaderExtractor;
use opentelemetry_otlp::{LogExporter, MetricExporter, Protocol, SpanExporter, WithExportConfig};
use opentelemetry_otlp::{
LogExporter, MetricExporter, Protocol, SpanExporter, WithExportConfig, WithTonicConfig,
};
use opentelemetry_sdk::Resource;
use opentelemetry_sdk::logs::SdkLoggerProvider;
use opentelemetry_sdk::metrics::SdkMeterProvider;
Expand Down Expand Up @@ -103,7 +106,7 @@ fn tracing_stdout_layer() -> impl Layer<Registry> {
///
/// Returns `Err` if logging was already initialized or if the exporters can't
/// be initialized.
pub fn init_tracing() -> Result<(), nativelink_error::Error> {
pub async fn init_tracing() -> Result<(), nativelink_error::Error> {
static INITIALIZED: OnceLock<()> = OnceLock::new();

if INITIALIZED.get().is_some() {
Expand All @@ -128,13 +131,18 @@ pub fn init_tracing() -> Result<(), nativelink_error::Error> {
]);
global::set_text_map_propagator(propagator);

let maybe_channel = maybe_load_balanced_channel().await;

// Logs
let mut log_exporter_builder = LogExporter::builder().with_tonic();
if let Some(channel) = maybe_channel.clone() {
log_exporter_builder = log_exporter_builder.with_channel(channel.into());
}
let otlp_log_layer = OpenTelemetryTracingBridge::new(
&SdkLoggerProvider::builder()
.with_resource(resource.clone())
.with_batch_exporter(
LogExporter::builder()
.with_tonic()
log_exporter_builder
.with_protocol(Protocol::Grpc)
.build()
.map_err(|e| make_err!(Code::Internal, "{e}"))
Expand All @@ -145,13 +153,16 @@ pub fn init_tracing() -> Result<(), nativelink_error::Error> {
.with_filter(otlp_filter());

// Traces
let mut span_exporter_builder = SpanExporter::builder().with_tonic();
if let Some(channel) = maybe_channel.clone() {
span_exporter_builder = span_exporter_builder.with_channel(channel.into());
}
let otlp_trace_layer = layer()
.with_tracer(
SdkTracerProvider::builder()
.with_resource(resource.clone())
.with_batch_exporter(
SpanExporter::builder()
.with_tonic()
span_exporter_builder
.with_protocol(Protocol::Grpc)
.build()
.map_err(|e| make_err!(Code::Internal, "{e}"))
Expand All @@ -163,11 +174,14 @@ pub fn init_tracing() -> Result<(), nativelink_error::Error> {
.with_filter(otlp_filter());

// Metrics
let mut metric_exporter_builder = MetricExporter::builder().with_tonic();
if let Some(channel) = maybe_channel {
metric_exporter_builder = metric_exporter_builder.with_channel(channel.into());
}
let meter_provider = SdkMeterProvider::builder()
.with_resource(resource)
.with_periodic_exporter(
MetricExporter::builder()
.with_tonic()
metric_exporter_builder
.with_protocol(Protocol::Grpc)
.build()
.map_err(|e| make_err!(Code::Internal, "{e}"))
Expand All @@ -191,6 +205,38 @@ pub fn init_tracing() -> Result<(), nativelink_error::Error> {
Ok(())
}

const NL_OTEL_ENDPOINT: &str = "NL_OTEL_ENDPOINT";

async fn maybe_load_balanced_channel() -> Option<LoadBalancedChannel> {
match env::var(NL_OTEL_ENDPOINT) {
Ok(endpoint) => {
let url = Url::parse(endpoint.as_str())
.map_err(|e| {
make_err!(Code::Internal, "Unable to parse endpoint {endpoint}: {e:?}")
})
.unwrap();

let host = url
.host()
.err_tip(|| format!("Unable to get host from endpoint {endpoint}"))
.unwrap();
let port = url
.port()
.err_tip(|| format!("Unable to get port from endpoint {endpoint}"))
.unwrap();

Some(
LoadBalancedChannel::builder((host.to_string(), port))
.channel()
.await
.map_err(|e| make_err!(Code::Internal, "Invalid hostname '{endpoint}': {e}"))
.unwrap(),
)
}
Err(_) => None,
}
}

/// Custom metadata key field for Bazel metadata.
const BAZEL_METADATA_KEY: &str = "bazel.metadata";

Expand All @@ -201,6 +247,7 @@ const BAZEL_REQUESTMETADATA_HEADER: &str = "build.bazel.remote.execution.v2.requ

use opentelemetry::baggage::BaggageExt;
use opentelemetry::context::FutureExt;
use url::Url;

#[derive(Debug, Clone)]
pub struct OtlpMiddleware<S> {
Expand Down
2 changes: 1 addition & 1 deletion nativelink-worker/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ bytes = { version = "1.10.1", default-features = false }
filetime = { version = "0.2.25", default-features = false }
formatx = { version = "0.2.3", default-features = false }
futures = { version = "0.3.31", default-features = false }
opentelemetry = { version = "0.29.1", default-features = false }
opentelemetry = { version = "0.30.0", default-features = false }
parking_lot = { version = "0.12.3", default-features = false }
prost = { version = "0.13.5", default-features = false }
relative-path = { version = "2.0.0", default-features = false, features = [
Expand Down
2 changes: 1 addition & 1 deletion src/bin/nativelink.rs
Original file line number Diff line number Diff line change
Expand Up @@ -720,7 +720,7 @@ fn main() -> Result<(), Box<dyn core::error::Error>> {
// The OTLP exporters need to run in a Tokio context
// Do this first so all the other logging works
#[expect(clippy::disallowed_methods, reason = "tracing init on main runtime")]
runtime.block_on(async { tokio::spawn(async { init_tracing() }).await? })?;
runtime.block_on(async { tokio::spawn(async { init_tracing().await }).await? })?;

let mut cfg = get_config()?;

Expand Down
2 changes: 1 addition & 1 deletion src/bin/redis_store_tester.rs
Original file line number Diff line number Diff line change
Expand Up @@ -305,7 +305,7 @@ fn main() -> Result<(), Box<dyn core::error::Error>> {
.unwrap()
.block_on(async {
// The OTLP exporters need to run in a Tokio context.
spawn!("init tracing", async { init_tracing() })
spawn!("init tracing", async { init_tracing().await })
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oof! Good catch.

.await?
.expect("Init tracing should work");

Expand Down
Loading