Files
wakey/wakey-core/tests/telemetry.rs
T

512 lines
18 KiB
Rust

#![cfg(feature = "telemetry")]
use opentelemetry_proto::tonic::collector::{
logs::v1 as logs, metrics::v1 as metrics, trace::v1 as traces,
};
use opentelemetry_proto::tonic::metrics::v1::{metric, number_data_point};
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::{Arc, Mutex};
use tonic::{Request, Response, Status};
use wakey_core::telemetry::{self, TelemetryConfig};
#[derive(Clone, Default)]
struct Collector {
traces: Arc<Mutex<Vec<traces::ExportTraceServiceRequest>>>,
logs: Arc<Mutex<Vec<logs::ExportLogsServiceRequest>>>,
metrics: Arc<Mutex<Vec<metrics::ExportMetricsServiceRequest>>>,
fail_until: usize,
attempts: [Arc<AtomicUsize>; 3],
}
fn check_auth<T>(request: &Request<T>) -> Result<(), Status> {
if request
.metadata()
.get("authorization")
.and_then(|v| v.to_str().ok())
!= Some("Basic dGVzdDp0ZXN0")
{
return Err(Status::unauthenticated(
"test receiver requires authorization",
));
}
Ok(())
}
/// Use a real receiver and counted RPCs, not sleep/elapsed-time expectations.
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn exporter_retries_are_bounded_and_bad_credentials_are_not_retried() {
use opentelemetry_otlp::{RetryPolicy, WithExportConfig, WithTonicConfig};
use opentelemetry_sdk::trace::SpanExporter as _;
use std::time::Duration;
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
let endpoint = format!("http://{}", listener.local_addr().unwrap());
let collector = Collector {
fail_until: usize::MAX,
..Default::default()
};
let (stop_tx, stop_rx) = tokio::sync::oneshot::channel();
let server = tokio::spawn(
tonic::transport::Server::builder()
.add_service(traces::trace_service_server::TraceServiceServer::new(
collector.clone(),
))
.serve_with_incoming_shutdown(
tokio_stream::wrappers::TcpListenerStream::new(listener),
async {
let _ = stop_rx.await;
},
),
);
let mut metadata = tonic::metadata::MetadataMap::new();
metadata.insert("authorization", "Basic dGVzdDp0ZXN0".parse().unwrap());
let policy = RetryPolicy::recommended()
.with_max_retries(2)
.with_initial_delay(Duration::from_millis(1))
.with_max_delay(Duration::from_millis(4))
.with_max_jitter(Duration::ZERO);
let exporter = opentelemetry_otlp::SpanExporter::builder()
.with_tonic()
.with_endpoint(&endpoint)
.with_metadata(metadata)
.with_timeout(Duration::from_secs(3))
.with_retry_policy(policy.clone())
.build()
.unwrap();
assert!(exporter.export(vec![]).await.is_err());
assert_eq!(collector.attempts[0].load(Ordering::SeqCst), 3);
let unauthorized = opentelemetry_otlp::SpanExporter::builder()
.with_tonic()
.with_endpoint(endpoint)
.with_timeout(Duration::from_secs(3))
.with_retry_policy(policy)
.build()
.unwrap();
assert!(unauthorized.export(vec![]).await.is_err());
assert_eq!(
collector.attempts[0].load(Ordering::SeqCst),
4,
"authentication failure must add only one attempt"
);
let _ = stop_tx.send(());
server.await.unwrap().unwrap();
}
#[tonic::async_trait]
impl traces::trace_service_server::TraceService for Collector {
async fn export(
&self,
request: Request<traces::ExportTraceServiceRequest>,
) -> Result<Response<traces::ExportTraceServiceResponse>, Status> {
let attempt = self.attempts[0].fetch_add(1, Ordering::SeqCst);
check_auth(&request)?;
if attempt < self.fail_until {
return Err(Status::unavailable("temporary receiver outage"));
}
self.traces.lock().unwrap().push(request.into_inner());
Ok(Response::new(Default::default()))
}
}
#[tonic::async_trait]
impl logs::logs_service_server::LogsService for Collector {
async fn export(
&self,
request: Request<logs::ExportLogsServiceRequest>,
) -> Result<Response<logs::ExportLogsServiceResponse>, Status> {
let attempt = self.attempts[1].fetch_add(1, Ordering::SeqCst);
check_auth(&request)?;
if attempt < self.fail_until {
return Err(Status::unavailable("temporary receiver outage"));
}
self.logs.lock().unwrap().push(request.into_inner());
Ok(Response::new(Default::default()))
}
}
#[tonic::async_trait]
impl metrics::metrics_service_server::MetricsService for Collector {
async fn export(
&self,
request: Request<metrics::ExportMetricsServiceRequest>,
) -> Result<Response<metrics::ExportMetricsServiceResponse>, Status> {
let attempt = self.attempts[2].fetch_add(1, Ordering::SeqCst);
check_auth(&request)?;
if attempt < self.fail_until {
return Err(Status::unavailable("temporary receiver outage"));
}
self.metrics.lock().unwrap().push(request.into_inner());
Ok(Response::new(Default::default()))
}
}
/// Shutdown is the synchronization point: no sleeps or export-interval polling.
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn exports_all_signals_and_preserves_remote_command_parent() {
// Exercise the real global subscriber without mutating this process's environment
// or inheriting a developer's RUST_LOG=warn/off setting.
if std::env::var_os("WAKEY_OTLP_TEST_CHILD").is_none() {
for retry in ["0", "1"] {
let output = std::process::Command::new(std::env::current_exe().unwrap())
.args([
"--exact",
"exports_all_signals_and_preserves_remote_command_parent",
"--nocapture",
])
.env("WAKEY_OTLP_TEST_CHILD", "1")
.env("WAKEY_OTLP_TEST_RETRY", retry)
.env("RUST_LOG", "info")
.env("WAKEY_OTLP_TEST_AUTH", "Basic dGVzdDp0ZXN0")
.output()
.unwrap();
assert!(
output.status.success(),
"{}",
String::from_utf8_lossy(&output.stderr)
);
for console in [&output.stdout, &output.stderr] {
assert!(
!String::from_utf8_lossy(console)
.contains("debug log exported without console output")
);
}
}
return;
}
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
let endpoint = format!("http://{}", listener.local_addr().unwrap());
let retry = std::env::var("WAKEY_OTLP_TEST_RETRY").as_deref() == Ok("1");
let collector = Collector {
fail_until: usize::from(retry),
..Default::default()
};
let (stop_tx, stop_rx) = tokio::sync::oneshot::channel();
let server = tonic::transport::Server::builder()
.add_service(traces::trace_service_server::TraceServiceServer::new(
collector.clone(),
))
.add_service(logs::logs_service_server::LogsServiceServer::new(
collector.clone(),
))
.add_service(metrics::metrics_service_server::MetricsServiceServer::new(
collector.clone(),
))
.serve_with_incoming_shutdown(
tokio_stream::wrappers::TcpListenerStream::new(listener),
async {
let _ = stop_rx.await;
},
);
let server = tokio::spawn(server);
// The exporter contract is OS-independent; Linux procfs collection is
// tested in wakey-linux rather than imported into core.
struct ProcessSample;
impl telemetry::ProcessMetricsSource for ProcessSample {
fn process_uptime_seconds(&self) -> Option<f64> {
Some(120.5)
}
fn resident_memory_bytes(&self) -> Option<u64> {
Some(32 * 1024 * 1024)
}
fn host_uptime_seconds(&self) -> Option<f64> {
Some(10_000.0)
}
fn cpu_time_seconds(&self) -> Option<f64> {
Some(1.25)
}
fn open_file_descriptors(&self) -> Option<u64> {
Some(12)
}
fn host_memory(&self) -> Option<telemetry::HostMemory> {
Some(telemetry::HostMemory {
total_bytes: 2 * 1024 * 1024 * 1024,
available_bytes: Some(512 * 1024 * 1024),
})
}
fn host_load(&self) -> Option<telemetry::HostLoad> {
Some(telemetry::HostLoad {
one_minute: 0.5,
five_minutes: 1.0,
fifteen_minutes: 1.5,
})
}
}
let guard = telemetry::init(
&TelemetryConfig {
otlp_endpoint: Some(endpoint),
authorization_env: Some("WAKEY_OTLP_TEST_AUTH".into()),
service_name: "wakey-test".into(),
json_logs: false,
console_filter: Some("info".into()),
otlp_log_filter: Some("debug".into()),
trace_filter: Some("info".into()),
},
"unused",
"info",
Some("test-agent"),
)
.unwrap()
.with_process_metrics(ProcessSample);
let fleet_metrics = telemetry::FleetMetrics::new().unwrap();
fleet_metrics.replace(Some(telemetry::FleetCounts {
agents: [(
"removed-agent".into(),
telemetry::AgentDeviceCounts {
devices: 9,
endpoints: 20,
},
)]
.into(),
saved: 9,
unsaved: 0,
}));
fleet_metrics.replace(None);
fleet_metrics.replace(Some(telemetry::FleetCounts {
agents: [
(
"router".into(),
telemetry::AgentDeviceCounts {
devices: 2,
endpoints: 7,
},
),
("empty-agent".into(), Default::default()),
]
.into(),
saved: 1,
unsaved: 1,
}));
let parent = tracing::info_span!("relay_command");
let context = parent.in_scope(telemetry::current_trace_context);
assert!(context.contains_key("traceparent"));
let child = tracing::info_span!("execute_command");
telemetry::set_remote_parent(&child, &context);
child.in_scope(|| {
tracing::info!(command = "inventory", "command complete");
let mut operation = telemetry::Operation::new("inventory");
operation.outcome("ok");
telemetry::count(telemetry::Counter::SnapshotDevices, 3);
let _active = telemetry::ActiveTerminal::new();
});
drop(child);
drop(parent);
tracing::debug!("debug log exported without console output");
let hidden = tracing::debug_span!("debug_span_not_exported");
drop(hidden);
tracing::warn!(target: "opentelemetry_sdk", "synthetic exporter failure remains local");
let invalid_parent = tracing::info_span!("invalid_remote_parent");
telemetry::set_remote_parent(
&invalid_parent,
&[("traceparent".into(), "malformed".into())].into(),
);
drop(invalid_parent);
tokio::task::spawn_blocking(move || guard.shutdown())
.await
.unwrap();
let _ = stop_tx.send(());
server.await.unwrap().unwrap();
for attempts in &collector.attempts {
assert!(
attempts.load(Ordering::SeqCst) > usize::from(retry),
"each signal must recover from its first failed export"
);
}
let traces = collector.traces.lock().unwrap();
let spans: Vec<_> = traces
.iter()
.flat_map(|r| &r.resource_spans)
.flat_map(|r| &r.scope_spans)
.flat_map(|s| &s.spans)
.collect();
let parent = spans.iter().find(|s| s.name == "relay_command").unwrap();
let child = spans.iter().find(|s| s.name == "execute_command").unwrap();
assert_eq!(parent.trace_id, child.trace_id);
assert_eq!(parent.span_id, child.parent_span_id);
let invalid_parent = spans
.iter()
.find(|s| s.name == "invalid_remote_parent")
.unwrap();
assert!(invalid_parent.parent_span_id.is_empty());
assert_ne!(parent.trace_id, invalid_parent.trace_id);
let logs = collector.logs.lock().unwrap();
assert!(
!spans
.iter()
.any(|span| span.name == "debug_span_not_exported")
);
let records: Vec<_> = logs
.iter()
.flat_map(|r| &r.resource_logs)
.flat_map(|r| &r.scope_logs)
.flat_map(|s| &s.log_records)
.collect();
assert!(
records
.iter()
.any(|r| r.trace_id == child.trace_id && r.span_id == child.span_id)
);
assert!(
!records
.iter()
.any(|r| format!("{:?}", r.body).contains("synthetic exporter failure"))
);
assert!(
records
.iter()
.any(|r| format!("{:?}", r.body).contains("debug log exported without console output"))
);
let metrics = collector.metrics.lock().unwrap();
let names: Vec<_> = metrics
.iter()
.flat_map(|r| &r.resource_metrics)
.flat_map(|r| &r.scope_metrics)
.flat_map(|s| &s.metrics)
.map(|m| m.name.as_str())
.collect();
for name in [
"wakey.operations",
"wakey.operation.duration",
"wakey.snapshot.devices",
"wakey.terminal.active",
"wakey.stored.devices",
"wakey.stored.endpoints",
"wakey.fleet.devices",
] {
assert!(names.contains(&name), "missing {name}");
}
let latest = metrics.last().unwrap();
{
for (name, unit, expected) in [
(
"wakey.process.uptime",
"s",
number_data_point::Value::AsDouble(120.5),
),
(
"wakey.process.memory.resident",
"By",
number_data_point::Value::AsInt(32 * 1024 * 1024),
),
(
"wakey.host.uptime",
"s",
number_data_point::Value::AsDouble(10_000.0),
),
(
"wakey.process.open_fds",
"",
number_data_point::Value::AsInt(12),
),
(
"wakey.host.memory.total",
"By",
number_data_point::Value::AsInt(2 * 1024 * 1024 * 1024),
),
(
"wakey.host.memory.available",
"By",
number_data_point::Value::AsInt(512 * 1024 * 1024),
),
] {
let metric = latest
.resource_metrics
.iter()
.flat_map(|resource| &resource.scope_metrics)
.flat_map(|scope| &scope.metrics)
.find(|metric| metric.name == name)
.unwrap_or_else(|| panic!("missing {name}"));
assert_eq!(metric.unit, unit);
let Some(metric::Data::Gauge(gauge)) = &metric.data else {
panic!("{name} must be a gauge");
};
assert_eq!(gauge.data_points.len(), 1);
let point = &gauge.data_points[0];
assert!(
point.attributes.is_empty(),
"process metrics need no PID/host/address labels"
);
assert_eq!(point.value, Some(expected));
}
let cpu = latest
.resource_metrics
.iter()
.flat_map(|resource| &resource.scope_metrics)
.flat_map(|scope| &scope.metrics)
.find(|metric| metric.name == "wakey.process.cpu.time")
.expect("CPU time exported");
assert_eq!(cpu.unit, "s");
let Some(metric::Data::Sum(sum)) = &cpu.data else {
panic!("CPU time must be a counter, not a gauge");
};
assert!(sum.is_monotonic);
assert_eq!(sum.data_points.len(), 1);
assert_eq!(
sum.data_points[0].value,
Some(number_data_point::Value::AsDouble(1.25))
);
assert!(sum.data_points[0].attributes.is_empty());
let load = latest
.resource_metrics
.iter()
.flat_map(|resource| &resource.scope_metrics)
.flat_map(|scope| &scope.metrics)
.find(|metric| metric.name == "wakey.host.load")
.expect("host load exported");
let Some(metric::Data::Gauge(gauge)) = &load.data else {
panic!("host load must be a gauge");
};
assert_eq!(gauge.data_points.len(), 3);
for (period, expected) in [("1m", 0.5), ("5m", 1.0), ("15m", 1.5)] {
let point = gauge.data_points.iter().find(|point| point.attributes.iter().any(|attribute| {
attribute.key == "period" && attribute.value.as_ref().and_then(|value| value.value.as_ref())
== Some(&opentelemetry_proto::tonic::common::v1::any_value::Value::StringValue(period.into()))
})).expect("load period exported");
assert_eq!(point.attributes.len(), 1, "only fixed period labels");
assert_eq!(
point.value,
Some(number_data_point::Value::AsDouble(expected))
);
}
}
for (name, label, expected) in [
(
"wakey.stored.devices",
"agent_id",
vec![("router", 2), ("empty-agent", 0)],
),
(
"wakey.stored.endpoints",
"agent_id",
vec![("router", 7), ("empty-agent", 0)],
),
(
"wakey.fleet.devices",
"identity",
vec![("saved", 1), ("unsaved", 1)],
),
] {
let metric = latest
.resource_metrics
.iter()
.flat_map(|r| &r.scope_metrics)
.flat_map(|s| &s.metrics)
.find(|m| m.name == name)
.unwrap();
let Some(metric::Data::Gauge(gauge)) = &metric.data else {
panic!("{name} must be a gauge");
};
assert_eq!(gauge.data_points.len(), expected.len());
for (value, count) in expected {
let point = gauge.data_points.iter().find(|p| p.attributes.iter().any(|a| {
a.key == label && a.value.as_ref().and_then(|v| v.value.as_ref())
== Some(&opentelemetry_proto::tonic::common::v1::any_value::Value::StringValue(value.into()))
})).unwrap();
assert_eq!(point.value, Some(number_data_point::Value::AsInt(count)));
assert_eq!(point.attributes.len(), 1, "no device/address labels");
}
}
}