mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-08 05:52:55 +00:00
pageserver: optionally export perf traces in OTEL format (#11140)
Based on https://github.com/neondatabase/neon/pull/11139 ## Problem We want to export performance traces from the pageserver in OTEL format. End goal is to see them in Grafana. ## Summary of changes https://github.com/neondatabase/neon/pull/11139 introduces the infrastructure required to run the otel collector alongside the pageserver. ### Design Requirements: 1. We'd like to avoid implementing our own performance tracing stack if possible and use the `tracing` crate if possible. 2. Ideally, we'd like zero overhead of a sampling rate of zero and be a be able to change the tracing config for a tenant on the fly. 3. We should leave the current span hierarchy intact. This includes adding perf traces without modifying existing tracing. To satisfy (3) (and (2) in part) a separate span hierarchy is used. `RequestContext` gains an optional `perf_span` member that's only set when the request was chosen by sampling. All perf span related methods added to `RequestContext` are no-ops for requests that are not sampled. This on its own is not enough for (3), so performance spans use a separate tracing subscriber. The `tracing` crate doesn't have great support for this, so there's a fair amount of boilerplate to override the subscriber at all points of the perf span lifecycle. ### Perf Impact [Periodic pagebench](https://neonprod.grafana.net/d/ddqtbfykfqfi8d/e904990?orgId=1&from=2025-02-08T14:15:59.362Z&to=2025-03-10T14:15:59.362Z&timezone=utc) shows no statistically significant regression with a sample ratio of 0. There's an annotation on the dashboard on 2025-03-06. ### Overview of changes: 1. Clean up the `RequestContext` API a bit. Namely, get rid of the `RequestContext::extend` API and use the builder instead. 2. Add pageserver level configs for tracing: sampling ratio, otel endpoint, etc. 3. Introduce some perf span tracking utilities and expose them via `RequestContext`. We add a `tracing::Span` wrapper to be used for perf spans and a `tracing::Instrumented` equivalent for it. See doc comments for reason. 4. Set up OTEL tracing infra according to configuration. A separate runtime is used for the collector. 5. Add perf traces to the read path. ## Refs - epic https://github.com/neondatabase/neon/issues/9873 --------- Co-authored-by: Christian Schwarz <christian@neon.tech>
This commit is contained in:
@@ -2697,11 +2697,12 @@ async fn getpage_at_lsn_handler_inner(
|
||||
let lsn: Option<Lsn> = parse_query_param(&request, "lsn")?;
|
||||
|
||||
async {
|
||||
let ctx = RequestContext::new(TaskKind::MgmtRequest, DownloadBehavior::Download);
|
||||
// Enable read path debugging
|
||||
let timeline = active_timeline_of_active_tenant(&state.tenant_manager, tenant_shard_id, timeline_id).await?;
|
||||
let ctx = RequestContextBuilder::extend(&ctx).read_path_debug(true)
|
||||
.scope(context::Scope::new_timeline(&timeline)).build();
|
||||
let ctx = RequestContextBuilder::new(TaskKind::MgmtRequest)
|
||||
.download_behavior(DownloadBehavior::Download)
|
||||
.scope(context::Scope::new_timeline(&timeline))
|
||||
.read_path_debug(true)
|
||||
.root();
|
||||
|
||||
// Use last_record_lsn if no lsn is provided
|
||||
let lsn = lsn.unwrap_or_else(|| timeline.get_last_record_lsn());
|
||||
@@ -3433,14 +3434,15 @@ async fn put_tenant_timeline_import_wal(
|
||||
|
||||
check_permission(&request, Some(tenant_id))?;
|
||||
|
||||
let ctx = RequestContext::new(TaskKind::MgmtRequest, DownloadBehavior::Warn);
|
||||
|
||||
let span = info_span!("import_wal", tenant_id=%tenant_id, timeline_id=%timeline_id, start_lsn=%start_lsn, end_lsn=%end_lsn);
|
||||
async move {
|
||||
let state = get_state(&request);
|
||||
|
||||
let timeline = active_timeline_of_active_tenant(&state.tenant_manager, TenantShardId::unsharded(tenant_id), timeline_id).await?;
|
||||
let ctx = RequestContextBuilder::extend(&ctx).scope(context::Scope::new_timeline(&timeline)).build();
|
||||
let ctx = RequestContextBuilder::new(TaskKind::MgmtRequest)
|
||||
.download_behavior(DownloadBehavior::Warn)
|
||||
.scope(context::Scope::new_timeline(&timeline))
|
||||
.root();
|
||||
|
||||
let mut body = StreamReader::new(request.into_body().map(|res| {
|
||||
res.map_err(|error| {
|
||||
|
||||
Reference in New Issue
Block a user