rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2026-01-07 05:22:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(pageserver): allow read path debug in getpagelsn API (#10748)

Browse Source 
## Problem

The usual workflow for me to debug read path errors in staging is:
download the tenant to my laptop, import, and then run some read tests.

With this patch, we can do this directly over staging pageservers.

## Summary of changes

* Add a new `touchpagelsn` API that does a page read but does not return
page info back.
* Allow read from latest record LSN from get/touchpagelsn
* Add read_debug config in the context.
* The read path will read the context config to decide whether to enable
read path tracing or not.

Signed-off-by: Alex Chi Z <chi@neon.tech>
This commit is contained in:
Alex Chi Z.
2025-02-18 13:54:53 -05:00
committed by GitHub
parent cb8060545d
commit 538ea03f73
3 changed files with 52 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
pageserver/src/http/routes.rs
View File

@@ -68,6 +68,7 @@ use tokio_util::sync::CancellationToken;
use tracing::*;
use crate::config::PageServerConf;
use crate::context::RequestContextBuilder;
use crate::context::{DownloadBehavior, RequestContext};
use crate::deletion_queue::DeletionQueueClient;
use crate::pgdatadir_mapping::LsnForTimestamp;
@@ -2571,14 +2572,30 @@ async fn deletion_queue_flush(
}
}
/// Try if `GetPage@Lsn` is successful, useful for manual debugging.
async fn getpage_at_lsn_handler(
request: Request<Body>,
cancel: CancellationToken,
) -> Result<Response<Body>, ApiError> {
getpage_at_lsn_handler_inner(false, request, cancel).await
}
async fn touchpage_at_lsn_handler(
request: Request<Body>,
cancel: CancellationToken,
) -> Result<Response<Body>, ApiError> {
getpage_at_lsn_handler_inner(true, request, cancel).await
}
/// Try if `GetPage@Lsn` is successful, useful for manual debugging.
async fn getpage_at_lsn_handler_inner(
touch: bool,
request: Request<Body>,
_cancel: CancellationToken,
) -> Result<Response<Body>, ApiError> {
let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
let timeline_id: TimelineId = parse_request_param(&request, "timeline_id")?;
check_permission(&request, Some(tenant_shard_id.tenant_id))?;
// Require pageserver admin permission for this API instead of only tenant-level token.
check_permission(&request, None)?;
let state = get_state(&request);
struct Key(pageserver_api::key::Key);
@@ -2593,22 +2610,29 @@ async fn getpage_at_lsn_handler(
let key: Key = parse_query_param(&request, "key")?
.ok_or_else(|| ApiError::BadRequest(anyhow!("missing 'key' query parameter")))?;
let lsn: Lsn = parse_query_param(&request, "lsn")?
.ok_or_else(|| ApiError::BadRequest(anyhow!("missing 'lsn' query parameter")))?;
let lsn: Option<Lsn> = parse_query_param(&request, "lsn")?;
async {
let ctx = RequestContext::new(TaskKind::MgmtRequest, DownloadBehavior::Download);
// Enable read path debugging
let ctx = RequestContextBuilder::extend(&ctx).read_path_debug(true).build();
let timeline = active_timeline_of_active_tenant(&state.tenant_manager, tenant_shard_id, timeline_id).await?;
// Use last_record_lsn if no lsn is provided
let lsn = lsn.unwrap_or_else(|| timeline.get_last_record_lsn());
let page = timeline.get(key.0, lsn, &ctx).await?;
Result::<_, ApiError>::Ok(
Response::builder()
.status(StatusCode::OK)
.header(header::CONTENT_TYPE, "application/octet-stream")
.body(hyper::Body::from(page))
.unwrap(),
)
if touch {
json_response(StatusCode::OK, ())
} else {
Result::<_, ApiError>::Ok(
Response::builder()
.status(StatusCode::OK)
.header(header::CONTENT_TYPE, "application/octet-stream")
.body(hyper::Body::from(page))
.unwrap(),
)
}
}
.instrument(info_span!("timeline_get", tenant_id = %tenant_shard_id.tenant_id, shard_id = %tenant_shard_id.shard_slug(), %timeline_id))
.await
@@ -3743,6 +3767,10 @@ pub fn make_router(
"/v1/tenant/:tenant_shard_id/timeline/:timeline_id/getpage",
|r| testing_api_handler("getpage@lsn", r, getpage_at_lsn_handler),
)
.get(
"/v1/tenant/:tenant_shard_id/timeline/:timeline_id/touchpage",
|r| api_handler(r, touchpage_at_lsn_handler),
)
.get(
"/v1/tenant/:tenant_shard_id/timeline/:timeline_id/keyspace",
|r| api_handler(r, timeline_collect_keyspace),