rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2026-01-14 00:42:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

pageserver_live_connections: track as counter pair (#8227)

Browse Source 
Generally counter pairs are preferred over gauges.
In this case, I found myself asking what the typical rate of accepted
page_service connections on a pageserver is, and I couldn't answer it
with the gauge metric.

There are a few dashboards using this metric:

https://github.com/search?q=repo%3Aneondatabase%2Fgrafana-dashboard-export%20pageserver_live_connections&type=code

I'll convert them to use the new metric once this PR reaches prod.

refs https://github.com/neondatabase/neon/issues/7427
This commit is contained in:
Christian Schwarz
2024-07-05 22:17:05 +02:00
committed by Vlad Lazar
parent 05b4169644
commit f3310143e4
3 changed files with 14 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
pageserver/src/metrics.rs
View File

@@ -1456,10 +1456,12 @@ impl<'a, 'c> BasebackupQueryTimeOngoingRecording<'a, 'c> {
}
}
pub(crate) static LIVE_CONNECTIONS_COUNT: Lazy<IntGaugeVec> = Lazy::new(|| {
register_int_gauge_vec!(
"pageserver_live_connections",
"Number of live network connections",
pub(crate) static LIVE_CONNECTIONS: Lazy<IntCounterPairVec> = Lazy::new(|| {
register_int_counter_pair_vec!(
"pageserver_live_connections_started",
"Number of network connections that we started handling",
"pageserver_live_connections_finished",
"Number of network connections that we finished handling",
&["pageserver_connection_kind"]
)
.expect("failed to define a metric")

13
pageserver/src/page_service.rs
View File

@@ -55,7 +55,7 @@ use crate::basebackup::BasebackupError;
use crate::context::{DownloadBehavior, RequestContext};
use crate::import_datadir::import_wal_from_tar;
use crate::metrics;
use crate::metrics::{ComputeCommandKind, COMPUTE_COMMANDS_COUNTERS, LIVE_CONNECTIONS_COUNT};
use crate::metrics::{ComputeCommandKind, COMPUTE_COMMANDS_COUNTERS, LIVE_CONNECTIONS};
use crate::pgdatadir_mapping::Version;
use crate::span::debug_assert_current_span_has_tenant_and_timeline_id;
use crate::span::debug_assert_current_span_has_tenant_and_timeline_id_no_shard_id;
@@ -215,14 +215,9 @@ async fn page_service_conn_main(
auth_type: AuthType,
connection_ctx: RequestContext,
) -> anyhow::Result<()> {
// Immediately increment the gauge, then create a job to decrement it on task exit.
// One of the pros of `defer!` is that this will *most probably*
// get called, even in presence of panics.
let gauge = LIVE_CONNECTIONS_COUNT.with_label_values(&["page_service"]);
gauge.inc();
scopeguard::defer! {
gauge.dec();
}
let _guard = LIVE_CONNECTIONS
.with_label_values(&["page_service"])
.guard();
socket
.set_nodelay(true)

13
pageserver/src/tenant/timeline/walreceiver/walreceiver_connection.rs
View File

@@ -26,7 +26,7 @@ use tracing::{debug, error, info, trace, warn, Instrument};
use super::TaskStateUpdate;
use crate::{
context::RequestContext,
metrics::{LIVE_CONNECTIONS_COUNT, WALRECEIVER_STARTED_CONNECTIONS, WAL_INGEST},
metrics::{LIVE_CONNECTIONS, WALRECEIVER_STARTED_CONNECTIONS, WAL_INGEST},
task_mgr::TaskKind,
task_mgr::WALRECEIVER_RUNTIME,
tenant::{debug_assert_current_span_has_tenant_and_timeline_id, Timeline, WalReceiverInfo},
@@ -208,14 +208,9 @@ pub(super) async fn handle_walreceiver_connection(
.instrument(tracing::info_span!("poller")),
);
// Immediately increment the gauge, then create a job to decrement it on task exit.
// One of the pros of `defer!` is that this will *most probably*
// get called, even in presence of panics.
let gauge = LIVE_CONNECTIONS_COUNT.with_label_values(&["wal_receiver"]);
gauge.inc();
scopeguard::defer! {
gauge.dec();
}
let _guard = LIVE_CONNECTIONS
.with_label_values(&["wal_receiver"])
.guard();
let identify = identify_system(&replication_client).await?;
info!("{identify:?}");