From fe156245708525d87bd3682595a3383e389efc65 Mon Sep 17 00:00:00 2001
From: Christian Schwarz <christian@neon.tech>
Date: Mon, 27 Mar 2023 13:33:40 +0200
Subject: [PATCH] eviction_task: only refresh layer accesses once per
 p.threshold (#3877)

Without this, we run it every p.period, which can be quite low. For
example, the running experiment with 3000 tenants in prod uses a period
of 1 minute.

Doing it once per p.threshold is enough to prevent eviction.
---
 pageserver/src/tenant/timeline.rs               |  8 ++++++++
 pageserver/src/tenant/timeline/eviction_task.rs | 15 ++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/pageserver/src/tenant/timeline.rs b/pageserver/src/tenant/timeline.rs
index 5fde1a77e0..dfa0e842f1 100644
--- a/pageserver/src/tenant/timeline.rs
+++ b/pageserver/src/tenant/timeline.rs
@@ -71,6 +71,8 @@ use crate::ZERO_PAGE;
 use crate::{is_temporary, task_mgr};
 use walreceiver::spawn_connection_manager_task;
 
+use self::eviction_task::EvictionTaskTimelineState;
+
 use super::layer_map::BatchedUpdates;
 use super::remote_timeline_client::index::IndexPart;
 use super::remote_timeline_client::RemoteTimelineClient;
@@ -216,6 +218,8 @@ pub struct Timeline {
     download_all_remote_layers_task_info: RwLock<Option<DownloadRemoteLayersTaskInfo>>,
 
     state: watch::Sender<TimelineState>,
+
+    eviction_task_timeline_state: tokio::sync::Mutex<EvictionTaskTimelineState>,
 }
 
 /// Internal structure to hold all data needed for logical size calculation.
@@ -1252,6 +1256,10 @@ impl Timeline {
                 download_all_remote_layers_task_info: RwLock::new(None),
 
                 state,
+
+                eviction_task_timeline_state: tokio::sync::Mutex::new(
+                    EvictionTaskTimelineState::default(),
+                ),
             };
             result.repartition_threshold = result.get_checkpoint_distance() / 10;
             result
diff --git a/pageserver/src/tenant/timeline/eviction_task.rs b/pageserver/src/tenant/timeline/eviction_task.rs
index 666768ff87..06dfe7a0b9 100644
--- a/pageserver/src/tenant/timeline/eviction_task.rs
+++ b/pageserver/src/tenant/timeline/eviction_task.rs
@@ -35,6 +35,11 @@ use crate::{
 
 use super::Timeline;
 
+#[derive(Default)]
+pub struct EvictionTaskTimelineState {
+    last_refresh_required_in_restart: Option<tokio::time::Instant>,
+}
+
 impl Timeline {
     pub(super) fn launch_eviction_task(self: &Arc<Self>) {
         let self_clone = Arc::clone(self);
@@ -139,7 +144,15 @@ impl Timeline {
         // for active tenants this will likely materialized page cache or in-memory layers. for
         // inactive tenants it will refresh the last_access timestamps so that we will not evict
         // and re-download on restart these layers.
-        self.refresh_layers_required_in_restart(cancel, ctx).await;
+        let mut state = self.eviction_task_timeline_state.lock().await;
+        match state.last_refresh_required_in_restart {
+            Some(ts) if ts.elapsed() < p.threshold => { /* no need to run */ }
+            _ => {
+                self.refresh_layers_required_in_restart(cancel, ctx).await;
+                state.last_refresh_required_in_restart = Some(tokio::time::Instant::now())
+            }
+        }
+        drop(state);
 
         if cancel.is_cancelled() {
             return ControlFlow::Break(());