delta & image layer spawned IOs: keep layer resident until IO is done

pageserver/src/tenant/storage_layer/delta_layer.rs

@@ -76,7 +76,9 @@ use utils::{
     lsn::Lsn,
 };
 
-use super::{AsLayerDesc, LayerName, OnDiskValue, PersistentLayerDesc, ValuesReconstructState};
+use super::{
+    AsLayerDesc, LayerName, OnDiskValue, PersistentLayerDesc, ResidentLayer, ValuesReconstructState,
+};
 
 ///
 /// Header stored in the beginning of the file
@@ -847,6 +849,7 @@ impl DeltaLayerInner {
     // can be further optimised to visit the index only once.
     pub(super) async fn get_values_reconstruct_data(
         &self,
+        this: ResidentLayer,
         keyspace: KeySpace,
         lsn_range: Range<Lsn>,
         reconstruct_state: &mut ValuesReconstructState,
@@ -879,7 +882,7 @@ impl DeltaLayerInner {
         .await
         .map_err(GetVectoredError::Other)?;
 
-        self.do_reads_and_update_state(reads, reconstruct_state, ctx)
+        self.do_reads_and_update_state(this, reads, reconstruct_state, ctx)
             .await;
 
         Ok(())
@@ -988,6 +991,7 @@ impl DeltaLayerInner {
 
     async fn do_reads_and_update_state(
         &self,
+        this: ResidentLayer,
         reads: Vec<VectoredRead>,
         reconstruct_state: &mut ValuesReconstructState,
         ctx: &RequestContext,
@@ -1020,6 +1024,7 @@ impl DeltaLayerInner {
                 );
             }
 
+            let read_extend_residency = this.clone();
             let read_from = self.file.clone();
             let read_ctx = ctx.attached_child();
             reconstruct_state
@@ -1064,6 +1069,10 @@ impl DeltaLayerInner {
                             }
                         }
                     }
+
+                    // keep layer resident until this IO is done; this spawned IO future generally outlives the
+                    // call to `self` / the `Arc<DownloadedLayer>` / the `ResidentLayer` that guarantees residency
+                    drop(read_extend_residency);
                 })
                 .await;
         }

pageserver/src/tenant/storage_layer/image_layer.rs

@@ -74,7 +74,9 @@ use utils::{
 };
 
 use super::layer_name::ImageLayerName;
-use super::{AsLayerDesc, LayerName, OnDiskValue, PersistentLayerDesc, ValuesReconstructState};
+use super::{
+    AsLayerDesc, LayerName, OnDiskValue, PersistentLayerDesc, ResidentLayer, ValuesReconstructState,
+};
 
 ///
 /// Header stored in the beginning of the file
@@ -442,6 +444,7 @@ impl ImageLayerInner {
     // the reconstruct state with whatever is found.
     pub(super) async fn get_values_reconstruct_data(
         &self,
+        this: ResidentLayer,
         keyspace: KeySpace,
         reconstruct_state: &mut ValuesReconstructState,
         ctx: &RequestContext,
@@ -451,7 +454,7 @@ impl ImageLayerInner {
             .await
             .map_err(GetVectoredError::Other)?;
 
-        self.do_reads_and_update_state(reads, reconstruct_state, ctx)
+        self.do_reads_and_update_state(this, reads, reconstruct_state, ctx)
             .await;
 
         reconstruct_state.on_image_layer_visited(&self.key_range);
@@ -573,6 +576,7 @@ impl ImageLayerInner {
 
     async fn do_reads_and_update_state(
         &self,
+        this: ResidentLayer,
         reads: Vec<VectoredRead>,
         reconstruct_state: &mut ValuesReconstructState,
         ctx: &RequestContext,
@@ -624,6 +628,7 @@ impl ImageLayerInner {
                 }
             }
 
+            let read_extend_residency = this.clone();
             let read_from = self.file.clone();
             let read_ctx = ctx.attached_child();
             reconstruct_state
@@ -661,6 +666,10 @@ impl ImageLayerInner {
                             }
                         }
                     }
+
+                    // keep layer resident until this IO is done; this spawned IO future generally outlives the
+                    // call to `self` / the `Arc<DownloadedLayer>` / the `ResidentLayer` that guarantees residency
+                    drop(read_extend_residency);
                 })
                 .await;
         }

pageserver/src/tenant/storage_layer/layer.rs

@@ -308,7 +308,7 @@ impl Layer {
         reconstruct_data: &mut ValuesReconstructState,
         ctx: &RequestContext,
     ) -> Result<(), GetVectoredError> {
-        let layer = self
+        let downloaded = self
             .0
             .get_or_maybe_download(true, Some(ctx))
             .await
@@ -318,11 +318,15 @@ impl Layer {
                 }
                 other => GetVectoredError::Other(anyhow::anyhow!(other)),
             })?;
+        let this = ResidentLayer {
+            downloaded: downloaded.clone(),
+            owner: self.clone(),
+        };
 
         self.record_access(ctx);
 
-        layer
-            .get_values_reconstruct_data(keyspace, lsn_range, reconstruct_data, &self.0, ctx)
+        downloaded
+            .get_values_reconstruct_data(this, keyspace, lsn_range, reconstruct_data, ctx)
             .instrument(tracing::debug_span!("get_values_reconstruct_data", layer=%self))
             .await
             .map_err(|err| match err {
@@ -1768,25 +1772,25 @@ impl DownloadedLayer {
 
     async fn get_values_reconstruct_data(
         &self,
+        this: ResidentLayer,
         keyspace: KeySpace,
         lsn_range: Range<Lsn>,
         reconstruct_data: &mut ValuesReconstructState,
-        owner: &Arc<LayerInner>,
         ctx: &RequestContext,
     ) -> Result<(), GetVectoredError> {
         use LayerKind::*;
 
         match self
-            .get(owner, ctx)
+            .get(&this.owner.0, ctx)
             .await
             .map_err(GetVectoredError::Other)?
         {
             Delta(d) => {
-                d.get_values_reconstruct_data(keyspace, lsn_range, reconstruct_data, ctx)
+                d.get_values_reconstruct_data(this, keyspace, lsn_range, reconstruct_data, ctx)
                     .await
             }
             Image(i) => {
-                i.get_values_reconstruct_data(keyspace, reconstruct_data, ctx)
+                i.get_values_reconstruct_data(this, keyspace, reconstruct_data, ctx)
                     .await
             }
         }