Test & bench for layer visibility

pageserver/benches/bench_layer_map.rs

@@ -1,3 +1,4 @@
+use criterion::measurement::WallTime;
 use pageserver::keyspace::{KeyPartitioning, KeySpace};
 use pageserver::repository::Key;
 use pageserver::tenant::layer_map::LayerMap;
@@ -15,7 +16,11 @@ use utils::id::{TenantId, TimelineId};
 
 use utils::lsn::Lsn;
 
-use criterion::{black_box, criterion_group, criterion_main, Criterion};
+use criterion::{black_box, criterion_group, criterion_main, BenchmarkGroup, Criterion};
+
+fn fixture_path(relative: &str) -> PathBuf {
+    PathBuf::from(env!("CARGO_MANIFEST_DIR")).join(relative)
+}
 
 fn build_layer_map(filename_dump: PathBuf) -> LayerMap {
     let mut layer_map = LayerMap::default();
@@ -109,7 +114,7 @@ fn uniform_key_partitioning(layer_map: &LayerMap, _lsn: Lsn) -> KeyPartitioning
 // between each test run.
 fn bench_from_captest_env(c: &mut Criterion) {
     // TODO consider compressing this file
-    let layer_map = build_layer_map(PathBuf::from("benches/odd-brook-layernames.txt"));
+    let layer_map = build_layer_map(fixture_path("benches/odd-brook-layernames.txt"));
     let queries: Vec<(Key, Lsn)> = uniform_query_pattern(&layer_map);
 
     // Test with uniform query pattern
@@ -139,7 +144,7 @@ fn bench_from_captest_env(c: &mut Criterion) {
 fn bench_from_real_project(c: &mut Criterion) {
     // Init layer map
     let now = Instant::now();
-    let layer_map = build_layer_map(PathBuf::from("benches/odd-brook-layernames.txt"));
+    let layer_map = build_layer_map(fixture_path("benches/odd-brook-layernames.txt"));
     println!("Finished layer map init in {:?}", now.elapsed());
 
     // Choose uniformly distributed queries
@@ -242,7 +247,72 @@ fn bench_sequential(c: &mut Criterion) {
     group.finish();
 }
 
+fn bench_visibility_with_map(
+    group: &mut BenchmarkGroup<WallTime>,
+    layer_map: LayerMap,
+    read_points: Vec<Lsn>,
+    bench_name: &str,
+) {
+    group.bench_function(bench_name, |b| {
+        b.iter(|| black_box(layer_map.get_visibility(read_points.clone())));
+    });
+}
+
+// Benchmark using synthetic data. Arrange image layers on stacked diagonal lines.
+fn bench_visibility(c: &mut Criterion) {
+    let mut group = c.benchmark_group("visibility");
+    {
+        // Init layer map. Create 100_000 layers arranged in 1000 diagonal lines.
+        let now = Instant::now();
+        let mut layer_map = LayerMap::default();
+        let mut updates = layer_map.batch_update();
+        for i in 0..100_000 {
+            let i32 = (i as u32) % 100;
+            let zero = Key::from_hex("000000000000000000000000000000000000").unwrap();
+            let layer = PersistentLayerDesc::new_img(
+                TenantShardId::unsharded(TenantId::generate()),
+                TimelineId::generate(),
+                zero.add(10 * i32)..zero.add(10 * i32 + 1),
+                Lsn(i),
+                0,
+            );
+            updates.insert_historic(layer);
+        }
+        updates.flush();
+        println!("Finished layer map init in {:?}", now.elapsed());
+
+        let mut read_points = Vec::new();
+        for i in (0..100_000).step_by(1000) {
+            read_points.push(Lsn(i));
+        }
+
+        bench_visibility_with_map(&mut group, layer_map, read_points, "sequential");
+    }
+
+    {
+        let layer_map = build_layer_map(fixture_path("benches/odd-brook-layernames.txt"));
+        let read_points = vec![Lsn(0x1C760FA190)];
+        bench_visibility_with_map(&mut group, layer_map, read_points, "real_map");
+
+        let layer_map = build_layer_map(fixture_path("benches/odd-brook-layernames.txt"));
+        let read_points = vec![
+            Lsn(0x1C760FA190),
+            Lsn(0x000000931BEAD539),
+            Lsn(0x000000931BF63011),
+            Lsn(0x000000931B33AE68),
+            Lsn(0x00000038E67ABFA0),
+            Lsn(0x000000931B33AE68),
+            Lsn(0x000000914E3F38F0),
+            Lsn(0x000000931B33AE68),
+        ];
+        bench_visibility_with_map(&mut group, layer_map, read_points, "real_map_many_branches");
+    }
+
+    group.finish();
+}
+
 criterion_group!(group_1, bench_from_captest_env);
 criterion_group!(group_2, bench_from_real_project);
 criterion_group!(group_3, bench_sequential);
-criterion_main!(group_1, group_2, group_3);
+criterion_group!(group_4, bench_visibility);
+criterion_main!(group_1, group_2, group_3, group_4);

pageserver/src/tenant/layer_map.rs

@@ -878,7 +878,7 @@ impl LayerMap {
     ///
     /// This function is O(N) and should be called infrequently.  The caller is responsible for
     /// looking up and updating the Layer objects for these layer descriptors.
-    pub(crate) fn get_visibility<'a>(
+    pub fn get_visibility<'a>(
         &'a self,
         mut read_points: Vec<Lsn>,
     ) -> (
@@ -1037,7 +1037,13 @@ impl LayerMap {
 
 #[cfg(test)]
 mod tests {
-    use pageserver_api::keyspace::KeySpace;
+    use crate::tenant::{storage_layer::LayerName, IndexPart};
+    use pageserver_api::{key::DBDIR_KEY, keyspace::KeySpace};
+    use std::collections::HashMap;
+    use utils::{
+        id::{TenantId, TimelineId},
+        shard::TenantShardId,
+    };
 
     use super::*;
 
@@ -1164,4 +1170,68 @@ mod tests {
             }
         }
     }
+
+    #[test]
+    fn layer_visibility() {
+        // Load a large example layermap
+        let index_raw =
+            std::fs::read_to_string("test_data/indices/mixed_workload/index_part.json").unwrap();
+        let index: IndexPart = serde_json::from_str::<IndexPart>(&index_raw).unwrap();
+
+        let tenant_id = TenantId::generate();
+        let tenant_shard_id = TenantShardId::unsharded(tenant_id);
+        let timeline_id = TimelineId::generate();
+
+        let mut layer_map = LayerMap::default();
+        let mut updates = layer_map.batch_update();
+        for (layer_name, layer_metadata) in index.layer_metadata {
+            let layer_desc = match layer_name {
+                LayerName::Image(layer_name) => PersistentLayerDesc {
+                    key_range: layer_name.key_range.clone(),
+                    lsn_range: layer_name.lsn_as_range(),
+                    tenant_shard_id,
+                    timeline_id,
+                    is_delta: false,
+                    file_size: layer_metadata.file_size,
+                },
+                LayerName::Delta(layer_name) => PersistentLayerDesc {
+                    key_range: layer_name.key_range,
+                    lsn_range: layer_name.lsn_range,
+                    tenant_shard_id,
+                    timeline_id,
+                    is_delta: true,
+                    file_size: layer_metadata.file_size,
+                },
+            };
+            updates.insert_historic(layer_desc);
+        }
+        updates.flush();
+
+        let read_points = vec![index.metadata.disk_consistent_lsn()];
+        let (layer_visibilities, shadow) = layer_map.get_visibility(read_points);
+        for (layer_desc, visibility) in &layer_visibilities {
+            tracing::info!("{layer_desc:?}: {visibility:?}");
+            eprintln!("{layer_desc:?}: {visibility:?}");
+        }
+
+        // The shadow should be non-empty, since there were some image layers
+        assert!(!shadow.ranges.is_empty());
+
+        // At least some layers should be marked covered
+        assert!(layer_visibilities
+            .iter()
+            .any(|i| matches!(i.1, LayerVisibilityHint::Covered)));
+
+        let layer_visibilities = layer_visibilities.into_iter().collect::<HashMap<_, _>>();
+
+        // Sanity: the layer that holds latest data for the DBDIR key should always be visible
+        // (just using this key as a key that will always exist for any layermap fixture)
+        let dbdir_layer = layer_map
+            .search(DBDIR_KEY, index.metadata.disk_consistent_lsn())
+            .unwrap();
+        assert!(matches!(
+            layer_visibilities.get(&dbdir_layer.layer).unwrap(),
+            LayerVisibilityHint::Visible
+        ));
+    }
 }

pageserver/src/tenant/storage_layer.rs

@@ -452,7 +452,7 @@ pub enum ValueReconstructResult {
 /// of layers (for example when creating a branch that makes some previously covered layers visible).  It should
 /// be used for cache management but not for correctness-critical checks.
 #[derive(Default, Debug, Clone, PartialEq, Eq)]
-pub(crate) enum LayerVisibilityHint {
+pub enum LayerVisibilityHint {
     /// A Visible layer might be read while serving a read, because there is not an image layer between it
     /// and a readable LSN (the tip of the branch or a child's branch point)
     Visible,

pageserver/src/tenant/timeline/compaction.rs

@@ -433,12 +433,11 @@ impl Timeline {
         Ok(())
     }
 
-    /// A post-compaction step to update the LayerVisibilityHint of layers covered by image layers.  This
-    /// should also be called when new branches are created.
+    /// Update the LayerVisibilityHint of layers covered by image layers, based on whether there is
+    /// an image layer between them and the most recent readable LSN (branch point or tip of timeline).  The
+    /// purpose of the visibility hint is to record which layers need to be available to service reads.
     ///
-    /// Sweep through the layer map, identifying layers which are covered by image layers
-    /// such that they do not need to be available to service reads. The resulting LayerVisibilityHint
-    /// result may be used as an input to eviction and secondary downloads to de-prioritize layers
+    /// The result may be used as an input to eviction and secondary downloads to de-prioritize layers
     /// that we know won't be needed for reads.
     pub(super) async fn update_layer_visibility(&self) {
         let head_lsn = self.get_last_record_lsn();

pageserver/test_data/indices/mixed_workload/README.md

@@ -0,0 +1,7 @@
+
+# This was captured from one shard of a large tenant in staging.
+
+# It has a mixture of deltas and image layers, >1000 layers in total.
+
+# This is suitable for general smoke tests that want an index which is not
+# trivially small, but doesn't contain weird/pathological cases.