From 2226d543f9145e6ff7582e89627180f719146b87 Mon Sep 17 00:00:00 2001
From: Duncan Tourolle <duncan@tourolle.paris>
Date: Sat, 26 Sep 2026 12:30:30 -0400
Subject: [PATCH] Time a develop landing in catalog_bench

Landing on a photograph in develop opens the catalog once to fetch the
original and once more per prefetched neighbour to ask whether the cache
already holds it: five opens, each running the whole backfill. The bench
timed one open but not the landing, so the cost of the shape was not
visible and a fix to it could not be measured.

Two figures now, both against an empty cache so the question is asked the
same way whatever the answer: the five-open shape the app had, and the
two-open shape where the prefetch worker keeps one connection for its
batch. On a copy of the reference catalog (23,582 images) under load, the
five-open landing costs ~80 ms of CPU.
---
 core/dr-catalog/examples/catalog_bench.rs | 43 +++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/core/dr-catalog/examples/catalog_bench.rs b/core/dr-catalog/examples/catalog_bench.rs
index fda9265..b39d54f 100644
--- a/core/dr-catalog/examples/catalog_bench.rs
+++ b/core/dr-catalog/examples/catalog_bench.rs
@@ -36,6 +36,49 @@ fn main() {
         drop(Catalog::open(&path).unwrap());
     });
 
+    // One develop landing, in the two shapes the app has had. Five opens is
+    // what `fetch_original` and a `holds_original` per prefetched neighbour
+    // cost when each asked on a connection of its own; two is the fetch plus
+    // one connection the prefetch worker keeps for its batch's row checks.
+    // Five images from the library, against an empty cache: the question is
+    // asked the same way whatever the answer.
+    let images: Vec<dr_types::ImageId> = {
+        let c = Catalog::open(&path).unwrap();
+        let mut stmt = c
+            .connection()
+            .prepare("SELECT id FROM images ORDER BY id LIMIT 5 OFFSET 1000")
+            .unwrap();
+        let ids = stmt
+            .query_map([], |r| r.get::<_, i64>(0))
+            .unwrap()
+            .map(|id| dr_types::ImageId(id.unwrap() as u64))
+            .collect();
+        ids
+    };
+    let cache_dir = path.with_extension("bench-cache");
+    let budget = dr_catalog::Budget::default();
+    time("landing: 5 opens (fetch + 4 row checks)", 20, || {
+        let store = dr_catalog::Cache::open(&cache_dir, budget).unwrap();
+        let c = Catalog::open(&path).unwrap();
+        let _ = store.load(c.connection(), images[0], 0).unwrap();
+        for &image in &images[1..] {
+            let store = dr_catalog::Cache::open(&cache_dir, budget).unwrap();
+            let c = Catalog::open(&path).unwrap();
+            let _ = store.holds_original(c.connection(), image);
+        }
+    });
+    time("landing: 2 opens (fetch + held row checks)", 20, || {
+        let store = dr_catalog::Cache::open(&cache_dir, budget).unwrap();
+        let c = Catalog::open(&path).unwrap();
+        let _ = store.load(c.connection(), images[0], 0).unwrap();
+        let held = Catalog::open(&path).unwrap();
+        for &image in &images[1..] {
+            let store = dr_catalog::Cache::open(&cache_dir, budget).unwrap();
+            let _ = store.holds_original(held.connection(), image);
+        }
+    });
+    let _ = std::fs::remove_dir_all(&cache_dir);
+
     let catalog = Catalog::open(&path).unwrap();
     let conn = catalog.connection();
     time("schema::backfill (all steps)", 20, || {