From 71382d1b722fd2388262b6ddc9c7c4e63924ec8c Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Mon, 25 May 2026 18:10:29 +0000
Subject: [PATCH] perf(flow): defer PathBuf allocations during graph traversal

Refactors `ensure_node` in `graph.rs` and `tarjan_dfs` in `invalidation.rs` to eliminate redundant O(E) heap allocations for path lookups. Map queries now use borrowed `&Path` references, deferring `to_path_buf()` calls until strictly needed for insertion.

Co-authored-by: bashandbone <89049923+bashandbone@users.noreply.github.com>
---
 .jules/bolt.md                              |  4 ++++
 crates/flow/src/incremental/graph.rs        |  7 ++++---
 crates/flow/src/incremental/invalidation.rs | 17 +++++++++--------
 3 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/.jules/bolt.md b/.jules/bolt.md
index fb3e8f1..ad764af 100644
--- a/.jules/bolt.md
+++ b/.jules/bolt.md
@@ -2,3 +2,7 @@
 ## 2026-04-08 - [Performance: Defer Allocation during Traversal]
 **Learning:** During DAG traversals, creating owned variants of identifiers (like `file.to_path_buf()`) *before* checking `visited` HashSets results in heap allocations (O(E)) for every edge instead of every visited node (O(V)). By moving the `&PathBuf` allocation strictly *after* all HashSet `contains` checks using the borrowed reference (`&Path`), we drastically reduce memory churn.
 **Action:** Always check `HashSet::contains` with a borrowed reference *before* creating the owned version required by `HashSet::insert`, especially in performance-critical graph traversal paths.
+
+## 2024-05-24 - Defer PathBuf allocations during graph traversal
+**Learning:** Repeated `.to_path_buf()` calls in tight loops for map lookups (e.g. `entry()` or `get()`) create redundant `O(E)` memory allocations, becoming a critical bottleneck.
+**Action:** Use borrowed `&Path` references for `RapidMap` lookups (`contains_key`, `get`, `get_mut`) and defer `PathBuf` heap allocation until strictly needed for initial insertion.
diff --git a/crates/flow/src/incremental/graph.rs b/crates/flow/src/incremental/graph.rs
index f0b07a9..9f0a55a 100644
--- a/crates/flow/src/incremental/graph.rs
+++ b/crates/flow/src/incremental/graph.rs
@@ -400,9 +400,10 @@ impl DependencyGraph {
     /// Ensures a node exists in the graph for the given file path.
     /// Creates a default fingerprint entry if the node does not exist.
     fn ensure_node(&mut self, file: &Path) {
-        self.nodes
-            .entry(file.to_path_buf())
-            .or_insert_with(|| AnalysisDefFingerprint::new(b""));
+        if !self.nodes.contains_key(file) {
+            self.nodes
+                .insert(file.to_path_buf(), AnalysisDefFingerprint::new(b""));
+        }
     }
 
     /// DFS visit for topological sort with cycle detection.
diff --git a/crates/flow/src/incremental/invalidation.rs b/crates/flow/src/incremental/invalidation.rs
index da9ac9c..821d6f9 100644
--- a/crates/flow/src/incremental/invalidation.rs
+++ b/crates/flow/src/incremental/invalidation.rs
@@ -342,11 +342,12 @@ impl InvalidationDetector {
     fn tarjan_dfs(&self, v: &Path, state: &mut TarjanState, sccs: &mut Vec<Vec<PathBuf>>) {
         // Initialize node
         let index = state.index_counter;
-        state.indices.insert(v.to_path_buf(), index);
-        state.lowlinks.insert(v.to_path_buf(), index);
+        let v_buf = v.to_path_buf();
+        state.indices.insert(v_buf.clone(), index);
+        state.lowlinks.insert(v_buf.clone(), index);
         state.index_counter += 1;
-        state.stack.push(v.to_path_buf());
-        state.on_stack.insert(v.to_path_buf());
+        state.stack.push(v_buf.clone());
+        state.on_stack.insert(v_buf);
 
         // Visit all successors (dependencies)
         let dependencies = self.graph.get_dependencies(v);
@@ -358,19 +359,19 @@ impl InvalidationDetector {
 
                 // Update lowlink
                 let w_lowlink = *state.lowlinks.get(dep).unwrap();
-                let v_lowlink = state.lowlinks.get_mut(&v.to_path_buf()).unwrap();
+                let v_lowlink = state.lowlinks.get_mut(v).unwrap();
                 *v_lowlink = (*v_lowlink).min(w_lowlink);
             } else if state.on_stack.contains(dep) {
                 // Successor is on stack (part of current SCC)
                 let w_index = *state.indices.get(dep).unwrap();
-                let v_lowlink = state.lowlinks.get_mut(&v.to_path_buf()).unwrap();
+                let v_lowlink = state.lowlinks.get_mut(v).unwrap();
                 *v_lowlink = (*v_lowlink).min(w_index);
             }
         }
 
         // If v is a root node, pop the stack to create an SCC
-        let v_index = *state.indices.get(&v.to_path_buf()).unwrap();
-        let v_lowlink = *state.lowlinks.get(&v.to_path_buf()).unwrap();
+        let v_index = *state.indices.get(v).unwrap();
+        let v_lowlink = *state.lowlinks.get(v).unwrap();
 
         if v_lowlink == v_index {
             let mut scc = Vec::new();