From ea15d0e8d94586d720decb48cc0b6343704ee7ea Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Wed, 8 Apr 2026 05:20:32 +0000
Subject: [PATCH] Optimize ProcessMemoryScanner concurrency with sliding window
 approach

Replaces static task chunking in `scanPIDs` with a continuous sliding window iterator inside `withTaskGroup`. This eliminates tail-latency wait times between chunks, keeping the worker pool fully saturated at `maxConcurrency` and improving overall scanning throughput.

Co-authored-by: acebytes <2820910+acebytes@users.noreply.github.com>
---
 .jules/bolt.md                                |  3 ++
 .../Memory/ProcessMemoryScanner.swift         | 38 +++++++++++--------
 2 files changed, 25 insertions(+), 16 deletions(-)
 create mode 100644 .jules/bolt.md

diff --git a/.jules/bolt.md b/.jules/bolt.md
new file mode 100644
index 0000000..9717895
--- /dev/null
+++ b/.jules/bolt.md
@@ -0,0 +1,3 @@
+## YYYY-MM-DD - Sliding Window Concurrency
+**Learning:** In Swift structured concurrency, when processing high-volume tasks using `withTaskGroup`, utilize a sliding window approach with an iterator instead of static chunking. Static chunking limits throughput due to tail latency (waiting for the slowest task in a chunk), whereas a sliding window maintains maximum concurrent execution limits continuously.
+**Action:** Use an iterator inside `withTaskGroup` to add tasks up to the concurrency limit, then add new tasks as previous ones complete.
diff --git a/Sources/Cacheout/Memory/ProcessMemoryScanner.swift b/Sources/Cacheout/Memory/ProcessMemoryScanner.swift
index 3f8e728..b987f3d 100644
--- a/Sources/Cacheout/Memory/ProcessMemoryScanner.swift
+++ b/Sources/Cacheout/Memory/ProcessMemoryScanner.swift
@@ -97,29 +97,35 @@ actor ProcessMemoryScanner {
     ///
     /// Returns the collected entries and the count of EPERM failures.
     private func scanPIDs(_ pids: [pid_t]) async -> (entries: [ProcessEntryDTO], epermCount: Int) {
-        // Chunk PIDs to cap concurrency at maxConcurrency.
-        let chunks = stride(from: 0, to: pids.count, by: maxConcurrency).map {
-            Array(pids[$0..<min($0 + maxConcurrency, pids.count)])
-        }
-
         var allEntries: [ProcessEntryDTO] = []
         var totalEperm = 0
 
-        for chunk in chunks {
-            await withTaskGroup(of: ScanPIDResult.self) { group in
-                for pid in chunk {
+        await withTaskGroup(of: ScanPIDResult.self) { group in
+            var iterator = pids.makeIterator()
+
+            // Add initial tasks up to maxConcurrency limit
+            for _ in 0..<maxConcurrency {
+                if let pid = iterator.next() {
                     group.addTask { [self] in
                         self.scanSinglePID(pid)
                     }
                 }
-                for await result in group {
-                    switch result {
-                    case .success(let entry):
-                        allEntries.append(entry)
-                    case .eperm:
-                        totalEperm += 1
-                    case .otherError:
-                        break
+            }
+
+            // As each task completes, add a new one from the iterator
+            for await result in group {
+                switch result {
+                case .success(let entry):
+                    allEntries.append(entry)
+                case .eperm:
+                    totalEperm += 1
+                case .otherError:
+                    break
+                }
+
+                if let pid = iterator.next() {
+                    group.addTask { [self] in
+                        self.scanSinglePID(pid)
                     }
                 }
             }