From df732f185a5e8c2024dd82eb23a1f296d86dbe65 Mon Sep 17 00:00:00 2001
From: Dillard Blom <dillard.blom@ensembia.com>
Date: Sun, 11 Oct 2026 14:31:57 +0200
Subject: [PATCH] Index: refresh the cache after a verify in one pass over the
 blobs, not one per pack

---
 CHANGELOG.md                 |  4 ++++
 lib/Repository/BlobIndex.php | 15 ++++++++-------
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7a1ba66..24f7ae1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -20,6 +20,10 @@ instead carried by the app description, the git tag, the release, and this file.
   overwriting the result. The lease now lasts at least 15 minutes, a step writes the run only if
   no other process wrote it since the step loaded it (in one database statement), and recording
   a snapshot that is already recorded is no longer an error.
+- `occ backup:verify` on a large repository failed with "SFTP connection failed while opening
+  snapshots/…": after downloading the index it refreshed the local index cache with a pass over
+  all blobs for every pack, which took 29 minutes for 1 TB (27,547 packs, 400,000 blobs). The
+  location dropped the idle connection in the meantime. It is one pass now (under a second).
 
 ## [0.9.4-beta.5] - 2026-10-09
 
diff --git a/lib/Repository/BlobIndex.php b/lib/Repository/BlobIndex.php
index eb7269e..2b270da 100644
--- a/lib/Repository/BlobIndex.php
+++ b/lib/Repository/BlobIndex.php
@@ -110,14 +110,15 @@ final class BlobIndex {
 		}
 		if ($verify && $this->cache !== null) {
 			// Refresh the cache from what was just verified.
+			// One pass over the blobs: a pass per pack took half an hour on a 1 TB repository
+			// (27,547 packs x 400,000 blobs), long enough for the location to drop the idle
+			// connection before the check went on.
+			$byPack = [];
+			foreach ($this->blobs as $id => [$pack, $offset, $length, $raw, $flags]) {
+				$byPack[$pack][] = ['id' => $id, 'offset' => $offset, 'length' => $length, 'raw' => $raw, 'flags' => $flags];
+			}
 			$this->cache->remove($this->repositoryId, array_keys($this->cache->all($this->repositoryId)));
-			foreach ($this->packs() as $packId => $_) {
-				$entries = [];
-				foreach ($this->blobs as $id => [$pack, $offset, $length, $raw, $flags]) {
-					if ($pack === $packId) {
-						$entries[] = ['id' => $id, 'offset' => $offset, 'length' => $length, 'raw' => $raw, 'flags' => $flags];
-					}
-				}
+			foreach ($byPack as $packId => $entries) {
 				$this->cache->put($this->repositoryId, $packId, $entries);
 			}
 			return;