Full restore over SFTP: read packs ahead on four connections at once

A restore read one pack at a time over one SFTP connection, which over a long line is bound by the round trip and by what one TCP connection gets: about 2-3 MiB/s from a Hetzner Storage Box to Canada, with PHP mostly waiting. Repository::restore() now first lists the ranges of packs the restore needs, in order (ReadAheadPlan), and the location reads them ahead into unlinked files in a spool folder in the target (IReadsAhead). Over SFTP, SftpRangeFetcher does that on four connections of its own, 16 requests in flight each, taking the answers of whichever connection has one. A range that fails, a damaged copy, or a blob that moved since the plan is read the usual way, which reports what is wrong. Other locations restore as before. On a test line with 120 ms RTT and 0.2% loss, a 1.6 GiB restore went from 5.1 to 17.8 MiB/s, all files identical.
2026-10-19 01:40:49 +02:00
parent b789d17636
commit ccbbf01c54
12 changed files with 1228 additions and 5 deletions
@@ -0,0 +1,103 @@
+<?php
+
+declare(strict_types=1);
+
+namespace OCA\NgBackup\Tests\Unit\Backend;
+
+use OCA\NgBackup\Backend\SftpRangeFetcher;
+use OCA\NgBackup\Backend\SftpReadStream;
+use OCA\NgBackup\Backend\StorageBackend;
+use OCA\NgBackup\Tests\Unit\TempDirTrait;
+use OCP\Files\Storage\IStorage;
+use PHPUnit\Framework\TestCase;
+
+require_once __DIR__ . '/SftpReadStreamTest.php'; // FakeSftpConnection
+require_once __DIR__ . '/StorageBackendReconnectTest.php'; // SftpLikeStorage
+
+/** StorageBackend::readAhead(): over SFTP on connections of its own, built with the reconnect function. */
+class StorageBackendReadAheadTest extends TestCase {
+	use TempDirTrait;
+
+	/** @var list<FakeSftpConnection> */
+	private array $connections = [];
+	/** @var array<string, string> */
+	private array $files = [];
+	/** New storages after this many fail to connect. */
+	private ?int $connectLimit = null;
+
+	protected function setUp(): void {
+		SftpReadStream::reset();
+		for ($i = 0; $i < 6; $i++) {
+			$this->files["/home/base/repo/packs/p$i"] = random_bytes(1048576 + $i);
+		}
+	}
+
+	private function storage(): IStorage {
+		if ($this->connectLimit !== null && count($this->connections) >= $this->connectLimit) {
+			throw new \RuntimeException('Too many connections');
+		}
+		$sftp = new FakeSftpConnection($this->files);
+		$this->connections[] = $sftp;
+		$storage = $this->createMock(SftpLikeRootStorage::class);
+		$storage->method('instanceOfStorage')->willReturnCallback(fn (string $class): bool => $class === \OCA\Files_External\Lib\Storage\SFTP::class);
+		$storage->method('getConnection')->willReturn($sftp);
+		$storage->method('getRoot')->willReturn('/home/');
+		$storage->method('is_dir')->willReturn(true);
+		return $storage;
+	}
+
+	/** @return list<array{0:string, 1:int, 2:int}> */
+	private static function ranges(): array {
+		return array_map(fn (int $i): array => ["packs/p$i", 7, 1048576 - 7], range(0, 5));
+	}
+
+	public function testReadsAheadOnNewConnectionsOnly(): void {
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, fn (): IStorage => $this->storage());
+		$this->assertTrue($backend->canReadAhead());
+
+		$result = [];
+		foreach ($backend->readAhead(self::ranges(), $this->tempDir()) as $i => $fh) {
+			$result[$i] = sha1(stream_get_contents($fh));
+		}
+
+		$expected = array_map(fn (int $i): string => sha1(substr($this->files["/home/base/repo/packs/p$i"], 7, 1048576 - 7)), range(0, 5));
+		$this->assertSame($expected, $result);
+		$this->assertCount(1 + SftpRangeFetcher::CONNECTIONS, $this->connections);
+		$this->assertSame(0, $this->connections[0]->sent, 'the storage\'s own connection stays free');
+		foreach (array_slice($this->connections, 1) as $c) {
+			$this->assertTrue($c->disconnected);
+		}
+	}
+
+	public function testGoesOnWithTheConnectionsTheServerAllows(): void {
+		$this->connectLimit = 3;
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, fn (): IStorage => $this->storage());
+
+		$count = 0;
+		foreach ($backend->readAhead(self::ranges(), $this->tempDir()) as $fh) {
+			$this->assertIsResource($fh);
+			$count++;
+		}
+
+		$this->assertSame(6, $count);
+		$this->assertCount(3, $this->connections);
+	}
+
+	public function testNoNewConnectionMeansNoReadingAhead(): void {
+		$this->connectLimit = 1;
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, fn (): IStorage => $this->storage());
+
+		$this->assertNull($backend->readAhead(self::ranges(), $this->tempDir()));
+	}
+
+	public function testWithoutAWayToConnectAgainItDoesNotReadAhead(): void {
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, null);
+
+		$this->assertFalse($backend->canReadAhead());
+		$this->assertNull($backend->readAhead(self::ranges(), $this->tempDir()));
+	}
+}
+
+interface SftpLikeRootStorage extends SftpLikeStorage {
+	public function getRoot(): string;
+}