Fast S3 verify and snapshot commit; shorter runs list; durations with days

On S3, index files and the tree segments read back when a snapshot is
written are fetched 16 at a time through the storage's S3 client
(IBackend::getRanges(), getMany()). Blobs that follow each other in a pack
are read as one range on every location. The snapshot is written in a step
of its own and the run shows "commit" meanwhile. On a 1 TB production
repository the check went from about 4 hours to 3.5 minutes.

backup:status and the web interface list the runs of the last 7 days,
running ones and at least the newest 5; --all / "Show older runs" list
all. Durations of a day or more show the days.
This commit is contained in:
2026-10-14 17:12:41 +02:00
parent 9a3bb99d12
commit ca003c88ba
20 changed files with 424 additions and 30 deletions
+106
View File
@@ -42,6 +42,61 @@ class BackupRunTest extends TestCase {
$this->assertSame(self::hashTree($src), self::hashTree($target));
}
public function testTheSnapshotIsWrittenInAStepOfItsOwnFromAllSegmentsAtOnce(): void {
$src = $this->tempDir();
for ($i = 0; $i < 60; $i++) {
file_put_contents("$src/f$i.txt", random_bytes(200000));
}
$backend = new RangeCountingBackend(new LocalBackend($this->tempDir()));
$keys = KeyRing::generate();
Repository::initWithKey($backend, $keys, $keys->wrap('pw'));
$state = BackupRun::start($src);
for ($i = 0; $i < 500 && $state['phase'] === 'files'; $i++) {
$state = BackupRun::step(Repository::openWithKey($backend, $keys), $state, microtime(true) + 0.01);
}
$this->assertSame('finish', $state['phase'], 'the step that read the last file does not write the snapshot');
$this->assertGreaterThan(2, count($state['segments']));
$backend->batches = [];
$state = BackupRun::step(Repository::openWithKey($backend, $keys), $state, microtime(true) + 0.01);
$this->assertSame('commit', $state['phase']);
// One batch; the blobs of a segment follow each other in its pack and are one read.
$this->assertSame([count($state['segments'])], $backend->batches);
Repository::openWithKey($backend, $keys)->recordSnapshot($state['snapshot']);
$target = $this->tempDir();
Repository::openWithKey($backend, $keys)->restore($state['snapshot'], $target);
$this->assertSame(self::hashTree($src), self::hashTree($target));
}
public function testBlobsThatFollowEachOtherInAPackAreReadAsOneRange(): void {
$backend = new RangeCountingBackend(new LocalBackend($this->tempDir()));
$keys = KeyRing::generate();
$repo = Repository::initWithKey($backend, $keys, $keys->wrap('pw'));
$stats = [];
$segments = [];
$expected = [];
for ($s = 0; $s < 3; $s++) {
$writer = new \OCA\NgBackup\Repository\BlobWriter(fn (string $data): string => $repo->storeData($data, $stats), 1000);
$lines = [];
for ($i = 0; $i < 100; $i++) {
$lines[] = json_encode(['segment' => $s, 'line' => $i, 'pad' => bin2hex(random_bytes(20))]);
}
$writer->write(implode("\n", $lines) . "\n");
$segments[] = $writer->finish();
$repo->flushPacks(); // one pack per segment, as one per step
array_push($expected, ...$lines);
}
$this->assertGreaterThan(3, count(array_merge(...$segments)));
$backend->batches = [];
$read = iterator_to_array(Repository::openWithKey($backend, $keys)->readLines(array_merge(...$segments)), false);
$this->assertSame($expected, array_values(array_filter($read, fn (string $l): bool => $l !== '')));
$this->assertSame([3], $backend->batches, 'one read per segment, all in one batch');
}
public function testFileChangedBetweenStepsIsReadAgain(): void {
$src = $this->tempDir();
file_put_contents("$src/big.bin", random_bytes(20 * 1048576));
@@ -100,3 +155,54 @@ class BackupRunTest extends TestCase {
$this->assertSame(self::hashTree($src), self::hashTree("$target/data"));
}
}
final class RangeCountingBackend implements \OCA\NgBackup\Backend\IBackend {
use \OCA\NgBackup\Backend\GetsOneByOne {
getRanges as private oneByOne;
}
/** @var list<int> number of ranges per getRanges() call */
public array $batches = [];
public function __construct(
private \OCA\NgBackup\Backend\IBackend $inner,
) {
}
public function getRanges(array $ranges): \Generator {
$this->batches[] = count($ranges);
return $this->oneByOne($ranges);
}
public function put(string $path, $stream): void {
$this->inner->put($path, $stream);
}
public function get(string $path) {
return $this->inner->get($path);
}
public function getRange(string $path, int $offset, int $length): string {
return $this->inner->getRange($path, $offset, $length);
}
public function exists(string $path): bool {
return $this->inner->exists($path);
}
public function move(string $from, string $to): void {
$this->inner->move($from, $to);
}
public function list(string $prefix): array {
return $this->inner->list($prefix);
}
public function listFiles(string $dir): array {
return $this->inner->listFiles($dir);
}
public function delete(string $path): void {
$this->inner->delete($path);
}
}