Files
nextcloud-ng_backup/lib/Backend/StorageBackend.php
T

610 lines
20 KiB
PHP

<?php
declare(strict_types=1);
// SPDX-FileCopyrightText: 2026 Dillard Blom
// SPDX-License-Identifier: AGPL-3.0-or-later
namespace OCA\NgBackup\Backend;
use OCP\Files\Storage\IStorage;
use OCP\Files\Storage\IWriteStreamStorage;
/**
* IBackend on top of a Nextcloud storage object (from files_external or core), below a base
* directory on that storage.
*/
final class StorageBackend implements IBackend, IReadsAhead {
/** Object stores write whole objects atomically; other storages get a temp name + rename. */
private bool $atomicPut;
/** SFTP: read through SftpReadStream, which keeps several requests in flight. */
private bool $sftpReads;
/** S3: many small reads go straight to the storage's S3 client, several at a time. */
private bool $s3Reads;
/** S3 requests in flight at once for getMany() and getRanges(). */
public const S3_CONCURRENCY = 16;
/** Most ranges, and bytes, getRanges() holds in memory at once. */
private const RANGES_LOT = 64;
private const RANGES_LOT_BYTES = 64 * 1048576;
/** Seconds without a request after which an SFTP connection is checked before it is used. */
public const IDLE_CHECK = 60;
private float $lastUsed;
/** Connections readAhead() opens (see SftpRangeFetcher::DEFAULT_CONNECTIONS). */
public int $readAheadConnections = SftpRangeFetcher::DEFAULT_CONNECTIONS;
/** Times the storage was built anew after its connection died (for tests and diagnostics). */
public int $reconnects = 0;
/**
* @param (\Closure():IStorage)|null $reconnect builds the same storage anew, with a new
* connection
*/
public function __construct(
private IStorage $storage,
private string $base = '',
bool $createBase = true,
private ?\Closure $reconnect = null,
) {
$this->lastUsed = microtime(true);
$this->base = trim($base, '/');
self::validate($this->base, true);
$this->atomicPut = $storage->instanceOfStorage(\OCA\Files_External\Lib\Storage\AmazonS3::class);
$this->sftpReads = $storage->instanceOfStorage(\OCA\Files_External\Lib\Storage\SFTP::class);
$this->s3Reads = $storage instanceof \OCA\Files_External\Lib\Storage\AmazonS3;
if ($createBase && $this->base !== '') {
$this->mkdirs($this->base);
}
}
/** A temporary upload of put(): "<name>.part-<8 hex>". */
public static function isTemporary(string $name): bool {
return preg_match('/\.part-[0-9a-f]{8}$/', $name) === 1;
}
public function put(string $path, $stream): void {
// not repeated on a new connection: the stream is (partly) read
$this->idleCheck();
$expected = self::remaining($stream);
$target = $this->abs($path);
$this->mkdirs(dirname($target));
$writeTo = $this->atomicPut ? $target : $target . '.part-' . bin2hex(random_bytes(4));
try {
if ($this->storage->instanceOfStorage(IWriteStreamStorage::class)) {
/** @var IWriteStreamStorage $s */
$s = $this->storage;
$written = $s->writeStream($writeTo, $stream);
if ($written <= 0 && $this->storage->filesize($writeTo) !== 0) {
throw new BackendException('Write reported no data for ' . $path);
}
} else {
$out = $this->storage->fopen($writeTo, 'w');
if ($out === false || stream_copy_to_stream($stream, $out) === false || !fflush($out)) {
throw new BackendException('Write failed for ' . $path);
}
if (!fclose($out)) {
throw new BackendException('Close failed for ' . $path);
}
}
if (is_resource($stream)) {
fclose($stream);
}
// Some adapters report success after a short write or a failed flush: check the size.
if ($expected !== null && $this->storage->filesize($writeTo) !== $expected) {
throw new BackendException('Incomplete write for ' . $path);
}
if ($writeTo !== $target && !$this->storage->rename($writeTo, $target)) {
throw new BackendException('Cannot finalise ' . $path);
}
} catch (\Throwable $e) {
if (is_resource($stream)) {
fclose($stream);
}
if ($writeTo !== $target) {
$this->storage->unlink($writeTo);
}
throw $e instanceof BackendException ? $e : new BackendException('Write failed for ' . $path . ': ' . $e->getMessage(), 0, $e);
}
}
public function get(string $path) {
return $this->call(fn () => $this->open($path));
}
/** @return resource */
private function open(string $path) {
if ($this->sftpReads) {
$fh = SftpReadStream::open($this->storage, $this->abs($path));
if (is_resource($fh)) {
return $fh;
}
// null: not supported or failing for now; false: not opened, which need not mean
// missing. Either way the storage's own stream decides.
}
$fh = $this->storage->fopen($this->abs($path), 'r');
if ($fh === false) {
throw new BackendException('Not found: ' . $path);
}
return $fh;
}
/**
* Over SFTP and S3 several at a time (SftpReadStream::readMany(), s3Fetch()); elsewhere one
* after the other.
*/
public function getMany(array $paths): \Generator {
$size = $this->s3Reads ? 16 * self::S3_CONCURRENCY : 8 * SftpReadStream::BATCH;
foreach (array_chunk($paths, $size) as $chunk) {
$fast = null;
if ($this->s3Reads) {
$this->idleCheck();
$fast = $this->s3Fetch(array_map(fn (string $p): array => [$p, null], $chunk));
$fast = $fast === null ? null : array_combine($chunk, array_map(fn (int $i): ?string => $fast[$i] ?? null, array_keys($chunk)));
} elseif ($this->sftpReads) {
$abs = array_map(fn (string $p): string => $this->abs($p), $chunk);
$fast = $this->call(fn () => SftpReadStream::readMany($this->storage, $abs));
$fast = $fast === null ? null : array_combine($chunk, array_map(fn (string $a): ?string => $fast[$a] ?? null, $abs));
}
foreach ($chunk as $path) {
$data = $fast[$path] ?? null;
if ($data === null) {
// not read in the batch (or no batches here): the usual way, which also
// reports a missing file as such
$fh = $this->get($path);
try {
$data = stream_get_contents($fh);
} finally {
fclose($fh);
}
if ($data === false) {
throw new BackendException('Read failed for ' . $path);
}
}
yield $path => $data;
}
}
}
/** Over S3 several at a time (s3Fetch()); elsewhere one after the other. */
public function getRanges(array $ranges): \Generator {
$lot = [];
$bytes = 0;
foreach ($ranges as $i => $range) {
if ($lot !== [] && (count($lot) >= self::RANGES_LOT || $bytes + $range[2] > self::RANGES_LOT_BYTES)) {
yield from $this->rangesLot($lot);
$lot = [];
$bytes = 0;
}
$lot[$i] = $range;
$bytes += $range[2];
}
if ($lot !== []) {
yield from $this->rangesLot($lot);
}
}
/**
* @param array<int, array{0:string, 1:int, 2:int}> $lot
* @return \Generator<int, string>
*/
private function rangesLot(array $lot): \Generator {
$fast = null;
if ($this->s3Reads) {
$this->idleCheck();
$fast = $this->s3Fetch(array_map(fn (array $r): array => [$r[0], $r[1] . '-' . ($r[1] + $r[2] - 1)], $lot));
}
foreach ($lot as $i => [$path, $offset, $length]) {
$data = $fast[$i] ?? null;
// not read in the batch, or not all of it: the usual way, which also reports why
yield $i => ($data !== null && strlen($data) === $length) ? $data : $this->getRange($path, $offset, $length);
}
}
/**
* Read objects (or byte ranges of them, "first-last") straight through the S3 client of
* files_external's S3 storage, S3_CONCURRENCY at a time. Its own reads open a new HTTPS
* connection per object, after a HEAD request: one after the other that is about two reads a
* second, which made checking the index of a large repository take hours. What fails here
* is left out of the result, for the caller to read the usual way (which reports the error).
*
* @param array<int, array{0:string, 1:?string}> $requests [path, range or null] by key
* @return array<int, string>|null contents by key; null when the storage is not as expected
* @psalm-suppress UndefinedClass the AWS SDK comes with Nextcloud, not with this app
*/
private function s3Fetch(array $requests): ?array {
try {
/** @psalm-suppress UndefinedMethod, UndefinedThisPropertyFetch */
[$client, $bucket, $sse] = (function (): array {
$sse = method_exists($this, 'getServerSideEncryptionParameters') ? $this->getServerSideEncryptionParameters()
: (method_exists($this, 'getSSECParameters') ? $this->getSSECParameters() : []);
return [$this->getConnection(), $this->getBucket(), $sse];
})->call($this->storage);
if (!$client instanceof \Aws\S3\S3Client || !is_string($bucket)) {
return null;
}
$results = [];
$keys = array_keys($requests); // the pool numbers results 0, 1, ...: mapped back below
$commands = (function () use ($requests, $client, $bucket, $sse): \Generator {
foreach (array_values($requests) as $n => [$path, $range]) {
$args = ['Bucket' => $bucket, 'Key' => trim($this->abs($path), '/')] + $sse;
if ($range !== null) {
$args['Range'] = 'bytes=' . $range;
}
yield $n => $client->getCommand('GetObject', $args);
}
})();
(new \Aws\CommandPool($client, $commands, [
'concurrency' => self::S3_CONCURRENCY,
'fulfilled' => function (mixed $result, int $n) use (&$results, $keys): void {
$results[$keys[$n]] = (string)$result['Body'];
},
'rejected' => static function (): void {
},
]))->promise()->wait();
return $results;
} catch (\Throwable) {
return null;
}
}
/**
* Over SFTP: SftpRangeFetcher, on readAheadConnections new connections of its own (built with the
* reconnect function), so the storage's connection stays free for other requests. Elsewhere
* not (yet): null.
*/
public function canReadAhead(): bool {
return $this->sftpReads && $this->reconnect !== null;
}
public function readAhead(array $ranges, string $spool): ?\Generator {
$reconnect = $this->reconnect;
if (!$this->sftpReads || $reconnect === null || $ranges === []) {
return null;
}
// before any connection is opened: an invalid path throws
$abs = array_map(fn (array $r): array => [$this->abs($r[0]), $r[1], $r[2]], $ranges);
$storages = [];
$connections = [];
$root = '';
$wanted = max(1, min(SftpRangeFetcher::MAX_CONNECTIONS, $this->readAheadConnections));
for ($n = 0; $n < $wanted; $n++) {
try {
$storage = $reconnect();
$sftp = SftpReadStream::connection($storage);
if ($sftp === null || !is_callable([$storage, 'getRoot'])) {
break;
}
$root = (string)$storage->getRoot();
} catch (\Throwable) {
break; // the server may allow fewer connections: go on with those that work
}
$storages[] = $storage;
$connections[] = $sftp;
}
if ($connections === []) {
return null;
}
// in place of a connection that broke: a new storage, kept like the others
$connect = static function () use ($reconnect, &$storages): ?object {
$storage = $reconnect();
$sftp = SftpReadStream::connection($storage);
if ($sftp !== null) {
$storages[] = $storage;
}
return $sftp;
};
return (static function () use (&$storages, $connections, $root, $abs, $spool, $connect): \Generator {
// the storages hold their connections: kept until the fetcher is done
try {
yield from SftpRangeFetcher::fetch($connections, $root, $abs, $spool, $connect);
} finally {
unset($storages);
}
})();
}
public function getRange(string $path, int $offset, int $length): string {
return $this->call(fn () => $this->readRange($path, $offset, $length));
}
private function readRange(string $path, int $offset, int $length): string {
$fh = $this->get($path);
try {
if (fseek($fh, $offset) !== 0) {
throw new BackendException('Seek failed in ' . $path);
}
$data = '';
while (strlen($data) < $length && !feof($fh)) {
$chunk = fread($fh, $length - strlen($data));
if ($chunk === false) {
break;
}
$data .= $chunk;
}
if (strlen($data) !== $length) {
throw new BackendException('Short read in ' . $path);
}
return $data;
} finally {
fclose($fh);
}
}
/** Whether the storage accepts the connection settings (files_external's own check). */
public function canConnect(): bool {
try {
return !method_exists($this->storage, 'test') || $this->storage->test();
} catch (\Throwable) {
return false;
}
}
public function exists(string $path): bool {
$abs = $this->abs($path);
return $this->call(fn () => $this->storage->file_exists($abs), fn (bool $found) => !$found);
}
public function list(string $prefix): array {
$abs = $this->abs($prefix);
$result = $this->call(function () use ($abs): array {
$result = [];
$this->listInto($abs, $result);
return $result;
}, fn (array $found) => $found === []);
sort($result);
$cut = $this->base === '' ? 0 : strlen($this->base) + 1;
return array_map(fn ($p) => substr($p, $cut), $result);
}
public function delete(string $path): void {
$this->idleCheck();
$this->storage->unlink($this->abs($path));
}
public function move(string $from, string $to): void {
// not repeated on a new connection: the server may have done it before the connection died
$this->idleCheck();
$target = $this->abs($to);
$this->mkdirs(dirname($target));
if (!$this->storage->rename($this->abs($from), $target)) {
throw new BackendException("Cannot move $from to $to");
}
}
public function listFiles(string $dir): array {
$abs = $this->abs($dir);
return $this->call(fn () => $this->filesIn($dir, $abs), fn (array $found) => $found === []);
}
/** @return list<string> */
private function filesIn(string $dir, string $abs): array {
if (!$this->storage->is_dir($abs)) {
return []; // not created yet
}
$cut = $this->base === '' ? 0 : strlen($this->base) + 1;
$names = $this->smbNames($abs);
if ($names !== null) {
$result = [];
foreach ($names as $name) {
if (!self::isTemporary($name)) {
$result[] = substr($abs . '/' . $name, $cut);
}
}
sort($result);
return $result;
}
$dh = $this->storage->opendir($abs);
if ($dh === false) {
// An existing folder read as empty would look like a new repository.
throw new BackendException('Cannot list ' . $dir);
}
$result = [];
while (($name = readdir($dh)) !== false) {
if ($name !== '.' && $name !== '..' && !self::isTemporary($name)) {
$result[] = substr($abs . '/' . $name, $cut);
}
}
closedir($dh);
sort($result);
return $result;
}
/**
* The names in an SMB folder, read in one listing; null for other storages, with access
* control lists on, or when the storage's internals are not as expected. The SMB storage's
* opendir() asks the server for the attributes of each entry to leave out hidden ones: with
* thousands of index files that took minutes. Hidden entries are still left out: names
* starting with a dot, and, after asking, any name a repository does not use (letters,
* digits, - and _), such as desktop.ini or Thumbs.db. The repository's own files have such
* names: they are not checked one by one, which was the cost.
*
* @return list<string>|null
*/
private function smbNames(string $abs): ?array {
if (!$this->storage instanceof \OCA\Files_External\Lib\Storage\SMB) {
return null;
}
try {
/** @var list<string>|null */
return (function (string $path): ?array {
/** @psalm-suppress UndefinedThisPropertyFetch */
if ($this->checkAcl) {
return null;
}
$names = [];
/** @psalm-suppress UndefinedThisPropertyFetch, UndefinedMethod */
foreach ($this->share->dir(ltrim($this->buildPath($path), '/')) as $info) {
$name = (string)$info->getName();
/** @psalm-suppress UndefinedThisPropertyFetch */
if (!$this->showHidden && (str_starts_with($name, '.')
|| (preg_match('/^[A-Za-z0-9_-]+$/', $name) !== 1 && $info->isHidden()))) {
continue;
}
$names[] = $name;
}
return $names;
})->call($this->storage, $abs);
} catch (\Throwable) {
return null; // another SMB storage version, or an error: the usual way reports it
}
}
/**
* Run $op; when it throws, or $failed says its result may come from a dead connection, and
* the SFTP connection turns out to be dead, run it once more on a new connection.
*
* @template T
* @param \Closure():T $op
* @param (\Closure(T):bool)|null $failed
* @return T
*/
private function call(\Closure $op, ?\Closure $failed = null): mixed {
$this->idleCheck();
try {
$result = $op();
} catch (\Throwable $e) {
if (!$this->reopenIfDead()) {
throw $e;
}
return $op();
}
if ($failed !== null && $failed($result) && $this->reopenIfDead()) {
return $op();
}
return $result;
}
/**
* A Hetzner Storage Box drops an SFTP connection that carried a lot of data and then stayed
* quiet for a few minutes, while phpseclib still takes it for open; files_external never
* builds a new one, and every request on it fails as if the file were missing. So after
* such a pause the connection is checked (one round trip) before it is used again.
*/
private function idleCheck(): void {
$now = microtime(true);
if ($this->reconnect !== null && $this->sftpReads && $now - $this->lastUsed >= self::IDLE_CHECK
&& $this->alive(true) === false) {
$this->reopen();
}
$this->lastUsed = microtime(true);
}
/** After a failed request: ask the server (one round trip), as phpseclib may not know it is gone. */
private function reopenIfDead(): bool {
if ($this->reconnect === null || !$this->sftpReads || $this->alive(true) !== false) {
return false;
}
$this->reopen();
return true;
}
/**
* Whether the storage's SFTP connection is alive; null when it cannot tell.
* $ask: send a request instead of trusting what phpseclib saw last.
*/
private function alive(bool $ask): ?bool {
try {
if (!is_callable([$this->storage, 'getConnection'])) {
return null;
}
$sftp = $this->storage->getConnection();
if (!is_object($sftp) || !is_callable([$sftp, 'isConnected'])) {
return null;
}
if (!$sftp->isConnected()) {
return false;
}
if (!$ask || !is_callable([$sftp, 'stat'])) {
return true;
}
if (is_callable([$sftp, 'clearStatCache'])) {
$sftp->clearStatCache(); // or stat() answers from memory
}
// A Storage Box drops a quiet connection without phpseclib noticing: it still says
// connected, and every request fails. So the answer counts, not what it says after.
return $sftp->stat('.') !== false && (bool)$sftp->isConnected();
} catch (\Throwable) {
return false;
}
}
private function reopen(): void {
/** @var \Closure():IStorage $reconnect */
$reconnect = $this->reconnect;
$this->storage = $reconnect();
$this->reconnects++;
$this->lastUsed = microtime(true);
if (function_exists('OCP\Log\logger')) {
\OCP\Log\logger('ng_backup')->info('The SFTP connection to the backup location was lost; reconnected');
}
}
private function listInto(string $dir, array &$result): void {
if (!$this->storage->is_dir($dir)) {
return;
}
$dh = $this->storage->opendir($dir);
if ($dh === false) {
return;
}
while (($name = readdir($dh)) !== false) {
if ($name === '.' || $name === '..') {
continue;
}
$child = $dir . '/' . $name;
if ($this->storage->is_dir($child)) {
$this->listInto($child, $result);
} elseif (!self::isTemporary($name)) {
$result[] = $child;
}
}
closedir($dh);
}
/**
* Bytes left to read in a local $stream (php://temp, php://memory or a plain file), or null:
* stream wrappers of remote storages do not report a reliable size.
*/
public static function remaining(mixed $stream): ?int {
if (!is_resource($stream)) {
return null;
}
$meta = stream_get_meta_data($stream);
if (!($meta['seekable'] ?? false) || !in_array($meta['wrapper_type'] ?? '', ['PHP', 'plainfile'], true)) {
return null;
}
$stat = fstat($stream);
$pos = ftell($stream);
if ($stat === false || $pos === false) {
return null;
}
return max(0, $stat['size'] - $pos);
}
private function mkdirs(string $dir): void {
if ($dir === '' || $dir === '.' || $this->storage->is_dir($dir)) {
return;
}
$this->mkdirs(dirname($dir) === '.' ? '' : dirname($dir));
$this->storage->mkdir($dir);
}
/** Reject empty segments, '.', '..', NUL, backslashes and absolute paths. */
private static function validate(string $path, bool $allowEmpty = false): void {
if ($path === '' && $allowEmpty) {
return;
}
if ($path === '' || str_starts_with($path, '/') || str_contains($path, "\\") || str_contains($path, "\0")) {
throw new BackendException('Invalid path: ' . $path);
}
foreach (explode('/', $path) as $segment) {
if ($segment === '' || $segment === '.' || $segment === '..') {
throw new BackendException('Invalid path: ' . $path);
}
}
}
private function abs(string $path): string {
self::validate(ltrim($path, '/'));
return ltrim(($this->base === '' ? '' : $this->base . '/') . ltrim($path, '/'), '/');
}
}