fs: copy directory trees for fs.cp() on the thread pool

fs.cp() and fs.promises.cp() walked the tree in JavaScript with several
thread pool round trips per entry (opendir batches, two stat()s, the
copyFile(), a chmod()), all awaited in sequence: a 2 100-file tree took
~215 ms with ~110 ms of that on the main thread, against ~36 ms for
fs.cpSync(), which copies the tree in C++ when no filter is given.

Factor that C++ walk into CopyDirRecursive(), which records the error
instead of throwing so that it can run on any thread, and run it as one
ThreadPoolWork request (CpDirJob) for fs.cp()/fs.promises.cp() when
the destination directory does not exist yet and nothing has to run per
entry (no filter, no dereference, permission model off). Copying into
an existing tree keeps the JavaScript walk and its rules for what may
already be there. The same tree now takes ~30 ms with under 1 ms on the
main thread.

For that job the walk follows the JavaScript walk's rules rather than
cpSync's: it creates every directory with mkdir() and every file with
an exclusive uv_fs_copyfile() (honouring the copyFile() mode flags) and
fails with EEXIST if anything has appeared in their place since the
JavaScript check, so it never opens or follows something it did not
create; sockets, FIFOs and unknown entries are reported back to
JavaScript, which rejects them with the same SystemErrors as before;
relative link targets are made absolute lexically as path.resolve()
does. cpSync keeps merging into existing directories, skipping special
files and canonicalizing link targets.

The walk now uses the error_code overloads of std::filesystem throughout
(directory iteration included), so an unreadable directory inside the
tree is reported as EACCES by both cp() and cpSync() instead of
terminating the process, which cpSync() has done since the walk moved
to C++. Filesystem errors raised inside the walk keep their codes, with
'cp' or 'copyfile'/'mkdir' as the syscall. With preserveTimestamps the
walk stamps each directory it filled, root included, so cp() keeps
preserving directory times and cpSync() without a filter now does too.
Both file copies set the destination's mode before writing the data,
which clears setuid and setgid, so the walk puts the source mode back
after each file it copied; the JavaScript walk already chmod()s there.

Signed-off-by: Shelley Vohr <shelley.vohr@gmail.com>
PR-URL: #65488
Refs: #58461
Reviewed-By: Matteo Collina <matteo.collina@gmail.com>
Reviewed-By: Aviv Keller <me@aviv.sh>
Reviewed-By: Jake Yuesong Li <jake.yuesong@gmail.com>
Reviewed-By: Gürgün Dayıoğlu <hey@gurgun.day>

Author: codebytere

benchmark/fs/bench-cp.js

@@ -0,0 +1,33 @@
+'use strict';
+
+// fs.promises.cp() of a directory tree.
+
+const common = require('../common');
+const fs = require('fs');
+const path = require('path');
+const tmpdir = require('../../test/common/tmpdir');
+
+const bench = common.createBenchmark(main, {
+  files: [500],
+  n: [3],
+});
+
+function prepareSource(files) {
+  const src = tmpdir.resolve('cp-src');
+  for (let i = 0; i < files; i++) {
+    const dir = path.join(src, `dir-${i % 10}`, `sub-${i % 7}`);
+    fs.mkdirSync(dir, { recursive: true });
+    fs.writeFileSync(path.join(dir, `file-${i}.js`), 'x'.repeat(1024 + (i % 512)));
+  }
+  return src;
+}
+
+async function main({ files, n }) {
+  tmpdir.refresh();
+  const src = prepareSource(files);
+  bench.start();
+  for (let i = 0; i < n; i++) {
+    await fs.promises.cp(src, tmpdir.resolve(`cp-dest-${i}`), { recursive: true });
+  }
+  bench.end(n);
+}

lib/internal/fs/cp/cp.js

@@ -6,6 +6,8 @@ const {
   ArrayPrototypeEvery,
   ArrayPrototypeFilter,
   Boolean,
+  ErrorCaptureStackTrace,
+  Promise,
   PromisePrototypeThen,
   PromiseReject,
   SafePromiseAll,
@@ -55,6 +57,7 @@ const {
   sep,
 } = require('path');
 const fsBinding = internalBinding('fs');
+const permission = require('internal/process/permission');
 
 async function cpFn(src, dest, opts) {
   // Warn about using preserveTimestamps on 32-bit node
@@ -211,30 +214,19 @@ async function getStatsForCopy(destStat, src, dest, opts) {
     return onFile(srcStat, destStat, src, dest, opts);
   } else if (srcStat.isSymbolicLink()) {
     return onLink(destStat, src, dest, opts);
-  } else if (srcStat.isSocket()) {
-    throw new ERR_FS_CP_SOCKET({
-      message: `cannot copy a socket file: ${dest}`,
-      path: dest,
-      syscall: 'cp',
-      errno: EINVAL,
-      code: 'EINVAL',
-    });
-  } else if (srcStat.isFIFO()) {
-    throw new ERR_FS_CP_FIFO_PIPE({
-      message: `cannot copy a FIFO pipe: ${dest}`,
-      path: dest,
-      syscall: 'cp',
-      errno: EINVAL,
-      code: 'EINVAL',
-    });
   }
-  throw new ERR_FS_CP_UNKNOWN({
-    message: `cannot copy an unknown file type: ${dest}`,
-    path: dest,
-    syscall: 'cp',
-    errno: EINVAL,
-    code: 'EINVAL',
-  });
+  throw errorForSpecialFile(srcStat.isSocket() ? 'socket' : srcStat.isFIFO() ? 'fifo' : 'unknown', dest);
+}
+
+function errorForSpecialFile(kind, dest) {
+  const info = { path: dest, syscall: 'cp', errno: EINVAL, code: 'EINVAL' };
+  if (kind === 'socket') {
+    return new ERR_FS_CP_SOCKET({ message: `cannot copy a socket file: ${dest}`, ...info });
+  }
+  if (kind === 'fifo') {
+    return new ERR_FS_CP_FIFO_PIPE({ message: `cannot copy a FIFO pipe: ${dest}`, ...info });
+  }
+  return new ERR_FS_CP_UNKNOWN({ message: `cannot copy an unknown file type: ${dest}`, ...info });
 }
 
 function onFile(srcStat, destStat, src, dest, opts) {
@@ -318,6 +310,15 @@ async function onDir(srcStat, destStat, src, dest, opts) {
 }
 
 async function mkDirAndCopy(srcMode, src, dest, opts) {
+  // A destination directory that does not exist yet is filled in one thread
+  // pool request by the walk fs.cpSync() uses, unless a filter has to run per
+  // entry, links inside the tree must be dereferenced, or the permission model
+  // has to check each path. Copying into an existing tree keeps the per-entry
+  // walk below and its rules for what may already be there.
+  if (!opts.filter && !opts.dereference && !permission.isEnabled()) {
+    // Creates dest itself, with the mode of src.
+    return copyDirNative(src, dest, opts);
+  }
   await mkdir(dest);
   await copyDir(src, dest, opts);
   if (opts.preserveTimestamps) {
@@ -326,6 +327,27 @@ async function mkDirAndCopy(srcMode, src, dest, opts) {
   return setDestMode(dest, srcMode);
 }
 
+function copyDirNative(src, dest, opts) {
+  return new Promise((resolve, reject) => {
+    const job = new fsBinding.CpDirJob(src, dest, opts.force, opts.dereference, opts.errorOnExist,
+                                       opts.verbatimSymlinks, opts.preserveTimestamps, opts.mode);
+    // Sockets, FIFOs and unknown entries come back as (kind, path) so that
+    // they reject with the same errors as the walk above.
+    job.ondone = (err, specialFile, specialFilePath) => {
+      if (specialFile !== undefined) {
+        err = errorForSpecialFile(specialFile, specialFilePath);
+      }
+      if (err != null) {
+        ErrorCaptureStackTrace(err, copyDirNative);
+        reject(err);
+      } else {
+        resolve();
+      }
+    };
+    job.run();
+  });
+}
+
 async function copyDir(src, dest, opts) {
   const dir = await opendir(src);