From 14aa6f2a00daa27da8f319fa25b6293703baf4c6 Mon Sep 17 00:00:00 2001
From: Kjetil Torgrim Homme <kjetil.homme@redpill-linpro.com>
Date: Wed, 14 Sep 2022 17:20:11 +0200
Subject: [PATCH] add --disable-scanner to backup command

The scanner process has only cosmetic effect for the progress printer,
and can be disabled without impacting functionality when the user does
not need an estimate of completion.

In many cases the scanner process can provide beneficial priming of
the file system cache, so as general advice it should not be disabled.
However, tests have shown that backup of NFS and fuse based filesystems,
where stat(2) is relatively expensive, can be significantly faster
without the scanner.
---
 changelog/unreleased/pull-3931 |  8 ++++++++
 cmd/restic/cmd_backup.go       | 20 ++++++++++++--------
 doc/040_backup.rst             | 11 ++++++++++-
 3 files changed, 30 insertions(+), 9 deletions(-)
 create mode 100644 changelog/unreleased/pull-3931

diff --git a/changelog/unreleased/pull-3931 b/changelog/unreleased/pull-3931
new file mode 100644
index 000000000..ca1e27314
--- /dev/null
+++ b/changelog/unreleased/pull-3931
@@ -0,0 +1,8 @@
+Enhancement: Allow backup file tree scanner to be disabled
+
+Restic walks the file tree in a separate scanner process to find the total size
+and file/directory count, and uses that to provide an ETA.  This can slow down
+backups, especially of network filesystems.  The new flag `--no-scan`
+can be used to speed up such backups.
+
+https://github.com/restic/restic/pull/3931
diff --git a/cmd/restic/cmd_backup.go b/cmd/restic/cmd_backup.go
index 2a1e703eb..c2c973c7d 100644
--- a/cmd/restic/cmd_backup.go
+++ b/cmd/restic/cmd_backup.go
@@ -99,6 +99,7 @@ type BackupOptions struct {
 	UseFsSnapshot     bool
 	DryRun            bool
 	ReadConcurrency   uint
+	NoScan            bool
 }
 
 var backupOptions BackupOptions
@@ -138,6 +139,7 @@ func init() {
 	f.BoolVar(&backupOptions.IgnoreInode, "ignore-inode", false, "ignore inode number changes when checking for modified files")
 	f.BoolVar(&backupOptions.IgnoreCtime, "ignore-ctime", false, "ignore ctime changes when checking for modified files")
 	f.BoolVarP(&backupOptions.DryRun, "dry-run", "n", false, "do not upload or write any data, just show what would be done")
+	f.BoolVar(&backupOptions.NoScan, "no-scan", false, "do not run scanner to estimate size of backup")
 	if runtime.GOOS == "windows" {
 		f.BoolVar(&backupOptions.UseFsSnapshot, "use-fs-snapshot", false, "use filesystem snapshot where possible (currently only Windows VSS)")
 	}
@@ -586,16 +588,18 @@ func runBackup(ctx context.Context, opts BackupOptions, gopts GlobalOptions, ter
 		targets = []string{filename}
 	}
 
-	sc := archiver.NewScanner(targetFS)
-	sc.SelectByName = selectByNameFilter
-	sc.Select = selectFilter
-	sc.Error = progressPrinter.ScannerError
-	sc.Result = progressReporter.ReportTotal
+	if !opts.NoScan {
+		sc := archiver.NewScanner(targetFS)
+		sc.SelectByName = selectByNameFilter
+		sc.Select = selectFilter
+		sc.Error = progressPrinter.ScannerError
+		sc.Result = progressReporter.ReportTotal
 
-	if !gopts.JSON {
-		progressPrinter.V("start scan on %v", targets)
+		if !gopts.JSON {
+			progressPrinter.V("start scan on %v", targets)
+		}
+		wg.Go(func() error { return sc.Scan(cancelCtx, targets) })
 	}
-	wg.Go(func() error { return sc.Scan(cancelCtx, targets) })
 
 	arch := archiver.New(repo, targetFS, archiver.Options{ReadConcurrency: backupOptions.ReadConcurrency})
 	arch.SelectByName = selectByNameFilter
diff --git a/doc/040_backup.rst b/doc/040_backup.rst
index 1b0888f6a..e038e1485 100644
--- a/doc/040_backup.rst
+++ b/doc/040_backup.rst
@@ -204,8 +204,17 @@ Combined with ``--verbose``, you can see a list of changes:
     modified  /archive.tar.gz, saved in 0.140s (25.542 MiB added)
     Would be added to the repository: 25.551 MiB
 
-.. _backup-excluding-files:
+Disabling Backup Progress Estimation
+************************************
 
+When you start a backup, restic will concurrently count the number of
+files and their total size, which is used to estimate how long it will
+take.  This will cause some extra I/O, which can slow down backup of
+network file systems or fuse mounts.
+
+-  ``--no-scan``  Do not run scanner to estimate size of backup
+
+.. _backup-excluding-files:
 Excluding Files
 ***************