syncthing/lib/versioner/trashcan.go

149 lines
4.2 KiB
Go
Raw Normal View History

// Copyright (C) 2015 The Syncthing Authors.
//
// This Source Code Form is subject to the terms of the Mozilla Public
// License, v. 2.0. If a copy of the MPL was not distributed with this file,
// You can obtain one at https://mozilla.org/MPL/2.0/.
package versioner
import (
"context"
"fmt"
"strconv"
"time"
"github.com/syncthing/syncthing/lib/config"
"github.com/syncthing/syncthing/lib/fs"
)
func init() {
// Register the constructor for this type of versioner
factories["trashcan"] = newTrashcan
}
type trashcan struct {
folderFs fs.Filesystem
versionsFs fs.Filesystem
cleanoutDays int
copyRangeMethod fs.CopyRangeMethod
}
func newTrashcan(cfg config.FolderConfiguration) Versioner {
cleanoutDays, _ := strconv.Atoi(cfg.Versioning.Params["cleanoutDays"])
// On error we default to 0, "do not clean out the trash can"
s := &trashcan{
folderFs: cfg.Filesystem(nil),
versionsFs: versionerFsFromFolderCfg(cfg),
cleanoutDays: cleanoutDays,
refactor: use modern Protobuf encoder (#9817) At a high level, this is what I've done and why: - I'm moving the protobuf generation for the `protocol`, `discovery` and `db` packages to the modern alternatives, and using `buf` to generate because it's nice and simple. - After trying various approaches on how to integrate the new types with the existing code, I opted for splitting off our own data model types from the on-the-wire generated types. This means we can have a `FileInfo` type with nicer ergonomics and lots of methods, while the protobuf generated type stays clean and close to the wire protocol. It does mean copying between the two when required, which certainly adds a small amount of inefficiency. If we want to walk this back in the future and use the raw generated type throughout, that's possible, this however makes the refactor smaller (!) as it doesn't change everything about the type for everyone at the same time. - I have simply removed in cold blood a significant number of old database migrations. These depended on previous generations of generated messages of various kinds and were annoying to support in the new fashion. The oldest supported database version now is the one from Syncthing 1.9.0 from Sep 7, 2020. - I changed config structs to be regular manually defined structs. For the sake of discussion, some things I tried that turned out not to work... ### Embedding / wrapping Embedding the protobuf generated structs in our existing types as a data container and keeping our methods and stuff: ``` package protocol type FileInfo struct { *generated.FileInfo } ``` This generates a lot of problems because the internal shape of the generated struct is quite different (different names, different types, more pointers), because initializing it doesn't work like you'd expect (i.e., you end up with an embedded nil pointer and a panic), and because the types of child types don't get wrapped. That is, even if we also have a similar wrapper around a `Vector`, that's not the type you get when accessing `someFileInfo.Version`, you get the `*generated.Vector` that doesn't have methods, etc. ### Aliasing ``` package protocol type FileInfo = generated.FileInfo ``` Doesn't help because you can't attach methods to it, plus all the above. ### Generating the types into the target package like we do now and attaching methods This fails because of the different shape of the generated type (as in the embedding case above) plus the generated struct already has a bunch of methods that we can't necessarily override properly (like `String()` and a bunch of getters). ### Methods to functions I considered just moving all the methods we attach to functions in a specific package, so that for example ``` package protocol func (f FileInfo) Equal(other FileInfo) bool ``` would become ``` package fileinfos func Equal(a, b *generated.FileInfo) bool ``` and this would mostly work, but becomes quite verbose and cumbersome, and somewhat limits discoverability (you can't see what methods are available on the type in auto completions, etc). In the end I did this in some cases, like in the database layer where a lot of things like `func (fv *FileVersion) IsEmpty() bool` becomes `func fvIsEmpty(fv *generated.FileVersion)` because they were anyway just internal methods. Fixes #8247
2024-12-01 15:50:17 +00:00
copyRangeMethod: cfg.CopyRangeMethod.ToFS(),
}
Implement facility based logger, debugging via REST API This implements a new debug/trace infrastructure based on a slightly hacked up logger. Instead of the traditional "if debug { ... }" I've rewritten the logger to have no-op Debugln and Debugf, unless debugging has been enabled for a given "facility". The "facility" is just a string, typically a package name. This will be slightly slower than before; but not that much as it's mostly a function call that returns immediately. For the cases where it matters (the Debugln takes a hex.Dump() of something for example, and it's not in a very occasional "if err != nil" branch) there is an l.ShouldDebug(facility) that is fast enough to be used like the old "if debug". The point of all this is that we can now toggle debugging for the various packages on and off at runtime. There's a new method /rest/system/debug that can be POSTed a set of facilities to enable and disable debug for, or GET from to get a list of facilities with descriptions and their current debug status. Similarly a /rest/system/log?since=... can grab the latest log entries, up to 250 of them (hardcoded constant in main.go) plus the initial few. Not implemented in this commit (but planned) is a simple debug GUI available on /debug that shows the current log in an easily pasteable format and has checkboxes to enable the various debug facilities. The debug instructions to a user then becomes "visit this URL, check these boxes, reproduce your problem, copy and paste the log". The actual log viewer on the hypothetical /debug URL can poll regularly for new log entries and this bypass the 250 line limit. The existing STTRACE=foo variable is still obeyed and just sets the start state of the system.
2015-10-03 15:25:21 +00:00
l.Debugf("instantiated %#v", s)
return s
}
// Archive moves the named file away to a version archive. If this function
// returns nil, the named file does not exist any more (has been archived).
func (t *trashcan) Archive(filePath string) error {
return archiveFile(t.copyRangeMethod, t.folderFs, t.versionsFs, filePath, func(name, tag string) string {
return name
})
}
func (t *trashcan) String() string {
return fmt.Sprintf("trashcan@%p", t)
}
func (t *trashcan) Clean(ctx context.Context) error {
if t.cleanoutDays <= 0 {
return nil
}
if _, err := t.versionsFs.Lstat("."); fs.IsNotExist(err) {
return nil
}
cutoff := time.Now().Add(time.Duration(-24*t.cleanoutDays) * time.Hour)
dirTracker := make(emptyDirTracker)
walkFn := func(path string, info fs.FileInfo, err error) error {
if err != nil {
return err
}
select {
case <-ctx.Done():
return ctx.Err()
default:
}
if info.IsDir() && !info.IsSymlink() {
dirTracker.addDir(path)
return nil
}
if info.ModTime().Before(cutoff) {
// The file is too old; remove it.
err = t.versionsFs.Remove(path)
} else {
// Keep this file, and remember it so we don't unnecessarily try
// to remove this directory.
dirTracker.addFile(path)
}
return err
}
if err := t.versionsFs.Walk(".", walkFn); err != nil {
return err
}
dirTracker.deleteEmptyDirs(t.versionsFs)
return nil
}
func (t *trashcan) GetVersions() (map[string][]FileVersion, error) {
return retrieveVersions(t.versionsFs)
}
func (t *trashcan) Restore(filepath string, versionTime time.Time) error {
// If we have an untagged file A and want to restore it on top of existing file A, we can't first archive the
// existing A as we'd overwrite the old A version, therefore when we archive existing file, we archive it with a
// tag but when the restoration is finished, we rename it (untag it). This is only important if when restoring A,
// there already exists a file at the same location
// If we restore a deleted file, there won't be a conflict and archiving won't happen thus there won't be anything
// in the archive to rename afterwards. Log whether the file exists prior to restoring.
_, dstPathErr := t.folderFs.Lstat(filepath)
taggedName := ""
tagger := func(name, tag string) string {
// We also abuse the fact that tagger gets called twice, once for tagging the restoration version, which
// should just return the plain name, and second time by archive which archives existing file in the folder.
// We can't use TagFilename here, as restoreFile would discover that as a valid version and restore that instead.
if taggedName != "" {
return taggedName
}
taggedName = fs.TempName(name)
return name
}
if err := restoreFile(t.copyRangeMethod, t.versionsFs, t.folderFs, filepath, versionTime, tagger); taggedName == "" {
return err
}
// If a deleted file was restored, even though the RenameOrCopy method is robust, check if the file exists and
// skip the renaming function if this is the case.
if fs.IsNotExist(dstPathErr) {
if _, err := t.folderFs.Lstat(filepath); err != nil {
return err
}
return nil
}
return t.versionsFs.Rename(taggedName, filepath)
}