feat: make block indexing configurable (#10608)

This adds a new folder-level configuration `FullBlockIndex`. It controls
whether we maintain the block index for a given folder -- currently
that's always true, now it becomes possible to turn off. The block index
is used for lookup of blocks across files and folders. Effectively, when
syncing a change, for each block, we check:

1. Is the block already present in the old version of the file? If so,
we can reuse (copy) it without network transfer. **This check is always
possible.**
2. Is the block already present in any other file in this folder or
other folders? If so we can copy it. **This check is only possible with
the full block index.**
3. We must transfer the block over the network.

Maintaining the full block index is costly in time, I/O and database
size. With this PR, maintaining the full block index becomes the default
for send-receive and receive-only folders only, with it disabled for
send-only and receive-encrypted folders. The block index is never useful
for encrypted folders, as blocks are encrypted separate for each file.
It is also not useful for send-only folders by themselves, though the
data in the send-only folder could be reused by other receive-type
folders if it were enabled.

For very large folders it may make sense to disable the full block index
regardless of folder type and just accept the resulting decrease in data
reuse.

Disabling or enabling the option in the GUI causes the index to be
destroyed or rebuilt accordingly.

https://github.com/syncthing/docs/pull/1005

---------

Signed-off-by: Jakob Borg <jakob@kastelo.net>
This commit is contained in:
Jakob Borg
2026-04-26 11:58:09 +02:00
committed by GitHub
parent 84c6b37913
commit 86ac4e5017
19 changed files with 449 additions and 36 deletions
+21 -7
View File
@@ -1166,6 +1166,7 @@ func (f *sendReceiveFolder) handleFile(ctx context.Context, file protocol.FileIn
blocks: blocks,
have: len(have),
}
copyChan <- cs
return nil
}
@@ -1322,7 +1323,7 @@ func (f *sendReceiveFolder) shortcutFile(file protocol.FileInfo, dbUpdateChan ch
func (f *sendReceiveFolder) copierRoutine(ctx context.Context, in <-chan copyBlocksState, pullChan chan<- pullBlockState, out chan<- *sharedPullerState) {
otherFolderFilesystems := make(map[string]fs.Filesystem)
for folder, cfg := range f.model.cfg.Folders() {
if folder == f.ID {
if folder == f.ID || !cfg.BlockIndexing {
continue
}
otherFolderFilesystems[folder] = cfg.Filesystem()
@@ -1390,13 +1391,26 @@ func (f *sendReceiveFolder) copyBlock(ctx context.Context, block protocol.BlockI
buf := protocol.BufferPool.Get(block.Size)
defer protocol.BufferPool.Put(buf)
// Hope that it's usually in the same folder, so start with that
// one. Also possibly more efficient copy (same filesystem).
if f.copyBlockFromFolder(ctx, f.ID, block, state, f.mtimefs, buf) {
return true
// Check for the block in the current version of the file
if idx, ok := state.curFileBlocks[string(block.Hash)]; ok {
if f.copyBlockFromFile(ctx, state.curFile.Name, state.curFile.Blocks[idx].Offset, state, f.mtimefs, block, buf) {
state.copiedFromOrigin(block.Size)
return true
}
if state.failed() != nil {
return false
}
}
if state.failed() != nil {
return false
if f.folder.BlockIndexing {
// Hope that it's usually in the same folder, so start with that
// one. Also possibly more efficient copy (same filesystem).
if f.copyBlockFromFolder(ctx, f.ID, block, state, f.mtimefs, buf) {
return true
}
if state.failed() != nil {
return false
}
}
for folderID, ffs := range otherFolderFilesystems {