octoleo/restic
2
2
Fork 0
mirror of https://github.com/octoleo/restic.git synced 2024-12-25 12:09:59 +00:00
Code Issues Releases Wiki Activity

repository: fix prune heuristic to allow resuming interrupted runs

Browse Source 
Pack files created by interrupted prune runs, appear to consist only of
duplicate blobs on the next run. This caused the previous heuristic to
ignore those pack files. Now, a duplicate blob in a specific pack file
is also selected if that pack file only contains duplicate blobs. This
allows prune to select the already rewritten pack files.
This commit is contained in:
Michael Eischer 2024-05-19 23:24:18 +02:00
parent e52033a8bd
commit 027cc64737
1 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
internal/repository/prune.go
View File

@ -72,10 +72,12 @@ type PrunePlan struct {
}
type packInfo struct {
usedBlobs uint
unusedBlobs uint
usedSize uint64
unusedSize uint64
usedBlobs uint
unusedBlobs uint
duplicateBlobs uint
usedSize uint64
unusedSize uint64
tpe restic.BlobType
uncompressed bool
}
@ -226,6 +228,7 @@ func packInfoFromIndex(ctx context.Context, idx restic.ListBlobser, usedBlobs re
// mark as unused for now, we will later on select one copy
ip.unusedSize += size
ip.unusedBlobs++
ip.duplicateBlobs++
// count as duplicate, will later on change one copy to be counted as used
stats.Size.Duplicate += size
@ -256,6 +259,8 @@ func packInfoFromIndex(ctx context.Context, idx restic.ListBlobser, usedBlobs re
// if duplicate blobs exist, those will be set to either "used" or "unused":
// - mark only one occurrence of duplicate blobs as used
// - if there are already some used blobs in a pack, possibly mark duplicates in this pack as "used"
// - if a pack only consists of duplicates (which by definition are used blobs), mark it as "used". This
// ensures that already rewritten packs are kept.
// - if there are no used blobs in a pack, possibly mark duplicates as "unused"
if hasDuplicates {
// iterate again over all blobs in index (this is pretty cheap, all in-mem)
@ -271,8 +276,10 @@ func packInfoFromIndex(ctx context.Context, idx restic.ListBlobser, usedBlobs re
ip := indexPack[blob.PackID]
size := uint64(blob.Length)
switch {
case ip.usedBlobs > 0, count == 0:
// other used blobs in pack or "last" occurrence -> transition to used
case ip.usedBlobs > 0, (ip.duplicateBlobs == ip.unusedBlobs), count == 0:
// other used blobs in pack, only duplicate blobs or "last" occurrence -> transition to used
// a pack file created by an interrupted prune run will consist of only duplicate blobs
// thus select such already repacked pack files
ip.usedSize += size
ip.usedBlobs++
ip.unusedSize -= size