GGLinnk/bees
1
0
Fork 0
mirror of https://github.com/Zygo/bees.git synced 2025-07-01 00:02:27 +02:00
Code Packages Activity

extent scan: introduce SCAN_MODE_EXTENT

Browse Source 
The EXTENT scan mode reads the extent tree, splits it into tiers by
extent size, converts each tiers's extents into subvol/inode/offset refs,
then runs the legacy bees dedupe engine on the refs.

The extent scan mode can cheaply compute completion percentage and ETA,
so do that every time a new transid is observed.

Signed-off-by: Zygo Blaxell <bees@furryterror.org>
This commit is contained in:
Zygo Blaxell
2022-12-21 22:42:39 -05:00
parent b99d80b40f
commit 6542917ffa
3 changed files with 749 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/bees.h
View File

@ -561,11 +561,8 @@ class BeesRoots : public enable_shared_from_this<BeesRoots> {
bool m_stop_requested = false;
void insert_new_crawl();
void insert_root(const BeesCrawlState &bcs);
Fd open_root_nocache(uint64_t root);
Fd open_root_ino_nocache(uint64_t root, uint64_t ino);
uint64_t transid_min();
uint64_t transid_max();
uint64_t transid_max_nocache();
void state_load();
ostream &state_to_stream(ostream &os);
@ -582,6 +579,9 @@ class BeesRoots : public enable_shared_from_this<BeesRoots> {
bool crawl_batch(shared_ptr<BeesCrawl> crawl);
void clear_caches();
friend class BeesScanModeExtent;
shared_ptr<BeesCrawl> insert_root(const BeesCrawlState &bcs);
friend class BeesCrawl;
friend class BeesFdCache;
friend class BeesScanMode;
@ -600,17 +600,20 @@ public:
Fd open_root_ino(const BeesFileId &bfi) { return open_root_ino(bfi.root(), bfi.ino()); }
bool is_root_ro(uint64_t root);
// TODO: do extent-tree scans instead
enum ScanMode {
SCAN_MODE_LOCKSTEP,
SCAN_MODE_INDEPENDENT,
SCAN_MODE_SEQUENTIAL,
SCAN_MODE_RECENT,
SCAN_MODE_EXTENT,
SCAN_MODE_COUNT, // must be last
};
void set_scan_mode(ScanMode new_mode);
void set_workaround_btrfs_send(bool do_avoid);
uint64_t transid_min();
uint64_t transid_max();
};
struct BeesHash {