From b44d3fc796484a50cd6854f20c9b46e5fddedc9d Mon Sep 17 00:00:00 2001 From: Alex Date: Wed, 8 Jun 2022 10:01:44 +0200 Subject: Abstract database behind generic interface and implement alternative drivers (#322) - [x] Design interface - [x] Implement Sled backend - [x] Re-implement the SledCountedTree hack ~~on Sled backend~~ on all backends (i.e. over the abstraction) - [x] Convert Garage code to use generic interface - [x] Proof-read converted Garage code - [ ] Test everything well - [x] Implement sqlite backend - [x] Implement LMDB backend - [ ] (Implement Persy backend?) - [ ] (Implement other backends? (like RocksDB, ...)) - [x] Implement backend choice in config file and garage server module - [x] Add CLI for converting between DB formats - Exploit the new interface to put more things in transactions - [x] `.updated()` trigger on Garage tables Fix #284 **Bugs** - [x] When exporting sqlite, trees iterate empty?? - [x] LMDB doesn't work **Known issues for various back-ends** - Sled: - Eats all my RAM and also all my disk space - `.len()` has to traverse the whole table - Is actually quite slow on some operations - And is actually pretty bad code... - Sqlite: - Requires a lock to be taken on all operations. The lock is also taken when iterating on a table with `.iter()`, and the lock isn't released until the iterator is dropped. This means that we must be VERY carefull to not do anything else inside a `.iter()` loop or else we will have a deadlock! Most such cases have been eliminated from the Garage codebase, but there might still be some that remain. If your Garage-over-Sqlite seems to hang/freeze, this is the reason. - (adapter uses a bunch of unsafe code) - Heed (LMDB): - Not suited for 32-bit machines as it has to map the whole DB in memory. - (adpater uses a tiny bit of unsafe code) **My recommendation:** avoid 32-bit machines and use LMDB as much as possible. **Converting databases** is actually quite easy. For example from Sled to LMDB: ```bash cd src/db cargo run --features cli --bin convert -- -i path/to/garage/meta/db -a sled -o path/to/garage/meta/db.lmdb -b lmdb ``` Then, just add this to your `config.toml`: ```toml db_engine = "lmdb" ``` Co-authored-by: Alex Auvolat Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/322 Co-authored-by: Alex Co-committed-by: Alex --- src/block/rc.rs | 49 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 32 insertions(+), 17 deletions(-) (limited to 'src/block/rc.rs') diff --git a/src/block/rc.rs b/src/block/rc.rs index ec3ea44e..ce6defad 100644 --- a/src/block/rc.rs +++ b/src/block/rc.rs @@ -1,5 +1,7 @@ use std::convert::TryInto; +use garage_db as db; + use garage_util::data::*; use garage_util::error::*; use garage_util::time::*; @@ -7,31 +9,41 @@ use garage_util::time::*; use crate::manager::BLOCK_GC_DELAY; pub struct BlockRc { - pub(crate) rc: sled::Tree, + pub(crate) rc: db::Tree, } impl BlockRc { - pub(crate) fn new(rc: sled::Tree) -> Self { + pub(crate) fn new(rc: db::Tree) -> Self { Self { rc } } /// Increment the reference counter associated to a hash. /// Returns true if the RC goes from zero to nonzero. - pub(crate) fn block_incref(&self, hash: &Hash) -> Result { - let old_rc = self - .rc - .fetch_and_update(&hash, |old| RcEntry::parse_opt(old).increment().serialize())?; - let old_rc = RcEntry::parse_opt(old_rc); + pub(crate) fn block_incref( + &self, + tx: &mut db::Transaction, + hash: &Hash, + ) -> db::TxOpResult { + let old_rc = RcEntry::parse_opt(tx.get(&self.rc, &hash)?); + match old_rc.increment().serialize() { + Some(x) => tx.insert(&self.rc, &hash, x)?, + None => unreachable!(), + }; Ok(old_rc.is_zero()) } /// Decrement the reference counter associated to a hash. /// Returns true if the RC is now zero. - pub(crate) fn block_decref(&self, hash: &Hash) -> Result { - let new_rc = self - .rc - .update_and_fetch(&hash, |old| RcEntry::parse_opt(old).decrement().serialize())?; - let new_rc = RcEntry::parse_opt(new_rc); + pub(crate) fn block_decref( + &self, + tx: &mut db::Transaction, + hash: &Hash, + ) -> db::TxOpResult { + let new_rc = RcEntry::parse_opt(tx.get(&self.rc, &hash)?).decrement(); + match new_rc.serialize() { + Some(x) => tx.insert(&self.rc, &hash, x)?, + None => tx.remove(&self.rc, &hash)?, + }; Ok(matches!(new_rc, RcEntry::Deletable { .. })) } @@ -44,12 +56,15 @@ impl BlockRc { /// deletion time has passed pub(crate) fn clear_deleted_block_rc(&self, hash: &Hash) -> Result<(), Error> { let now = now_msec(); - self.rc.update_and_fetch(&hash, |rcval| { - let updated = match RcEntry::parse_opt(rcval) { - RcEntry::Deletable { at_time } if now > at_time => RcEntry::Absent, - v => v, + self.rc.db().transaction(|mut tx| { + let rcval = RcEntry::parse_opt(tx.get(&self.rc, &hash)?); + match rcval { + RcEntry::Deletable { at_time } if now > at_time => { + tx.remove(&self.rc, &hash)?; + } + _ => (), }; - updated.serialize() + tx.commit(()) })?; Ok(()) } -- cgit v1.2.3