garage/src/block/metrics.rs

113 lines
3.6 KiB
Rust
Raw Normal View History

2022-02-16 13:23:04 +00:00
use opentelemetry::{global, metrics::*};
use garage_db as db;
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 <alex@adnab.me> Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/322 Co-authored-by: Alex <alex@adnab.me> Co-committed-by: Alex <alex@adnab.me>
2022-06-08 08:01:44 +00:00
use garage_db::counted_tree_hack::CountedTree;
2022-02-16 13:23:04 +00:00
/// TableMetrics reference all counter used for metrics
pub struct BlockManagerMetrics {
pub(crate) _rc_size: ValueObserver<u64>,
2022-02-16 13:23:04 +00:00
pub(crate) _resync_queue_len: ValueObserver<u64>,
pub(crate) _resync_errored_blocks: ValueObserver<u64>,
2022-02-16 13:23:04 +00:00
pub(crate) resync_counter: BoundCounter<u64>,
pub(crate) resync_error_counter: BoundCounter<u64>,
pub(crate) resync_duration: BoundValueRecorder<f64>,
pub(crate) resync_send_counter: Counter<u64>,
pub(crate) resync_recv_counter: BoundCounter<u64>,
pub(crate) bytes_read: BoundCounter<u64>,
pub(crate) block_read_duration: BoundValueRecorder<f64>,
pub(crate) bytes_written: BoundCounter<u64>,
pub(crate) block_write_duration: BoundValueRecorder<f64>,
pub(crate) delete_counter: BoundCounter<u64>,
pub(crate) corruption_counter: BoundCounter<u64>,
}
impl BlockManagerMetrics {
pub fn new(rc_tree: db::Tree, resync_queue: CountedTree, resync_errors: CountedTree) -> Self {
2022-02-16 13:23:04 +00:00
let meter = global::meter("garage_model/block");
Self {
_rc_size: meter
.u64_value_observer("block.rc_size", move |observer| {
if let Ok(Some(v)) = rc_tree.fast_len() {
observer.observe(v as u64, &[])
}
})
.with_description("Number of blocks known to the reference counter")
.init(),
2022-02-16 13:23:04 +00:00
_resync_queue_len: meter
.u64_value_observer("block.resync_queue_length", move |observer| {
observer.observe(resync_queue.len() as u64, &[])
})
.with_description(
"Number of block hashes queued for local check and possible resync",
)
.init(),
_resync_errored_blocks: meter
.u64_value_observer("block.resync_errored_blocks", move |observer| {
observer.observe(resync_errors.len() as u64, &[])
})
.with_description("Number of block hashes whose last resync resulted in an error")
.init(),
2022-02-16 13:23:04 +00:00
resync_counter: meter
.u64_counter("block.resync_counter")
.with_description("Number of calls to resync_block")
.init()
.bind(&[]),
resync_error_counter: meter
.u64_counter("block.resync_error_counter")
.with_description("Number of calls to resync_block that returned an error")
.init()
.bind(&[]),
resync_duration: meter
.f64_value_recorder("block.resync_duration")
.with_description("Duration of resync_block operations")
.init()
.bind(&[]),
resync_send_counter: meter
.u64_counter("block.resync_send_counter")
.with_description("Number of blocks sent to another node in resync operations")
.init(),
resync_recv_counter: meter
.u64_counter("block.resync_recv_counter")
.with_description("Number of blocks received from other nodes in resync operations")
.init()
.bind(&[]),
bytes_read: meter
.u64_counter("block.bytes_read")
.with_description("Number of bytes read from disk")
.init()
.bind(&[]),
block_read_duration: meter
.f64_value_recorder("block.read_duration")
.with_description("Duration of block read operations")
.init()
.bind(&[]),
bytes_written: meter
.u64_counter("block.bytes_written")
.with_description("Number of bytes written to disk")
.init()
.bind(&[]),
block_write_duration: meter
.f64_value_recorder("block.write_duration")
.with_description("Duration of block write operations")
.init()
.bind(&[]),
delete_counter: meter
.u64_counter("block.delete_counter")
.with_description("Number of blocks deleted")
.init()
.bind(&[]),
corruption_counter: meter
.u64_counter("block.corruption_counter")
.with_description("Data corruptions detected on block reads")
.init()
.bind(&[]),
}
}
}