use opentelemetry::{global, metrics::*}; use garage_db as db; use garage_db::counted_tree_hack::CountedTree; /// TableMetrics reference all counter used for metrics pub struct BlockManagerMetrics { pub(crate) _compression_level: ValueObserver, pub(crate) _rc_size: ValueObserver, pub(crate) _resync_queue_len: ValueObserver, pub(crate) _resync_errored_blocks: ValueObserver, pub(crate) resync_counter: BoundCounter, pub(crate) resync_error_counter: BoundCounter, pub(crate) resync_duration: BoundValueRecorder, pub(crate) resync_send_counter: Counter, pub(crate) resync_recv_counter: BoundCounter, pub(crate) bytes_read: BoundCounter, pub(crate) block_read_duration: BoundValueRecorder, pub(crate) bytes_written: BoundCounter, pub(crate) block_write_duration: BoundValueRecorder, pub(crate) delete_counter: BoundCounter, pub(crate) corruption_counter: BoundCounter, } impl BlockManagerMetrics { pub fn new( compression_level: Option, rc_tree: db::Tree, resync_queue: CountedTree, resync_errors: CountedTree, ) -> Self { let meter = global::meter("garage_model/block"); Self { _compression_level: meter .u64_value_observer("block.compression_level", move |observer| { match compression_level { Some(v) => observer.observe(v as u64, &[]), None => observer.observe(0 as u64, &[]), } }) .with_description("Garage compression level for node") .init(), _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(), _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(), 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(&[]), } } }