mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-28 07:57:01 +00:00
feat(get): consolidate GET performance optimization (#3972)
* feat(get): consolidate GET performance optimization Consolidated implementation of all GET performance optimizations into a single, well-organized commit replacing the previous patch-on-patch approach. ## Changes ### Configuration (set_disk/mod.rs) - Consolidated all GET optimization flags into a single organized section - Enabled by default: codec streaming, metadata early-stop, page cache reclaim - Added codec streaming multipart flag (default: disabled) - Added version-aware early-stop flag (default: disabled) - Added adaptive duplex buffer sizing based on object size - All flags use OnceLock caching with rollout percentage support ### Metadata Early-Stop (set_disk/read.rs) - Delete marker early-stop when quorum agrees - Version-aware early-stop for versioned GET requests - MetadataQuorumAccumulator enhanced with: - delete_marker_votes tracking - requested_version_id and matching_version_votes tracking - version_early_stop_decision() method - 6 new tests for version early-stop scenarios ### Codec Streaming (erasure/coding/decode_reader.rs) - DualInFlight (2-stripe lookahead) enabled by default ### Decode Pipeline (erasure/coding/decode.rs) - Stripe prefetch count configuration - Bitrot-decode overlap configuration ### Disk Layer (disk/local.rs) - O_DIRECT read configuration constants (preparation) ### Metrics (io-metrics/lib.rs) - BytesPool acquisition/return metrics - Metadata phase duration with early-stop label - Total duration with reader_path label ### Diagnostics (diagnostics/) - Early-stop reason constants - Pool tier/outcome label constants ### Observability (.docker/observability/) - 3 Grafana dashboards for GET optimization monitoring - Prometheus alert rules (6 alerts: 3 critical, 3 warning) - Updated README.md and README_ZH.md with usage docs ### Config (config/src/constants/runtime.rs) - Page cache reclaim read enabled by default ## Environment Variables | Variable | Default | Description | |----------|---------|-------------| | RUSTFS_GET_CODEC_STREAMING_ENABLE | true | Codec streaming base flag | | RUSTFS_GET_CODEC_STREAMING_ROLLOUT_PCT | 100 | Codec streaming rollout % | | RUSTFS_GET_CODEC_STREAMING_MULTIPART_ENABLE | false | Multipart codec streaming | | RUSTFS_GET_METADATA_EARLY_STOP_ENABLE | true | Early-stop base flag | | RUSTFS_GET_METADATA_EARLY_STOP_ROLLOUT_PCT | 100 | Early-stop rollout % | | RUSTFS_GET_METADATA_VERSION_EARLY_STOP_ENABLE | false | Version-aware early-stop | | RUSTFS_OBJECT_FILE_CACHE_RECLAIM_READ_ENABLE | true | Page cache reclaim | | RUSTFS_OBJECT_DIRECT_IO_READ_ENABLE | false | O_DIRECT (preparation) | | RUSTFS_GET_DECODE_STRIPE_PREFETCH_COUNT | 1 | Stripe prefetch | | RUSTFS_GET_BITROT_DECODE_OVERLAP_ENABLE | false | Bitrot-decode overlap | | RUSTFS_GET_CODEC_STREAMING_MAX_INFLIGHT | 2 | DualInFlight stripes | ## Rollback All optimizations can be disabled via environment variables: RUSTFS_GET_CODEC_STREAMING_ENABLE=false RUSTFS_GET_METADATA_EARLY_STOP_ENABLE=false RUSTFS_OBJECT_FILE_CACHE_RECLAIM_READ_ENABLE=false Co-Authored-By: heihutu <heihutu@gmail.com> * test(get): add stress test scripts for GET optimization validation - quick-validate-get-optimization.sh: Quick 5-minute validation - stress-test-get-optimization.sh: Full 30+ minute stress test - README-stress-test.md: Usage documentation Co-Authored-By: heihutu <heihutu@gmail.com> * test(ecstore): align file cache reclaim defaults * chore(deps): update redis and erasure codec * test(ecstore): align decode fill policy default * test(ecstore): align metadata early-stop default * fix(ecstore): keep metadata early stop opt-in --------- Co-authored-by: heihutu <heihutu@gmail.com>
This commit is contained in:
houseme
@@ -947,6 +947,31 @@ pub fn record_get_object_metadata_phase_duration(duration_secs: f64) {
|
||||
record_get_object_stage_duration("legacy_duplex", "metadata", duration_secs);
|
||||
}
|
||||
|
||||
/// Record metadata phase duration with early-stop state label.
|
||||
#[inline(always)]
|
||||
pub fn record_get_object_metadata_phase_duration_with_early_stop(duration_secs: f64, early_stop_active: &'static str) {
|
||||
if !get_stage_metrics_enabled() {
|
||||
return;
|
||||
}
|
||||
histogram!(
|
||||
"rustfs_io_get_object_stage_duration_seconds",
|
||||
"path" => "legacy_duplex",
|
||||
"stage" => "metadata",
|
||||
"early_stop_active" => early_stop_active
|
||||
)
|
||||
.record(duration_secs);
|
||||
}
|
||||
|
||||
/// Record GET object total duration with reader path label.
|
||||
#[inline(always)]
|
||||
pub fn record_get_object_total_duration_with_path(duration_secs: f64, reader_path: &'static str) {
|
||||
histogram!(
|
||||
"rustfs_io_get_object_total_duration_seconds_with_path",
|
||||
"reader_path" => reader_path
|
||||
)
|
||||
.record(duration_secs);
|
||||
}
|
||||
|
||||
/// Record GetObject shard reader setup duration.
|
||||
#[inline(always)]
|
||||
pub fn record_get_object_shard_reader_setup_duration(duration_secs: f64) {
|
||||
@@ -1075,6 +1100,34 @@ pub fn record_bytes_pool_hit_rate(tier: &str, hit_rate: f64) {
|
||||
gauge!("rustfs_bytes_pool_hit_rate", "tier" => tier.to_string()).set(hit_rate * 100.0);
|
||||
}
|
||||
|
||||
/// Record a BytesPool buffer acquisition attempt.
|
||||
///
|
||||
/// `outcome` = `"hit"` when a buffer is available in the pool, `"miss"` when the
|
||||
/// pool is empty and a new allocation is required.
|
||||
///
|
||||
/// # Arguments
|
||||
///
|
||||
/// * `tier` - Pool tier ("small", "medium", "large", "xlarge")
|
||||
/// * `outcome` - Acquisition outcome ("hit" or "miss")
|
||||
#[inline(always)]
|
||||
pub fn record_bytespool_acquisition(tier: &'static str, outcome: &'static str) {
|
||||
counter!("rustfs_io_bytespool_acquisition_total", "tier" => tier, "outcome" => outcome).increment(1);
|
||||
}
|
||||
|
||||
/// Record a BytesPool buffer return attempt.
|
||||
///
|
||||
/// `outcome` = `"recycled"` when the buffer is successfully returned to the
|
||||
/// pool, `"dropped"` when `try_lock` fails and the buffer is deallocated.
|
||||
///
|
||||
/// # Arguments
|
||||
///
|
||||
/// * `tier` - Pool tier ("small", "medium", "large", "xlarge")
|
||||
/// * `outcome` - Return outcome ("recycled" or "dropped")
|
||||
#[inline(always)]
|
||||
pub fn record_bytespool_return(tier: &'static str, outcome: &'static str) {
|
||||
counter!("rustfs_io_bytespool_return_total", "tier" => tier, "outcome" => outcome).increment(1);
|
||||
}
|
||||
|
||||
/// Record zero-copy write operation.
|
||||
///
|
||||
/// # Arguments
|
||||
@@ -1564,6 +1617,21 @@ mod tests {
|
||||
record_bytes_pool_hit_rate("small", 0.85);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_record_bytespool_acquisition_and_return() {
|
||||
// Acquisition outcomes
|
||||
record_bytespool_acquisition("small", "hit");
|
||||
record_bytespool_acquisition("medium", "miss");
|
||||
record_bytespool_acquisition("large", "hit");
|
||||
record_bytespool_acquisition("xlarge", "miss");
|
||||
|
||||
// Return outcomes
|
||||
record_bytespool_return("small", "recycled");
|
||||
record_bytespool_return("medium", "dropped");
|
||||
record_bytespool_return("large", "recycled");
|
||||
record_bytespool_return("xlarge", "dropped");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_record_zero_copy_write() {
|
||||
record_zero_copy_write(1024, 10.5);
|
||||
@@ -1612,6 +1680,8 @@ mod tests {
|
||||
record_get_object_full_body_latency("s3_handler", 0.009);
|
||||
record_get_object_response_handoff_duration("s3_handler", 0.0001);
|
||||
record_get_object_metadata_phase_duration(0.002);
|
||||
record_get_object_metadata_phase_duration_with_early_stop(0.002, "hit");
|
||||
record_get_object_total_duration_with_path(0.050, "legacy_duplex");
|
||||
record_get_object_shard_reader_setup_duration(0.003);
|
||||
record_get_object_decode_duration(0.004);
|
||||
record_get_object_duplex_backpressure_duration(0.005);
|
||||
@@ -1747,6 +1817,8 @@ mod tests {
|
||||
record_get_object_first_byte_latency("s3_handler", 0.008);
|
||||
record_get_object_full_body_latency("s3_handler", 0.009);
|
||||
record_get_object_response_handoff_duration("s3_handler", 0.0001);
|
||||
record_get_object_metadata_phase_duration_with_early_stop(0.002, "hit");
|
||||
record_get_object_total_duration_with_path(0.050, "legacy_duplex");
|
||||
record_get_object_shard_reader_setup_duration(0.003);
|
||||
record_get_object_decode_duration(0.004);
|
||||
record_get_object_duplex_backpressure_duration(0.005);
|
||||
|
||||
Reference in New Issue
Block a user