gsadmin/rustfs
1
0
Fork 0
mirror of https://github.com/rustfs/rustfs.git synced 2026-08-24 21:26:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf(runtime): enable fsync thread isolation by default (#6438)

Browse Source 
Change DEFAULT_FSYNC_BLOCKING_THREADS from 0 to 64 to isolate
fsync/fdatasync operations into a dedicated blocking thread pool.

A/B validation on 4-node EC cluster (testing, 10.0.0.5/8/9/11:9000):

  PUT 256KiB c16:  p99 226ms → 135ms (−40%), p50 60ms → 19ms (−68%)
  GET 256KiB c16:  p99 3.97ms → 3.63ms (−9%), throughput +1.8%
  GET 4KiB c64:    neutral (pure read, no fsync involvement)

Without isolation, fsync operations contend with read I/O (pread/stat/open)
on the main blocking pool, causing device-bound fsync to starve read
operations under mixed PUT+GET workloads.

Co-authored-by: heihutu <heihutu@gmail.com>
This commit is contained in:
houseme
2026-08-23 13:47:33 +08:00
committed by GitHub
parent 66da8565c9
commit ab8f8b94dc
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/config/src/constants/runtime.rs
+2 -2
View File
@@ -60,9 +60,9 @@ pub const DEFAULT_RNG_SEED: Option<u64> = None; // None means random
/// Dedicated blocking thread pool for fsync/fdatasync operations.
/// When > 1, fsync operations are isolated from the main blocking pool to
/// prevent device-bound fsync from starving read operations (pread/stat/open).
/// Default 0 means auto (no isolation, use main runtime).
/// Default 64 isolates fsync from the main blocking pool to prevent device-bound fsync from starving read I/O.
pub const ENV_FSYNC_BLOCKING_THREADS: &str = "RUSTFS_RUNTIME_FSYNC_BLOCKING_THREADS";
pub const DEFAULT_FSYNC_BLOCKING_THREADS: usize = 0;
pub const DEFAULT_FSYNC_BLOCKING_THREADS: usize = 64;
// Dial9 Tokio Telemetry Default values
pub const DEFAULT_RUNTIME_DIAL9_ENABLED: bool = false; // Disabled by default