From 3394a5b3fe395d1643eb02d1d7620261aa1ac774 Mon Sep 17 00:00:00 2001 From: MattJackson <1085847+MattJackson@users.noreply.github.com> Date: Sun, 17 May 2026 09:48:35 -0700 Subject: [PATCH] Revert "iter12: fallocate without KEEP_SIZE + truncate_at_sync; chunk back to 32 MiB" This reverts commit e2c7e2032940da3bdf9d52870dbaa07e4402f3c8. --- src/io/writeback_file/linux.rs | 28 +++++++++++----------- src/io/writeback_file/mod.rs | 44 +++++++--------------------------- 2 files changed, 22 insertions(+), 50 deletions(-) diff --git a/src/io/writeback_file/linux.rs b/src/io/writeback_file/linux.rs index 34daa47..f7204a1 100644 --- a/src/io/writeback_file/linux.rs +++ b/src/io/writeback_file/linux.rs @@ -1,14 +1,9 @@ //! Linux platform impl for [`super::WritebackFile`]. //! -//! - `preallocate`: `fallocate(0)` — reserve extents AND extend the -//! reported file size up-front. iter12 (2026-05-17): switched from -//! `FALLOC_FL_KEEP_SIZE` to plain mode 0. With KEEP_SIZE the file's -//! reported length stayed at 0 and every write past the previous -//! EOF triggered an NFS SETATTR (server-side metadata commit) to -//! grow the file. With mode 0, the file is full-size from the -//! start; subsequent writes overwrite pre-extended region in place -//! with zero metadata ops. At end of mux, caller `ftruncate`s down -//! to actual content size if hint was an overestimate. +//! - `preallocate`: `fallocate(FALLOC_FL_KEEP_SIZE)` — reserve extents +//! without growing the reported file size. Reduces extent +//! fragmentation on large sequential writes (mux output on NFS in +//! particular). //! - `durable_sync`: `fsync` wrapped in //! [`crate::io::bounded::bounded_syscall`] with a 60 s deadline so a //! wedged NFS server can't trap the calling thread indefinitely. @@ -22,11 +17,16 @@ use std::time::Duration; /// Best-effort: a non-zero rc is logged but not propagated, since the /// caller would just continue with the unreserved file anyway. pub(super) fn preallocate(file: &File, size_bytes: u64) { - // Mode 0 (no KEEP_SIZE) — reserve extents AND extend the - // reported file size to `size_bytes`. On NFS this eliminates the - // per-write SETATTR that would otherwise fire each time writes - // crossed the previous EOF. - let rc = unsafe { libc::fallocate(file.as_raw_fd(), 0, 0, size_bytes as i64) }; + // FALLOC_FL_KEEP_SIZE = 0x01 — keep the reported file size at 0 + // (writes grow it normally) while still pre-reserving the extents. + let rc = unsafe { + libc::fallocate( + file.as_raw_fd(), + libc::FALLOC_FL_KEEP_SIZE, + 0, + size_bytes as i64, + ) + }; tracing::debug!( target: "mux", "WritebackFile fallocate size_hint={size_bytes} rc={rc} ok={}", diff --git a/src/io/writeback_file/mod.rs b/src/io/writeback_file/mod.rs index e26bac1..0995c98 100644 --- a/src/io/writeback_file/mod.rs +++ b/src/io/writeback_file/mod.rs @@ -73,23 +73,18 @@ use std::path::Path; use super::writeback::WritebackPipeline; /// Granularity at which the Linux writeback pipeline issues -/// `sync_file_range` pairs. 32 MiB is the empirically best value -/// (iter8: 28.7; iter9 64 MiB: 27.5; iter11 128 MiB: 16.6; iter6 -/// 8 MiB: 15.8). Locking in. -const WRITEBACK_CHUNK_BYTES: u64 = 32 * 1024 * 1024; +/// `sync_file_range` pairs. +/// +/// iter11 (2026-05-17): 32 → 128 MiB. 0.21.14 tried this under Phase +/// 2.5 and reverted; with Phase 2.5 disabled (iter8 baseline) the +/// tradeoff is different. iter8 (32 MiB) = 28.7, iter9 (64 MiB) = 27.5. +/// Trying 128 to see if the iter9 dip was noise or a real trend. +const WRITEBACK_CHUNK_BYTES: u64 = 128 * 1024 * 1024; pub(crate) struct WritebackFile { file: File, pipeline: WritebackPipeline, pos: u64, - /// Highest position ever reached by `write`/`write_all`. Used by - /// `sync_all` to truncate the file down to the actual content - /// extent if `preallocate` over-reserved. - high_water: u64, - /// True if the file was preallocated AND extended to a hint size - /// at construction. `sync_all` will `ftruncate` to `high_water` - /// when this is set, to discard any over-reservation. - truncate_at_sync: bool, } impl WritebackFile { @@ -104,8 +99,6 @@ impl WritebackFile { file, pipeline, pos, - high_water: pos, - truncate_at_sync: false, }) } @@ -138,14 +131,7 @@ impl WritebackFile { pub(crate) fn create_with_size_hint(path: &Path, size_bytes: u64) -> io::Result { let file = File::create(path)?; platform::preallocate(&file, size_bytes); - let mut wbf = Self::new(file)?; - // `preallocate` (on Linux/macOS where it's implemented) extends - // the file's reported size to `size_bytes`. We mark this so - // `sync_all` will truncate down to actual content extent at - // mux end. If the hint was an underestimate, writes simply - // extend past it as normal. - wbf.truncate_at_sync = true; - Ok(wbf) + Self::new(file) } /// Open an existing file at `path` for writing (no truncation) and @@ -168,14 +154,6 @@ impl WritebackFile { /// effort, but bounded. pub(crate) fn sync_all(&mut self) -> io::Result<()> { self.pipeline.finalize(); - if self.truncate_at_sync { - // Truncate down to the actual content extent. If - // `preallocate` extended past the muxer's real output - // size, the tail is otherwise zero-filled garbage. - // `set_len` is ftruncate; safe to call even when - // high_water == current file size (no-op). - self.file.set_len(self.high_water)?; - } platform::durable_sync(&self.file) } } @@ -184,9 +162,6 @@ impl Write for WritebackFile { fn write(&mut self, buf: &[u8]) -> io::Result { let n = self.file.write(buf)?; self.pos += n as u64; - if self.pos > self.high_water { - self.high_water = self.pos; - } self.pipeline.note_progress(self.pos); Ok(n) } @@ -194,9 +169,6 @@ impl Write for WritebackFile { fn write_all(&mut self, buf: &[u8]) -> io::Result<()> { self.file.write_all(buf)?; self.pos += buf.len() as u64; - if self.pos > self.high_water { - self.high_water = self.pos; - } self.pipeline.note_progress(self.pos); Ok(()) }