Hello,

Milos Nikic, le mar. 27 janv. 2026 21:57:27 -0800, a ecrit:
> I have benchmarked the patch with "Full Sync" (sync in diskfs_write_disknode
> and in block_getblk) on a clean build (latest GNUMach/Rumpdisk/Ext2fs)
> vs. the "Vanilla" (no sync in diskfs_write_disknode and block_getblk) with
> the exact same setup to measure the impact of the barrier logic.
> 
> Test Setup
>   Workload: A run is 1,000 iterations of open() -> write() -> fsync() -> close
> ()
>             (small C program compiled and ran inside Hurd).
>   Storage:  QEMU VM (cache:none) backed by SSD.

I was rather thinking about the usual workload that people use:
installing debian packages, cloning a large git repo locally, etc.,
typically.

Synthetic benchmarks will always show the overhead with large
amplification, so they are not representative of what people will
actually see: we don't usually have fsync() called that often.

Samuel

Reply via email to