On Tue, Dec 30, 2025 at 11:26:28AM +0100, Nicolas George wrote: > Henrique de Moraes Holschuh (HE12025-12-29): > > The "does not even hit the underlying storage" behavior is a function > > of the Linux page-cache, and most of the widely-used filesystems > > (certainly ext4 and xfs) will behave like that unless specifically > > configured to operate in "sync" mode. > > Sure, but that raises all sorts of questions about HOW it is done. > > For example what happens two files are submitted for writing, but the > first one would use the last block of the device? The second one should > error with No space left on device, but that would imply the free blocks > were already updated to account for the first one before it could have > reached the block device. "No space left on device" is handled by the fs code, when it decides where to put a block. No need to actually write the block to disk. Possibly some fs's permanent data are updated and thus scheduled for write -- again a job for the buffer cache, which has to honour itself ordering constraints (what to write first, etc.) This one [1] seems to be a good entry point into that. Cheers [1] https://www.thomas-krenn.com/en/wiki/Linux_Page_Cache_Basics -- t >
Attachment:
signature.asc
Description: PGP signature