News for hackers. Stuff that matters.
Re:POSIX v. reality: A position on O_PONIES by appplication on Thursday November 23, 2023 @06:04PM (#38398730)
Does this suggest that the idea of an overarching fsync/rename is perhaps being proposed at the wrong level of abstraction? If it can’t be reliably implemented at every subsequent level, what’s the point in having it at this level?
Re:POSIX v. reality: A position on O_PONIES by tedunangst on Thursday November 23, 2023 @06:20PM (#38398886)
Different filesystems have different on disk structures, with varying degrees of complexity and cost in getting those things on disk. Everything can reliably get everything written eventually, but if you want to fully utilize your disk bandwidth, you only want to flush the data that can get there fast, which is going to vary by filesystem. And different applications have different durability requirements.
Re:POSIX v. reality: A position on O_PONIES by layer8 on Thursday November 23, 2023 @06:31PM (#38398965)
This is still no argument to not define syscalls for the semantics that applications typically care about. If it is slow on a particular file system, then so be it, it’s still the semantics the application requires.
Re:POSIX v. reality: A position on O_PONIES by tedunangst on Thursday November 23, 2023 @07:22PM (#38399390)
So call fsync.