Pekka Enberg 8337e86794 core: Use sequential consistency for atomics by default ...

We use relaxed ordering in a lot of places where we really need to
ensure all CPUs see the write. Switch to sequential consistency, unless
acquire/release is explicitly used. If there are places that can be
optimized, we can switch to relaxed case-by-case, but have a comment
explaning *why* it is safe.

2025-09-18 13:38:13 +03:00

..

clock.rs

modify semantics of busy_timeout to be more on par with sqlite

2025-09-15 02:20:32 -03:00

common.rs

O_DIRECT disable on WAL

2024-11-13 13:45:42 +00:00

generic.rs

core: Rename IO::run_once() to IO::step()

2025-09-10 14:36:02 +03:00

io_uring.rs

core: Rename IO::run_once() to IO::step()

2025-09-10 14:36:02 +03:00

memory.rs

Use u64 for file offsets in IO and calculate such offsets in u64

2025-08-28 09:44:00 -04:00

mod.rs

core: Use sequential consistency for atomics by default

2025-09-18 13:38:13 +03:00

unix.rs

Handle partial writes in unix IO for pwrite and pwritev

2025-09-12 18:13:02 -04:00

vfs.rs

core: Rename IO::run_once() to IO::step()

2025-09-10 14:36:02 +03:00

windows.rs

core: Rename IO::run_once() to IO::step()

2025-09-10 14:36:02 +03:00