Hi,

On 2021-01-23 15:50:55 -0800, Andres Freund wrote:

It's also not clear to me that right now you'd necessarily get correct
results if multiple IORING_OP_GETDENTS64 for the same fd get processed
in different workers.  Looking at iterate_dir(), it looks to me that the
locking around the file position would end up being insufficient on
filesystems that implement iterate_shared?
[...]
As there's only a shared lock, seems like both would end up with the
same ctx->pos and end up updating f_pos to the same offset (assuming the
same count).

Am I missing something?

A minimal and brute force approach to this would be to use
io_op_def.hash_reg_file, but brrr, that doesn't seem like a great way
forward.

Greetings,

Andres Freund