On 12/3/24 6:54 PM, lizetao wrote:
> Hi,
>
>> -----Original Message-----
>> From: Pavel Begunkov <asml.silence@xxxxxxxxx>
>> Sent: Tuesday, December 3, 2024 10:44 PM
>> To: lizetao <lizetao1@xxxxxxxxxx>; Jens Axboe <axboe@xxxxxxxxx>
>> Cc: io-uring@xxxxxxxxxxxxxxx
>> Subject: Re: [PATCH -next] io_uring: add support for fchmod
>>
>> On 11/26/24 15:07, lizetao wrote:
>>>>>>> On 11/19/24 1:12 AM, lizetao wrote:
>>>>>>> Adds support for doing chmod through io_uring.
>> IORING_OP_FCHMOD
>>>>>>> behaves like fchmod(2) and takes the same arguments.
>>>>>
>>>>>> Looks pretty straight forward. The only downside is the forced use of
>> REQ_F_FORCE_ASYNC - did you look into how feasible it would be to allow
>> non-blocking issue of this? Would imagine the majority of fchmod calls end
>> up not blocking in the first place.
>>>>>
>>>>> Yes, I considered fchmod to allow asynchronous execution and wrote a
>> test case to test it, the results are as follows:
>>>>>
>>
>> FYI, this email got into spam.
> Sorry to bother everyone, but I would like to know if there are any
> plans to implement asynchronous system calls through io_uring, and
> which system calls are in the planning.
No specific plans, existing syscalls are mostly sync by nature of the
API for them. Supporting syscalls through io_uring in an efficient
manner generally necessitates changing something ala:
syscall_foo(..)
{
return do_foo_syscall(...);
}
into
syscall_foo(...)
{
start_foo_syscall(...);
return wait_on_foo_syscall(...);
}
where the act of issuing and waiting for the completion of it are two
separate entities, generally where the waiting is a waitqueue and the
wait_on_foo_syscall() simply waits on it to be completed, and io_uring
can use this waitqueue to get a callback when it has finished.
That allows efficient processing of syscalls through io_uring. If you
don't do that, then you're stuck with do_foo_syscall(), and then
io_uring can only support it by punting to the io-wq worker threads
which will do the sync do_foo_sycall() part.
--
Jens Axboe
