Re: Short sends returned in IORING

[Jens Axboe <axboe@kernel.dk>]

On 5/4/22 9:28 AM, Jens Axboe wrote:
> On 5/4/22 9:21 AM, Constantine Gavrilov wrote:
>> On Wed, May 4, 2022 at 4:54 PM Jens Axboe <axboe@kernel.dk> wrote:
>>>
>>> On 5/3/22 5:05 PM, Constantine Gavrilov wrote:
>>>> Jens:
>>>>
>>>> This is related to the previous thread "Fix MSG_WAITALL for
>>>> IORING_OP_RECV/RECVMSG".
>>>>
>>>> We have a similar issue with TCP socket sends. I see short sends
>>>> regarding of the method (I tried write, writev, send, and sendmsg
>>>> opcodes, while using MSG_WAITALL for send and sendmsg). It does not
>>>> make a difference.
>>>>
>>>> Most of the time, sends are not short, and I never saw short sends
>>>> with loopback and my app. But on real network media, I see short
>>>> sends.
>>>>
>>>> This is a real problem, since because of this it is not possible to
>>>> implement queue size of > 1 on a TCP socket, which limits the benefit
>>>> of IORING. When we have a short send, the next send in queue will
>>>> "corrupt" the stream.
>>>>
>>>> Can we have complete send before it completes, unless the socket is
>>>> disconnected?
>>>
>>> I'm guessing that this happens because we get a task_work item queued
>>> after we've processed some of the send, but not all. What kernel are you
>>> using?
>>>
>>> This:
>>>
>>> https://git.kernel.dk/cgit/linux-block/commit/?h=for-5.19/io_uring&id=4c3c09439c08b03d9503df0ca4c7619c5842892e
>>>
>>> is queued up for 5.19, would be worth trying.
>>>
>>> --
>>> Jens Axboe
>>>
>>
>> Jens:
>>
>> Thank you for your reply.
>>
>> The kernel is 5.17.4-200.fc35.x86_64. I have looked at the patch. With
>> the solution in place, I am wondering whether it will be possible to
>> use multiple uring send IOs on the same socket. I expect that Linux
>> TCP will serialize multiple send operations on the same socket. I am
>> not sure it happens with uring (meaning that socket is blocked for
>> processing a new IO until the pending IO completes). Do I need
>> IOSQE_IO_DRAIN / IOSQE_IO_LINK for this to work? Would not be optimal
>> because of multiple different sockets in the same uring. While I
>> already have a workaround in the form of a "software" queue for
>> streaming data on TCP sockets, I would rather have kernel to do
>> "native" queueing in sockets layer, and have exrtra CPU cycles
>> available to the  application.
> 
> The patch above will mess with ordering potentially. If the cause is as
> I suspect, task_work causing it to think it's signaled, then the better
> approach may indeed be to just flush that work and retry without
> re-queueing the current one. I can try a patch against 5.18 if you are
> willing and able to test?

You can try something like this, if you run my for-5.19/io_uring branch.
I'd be curious to know if this solves the short send issue for you.


diff --git a/fs/io_uring.c b/fs/io_uring.c
index f6b6db216478..b835e80be1fa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5684,6 +5684,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 	if (flags & MSG_WAITALL)
 		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
 
+retry:
 	ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
 
 	if (ret < min_ret) {
@@ -5694,6 +5695,8 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
 			req->flags |= REQ_F_PARTIAL_IO;
+			if (io_run_task_work())
+				goto retry;
 			return io_setup_async_msg(req, kmsg);
 		}
 		req_set_fail(req);
@@ -5744,6 +5747,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
 		min_ret = iov_iter_count(&msg.msg_iter);
 
 	msg.msg_flags = flags;
+retry:
 	ret = sock_sendmsg(sock, &msg);
 	if (ret < min_ret) {
 		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
@@ -5755,6 +5759,8 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
 			sr->buf += ret;
 			sr->done_io += ret;
 			req->flags |= REQ_F_PARTIAL_IO;
+			if (io_run_task_work())
+				goto retry;
 			return -EAGAIN;
 		}
 		req_set_fail(req);

-- 
Jens Axboe