Re: [PATCH v2 0/2] Optimise io_uring completion waiting

[Jens Axboe <axboe@kernel.dk>]

On 9/23/19 2:48 PM, Jens Axboe wrote:
> On 9/23/19 10:32 AM, Pavel Begunkov wrote:
>> Sorry, mixed the threads.
>>
>>>>
>>>> I'm not sure an extension is needed for such a special interface, why not
>>>> just put a ->threshold value next to the ctx->wait field and use either
>>>> the regular wait_event() APIs with the proper condition, or
>>>> wait_event_cmd() style APIs if you absolutely need something more complex
>>>> to happen inside?
>> Ingo,
>> io_uring works well without this patch just using wait_event_*() with
>> proper condition, but there are performance issues with spurious
>> wakeups. Detailed description in the previous mail.
>> Am I missing something?
> 
> I think we can do the same thing, just wrapping the waitqueue in a
> structure with a count in it, on the stack. Got some flight time
> coming up later today, let me try and cook up a patch.

Totally untested, and sent out 5 min before departure... But something
like this.


diff --git a/fs/io_uring.c b/fs/io_uring.c
index ca7570aca430..c2f9e1da26dd 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2768,6 +2768,37 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
 	return submit;
 }
 
+struct io_wait_queue {
+	struct wait_queue_entry wq;
+	struct io_ring_ctx *ctx;
+	struct task_struct *task;
+	unsigned to_wait;
+	unsigned nr_timeouts;
+};
+
+static inline bool io_should_wake(struct io_wait_queue *iowq)
+{
+	struct io_ring_ctx *ctx = iowq->ctx;
+
+	return io_cqring_events(ctx->rings) >= iowq->to_wait ||
+			atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
+}
+
+static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
+			    int wake_flags, void *key)
+{
+	struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
+							wq);
+
+	if (io_should_wake(iowq)) {
+		list_del_init(&curr->entry);
+		wake_up_process(iowq->task);
+		return 1;
+	}
+
+	return -1;
+}
+
 /*
  * Wait until events become available, if we don't already have some. The
  * application must reap them itself, as they reside on the shared cq ring.
@@ -2775,8 +2806,16 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
 static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			  const sigset_t __user *sig, size_t sigsz)
 {
+	struct io_wait_queue iowq = {
+		.wq = {
+			.func	= io_wake_function,
+			.entry	= LIST_HEAD_INIT(iowq.wq.entry),
+		},
+		.task		= current,
+		.ctx		= ctx,
+		.to_wait	= min_events,
+	};
 	struct io_rings *rings = ctx->rings;
-	unsigned nr_timeouts;
 	int ret;
 
 	if (io_cqring_events(rings) >= min_events)
@@ -2795,15 +2834,16 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			return ret;
 	}
 
-	nr_timeouts = atomic_read(&ctx->cq_timeouts);
-	/*
-	 * Return if we have enough events, or if a timeout occured since
-	 * we started waiting. For timeouts, we always want to return to
-	 * userspace.
-	 */
-	ret = wait_event_interruptible(ctx->wait,
-				io_cqring_events(rings) >= min_events ||
-				atomic_read(&ctx->cq_timeouts) != nr_timeouts);
+	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
+	prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, TASK_INTERRUPTIBLE);
+	do {
+		if (io_should_wake(&iowq))
+			break;
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	} while (1);
+	finish_wait(&ctx->wait, &iowq.wq);
+
 	restore_saved_sigmask_unless(ret == -ERESTARTSYS);
 	if (ret == -ERESTARTSYS)
 		ret = -EINTR;

-- 
Jens Axboe