Re: [PATCH] tcp: do not promote SPLICE_F_NONBLOCK to socket O_NONBLOCK

[Octavian Purdila]

> Why? There is clearly documented behaviour of the call, it works exactly
> like it is supposed to work - it tries to be non-blocking everywhere
> where it can, but not always, that's why there is a sentence which
> states that even with given flag call may block.

I think that it tries a bit too hard to be non-blocking in the TCP receive 
implementation, and that is causing problems for some usecases. 

And (sorry for saying this again - it will be the last time) to me it looks 
like SPLICE_F_NONBLOCK is intended for the pipe only:

commit 29e350944fdc2dfca102500790d8ad6d6ff4f69d
Author: Linus Torvalds <torvalds@xxxxxxxxxxx>
Date:   Sun Apr 2 12:46:35 2006 -0700

    splice: add SPLICE_F_NONBLOCK flag
    
    It doesn't make the splice itself necessarily nonblocking (because the
    actual file descriptors that are spliced from/to may block unless they
    have the O_NONBLOCK flag set), but it makes the splice pipe operations
    nonblocking.

>
> If there are 20 packets in the queue it will get 16 and put them into
> another end (in the next call in your example). Where will it block?
>

It will take 17 because this is what the user requested. And when trying to 
push the 17th on the pipe, it will block. I base this both on experiments and 
on my understanding of the tcp splice receive implementation. 

>
> I really do not think that there is any kind of problem with current
> behaviour, and thus there is no need to introduce additional flags
> and/or change existing behaviour, but I can understand you that existing
> approach does not met your expectation, so you are trying to change it.
> I've added Jens Axboe to copy list, who is responsible for splice
> design.
>
> Btw, you are also trying to change existing userspace API, which may be
> very much forbidden at this stage.

If people here will be telling me that for splice you must always use 
non-blocking I/O since you can't get the blocking case to work reliably, than 
I will accept that. After all, they know better :) 

Thanks,
tavi
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/