[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <E1LN0MC-00DaJs-M2@intern.SerNet.DE>
Date: Wed, 14 Jan 2009 08:40:08 +0100
From: Volker Lendecke <Volker.Lendecke@...Net.DE>
To: Eric Dumazet <dada1@...mosbay.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
linux-kernel@...r.kernel.org, Steven French <sfrench@...ibm.com>,
Jens Axboe <jens.axboe@...cle.com>, netdev@...r.kernel.org
Subject: Re: maximum buffer size for splice(2) tcp->pipe?
On Wed, Jan 14, 2009 at 12:15:04AM +0100, Eric Dumazet wrote:
> Volker, your splice() is a blocking one, from tcp socket to a pipe ?
Yes, it is.
> If no other thread is reading the pipe, then you might block forever
> in splice_to_pipe() as soon pipe is full (16 pages).
Why does it block when the pipe is full? Why doesn't it
return a short read, just like the read(2) call does? We
need to cope with that behaviour anyway.
> As pages are not necessarly full (each skb will use at least one page, even if
> its length is small), it is not really possible to use splice() like this.
>
> In your case, only safe way with current kernel would be to call splice()
> asking for no more than 16 bytes, that would be really insane for your needs.
>
> You may prefer a non blocking mode, at least when calling splice_to_pipe()
Which fd do I have to set the nonblocking flag on? The TCP
socket I read from, or the pipe I write to?
Thanks for the hint anyway :-)
Volker
Content of type "application/pgp-signature" skipped
Powered by blists - more mailing lists