Much improved sendfile(2) kernel implementation

[Claudio Jeker]

On Thu, Sep 21, 2006 at 05:59:03PM +1000, Peter Jeremy wrote:
> On Wed, 2006-Sep-20 23:59:13 +0200, Andre Oppermann wrote:
> >I have rewritten kern_sendfile() to work in two loops, the inner which turns
> >as many pages into mbufs as it can up to the free send socket buffer space.
> 
> The 64K blocks sounds good but how does this interact with TCP slow
> start?  Is there the possibility that a couple (for some reasonably
> large value of 'couple') of TCP connections slowly accepting a file
> could eat all the mbuf space?
> 

You always have this issue no matter if you use sendfile or not.
This is why the socket buffers are limited and why sometimes having large
sendbuffers is bad -- especially on busy servers.

-- 
:wq Claudio