lkml.org 
[lkml]   [1998]   [Jun]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Thread implementations...
On Sat, 27 Jun 1998, Michiel Boland wrote:

> On Fri, 26 Jun 1998, Alan Cox wrote:
>
> > > Is nagle _really_ that big a deal?
> >
> > Yes. On a 30mS round trip time the fact Nagle kicks in between headers
> > and body just took you out of the web server benchmarks completely.
>
> My guess then is that your web server isn't very clever.

Erm... you would have to be more specific than that.

If you are using a sendfile() type interface that doesn't let you add
headers (as opposed to HPUX sendfile() which does), then the web server
has no choice but to send the headers in a different syscall, which means
either you can run into Nagle or you have to disable Nagle and end up with
more packets than necessary on the wire.

That is the whole point of the above thread.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu

\
 
 \ /
  Last update: 2005-03-22 13:43    [W:0.118 / U:0.516 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site