> 4.2.3.2 A TCP SHOULD implement a delayed ACK,....and in a stream of
> full-sized segments there SHOULD be an ACK for at least every second
!!!!!!!!!!
> segment.
> Obviously Linux complies with the second (MUST) and chooses to ignore
> the first (SHOULD).
Linux-2.2 perfectly complies to all these musts and shoulds.
Solaris ftp server is broken. Apparently, it turns off Nagle algorithm
by an unknown reason and fragments 8K chunks brainlessly and shamelessly,
never merging segments, even if it has queued data.
And it gets exactly the thing which it deserves. 8)8)
> Is it possible to make this behaviour configurable?
Not configurable, but always. RFC "should" is too weak for real world.
> start. 'tcp_input.c' specifically states that Linux ack's each segment
> to make the sender enlarge its congestion window as fast as possible.
The comment is misguiding. Linux-2.2 does not this.
To be more exact, it ACKs only the first packet.
> Is this behaviour fixed with 2.3.x kernels?
No. I digged in this last week and, seems, found an acceptable
solution. ftp;//ftp.inr.ac.ru/ip-routing/softnet-991214-wrt-2.3.33.dif.gz.
Alexey Kuznetsov
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/