[lkml]   [2000]   [Sep]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: zero-copy TCP

Alan Cox wrote:
> > **NCP** is does not reside in IPX at all. That's why the implementation
> > in Linux is busted. The window size is variable and keys off of HOW
> > MANY FREE ECBS ARE IN THE SYSTEM. It doe not belong in the IPX/SPX
> > stack, but inside of MARS-NWE proper.
> Packet burst is in MARS-NWE not the kernel IPX code. Our IPX code actually
> doesnt know about NCP at all - so it has no fast paths or kernel helpers for
> the cache. It means we are materially poorer but we dont have to maintain
> magic for NCP. If you were doing a Linux netware clone you would want a
> kncpd for the cache hit cases

There's some code in the IPX stack obviously put there for MARS-NWE.
The Packet Burst in MARS malfunctions and causes NetWare server resets.
I think they've got the windowing wrong, but have not looked at it
closely. Packet Burst was one of Drew's Brain Farts that was done as an
afterthought, and most folks at Novell wish it wasn't implemented the
way it is. There model works by pre-reserving buffers in the target
system, then batching packets and releasing them. THe window could
change based on how many free ECBs were around to receive the data. The
they did data integrity on NetWare IPX without a checksum was to snoop
some key fields in the packet --- not a good way to ensure data
integrity, but hey -- it seems to work. Not a good internet protocol,
but a great LAN protocol.

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
Please read the FAQ at

 \ /
  Last update: 2005-03-22 12:38    [W:0.102 / U:1.764 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site