Questions comparing 1394 and Ethernet [was Re: Recommended 1394 chipsets?]

Steve Kinneberg wrote:

>The eth1394 driver has been clocked at 135 Mbps on a 400 Mbps link.
>Definitely room for improvement, but still, not bad. Can't say what the
>CPU utilization was.
>
>
That's a little disappointing for the toy application that I'm
targetting. I think I can beat that by adding 1 or 2 100Mb cardbus NICs
+ using a combination of md, nbd, and VLAN tricks, probably with better
stability, too.

Do you have any more details about the benchmark? E.g., does the
transfer include disk overheads? Also, do you know the ballpark figure
for SCSI transfers? (preferably measured host to host, rather than host
to IDE bridge). If the SCSI transfer rate is reasonable, I would feel
better about getting into 1394.

That brings up another question. I'm in networking, so most of my
detailed hardware knowledge stops at the Ethernet NIC level.
In a typical 1394 hardware/software stack, how much acceleration does
the SCSI layer get? For instance, a plain Ethernet NIC (i.e. no RDMA or
TCP offload magic) will blindly DMA incoming packets into the descriptor
ring, without any sort of intelligent parsing. This can complicate
zero-copy design. Does OHCI (please correct me if I have my layers
messed up, as I'm not up to speed on the 1394 lingo) provide nicer DMA
features? E.g., is the hardware smart enough to match a SCSI reply
directly to the intended buffer?

If so then 1394 could be useful as a very low-cost RDMA wannabe. 1394a
is very much at a price point where OSS hobbiests and students could
pick up a card and start playing with RDMA ideas on real hardware. Plus,
since 1394* is a consumer product (while RDMA most likely won't touch
the consumer space for a long long time), the relative price/performance
for this type of experimentation will increasingly skew towards 1394.

>> ** are there any 1394 hardware switching crossbars?
>>
>>
>I haven't of heard of anything like that for 1394. Keep in mind that
>1394 wasn't designed for data center grade networking.
>
>
I figured as much :-) I guess switching crossbars will emerge once the
1394b/Ethernet PHYs converge, and someone figures out a business reason
for adding 1394b's link layer magic to a gigabit switching fabric. I
think this is reasonable to expect, considering the consumer electronics
industry has been on the cusp of converging HDTV and computers.

Alan

-------------------------------------------------------
This SF.Net email is sponsored by the new InstallShield X.
>From Windows to Linux, servers to mobile, InstallShield X is the one
installation-authoring solution that does it all. Learn more and
evaluate today! http://www.installshield.com/Dev2Dev/0504
_______________________________________________
mailing list Linux1394-user@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux1394-user
Received on Sat Jun 5 21:32:11 2004