He then says: "If “virtual connections” are used rather than a series of physical connections, it is possible to send all the data down a single physical connection. At this point the line utilisation rate will increase to nearly 100 per cent and the effects of latency will be reduced to almost zero. With full link bandwidth utilisation irrespective of RTT and latency, it is now possible to transport data over vast distances without performance drop-off."
Bridgeworks is aiming to sell this technology through its OEM and distribution channel to small and medium businesses. To get over TCP/IP network set up and management complexity an artificial intelligence-based management function has been developed to make the SANSlide link nearly autonomous.
The AI manager varies TCP/IP network parameters, such as window scaling, maximum concurrent session number, compression level and transmit buffer sizes, continuously. If they improve performance the changes are kept and if they don't they are not. When the product is first installed on a customer's network it is switched on and given an IP address. A self-learn mode period follows in which initial optimisation parameters are set. Then it constantly monitors and adjusts all parameters to optimise data transmission performance. Trossell says this means there is no user set-up and no user maintenance.
He says SANSlide can be thought of, roughly, as a bridge product with a WAN link inserted in the middle: "Because we transport the same core data we use in our bridges, we can support the same protocol on both nodes or differing protocols on both nodes. In fact we support any of the major storage protocols – a unique feature of our product."
SANSlide is pitched as lower cost and complexity than Cisco (MDS 922i) and Brocade (7500) FCIP-type products, and better performance and lower complexity than QLogic's 6142 product. Its target markets include remote replication, offsite archives, disaster recovery, and remote backup. The development roadmap includes compression, encryption, FCoE, priority paths, InfiniBand and multi-node support.
This is new technology, a version one product. The theory looks valid and Bridgeworks' internal testing proves it works. It begins to look as if a small and clever UK protocol bridging company has actually come up with a pipelining method to bypass WAN latency and so steal a march on Brocade, Cisco, QLogic, Riverbed and other very much larger companies.®
No Sir you are nor going senile and yes fake acks or polls was standard procedure 20 years plus ago. We used it for low speed ie. 2400bps to 9600 for Quantel intercountry Nz to Australia terminal conections. I fnot the delay would have caused the end user to go off the deep end...
Isn't that what "power upload" does?
I use FTP Voyager. One of the features called "power upload" is that it will open n threads (default 4) to keep the pipe full.
But then, why not just use UDP and a back connection to verify correct receipt.
This could improve usage efficiency, but I can see it potentially causing a headache for network operators who almost certainly include latency as part of their overall bandwidth calculations.
Especially if there is widespread adoption of this technique by say, p2p technologies.
I'd also be interested in knowing what processing overhead is