DOCUMENTATION 》 WAN Optimization Network Stack Architecture - Linux Kernel vs Intel DPDK vs Custom Packet Forward

In case if you need to deploy TOFFEE along with your existing VPN devices you can deploy the same as shown below. This will allow your VPN devices to encrypt your TOFFEE WAN Optimized network data. NOTE: Make sure about the VPN deployment topology done in the right order. Else TOFFEE (LAN side) may get VPN encrypted packets which may not be possible (and or difficult) to further optimize. Hence always make sure to deploy them in a topology suggested below so that TOFFEE devices are out of VPN tunnel.

Today I refined the first page consolidated report graphs. TOFFEE-Mocha (unlike TOFFEE) is a WAN Emulator, so the graphs are supposed to highlight this purpose and should display the overall network activity. Unlike TOFFEE, the TOFFEE-Mocha report should contain in general what is received versus what is sent across the wire. In case if the packet drop feature is enabled, you should see few missing bytes and packets. Similarly in future I may support packet duplication feature, in that case you may see more packets/bytes sent versus the packets/bytes actually received.

Timelapse Screen Capture of TOFFEE-DataCenter Network Acceleration - with new RRDtool graph support

TOFFEE-Butterscotch is an open-source software which can be used to save and optimize your Internet/WAN bandwidth. Unlike TOFFEE (and TOFFEE-DataCenter) TOFFEE-Butterscotch is a non peer-to-peer (and asymmetric) network optimization solution. This makes TOFFEE-Butterscotch an ideal tool for all Home and SOHO users.

Here is the TOFFEE WAN Optimization benchmarks of the TOFFEE version: TOFFEE-1.1.28. This is the current TOFFEE development version till date (2-Jul-2016). This is a HPC TOFFEE variant meant for high-end custom build servers and high-end desktops (i.e High Performance Computing a.k.a HPC). TOFFEE built this way often needs customized kernel compilation and build such as processor specific and hardware specific tune-ups since it is highly CPU intensive (if not offloaded via Hardware Accelerator Cards).

I always wanted to do some real experiments and research on packet flow patterns from High-bandwidth to Low-bandwidth networks via networking devices. This is something can be analyzed via capturing Network stack buffer data and other parameters, bench-marking, and so on. But eventually the data-transfer nature and other aspects is often contaminated due to the underlying OS and the way Network stack is implemented. So to understand the nature of packet flow from Higher to Lower bandwidth and vice-versa such as Lower to higher bandwidth, I thought I experiment with various tools and things which physically we can observe this phenomena.

This is my first TOFFEE-Mocha combined x86-64 and i386 (Intel x86 64-bit and 32-bit) code release.

Currently what we have is a single homogeneous (sort of) WWW Internet. Which we can consider as a single-dimensional network. What I propose is that we can create complete independent multiple Internets with each Internet having its own IP-address space, Domain namespace and an authority to manage Domain names. And these networks/Internets can be entirely IPv4 only based or IPv6 only based.

VPN Networks may degrade network performance due to various packet processing overheads such as encryption and by adding extra network protocol header(s) (such as IPv4/IPv6, IPSec, etc). This may inflate near MTU sized packets and causes excessive packet fragmentation. Here are the few examples of packet processing involved in a VPN (or a VPN like) Tunnel. With TOFFEE you can optimize these packets even before they get processed on to a VPN device. TOFFEE optimizes packet contents (application payload and transport headers) so that these TOFFEE optimized packets when they get processed by VPN devices (or VPN software stack) they may never need further packet fragmentation. Here is a deployment scenario of TOFFEE with VPN devices.