The TOFFEE Project
HOMEDOCUMENTATIONUPDATESVIDEOSRESEARCHDOWNLOADSPONSORSCONTACT


DOCUMENTATION 》 TOFFEE with Hardware Compression and Decompression Accelerator Cards

You can build a basic TOFFEE WAN Optimization hardware completely in software layer (i.e its networking data-plane and control-plane). And if you are a product manufacturer you can make commercial WAN Optimization products with TOFFEE with software layer alone. And if you choose to improve its performance, you can use any third-party PCIe Compression Accelerator cards.

Here is the TOFFEE system architecture with and without hardware accelerator card (i.e Hardware offload). Hardware offload will greatly reduce the load on general purpose CPU (which is your software/OS layer) and the core data optimization operation such as loss-less compression (sometimes even encryption) is done within a dedicated Hardware Accelerator card (or chip) as shown below.
TOFFEE Architecture with Compression and Decompression Accelerator Card

In this case TOFFEE will work as an WAN Optimization framework. With this framework you can architect your entire commercial WAN Optimization product series. You need to modify TOFFEE Linux kernel modules (and APIs) so that it no longer choose kernel's LZ77, LZO or LZ4 software compression libraries (which is CPU bound), instead point to the hardware accelerator card vendor provided kernel's driver/library APIs. This makes packet data compression within TOFFEE Linux Kernel module CPU bound to dedicated co-processor hardware compression accelerator card bound.

It is a well known fact that Linux Kernel's Kernel modules are not great at scaling with multiple CPU Processor Cores. So in a systems architecture point of having more CPU cores in a TOFFEE WAN Optimization device gives no significant advantage. The per-core CPU performance is what required for a workload like TOFFEE packet data optimization. So if architect a high-end WAN Optimization device you need to consider hardware acceleration offload if feasible.

For example: Here is a general purpose AHA AHA363PCIE0301G 5Gbs GZIP Compression/Decompression Accelerator Card. Typical applications (or use-cases) of this card could be Storage Arrays, Load Balancers, WAN Optimization, Web Servers, Data Analytics, etc.
Comtech AHA AHA363PCIE0301G 5Gbs GZIP Compression/Decompression Accelerator Card
Image courtesy/link: https://images-na.ssl-images-amazon.com/images/I/61kMl1v4BmL._SL1500_.jpg



Intel FPGA PAC D5005 High-end Drop-in Accelerator: Here is yet another but general purpose FPGA Accelerator card can be used for processing high-bandwidth Network and Storage Data Processing (hardware offload). Read the complete article here.
Intel FPGA PAC D5005 On HPE ProLiant DL380 Gen10
Image courtesy/link: https://www.servethehome.com/wp-content/uploads/2019/08/Intel-FPGA-PAC-D5005-on-HPE-ProLiant-DL380-Gen10.jpg
Intel FPGA PAC D5005
Image courtesy/link: https://www.servethehome.com/wp-content/uploads/2019/08/Intel-FPGA-PAC-D5005-Diagram.jpg


References:



Suggested Topics:


TOFFEE - WAN Optimization


Categories

💎 TOFFEE-MOCHA new bootable ISO: Download
💎 TOFFEE Data-Center Big picture and Overview: Download PDF


Recommended Topics:

Bulk Ping Tests - WAN Acceleration ↗
Saturday' 13-Mar-2021

First TOFFEE Code Release ↗
Saturday' 13-Mar-2021
I started working on the new TOFFEE project (which is the fork of my earlier TrafficSqueezer open-source project) starting from 1st January 2016 onwards. Ever since I was busy in research and altering certain old features so that it is more minimal than TrafficSqueezer, a more focused agenda, deliver refined code and a broader vision. I have lined up more things to follow in the upcoming months. I want to focus about all aspects of WAN communication technologies not just on core WAN Optimization research and technology.

First TOFFEE-Butterscotch Code Release ↗
Saturday' 13-Mar-2021
TOFFEE-Butterscotch is a variant of TOFFEE can be used to save and optimize your Home/SOHO 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.

My Lab Battery Purchase and Service logs for Research ↗
Saturday' 13-Mar-2021
Here is a complete log of my lab battery purchase, service record which I maintain in Google drive. These I use for my home (or my family generic use) as well as a part of my home lab. I maintain a detailed log this way to monitor the failure rate of these batteries. This will allow me to select a specific brand/model which has higher success rate and to monitor any premature failure/expiry. The service log helps me to monitor and schedule the next service routine so that I can maintain these batteries in tip-top condition.

Setting up a WAN Emulator within VirtualBox ↗
Saturday' 13-Mar-2021

TOFFEE-DataCenter WAN Optimization software development - Update: 13-Aug-2016 ↗
Saturday' 13-Mar-2021
Earlier the TOFFEE is intended to work on IoT devices, Satellite Networks, branch office/SOHO deployments. In most cases the users may deploy just one or couple of TOFFEE devices per site. But in the case of TOFFEE-DataCenter, users can scale-up deploying the same in multiple servers in a sort of distributed cluster computing scenario. Besides the core TOFFEE-DataCenter components (such as packet processing engine/framework), I need to do lot of changes in its Graphical User Interface (GUI) too to address these new requirements.



TOFFEE-Mocha WAN Emulation software development - Update: 19-July-2016 ↗
Saturday' 13-Mar-2021
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.

Demo TOFFEE_DataCenter WAN Optimization VM (in VirtualBox) Test Setup ↗
Saturday' 13-Mar-2021
Demo TOFFEE_DataCenter WAN Optimization VM (in VirtualBox) Test Setup

Building my own CDN - Moving away from Joomla to non-Joomla website - Update: 01-Oct-2016 ↗
Saturday' 13-Mar-2021
Seems there are couple of Inmotionhosting servers are down. And one of the server includes The TOFFEE Project website hosted server. I was in touch with the Inmotionhosting team trying to resolve the same. I found a unique issue that all my website files are intact and the Joomla database. But the Joomla database tables are completely wiped out and missing. Besides there is also a sort of upgrade going on in their servers. Luckily I have the most recent backup of the entire website.

Tracking Live Network Application Data - in a WAN Acceleration (WAN Optimization) Device ↗
Saturday' 13-Mar-2021



Featured Educational Video:
Watch on Youtube - [17088//1] 294 - VRF - Virtual Routing and Forwarding - Introduction ↗

Replacing in Lab Intel Core i7 5820K Desktop PC with Intel Celeron 1037U Mini-PC ↗
Saturday' 13-Mar-2021
As a research experiment I replaced my Intel Core i7 5820K desktop PC with my Intel Celeron 1037U Mini-PC as my everyday desktop system. This is an attempt to reduce my overall monthly power consumption. As well an attempt to do feasibility tests and research to know how far Mini PC will dominate the market in future and to study the real potential of Mini PCs.

TOFFEE deployment topology guide ↗
Saturday' 13-Mar-2021
Assume you have two sites (such as Site-A and Site-B) connected via slow/critical WAN link as shown below. You can optimize this link by saving the bandwidth as well possibly improve the speed. However, the WAN speed can be optimized only if the WAN link speeds are below that of the processing latency of your TOFFEE installed hardware. Assume your WAN link is 12Mbps, and assume the maximum WAN optimization speed/capacity of Raspberry Pi is 20Mbps, then your link will get speed optimization too. And in another case, assume your WAN link is 50Mbps, then using the Raspberry Pi as WAN Optimization device will actually increase the latency (i.e slows the WAN link). But in all the cases the bandwidth savings should be the same irrespective of the WAN link speed. In other words, if you want to cut down the WAN link costs via this WAN Optimization set up, you can always get it since it reduces the overall bandwidth in almost all the cases (including encrypted and pre-compressed data).

TOFFEE-Mocha-1.0.32-1-x86_64 and TOFFEE-Mocha-1.0.32-1-i386 Code Release ↗
Saturday' 13-Mar-2021
This is my first TOFFEE-Mocha combined x86-64 and i386 (Intel x86 64-bit and 32-bit) code release.

TOFFEE-Mocha Documentation :: TOFFEE-Mocha-1.0.14-1-rpi2 - Raspberry Pi WAN Emulator ↗
Saturday' 13-Mar-2021




WAN Optimization Network Stack Architecture - Linux Kernel vs Intel DPDK vs Custom Packet Forward ↗
Saturday' 13-Mar-2021



Research :: Optimization of network data (WAN Optimization) at various levels:
Network File level network data WAN Optimization


Learn Linux Systems Software and Kernel Programming:
Linux, Kernel, Networking and Systems-Software online classes


Hardware Compression and Decompression Accelerator Cards:
TOFFEE Architecture with Compression and Decompression Accelerator Card


TOFFEE-DataCenter on a Dell Server - Intel Xeon E5645 CPU:
TOFFEE-DataCenter screenshots on a Dual CPU - Intel(R) Xeon(R) CPU E5645 @ 2.40GHz - Dell Server