Going to the next level
After
5 years of building and prototyping wireless mesh access points I
finally have figured out what type of mesh access point I want to deploy
for a commercial operation. Once
I came up with the concept I figured I would go and build it and try it
out. The criteria were to
have an embedded system with the option of software.
What was produced was an open embedded hardware solution.
The
wireless mesh access points are growing and the demand of the access
points exceeds 500 MHz. I’ve
noticed that many of us want more power, more functionality and the
ability to do consolidated services.
We need not only a system that can be embedded but also run with
existing technology infrastructure such as server room.
This system should also be carrier class such that it must be
redundant. With all these needs, the single mesh access point needs a
bigger brother. I looked at
other server type hardware but was a little discouraged that they were
all fan based with a lot of moving parts.
This
new access point is scalable and flexible enough for you to create
various solutions. Wireless
mesh operators are looking at the next best thing.
I believe I have the answer with new Array-AP.
Going beyond the wireless mesh I have written a description of my
prototype and hopefully soon have a production model ranging around $600
- $800 US. If you
interested please call me at 647-476-2231 ext 2000 or email me don@moskaluk.com
(World wide distribution is also being considered.)
Moskaluk
Array-AP comes with VIA Eden-V4 processors with speeds of 1GHz using a
400MHz front size bus and a DDR2 SO-DIMM socket accommodating up to 1GB
memory & 4
GB or more of HD, offering 18-20% increased network
performance levels when compared with VIA Eden-based appliances.
The unit does not require any active cooling, offering much
higher reliability and longer life span compared with existing network
platforms.
Designed
for the Wireless mesh market, Moskaluk Array-AP supports a LAN bypass
function that helps ensure all network traffic passes through the device
in the event of power failure. The
unit supports flexible data storage with a Compact Flash socket. The onboard Mini PCI slot offers wireless modules.
Next
Level of Mesh Access Point is geared towards a structure data centre.
The Moskaluk Array-AP is a network appliance that can fit into a
standard rack mount. This
1u network appliance is noiseless, fanless, and motionless such that it
has no moving parts. The
Array-AP does not need any special air-conditioning and is a low powered
fitting for Green computing.
This
unit is designed for carrier class wired or wireless mesh routing.
It can be fully redundant and provide the necessary framework to
be deployed in a point to multipoint topology.
The
Array-AP will have the ability to also be a stand-alone unit similar to
existing wireless access points. This
unit is housed in a watertight enclosure and only has the attachment
exposed.
The
current version shows a sample antenna production model
that
will be replaced with one or possible multi “N” connectors.
The
four Ethernet connections can connect to the Internet using an Ethernet
connection and can be linked to other application sources linked servers
or other radio devices. At
one point I was thinking to remove the radio card out of the device and
only have a firmware control the other radio devices; however, I saw
that a basic Wi-Fi device was needed.
I’m not sure if I will be offering various radio cards but the
device uses mini-PCI cards and is flexible to modify.
This
unit is designed to house within a special NEMA Enclosure for outdoor
operations.
Hyperlink
enclosure illustrated. This
unit, although robust, may not be needed for outdoor operations.
Using existing access points like WRAP or ALIX, Locustworld
MeshAP would be a better fit. But if the requirement were to put the device in the outdoors
than a device like the hyperlink enclosure would work.
Wired or Wireless
Either wired (1000 feet
Ethernet cable) or wireless clustering provides a modular way to achieve
a multi-channel mesh, which is more resilient, more secure, reduces
interference and increases flexibility.
Array-AP clusters work over Ethernet or Wi-Fi connections, and
many other media, including licensed microwave, free-space optics, power
line adapters, leased lines, and other network types.
Array-AP can provide 4 Ethernet connections from a single node, using
clustering, with a local network link, to create a multi-channel
connection that works with any number of different radio interfaces. By
using standard machines, the cluster can be built in a modular fashion,
with great flexibility. This approach is preferred to adding multiple
access points to achieve the same.
The Array-AP can work as a
single uplink such that when one is connected into another without using
clustering a TCP/IP gateway connection is established, where the gateway
node on one mesh connects in as a client to a node on the other mesh. It
also can be used a multi-channel meshing other than gateway. Using
clustering the mesh appears as one large network. Using gateways creates
a series of independent, interconnected meshes. Clustering provides
improved management, unified bandwidth controls, more resilience, easier
configuration and greater security.
Built for Power
VMware.
The Array-AP is not just another access point. It has been
designed to run VMware applications. Giving the node additional
CPU, RAM, and disk space the Array-AP can also run as a VMware client.
This gives the unit the ability to run LAMP services, Telephony, etc.
The criteria were further enhanced, as many
ISP’s who have dial up capabilities need to start to migrate off these
systems. I believe I have a solution that can extend the
capabilities of dialup providers. It is, however, not only for dialup ISP but also built for
the next generation of computing such as High Performance Clustering (HPC.)
Imagine that your 100 or 200 node system came running as Beowulf
clustered, giving your clients access to faster computing. X
window appliance can be used with Wi-Fi to access this new high
performance computing.
Beowulf is a multi-computer
architecture which can be used for parallel computations. It is a system
which usually consists of one server node, and one or more client nodes
connected together via Ethernet or some other network. It is a system
built using commodity hardware components, like any PC capable of
running a Unix-like operating system, with standard Ethernet adapters,
and switches. It does not
contain any custom hardware components and is trivially reproducible.
Beowulf also uses commodity software like the Linux or Solaris
operating system, Parallel Virtual Machine (PVM) and Message Passing
Interface (MPI). The server
node controls the whole cluster and serves files to the client nodes. It is also the cluster's console and gateway to the outside
world. Large Beowulf machines might have more than one server node, and
possibly other nodes dedicated to particular tasks, for example,
consoles or monitoring stations. In most cases client nodes in a Beowulf
system are dumb, the dumber the better.
Nodes are configured and controlled by the server node, and do
only what they are told to do. In
a disk-less client configuration, client nodes don't even know their IP
address or name until the server tells them what it is.
One of the main differences between Beowulf
and a Cluster of Workstations (COW) is the fact that Beowulf behaves
more like a single machine rather than many workstations. In most cases
client nodes do not have keyboards or monitors, and are accessed only
via remote login or possibly a serial terminal. Beowulf nodes can be
thought of as a CPU + memory package which can be plugged in to the
cluster, just like a CPU or memory module can be plugged into a
motherboard.
Beowulf is not a special software package, new network
topology or the latest kernel hack. Beowulf is a technology of
clustering computers to form a parallel, virtual supercomputer. Although
there are many software packages such as kernel modifications, PVM and
MPI libraries, and configuration tools which make the Beowulf
architecture faster, easier to configure, and much more usable, one can
build a Beowulf class machine using standard Linux distribution without
any additional software. If you have two networked computers which share
at least the home
file system via NFS, and trust each other to execute remote shells (rsh),
then it could be argued that you have a simple, two node Beowulf
machine.
Clients can access a
Supercomputer base wireless mesh access point, the X Window System
(commonly X11 or X) as it is a windowing
system which implements the X display
protocol and provides windowing on bitmap
displays. It provides the standard toolkit and protocol with which to
build graphical
user interfaces (GUIs) on most Unix-like
operating systems and OpenVMS, and has been ported to many other
contemporary general purpose operating systems.
X provides the basic framework, or primitives, for
building GUI environments: drawing and moving windows on the screen and
interacting with a mouse and/or keyboard. X does not mandate the user
interface — individual client programs handle this. As
such, the visual styling of X-based environments varies greatly;
different programs may present radically different interfaces. X is not
an integral part of the operating system; instead, it is built as an
additional application layer on top of the operating
system kernel.
Unlike previous display protocols, X was specifically designed to be used
over network
connections rather than on an integral or attached display device. X
features network
transparency: the machine where an application program (the client
application) runs can differ from the user's local machine (the display server.)
Built for multi operating system
The Array-AP is an embedded system with a
special-purpose computer system designed to perform one or a few
dedicated functions, often with real-time computing constraints. It is
usually embedded as part of a complete device including hardware
and mechanical parts. In contrast, a general-purpose computer, such as a
personal computer, can do many different tasks depending on programming.
Embedded systems control many of the common devices in use today.
Embedded systems are designed to do some specific task,
rather than be a general-purpose computer for multiple tasks. Some also
have real-time performance constraints that must be met, for reasons
such as safety and usability; others may have low or no performance
requirements, allowing the system hardware to be simplified to reduce
costs.
Embedded systems are not always separate
devices. Most often they are physically built-in to the devices they
control.
The software written for embedded systems is often
called firmware, and is stored in read-only memory or Flash memory chips
rather than a disk drive. It often runs with limited computer hardware
resources: small or no keyboard, screen, and little memory.
Firmware
Currently testing with Free Locustworld and
also looking at the following:
