Re: [OT]call for backers: open source hardware for networking innovation (ONetSwitch)

2015-04-07 Thread huc@ieee
The kickstarter project is going to be expired in about 2 days. The price will 
go up a bit after the kickstarter promotion. One board now is $699 (which will 
go up to over $1000), and we also have sets of 1299 for two boards, 2599 for 
four boards, and 3899 for 6 boards.

We still has gap to make the kickstarter project success, so if you'd like to 
buy some boards, we appreciate you to back now at 
https://www.kickstarter.com/projects/onetswitch/onetswitch-open-source-hardware-for-networking

Thanks and regards,

Chengchen 


On 2015-3-3, at 下午9:47, huc@ieee  wrote:

> 
> Sorry for a little bit off topic.
> 
> This email is to inform you a new open source hardware for networking 
> innovation called ONetSwitch. It is an all-programmable networking platform 
> combining ARM and FPGA in a 17cm*13cm area (notebook size) for testing and 
> verifying research idea related to networking. Different from previous FPGA 
> develop board like NetFPGA/Xilinx PCIe board, host PC is not required any 
> more for ONetSwitch, and it is smaller, cheaper, and more power efficient. 
> and more flexible.
> 
> We have launched the ONetSwitch project on Kickstarter.com weeks ago. You can 
> get an abstract from the short video, which will not take you long to get our 
> idea :-) 
> 
> https://www.kickstarter.com/projects/onetswitch/onetswitch-open-source-hardware-for-networking
> 
> We had a paper at ONS 2014 presenting the preliminary design of ONetSwitch 
> (https://www.usenix.org/system/files/conference/ons2014/ons2014-paper-hu_chengchen.pdf)
>  and a demo at SIGCOMM'14 setting a data center testbed on only desktop using 
> ONetSwitch (http://nskeylab.xjtu.edu.cn/people/huc/Pub/DesktopDC_2014.pdf). 
> In the new version now at kickstarter, we add further physical support on 
> 802.11 AC, mSATA, which suits for more scenarios. Also, we have open source 
> ref. design and supporting wiki available at github 
> (https://github.com/MeshSr/wiki/wiki/REF-OpenFlowSwitch-HWFT). The processing 
> logic can be modified in both software (ARM) and hardware (FPGA) to fit your 
> own needs. Although it is currently highlighted mainly on SDN and DCN, we aim 
> to provide the research community a way to set their testbeds for any 
> networking innovations easily. 
> 
> I send the info. about ONetSwitch to this mail list since I think it may be 
> useful to guys in this community. Please do us a favor and back us to get 
> your own programmable testbed. We believe ONetSwitch would give much help to 
> your research and development work. Also, can you help distribute it to 
> friends and colleagues who will be interested with this? Even for the guys, 
> who do not need ONetSwitch but think it is good, we greatly appreciate you to 
> back us with $1 for encouraging.
> 
> Regards,
> 
> Chengchen
> 
> ===
> Dr. Chengchen Hu, 
> 
> ERCIM Fellow
> Norwegian University of Science and Technology (NTNU)
> 
> Associate Professor (Sabbatical leave till Oct., 2015)
> Xi'an Jiaotong University
> 
> http://nskeylab.xjtu.edu.cn/people/cchu
> ===
> 
> 
> 



[OT]call for backers: open source hardware for networking innovation (ONetSwitch)

2015-03-03 Thread huc@ieee

Sorry for a little bit off topic.

This email is to inform you a new open source hardware for networking 
innovation called ONetSwitch. It is an all-programmable networking platform 
combining ARM and FPGA in a 17cm*13cm area (notebook size) for testing and 
verifying research idea related to networking. Different from previous FPGA 
develop board like NetFPGA/Xilinx PCIe board, host PC is not required any more 
for ONetSwitch, and it is smaller, cheaper, and more power efficient. and more 
flexible.

We have launched the ONetSwitch project on Kickstarter.com weeks ago. You can 
get an abstract from the short video, which will not take you long to get our 
idea :-) 
 
https://www.kickstarter.com/projects/onetswitch/onetswitch-open-source-hardware-for-networking

We had a paper at ONS 2014 presenting the preliminary design of ONetSwitch 
(https://www.usenix.org/system/files/conference/ons2014/ons2014-paper-hu_chengchen.pdf)
 and a demo at SIGCOMM'14 setting a data center testbed on only desktop using 
ONetSwitch (http://nskeylab.xjtu.edu.cn/people/huc/Pub/DesktopDC_2014.pdf). In 
the new version now at kickstarter, we add further physical support on 802.11 
AC, mSATA, which suits for more scenarios. Also, we have open source ref. 
design and supporting wiki available at github 
(https://github.com/MeshSr/wiki/wiki/REF-OpenFlowSwitch-HWFT). The processing 
logic can be modified in both software (ARM) and hardware (FPGA) to fit your 
own needs. Although it is currently highlighted mainly on SDN and DCN, we aim 
to provide the research community a way to set their testbeds for any 
networking innovations easily. 

I send the info. about ONetSwitch to this mail list since I think it may be 
useful to guys in this community. Please do us a favor and back us to get your 
own programmable testbed. We believe ONetSwitch would give much help to your 
research and development work. Also, can you help distribute it to friends and 
colleagues who will be interested with this? Even for the guys, who do not need 
ONetSwitch but think it is good, we greatly appreciate you to back us with $1 
for encouraging.

Regards,

Chengchen

===
Dr. Chengchen Hu, 

ERCIM Fellow
Norwegian University of Science and Technology (NTNU)

Associate Professor (Sabbatical leave till Oct., 2015)
Xi'an Jiaotong University

http://nskeylab.xjtu.edu.cn/people/cchu
===





Re: Open source hardware

2014-01-09 Thread Saku Ytti
On (2014-01-09 00:36 -0500), Brandon Ross wrote:

> So, in other words, you should make higher demands of your 3rd party
> optics providers than any of the OEMs could meet?  When was the last
> time your OEM lowered your pricing for you when their supplies got
> cheaper? And when was the last time they changed their part number
> when they changed the casing of an optic?

We have some contracts were price decreases automatically each year for next
5-6 years.
Cisco sometimes changes P#, sometimes not, change is documented and explained
in either case, you can track these in Cisco PCN Tool. It's everything down to
rack screws.

Specialized shop, doing professionally just optics are able to do this for
you, brokers buying where they can get cheapest, have no idea what they sell
to you.

-- 
  ++ytti



Re: Open source hardware

2014-01-08 Thread Brandon Ross

On Wed, 8 Jan 2014, Saku Ytti wrote:


On (2014-01-08 13:56 -0500), Ray Soucy wrote:


Just to toss in a few more vendors so not to look biased:


Instead of suggesting names, I'm giving some suggestions want to ask for
vendor when looking for new partner


So, in other words, you should make higher demands of your 3rd party 
optics providers than any of the OEMs could meet?  When was the last time 
your OEM lowered your pricing for you when their supplies got cheaper? 
And when was the last time they changed their part number when they 
changed the casing of an optic?


--
Brandon Ross  Yahoo & AIM:  BrandonNRoss
+1-404-635-6667ICQ:  2269442
 Skype:  brandonross
Schedule a meeting:  http://www.doodle.com/bross



Re: Open source hardware

2014-01-08 Thread Saku Ytti
On (2014-01-08 13:56 -0500), Ray Soucy wrote:

> Just to toss in a few more vendors so not to look biased:

Instead of suggesting names, I'm giving some suggestions want to ask for
vendor when looking for new partner

- DDM/DOM, should be included in each (<1USD price premium), min/max TX/RX in
  eeprom should match that of PDF specsheet

- accountability - supplier knows what they've sold to you, and where they've
  sourced them, so if there is problem, they can easily state you which of
  your optics are affected

- replacement - advance replacement for non-critical replacement

- eeprommer - usable by field-tech without training. If they are 'x compatible'
  it only means that someone programmed the eeprom with 'x' data. That someone
  might as well be your field tech, as it reduces your spare cost and ensures
  you always have correct part. Verify software has codes for kit you need it
  for.

- if you need part (like for example dwdm) when 1st party only support
  something like SR, make sure you get the eeprom saying something that still
  allows you to inventory it correctly for easing operations when it needs to
  be replaced

- part numbers - product ordered with given partnumber should be same part,
  single source laser, microcontroller, casing etc. If some source/supplier is
  changed, part number is changed. (So you can rely on getting something you
  know to work, to avoid testing everything)

- product change notification - if something is changed with 'compatible' part
  without part number change, you should be informed of what was changed and
  why

- prices decrease rapidly, it's chore to keep renegotiating constantly, try to
  negotiate contract where your price changes in reflection to vendors
  supplies becoming cheaper

And of course make sure they sell all the stuff you need, so you don't need to
have many sources, fewer sources, larger volume, better prices and also less
parts to track/test. Chances are if you're just using 1st party, there may be
lot of interesting optics available which will allow you to engineer some
problems lot cheaper than you've used to.

> When all is said and done, my experience with third-party optics has been
> that they're identical to brand-name optics except for the sticker.  In
> fact, it's pretty clear most of the time that they're often made by the
> same place.

-- 
  ++ytti



Re: Open source hardware

2014-01-08 Thread Ray Soucy
Just to toss in a few more vendors so not to look biased:

Champion One:
http://www.championone.net/

Have used them with no complaints.

And a new company I heard about off-list:

Luma Optics:
http://www.lumaoptics.net/

I haven't dealt with them before, but their solution seems to be pretty
slick in that they give you the tools to recode optics yourself.

When all is said and done, my experience with third-party optics has been
that they're identical to brand-name optics except for the sticker.  In
fact, it's pretty clear most of the time that they're often made by the
same place.

I haven't counted them all up, but I believe we have over 1,000 third-party
optics in use, so a fair enough sample size.  Most of the optics that I've
replaced in the last year have had a "Cisco" label on them. ;-)



On Tue, Jan 7, 2014 at 9:58 AM, Ray Soucy  wrote:

> http://approvedoptics.com/ is a good starting point if you want correct
> vendor codes
>
>
> On Tue, Jan 7, 2014 at 8:57 AM, Vlade Ristevski wrote:
>
>> Sorry to get off topic, but is there a company that you can recommend?
>> The price of the Cisco single mode GLC-LH-SMD= is killing me. I see a bunch
>> of third party  ones on Amazon and CDW but I'd to love to get my hands one
>> that has the correct vendor code without going and trying them all.
>>
>>
>> On 1/3/2014 7:48 AM, Ray Soucy wrote:
>>
>>> You actually buy brand-name SFP's? That's like buying the gold-plated
>>> HDMI
>>> Monster Cable at Best Buy at markup ...
>>>
>>> I just find the the companies that the vendors contract to make their OEM
>>> SFP's and buy direct.  Same SFP from the same factory except one has a
>>> Cisco sticker. ;-)
>>>
>>> You can even get them with the correct vendor code, been doing this for
>>> years and there is no difference in failure rate or quality and we go
>>> through hundreds of SFPs.
>>>
>>>
>>>
>>>
>>>  Vlad
>> Network Manager
>>
>
>
>
> --
> Ray Patrick Soucy
> Network Engineer
> University of Maine System
>
> T: 207-561-3526
> F: 207-561-3531
>
> MaineREN, Maine's Research and Education Network
> www.maineren.net
>



-- 
Ray Patrick Soucy
Network Engineer
University of Maine System

T: 207-561-3526
F: 207-561-3531

MaineREN, Maine's Research and Education Network
www.maineren.net


Re: Open source hardware

2014-01-08 Thread Mark Tinka
On Tuesday, January 07, 2014 05:12:38 PM Aled Morris wrote:

> In Europe, http://www.flexoptix.net are recommended.
> 
> They also sell blank modules and give you a programmer
> too, so you can stock fewer spares and program them for
> whatever vendor you need in an outage/rapid deployment
> situation.
> 
> I'm sure they'd ship to the US.

Yep, would recommend them.

Mark.


signature.asc
Description: This is a digitally signed message part.


Re: Open source hardware

2014-01-07 Thread Aled Morris
On 7 January 2014 13:57, Vlade Ristevski  wrote:

> Sorry to get off topic, but is there a company that you can recommend? The
> price of the Cisco single mode GLC-LH-SMD= is killing me. I see a bunch of
> third party  ones on Amazon and CDW but I'd to love to get my hands one
> that has the correct vendor code without going and trying them all.


In Europe, http://www.flexoptix.net are recommended.

They also sell blank modules and give you a programmer too, so you can
stock fewer spares and program them for whatever vendor you need in an
outage/rapid deployment situation.

I'm sure they'd ship to the US.

Aled


Re: Open source hardware

2014-01-07 Thread Ray Soucy
http://approvedoptics.com/ is a good starting point if you want correct
vendor codes


On Tue, Jan 7, 2014 at 8:57 AM, Vlade Ristevski  wrote:

> Sorry to get off topic, but is there a company that you can recommend? The
> price of the Cisco single mode GLC-LH-SMD= is killing me. I see a bunch of
> third party  ones on Amazon and CDW but I'd to love to get my hands one
> that has the correct vendor code without going and trying them all.
>
>
> On 1/3/2014 7:48 AM, Ray Soucy wrote:
>
>> You actually buy brand-name SFP's? That's like buying the gold-plated HDMI
>> Monster Cable at Best Buy at markup ...
>>
>> I just find the the companies that the vendors contract to make their OEM
>> SFP's and buy direct.  Same SFP from the same factory except one has a
>> Cisco sticker. ;-)
>>
>> You can even get them with the correct vendor code, been doing this for
>> years and there is no difference in failure rate or quality and we go
>> through hundreds of SFPs.
>>
>>
>>
>>
>>  Vlad
> Network Manager
>



-- 
Ray Patrick Soucy
Network Engineer
University of Maine System

T: 207-561-3526
F: 207-561-3531

MaineREN, Maine's Research and Education Network
www.maineren.net


Re: Open source hardware

2014-01-07 Thread Vlade Ristevski
Sorry to get off topic, but is there a company that you can recommend? 
The price of the Cisco single mode GLC-LH-SMD= is killing me. I see a 
bunch of third party  ones on Amazon and CDW but I'd to love to get my 
hands one that has the correct vendor code without going and trying them 
all.


On 1/3/2014 7:48 AM, Ray Soucy wrote:

You actually buy brand-name SFP's? That's like buying the gold-plated HDMI
Monster Cable at Best Buy at markup ...

I just find the the companies that the vendors contract to make their OEM
SFP's and buy direct.  Same SFP from the same factory except one has a
Cisco sticker. ;-)

You can even get them with the correct vendor code, been doing this for
years and there is no difference in failure rate or quality and we go
through hundreds of SFPs.





Vlad
Network Manager


Re: Open source hardware

2014-01-06 Thread TGLASSEY
Arnd - the German Government is most likely a partner meaning 
overloading the NSA is pointless if you could.


Todd

On 1/5/2014 1:15 AM, Arnd Vehling wrote:

Hi,

On 04.01.2014 21:07, Daniël W. Crompton wrote:

To my surprise I am seeing a theme fatalistic acceptance in this thread,


thats not really suprising. Then most poeple dont understand the 
implications "this" has.



A number have mentioned that if you are targeted there is little you can
do, and this is something that I agree with to a certain extent.


Here i agree too. But i think it should be in possible to overload 
them by mass-creating fake data and honey pots. They dont have endless 
resources especially when it comes to decrypting. So, if just 10% of 
the "aware persons" start firing up "NSA honeypots" they get a 
resource problem and will fail at selecting targets.


// Arnd





--
-

Personal Email - Disclaimers Apply




Re: Open source hardware

2014-01-05 Thread Arnd Vehling

Hi,

On 04.01.2014 21:07, Daniël W. Crompton wrote:

To my surprise I am seeing a theme fatalistic acceptance in this thread,


thats not really suprising. Then most poeple dont understand the 
implications "this" has.



A number have mentioned that if you are targeted there is little you can
do, and this is something that I agree with to a certain extent.


Here i agree too. But i think it should be in possible to overload them 
by mass-creating fake data and honey pots. They dont have endless 
resources especially when it comes to decrypting. So, if just 10% of the 
"aware persons" start firing up "NSA honeypots" they get a resource 
problem and will fail at selecting targets.


// Arnd



Re: Open source hardware

2014-01-04 Thread Mark Tinka
On Friday, January 03, 2014 03:33:56 PM Saku Ytti wrote:

> Right now, if you need perfomance, you're going to have
> to buy something like bcom chip and then cumulusnetworks
> linux on top of it, it's as close to 'open source' as
> you're going to get with good performance. And this is
> more or less DC stuff, SP market needs more intelligent
> chips than those ASICs, and I don't think there anything
> 'open source' in the market place for NPU stuff.

Indeed.

Broadcom are making lots of interesting cheap and fast 
ASIC's, but they're data centre focused, or serve a specific 
platform feature set with Cisco/Juniper that has a number of 
restrictions, just to keep the costs down.

Mark.


signature.asc
Description: This is a digitally signed message part.


Re: Open source hardware

2014-01-04 Thread Nick Hilliard
On 04/01/2014 11:38, Saku Ytti wrote:
> Right now some of the big name vendors are running really archaic and naive
> control-planes, and it's hard for them internally to justify project to
> rebuild it all, because customers will largely accept even the shitty
> control-plane, because that is only thing you get with that hardware.

Re: crappy control planes, I wouldn't particularly mind paying licensing
fees if there were a choice about what software to use.  But there isn't
and you end up with with the worst of all worlds: no choice about which
particular control plane software (and consequently which bug+feature set)
you want to run, no incentive for vendors to deal with enhancements other
than on the basis of how much revenue they'll create in the next quarter,
and no option but to pay twice: once for the hardware and a second time if
you actually want to use it.  Open source control planes may not fix all
these problems, but there is no doubt that they will put pressure on
vendors to compete on uncomfortably close turf.

Nick




Re: Open source hardware

2014-01-04 Thread Daniël W . Crompton
On 4 January 2014 08:34, Arnd Vehling  wrote:

> On 04.01.2014 07:49, Darren Pilgrim wrote:
>
>  Dell, HP, Cisco, etc. were named because the leaked docs mention
>> hardware-specific BIOS/firmware bugging such as ILO piggybacking in a
>> Proliant. I think it's foolhardy believing they wouldn't have similar
>> attacks for just about everything.
>>
>
> Highly unlickely they have similiar attacks for everything. They for sure
> can make em if they see fit but they dont have backdoors to everything.


To my surprise I am seeing a theme fatalistic acceptance in this thread, it
seems like some who have been kind enough to answer privately or publicly
are of the opinion that either everything is already backdoored by the US
designers and/or by the Chinese manufacturers. I doubt however that any of
these people would hand over their root passwords to the US or Chinese
government willingly.

A number have mentioned that if you are targeted there is little you can
do, and this is something that I agree with to a certain extent. This
doesn't mean you leave the barndoor open.

D.

-- 
Daniël W. Crompton 




http://specialbrands.net/

   



Re: Open source hardware

2014-01-04 Thread Daniël W . Crompton
On 4 January 2014 00:49, Darren Pilgrim  wrote:

> Why would you think other platforms would be any safer?  The NSA plants
> those bugs with interdiction operations.  They could similarly install
> eavesdroppers in the USB/serial links of your KVM switches and terminal
> servers and capture your root/admin/console passwords.


In my opinion there is a clear difference between being targeted and having
a backdoor in your network equipment by default.

D.

-- 
Daniël W. Crompton 




http://specialbrands.net/

   



Re: Open source hardware

2014-01-04 Thread Saku Ytti
On (2014-01-04 12:08 +0100), Benno Overeinder wrote:

> No hands-on experience with Cumulus Networks equipment, but from
> what I have heard I like their approach to open hardware/software
> for routing equipment.  It is flexible what you want to configure
> and run (all open source software).  For the hardware switching
> support they license their Switch HAL module.

I love the notion of COTS control-plane software, it has potential to
fundamentally change the market dynamics.
COTS ASICs (bcom the most prominient) and COTS NPU (ezchip, xelerated/marvell)
have done lot of good to the market in terms of features/performance/price.

Right now some of the big name vendors are running really archaic and naive
control-planes, and it's hard for them internally to justify project to
rebuild it all, because customers will largely accept even the shitty
control-plane, because that is only thing you get with that hardware.

Company doing only COTS control-plane can't get away with shitty software,
it's their only product. And conversely, they can get away having many
generation of incompatible operating systems, as older customers will keep on
wanting+paying on the development of the older version while newer greenfield
customers will want to start with the latest generation.
This creates pressure on the established companies to have great
control-plane, not some 20 year old TTM house of cards.

-- 
  ++ytti



Re: Open source hardware

2014-01-04 Thread Benno Overeinder

On 3-1-2014 14:33, Saku Ytti wrote:

Right now, if you need perfomance, you're going to have to buy something like
bcom chip and then cumulusnetworks linux on top of it, it's as close to 'open
source' as you're going to get with good performance.
And this is more or less DC stuff, SP market needs more intelligent chips than
those ASICs, and I don't think there anything 'open source' in the market
place for NPU stuff.


No hands-on experience with Cumulus Networks equipment, but from what I 
have heard I like their approach to open hardware/software for routing 
equipment.  It is flexible what you want to configure and run (all open 
source software).  For the hardware switching support they license their 
Switch HAL module.


Cheers,

-- Benno



Re: Open source hardware

2014-01-03 Thread Arnd Vehling

On 04.01.2014 07:49, Darren Pilgrim wrote:


Dell, HP, Cisco, etc. were named because the leaked docs mention
hardware-specific BIOS/firmware bugging such as ILO piggybacking in a
Proliant. I think it's foolhardy believing they wouldn't have similar
attacks for just about everything.


Highly unlickely they have similiar attacks for everything. They for 
sure can make em if they see fit but they dont have backdoors to everything.


// Arnd




Re: Open source hardware

2014-01-03 Thread Darren Pilgrim

On 1/3/2014 2:05 AM, Daniël W. Crompton wrote:

Good point Jimmy, there is a world of hurt involved, although it may be
slightly less painless when you realize that the alternative is: "*the NSA
[who] has modified the firmware of computers and network hardware—including
systems shipped by Cisco, Dell, Hewlett-Packard, Huawei, and Juniper
Networks—to give its operators both eyes and ears inside the offices the
agency has targeted.*"[1]


Why would you think other platforms would be any safer?  The NSA plants 
those bugs with interdiction operations.  They could similarly install 
eavesdroppers in the USB/serial links of your KVM switches and terminal 
servers and capture your root/admin/console passwords.


Dell, HP, Cisco, etc. were named because the leaked docs mention 
hardware-specific BIOS/firmware bugging such as ILO piggybacking in a 
Proliant.  I think it's foolhardy believing they wouldn't have similar 
attacks for just about everything.




Re: Open source hardware

2014-01-03 Thread Saku Ytti
On (2014-01-03 07:48 -0500), Ray Soucy wrote:
> 
> Juniper is a FreeBSD shop, and Cisco's new OS lines are based on Linux.
>  Ciena is largely based on Linux as well.  In poking around at these
> platforms recently one of the big things I'm noticing is that there is a
> lot less done in hardware than we traditionally saw, especially from Cisco.

I'm not sure which platforms you refer to. But if we look at SP segment we're
talking about JNPR M, MX, T, PTX or Cisco ASR9k, NCS6k, CRS-1.

JNPR is indeed FreeBSD, but FreeBSD is used very sparsely, to boot box up and
to run RPD, which is essentially router-control-plane-in-a-process, it runs
all routing protocols and configures hardware.
ASR9k, CRS-1 run IOS-XR on QNX and NCS6k on Linux and there at least Cisco
capitalizes on OS scheduling, it's not single fat process on top of OS.

All of these boxes do all packet pushing in NPU (ezchip, trio, ichip...)

For IOS XE boxes, it's almost same as JNPR, except instead of single process
single threaded RPD, IOSd is actually running several threads.

> by under-sizing and over-pricing their CPUs for years.  But when you have a
> modern server-grade platform, multi-Gigabit performance, even with
> significant levels of packet processing and small packet sizes, is a joke.
>  So at least for the low end of the spectrum there is a huge savings for
> equal (often better) performance.

Low end has always been using COTS CPU, RISC, PPC etc, so not much has changed
there. For low end, linux pc can be competitive in some applications.

> With the new Intel DPDK stuff, Intel is claiming 80M PPS performance on a
> standard Xeon platform:
> http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/packet-processing-is-enhanced-with-software-from-intel-dpdk.html

DPDK is super interesting and it shows Intel is looking at the NPU market,
unfortunately these numbers have nothing to do with real-life application,
lookup against million+ routes, ACLs, QoS etc.
But maybe not in too distant future x86 Intel is usable as NPU, Intel seems to
be looking NPU market demands when designing new x86 chips.

Right now, if you need perfomance, you're going to have to buy something like
bcom chip and then cumulusnetworks linux on top of it, it's as close to 'open
source' as you're going to get with good performance.
And this is more or less DC stuff, SP market needs more intelligent chips than
those ASICs, and I don't think there anything 'open source' in the market
place for NPU stuff.


-- 
  ++ytti



Re: Open source hardware

2014-01-03 Thread Thomas Nadeau

On Jan 3, 2014:12:01 AM, at 12:01 AM, Jimmy Hess  wrote:

> On Thu, Jan 2, 2014 at 8:53 PM, Andrew Duey <
> andrew.d...@widerangebroadband.net> wrote:
> 
>> I'm surprised nobody's mentioned vyatta.org or the new fork of VyOs.  We
>> are currently using the vyatta community edition and so far it's been good
>> to to us.  It depends on your hardware and how small of an ISP you are but
>> it might be a great open source fit for you.
> 
> 
> The orig. author has potentially set course for a world of hurt --  if the
> plan is to scrap robust packaged highly-validated gear having separate
> hardware forwarding planes and ASIC-driven filtering,  to stick cheap x86
> servers in the SP core and internet borders.
> 
> Sure... anyone can install Vyatta on a x86 server,   but  assembly of all
> the pieces and full validation for a resilient platform comparable to
> carrier grade gear, for a mission critical network,  should be a bit more
> involved than that.
> 
> Next up   how to build your own  10-Gigabit  SFPs to avoid paying for
> expensive brand-name SFPs,  by putting together some chips,  wires,  fiber,
> and tying it all together with a piece of duck tape
> 
> just saying... :)

That does seem a bit harsh given there are numerous examples of 
companies out there successfully putting together and deploying their own 
switches/routers in production. It may require significant resources and not be 
for the faint of heart, but from what I've seen, its far from a bailing wire 
and bubblegum operation.

--Tom



> 
> 
>> --Andrew Duey
>> 
> --
> -JH
> 



signature.asc
Description: Message signed with OpenPGP using GPGMail


RE: Open source hardware

2014-01-03 Thread Raymond Burkholder
> 
> Vyatta and now VyOS are important projects for networking.  We really need
> to get away from locked down non-free hardware and software for critical
> infrastructure.
> 
> It's natural that most of the people in this community (myself included)
> will be fans of companies like Cisco and Juniper and dismiss anything
else,
> but that mindset for me change when I deployed 100+ whitebox units 3
> years
> ago and saved nearly a million in the process.
> 

If all you want to do is push regular packets around, these opensource
alternatives might be adequate to the task.  

But many networks catering to business endpoints deal with private circuit
issues.  Which generally leads to an MPLS/VPLS based infrastructure.  Which
I havn't seen in a reliable opensource flavor.  But I could be mistaken.


-- 
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.




Re: Open source hardware

2014-01-03 Thread Ray Soucy
You actually buy brand-name SFP's? That's like buying the gold-plated HDMI
Monster Cable at Best Buy at markup ...

I just find the the companies that the vendors contract to make their OEM
SFP's and buy direct.  Same SFP from the same factory except one has a
Cisco sticker. ;-)

You can even get them with the correct vendor code, been doing this for
years and there is no difference in failure rate or quality and we go
through hundreds of SFPs.

It is nice to have a solution provider if you're only looking at one unit,
but if you're deploying a large amount then building and testing your own
configuration really isn't that hard and will save you a lot of money.  You
can even contract an OEM appliance vendor to take care of the actual build
for you and they'll usually provide 3-year replacement on the hardware.
(I've found "Sourcecode" to be the best price-wise for smaller projects).
As a bonus they'll slap whatever branding you want on the thing for that
professional touch.

Vyatta and now VyOS are important projects for networking.  We really need
to get away from locked down non-free hardware and software for critical
infrastructure.

It's natural that most of the people in this community (myself included)
will be fans of companies like Cisco and Juniper and dismiss anything else,
but that mindset for me change when I deployed 100+ whitebox units 3 years
ago and saved nearly a million in the process.

Juniper is a FreeBSD shop, and Cisco's new OS lines are based on Linux.
 Ciena is largely based on Linux as well.  In poking around at these
platforms recently one of the big things I'm noticing is that there is a
lot less done in hardware than we traditionally saw, especially from Cisco.


Having your networking in silicon is great when you have a 100 MHz CPU;
Cisco even conditioned us to be terrified of anything being punted to CPU
by under-sizing and over-pricing their CPUs for years.  But when you have a
modern server-grade platform, multi-Gigabit performance, even with
significant levels of packet processing and small packet sizes, is a joke.
 So at least for the low end of the spectrum there is a huge savings for
equal (often better) performance.

As I mentioned before I haven't done much with 10-Gigabit, but I imagine
with Intel-based cards on a modern PCIe bus that you can at least get
entry-level performance.  Sometimes the biggest push for 10G is avoiding a
2G or 4G port-channel.

With the new Intel DPDK stuff, Intel is claiming 80M PPS performance on a
standard Xeon platform:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/packet-processing-is-enhanced-with-software-from-intel-dpdk.html

Eventually, DPDK support will likely start being included in projects like
VyOS, perhaps in Linux in general.

As for VyOS, the project is starting to get some momentum and is run by
former Vyatta employees and even some people from UBNT.  I think we'll see
some good stuff from them in the future.  The 1.0 release is solid from
what I've seen (and even fixes some bugs Vyatta hasn't yet).




On Fri, Jan 3, 2014 at 12:01 AM, Jimmy Hess  wrote:

> On Thu, Jan 2, 2014 at 8:53 PM, Andrew Duey <
> andrew.d...@widerangebroadband.net> wrote:
>
> > I'm surprised nobody's mentioned vyatta.org or the new fork of VyOs.  We
> > are currently using the vyatta community edition and so far it's been
> good
> > to to us.  It depends on your hardware and how small of an ISP you are
> but
> > it might be a great open source fit for you.
>
>
> The orig. author has potentially set course for a world of hurt --  if the
> plan is to scrap robust packaged highly-validated gear having separate
> hardware forwarding planes and ASIC-driven filtering,  to stick cheap x86
> servers in the SP core and internet borders.
>
> Sure... anyone can install Vyatta on a x86 server,   but  assembly of all
> the pieces and full validation for a resilient platform comparable to
> carrier grade gear, for a mission critical network,  should be a bit more
> involved than that.
>
> Next up   how to build your own  10-Gigabit  SFPs to avoid paying for
> expensive brand-name SFPs,  by putting together some chips,  wires,  fiber,
> and tying it all together with a piece of duck tape
>
> just saying... :)
>
>
> > --Andrew Duey
> >
> --
> -JH
>



-- 
Ray Patrick Soucy
Network Engineer
University of Maine System

T: 207-561-3526
F: 207-561-3531

MaineREN, Maine's Research and Education Network
www.maineren.net


Re: Open source hardware

2014-01-03 Thread Daniël W . Crompton
Good point Jimmy, there is a world of hurt involved, although it may be
slightly less painless when you realize that the alternative is: "*the NSA
[who] has modified the firmware of computers and network hardware—including
systems shipped by Cisco, Dell, Hewlett-Packard, Huawei, and Juniper
Networks—to give its operators both eyes and ears inside the offices the
agency has targeted.*"[1]

There's already a world of hurt involved when you can't trust your
equipment because they potentially have backdoors in them.

D.


1.
http://arstechnica.com/information-technology/2013/12/inside-the-nsas-leaked-catalog-of-surveillance-magic/






Oplerno is built upon empowering faculty and students We want you to found
(and fund) Oplerno with
us
[image: Support Us
Here]
-- 
Daniël W. Crompton 




http://specialbrands.net/

   




On 3 January 2014 06:01, Jimmy Hess  wrote:

> On Thu, Jan 2, 2014 at 8:53 PM, Andrew Duey <
> andrew.d...@widerangebroadband.net> wrote:
>
> > I'm surprised nobody's mentioned vyatta.org or the new fork of VyOs.  We
> > are currently using the vyatta community edition and so far it's been
> good
> > to to us.  It depends on your hardware and how small of an ISP you are
> but
> > it might be a great open source fit for you.
>
>
> The orig. author has potentially set course for a world of hurt --  if the
> plan is to scrap robust packaged highly-validated gear having separate
> hardware forwarding planes and ASIC-driven filtering,  to stick cheap x86
> servers in the SP core and internet borders.
>
> Sure... anyone can install Vyatta on a x86 server,   but  assembly of all
> the pieces and full validation for a resilient platform comparable to
> carrier grade gear, for a mission critical network,  should be a bit more
> involved than that.
>
> Next up   how to build your own  10-Gigabit  SFPs to avoid paying for
> expensive brand-name SFPs,  by putting together some chips,  wires,  fiber,
> and tying it all together with a piece of duck tape
>
> just saying... :)
>
>
> > --Andrew Duey
> >
> --
> -JH
>


Re: Open source hardware

2014-01-02 Thread Jorge Amodio

I use a RouterBoard with RouterOS and afaik not the hardware nor the software 
are open

-Jorge

> On Jan 2, 2014, at 9:53 AM, Faisal Imtiaz  wrote:
> 
> Have you looked at Mikrotik.com (Software) and Routerboard.com (Hardware)
> 



Re: Open source hardware

2014-01-02 Thread Jimmy Hess
On Thu, Jan 2, 2014 at 8:53 PM, Andrew Duey <
andrew.d...@widerangebroadband.net> wrote:

> I'm surprised nobody's mentioned vyatta.org or the new fork of VyOs.  We
> are currently using the vyatta community edition and so far it's been good
> to to us.  It depends on your hardware and how small of an ISP you are but
> it might be a great open source fit for you.


The orig. author has potentially set course for a world of hurt --  if the
plan is to scrap robust packaged highly-validated gear having separate
hardware forwarding planes and ASIC-driven filtering,  to stick cheap x86
servers in the SP core and internet borders.

Sure... anyone can install Vyatta on a x86 server,   but  assembly of all
the pieces and full validation for a resilient platform comparable to
carrier grade gear, for a mission critical network,  should be a bit more
involved than that.

Next up   how to build your own  10-Gigabit  SFPs to avoid paying for
expensive brand-name SFPs,  by putting together some chips,  wires,  fiber,
and tying it all together with a piece of duck tape

just saying... :)


> --Andrew Duey
>
--
-JH


Re: Open source hardware

2014-01-02 Thread Andrew Duey
I'm surprised nobody's mentioned vyatta.org or the new fork of VyOs.  We are 
currently using the vyatta community edition and so far it's been good to to 
us.  It depends on your hardware and how small of an ISP you are but it might 
be a great open source fit for you.

--Andrew Duey

On Jan 2, 2014, at 10:37 AM, Chris Russell  wrote:

> 
>> haven't been able to find anything that would fulfill the requirements that
>> a smallish ISP might have.
> 
> The Cumulus guys might be able to provide some pointers ?
> 
> http://cumulusnetworks.com/
> 
> Chris
> 
> 



Re: Open source hardware

2014-01-02 Thread Chris Russell


haven't been able to find anything that would fulfill the 
requirements that

a smallish ISP might have.


 The Cumulus guys might be able to provide some pointers ?

 http://cumulusnetworks.com/

Chris




Re: Open source hardware

2014-01-02 Thread Matthew Walster
On 2 January 2014 15:53, Faisal Imtiaz  wrote:

> Have you looked at Mikrotik.com (Software) and Routerboard.com (Hardware)
>

That's not Open Source.

M​​


Re: Open source hardware

2014-01-02 Thread Faisal Imtiaz
Have you looked at Mikrotik.com (Software) and Routerboard.com (Hardware)

Faisal Imtiaz
Snappy Internet & Telecom
7266 SW 48 Street
Miami, FL 33155
Tel: 305 663 5518 x 232

Help-desk: (305)663-5518 Option 2 or Email: supp...@snappytelecom.net 

- Original Message -
> From: "Daniël W. Crompton" 
> To: "nanog" 
> Sent: Thursday, January 2, 2014 10:48:39 AM
> Subject: Open source hardware
> 
> Hi,
> 
> a friend of mine mentioned he wants to migrate away from carrier grade
> equipment such as Juniper and Cisco to open source hardware. Both of us
> haven't been able to find anything that would fulfill the requirements that
> a smallish ISP might have.
> 
> Does anybody here have any advise?
> 
> Kind regards and best wishes for the new year,
> Daniël
> 
> 
> 
> Oplerno is built upon empowering faculty and students We want you to found
> (and fund) Oplerno with
> us<http://www.indiegogo.com/projects/oplerno-a-new-and-affordable-higher-education?utm_source=email&utm_medium=daniel&utm_content=signaturetext&utm_campaign=indiegogo>
> [image: Support Us
> Here]<http://www.indiegogo.com/projects/oplerno-a-new-and-affordable-higher-education?utm_source=email&utm_medium=daniel&utm_content=signaturecta&utm_campaign=indiegogo>
> --
> Daniël W. Crompton 
> 
> <http://specialbrands.net/>
> 
> <http://specialbrands.net/>
> http://specialbrands.net/
> 
><http://twitter.com/webhat>
> <http://www.facebook.com/webhat><http://plancast.com/webhat><http://www.linkedin.com/in/redhat>
> 



Open source hardware

2014-01-02 Thread Daniël W . Crompton
Hi,

a friend of mine mentioned he wants to migrate away from carrier grade
equipment such as Juniper and Cisco to open source hardware. Both of us
haven't been able to find anything that would fulfill the requirements that
a smallish ISP might have.

Does anybody here have any advise?

Kind regards and best wishes for the new year,
Daniël



Oplerno is built upon empowering faculty and students We want you to found
(and fund) Oplerno with
us<http://www.indiegogo.com/projects/oplerno-a-new-and-affordable-higher-education?utm_source=email&utm_medium=daniel&utm_content=signaturetext&utm_campaign=indiegogo>
[image: Support Us
Here]<http://www.indiegogo.com/projects/oplerno-a-new-and-affordable-higher-education?utm_source=email&utm_medium=daniel&utm_content=signaturecta&utm_campaign=indiegogo>
-- 
Daniël W. Crompton 

<http://specialbrands.net/>

<http://specialbrands.net/>
http://specialbrands.net/

   <http://twitter.com/webhat>
<http://www.facebook.com/webhat><http://plancast.com/webhat><http://www.linkedin.com/in/redhat>