Re: 100G - Whitebox

2017-12-04 Thread Stephen Fulton
> Midwest-IX > http://www.midwest-ix.com > > - Original Message - > > From: "Nick Hilliard" <n...@foobar.org> > To: "Mikael Abrahamsson" <swm...@swm.pp.se> > Cc: "NANOG list" <nanog@nanog.org> > Sent: Monday, Aug

Re: 100G - Whitebox

2017-12-04 Thread Mike Hammett
hamsson" <swm...@swm.pp.se> Cc: "NANOG list" <nanog@nanog.org> Sent: Monday, August 21, 2017 6:10:17 AM Subject: Re: 100G - Whitebox Mikael Abrahamsson wrote: > On Sun, 20 Aug 2017, Nick Hilliard wrote: >> Mostly you can engineer around this, but it's not

Re: 100G - Whitebox

2017-08-21 Thread Coyo Stormcaller
On Mon, 21 Aug 2017 12:10:17 +0100 Nick Hilliard wrote: > IOW, know your requirements and choose your tools to match. Same as > with all engineering. Very fascinating read. Thank you for posting.

Re: 100G - Whitebox

2017-08-21 Thread Jérôme Nicolle
Hello Mike, Le 20/08/2017 à 17:45, Mike Hammett a écrit : > Looking at cost effective options brings us to whitebox switches. Obviously > there's a wide range of hardware vendors and there are a few OSes available > as well. Cumulus seems to be the market leader, while IPinFusion seems to be >

Re: 100G - Whitebox

2017-08-21 Thread Nick Hilliard
Mikael Abrahamsson wrote: > On Sun, 20 Aug 2017, Nick Hilliard wrote: >> Mostly you can engineer around this, but it's not as simple as saying >> that small-buffer switches aren't suitable for an IXP. > > Could you please elaborate on this? > > How do you engineer around having basically no

Re: 100G - Whitebox

2017-08-20 Thread Mikael Abrahamsson
On Sun, 20 Aug 2017, Nick Hilliard wrote: Mostly you can engineer around this, but it's not as simple as saying that small-buffer switches aren't suitable for an IXP. Could you please elaborate on this? How do you engineer around having basically no buffers at all, and especially if these

Re: 100G - Whitebox

2017-08-20 Thread Nick Hilliard
Fredrik Korsbäck wrote: > The only viable merchant silicon chip that would be useful for a IXP > is from the StrataDNX-family which house the > jericho/qumran/petra/arad chips from broadcom. No packetbuffer in the > exhangepoint will shred performance significantly, especially when > one of your

Re: 100G - Whitebox

2017-08-20 Thread Fredrik Korsbäck
The only viable merchant silicon chip that would be useful for a IXP is from the StrataDNX-family which house the jericho/qumran/petra/arad chips from broadcom. No packetbuffer in the exhangepoint will shred performance significantly, especially when one of your bursty 100G customers starts

Re: 100G - Whitebox

2017-08-20 Thread Bill Woodcock
Why don't we just swap out your 40g switch for a 100g switch? You've had the 40g one for a while, and we anticipate upgrades every 18-24 months. -Bill > On Aug 20, 2017, at 08:46, Mike Hammett wrote: > > I first sent to an IX-specific mailing list, but

Re: 100G - Whitebox

2017-08-20 Thread Raymond Burkholder
On 08/20/17 13:30, Mike Hammett wrote: DNX/Jericho would have sufficient buffers to handle the rate conversions? You could try Mellanox. Some of the promotional stuff I've seen/heard indicates their focus on appropriate sized buffers & low packet loss on rate conversion. - Mike

Re: 100G - Whitebox

2017-08-20 Thread Mike Hammett
e Hammett" <na...@ics-il.net> Cc: "NANOG list" <nanog@nanog.org> Sent: Sunday, August 20, 2017 11:07:07 AM Subject: Re: 100G - Whitebox > On Aug 20, 2017, at 08:45, Mike Hammett <na...@ics-il.net> wrote: > > Any particular hardware platforms

Re: 100G - Whitebox

2017-08-20 Thread Joel Jaeggli
> On Aug 20, 2017, at 08:45, Mike Hammett wrote: > > Any particular hardware platforms to go towards or avoid? Broadcom Tomahawk > seems to be quite popular with varying control planes. LINX went Edgecore, > which was on my list given my experience with other Accton