Re: Paypal outage?

[Mark Tinka]

On Sunday, January 29, 2012 03:09:10 AM Chris wrote:

> I switched browsers and it seemed to clear it up. Just
> never seen an odd error like that before..

Tried emptying your browser cache and limiting how much it 
grows over time? This helped solve a similar issue when my 
browser assumed my bank's Internet banking web site was 
under maintenance for 2 weeks :-).

Mark.


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

MPLS Traffic Engineering Help

[Jeremy]

Hi Everyone,
I could use a little help on MPLS and Traffic Engineering. Right now I'm
just trying to wrap my head around it. I currently have a couple tunnels
going in either direction, those are working fine (but certainly took me
long enough to get them working!) and I can direct traffic over them easy
enough. Now I'm looking into allocating/reserving bandwidth for a given
tunnel and if possible have it react to increased network loads and
recalculate its path if need be.

(Poor) Example:
I have two paths that two different tunnels (A and B) that will go over a
T-1 and 100mbps ethernet. A is more important than B. When traffic is low,
I'd like them both to go over the 100mbps link so either tunnel can fill
the pipe, but if Tunnel A requires more bandwidth, Tunnel B should react
and move to the T-1. Is this possible? or am I horribly confused?

I'm not really looking for the exact commands or the 'answer' to this
problem, but some guidance would be greatly appreciated. I'm working with
Cisco gear, 2800's and such. This is purely an academic exercise.

Thanks!
Jeremy

Re: US DOJ victim letter

[Ryan Gelobter]

The e-mail states it was sent to the specific e-mail address because it was
listed as the contact in WHOIS. Although you can opt-out from these notices
I believe as part of the DNS Changer case the court ordered the FBI to
notify ISPs.

On Sat, Jan 28, 2012 at 10:39 AM, John Peach wrote:

> On Sat, 28 Jan 2012 16:30:47 +
> bmann...@vacation.karoshi.com wrote:
>
> > On Fri, Jan 27, 2012 at 10:20:08PM -0500, Martin Hannigan wrote:
> > > On Fri, Jan 27, 2012 at 1:32 PM, Randy Epstein 
> wrote:
> > > >
> [snip]
> >   I missed the part where ARIN turned over its address database w/
> associatedd
> >   registration information to the Fed ... I mean I've always
> advocated for
> >   LEO access, but ther has been significant pushback fromm the
> community on
> >   unfettered access to that data.  As I recall, there are even
> policies and
> >   processes to limit/restrict external queries to prevent a DDos of
> the whois
> >   servers.  And some fairly strict policies on who gets dumps of the
> address
> >   space.  As far as I know (not very far) bundling the address
> database
> >   -and- the registration data are not available to mere mortals.
> >
> >   So - just how DID the Fed get the data w/o violating ARIN policy?
> >
> > /bill
> >
> >
>
> Ours came from our whois information.
>
> --
> John
>
>

Re: XBOX 720: possible digital download mass service.

[J. M. D. Patterson, CEO]

Ahem:

"Never underestimate the bandwidth of a carrier pidgeon with a 4GB USB
stick"

http://news.bbc.co.uk/2/hi/8248056.stm


John Patterson
a.k.a "InetDaemon"


-Original Message-
Date: Sat, 28 Jan 2012 11:35:59 -0500
From: Lamar Owen 
To: nanog@nanog.org
Subject: Re: XBOX 720: possible digital download mass service.
Message-ID: <201201281136.00093.lo...@pari.edu>
Content-Type: Text/Plain;   charset="US-ASCII"

On Friday, January 27, 2012 05:56:19 AM Randy Bush wrote:
> > Can internet in USA support that?   Call of Duty 15 releases may 2014
> > and 30 million gamers start downloading a 20 GB files.  Would the 
> > internet collapse like a house of cards?.

> not a problem.  the vast majority of the states is like a developing 
> country [0], the last mile is pretty much a tin can and a string.  so 
> this will effectively throttle the load.

Being in 'the middle of nowhere' as I write, even we are a few notches above
RFC1149 capabilities.  As one visitor to our site (who had been recently to
NRAO Greenbank) said 'if this isn't the middle of nowhere, you can probably
see it from here.'

Our base DSL is 7Mb/s down, 0.5Mb/s up, with 11Mb/s down and 1Mb/s up
available to over 99% of our very rural county.  We (work) have 1Gb/s on the
local loop fiber pair, throttled to the amount of IP we actually pay for at
the ISP's PoP.

Now if RFC1149 supported jumbo frames, it might give tin-cans-and-string a
run for its money

Re: XBOX 720: possible digital download mass service.

[Pete Carah]

On 01/28/2012 12:01 PM, Josh Hoppes wrote:
> ...

> There is also the system
> Blizzard is using for World of Warcraft where the game can stream
> content down while playing. Most of these publishers/developers
> already have pretty good grasps on what capabilities are at their
> disposal thanks to the DLC model they have now, they will just be
> going an order of magnitude larger on the downloads. I wonder how many
> will also attempt to leverage P2P models as well to assist CDNs,
Blizzard already does this, torrent-like downloads for larger patch
sets.  At least,
unlike torrent itself, the upload direction does stop when you stop the
game...
> cheaper for them and maybe even a revenue generator for ISPs charging
> for transfer overages.
-- Pete

Re: XBOX 720: possible digital download mass service.

[Josh Hoppes]

I've seen this discussion show up in a number of venues lately. I'm
not at all surprised about the trend as I've been using Steam for a
few years now. I expect they will take a similar path and continue to
sell physical medium with keys to tie the game to an account, and do
staged downloads using encrypted data which is unlocked at release
time. The biggest content for games is really art assets, and much of
that work is done months ahead of release and unlikely to change,
while fine tuning and game logic (binaries) are small enough that
staging downloads in tiers should be easy. There is also the system
Blizzard is using for World of Warcraft where the game can stream
content down while playing. Most of these publishers/developers
already have pretty good grasps on what capabilities are at their
disposal thanks to the DLC model they have now, they will just be
going an order of magnitude larger on the downloads. I wonder how many
will also attempt to leverage P2P models as well to assist CDNs,
cheaper for them and maybe even a revenue generator for ISPs charging
for transfer overages.

Re: Fiber outage in Miami

[Jason LeBlanc]

We got the same RFO.  BS.

On 01/28/2012 01:36 PM, Randy Epstein wrote:

Anyone has seen on gotten a  RFA  or a deeper explanation of what
happened from them ?


Faisal Imtiaz
Snappy Internet&   Telecom
7266 SW 48 Street
Miami, Fl 33155
Tel: 305 663 5518 x 232
Helpdesk: 305 663 5518 option 2 Email: supp...@snappydsl.net

Yes.  They blamed/burned the local crew and suggested that they fired
them.  Yes, they put this in the RFO.  I have it, but I'm having legal
determine if it can be made public record.

Randy

Re: Paypal outage?

[Chris]

I switched browsers and it seemed to clear it up. Just never seen an
odd error like that before..

Re: XBOX 720: possible digital download mass service.

[Joel jaeggli]

On 1/27/12 02:35 , Tei wrote:
> Can internet in USA support that?   Call of Duty 15 releases may 2014
> and 30 million gamers start downloading a 20 GB files.  Would the
> internet collapse like a house of cards?.

Given the way the these things are staged, the pre-order/pre-load model
works pretty well. I would expect that many users sufficiently
interested in Battle Field 3 to acquire it for launch day, already had a
copy cached locally that unlocked itself at the right time. Mine did.

To the extent that cached content can be tweaked via patching the
distribution system can substantially anticipate the release of product.

> If not, will be internet USA ready for the next next generation? ( 2018 ).
> 
> 

Re: XBOX 720: possible digital download mass service.

[Joel jaeggli]

On 1/27/12 06:13 , Eric Tykwinski wrote:
> The PS Vita still uses a proprietary memory card format, so it's not just
> download only.
> The best example of download only would be OnLive, which basically is a game
> system that only delivers on demand games.

Onlive isn't download at all. the games play in the cloud and the
input/output is streaming to from your devices.

Steam, EA Origin, Xbox live are all examples of download delivery systems.

> IMHO, it's the market that will determine whether this is the right choice
> in the long run.
> It's a creative way to eliminate the used market and stop piracy, but if the
> consumers don't join up like the PSP Go, it will eventually fail.
> 
> Sincerely,
> 
> Eric Tykwinski
> TrueNet, Inc.
> P: 610-429-8300
> F: 610-429-3222
> 
> -Original Message-
> From: -Hammer- [mailto:bhmc...@gmail.com] 
> Sent: Friday, January 27, 2012 9:02 AM
> To: nanog@nanog.org
> Subject: Re: XBOX 720: possible digital download mass service.
> 
> Here's your baseline: Sony Vita. They already tossed the UMD out with the
> PSP-GO and that failed miserably. Now they are trying again to go to digital
> only with the Vita. It's not the scale of PS3 or XBOX360 but it may be a
> good way to gauge the potential success of the concept.
> 
> -Hammer-
> 
> "I was a normal American nerd"
> -Jack Herer
> 
> 
> 
> On 1/27/2012 7:34 AM, Jared Mauch wrote:
>> It's already done on a similar scale when apple releases new software for
> their mobile devices.
>>
>> Just don't do it if you are on a low cap plan (eg: mobile, satellite etc).
> Caps will be the new market discriminator IMHO.
>>
>> Jared Mauch
>>
>> On Jan 27, 2012, at 3:35 AM, Tei  wrote:
>>
>>> Can internet in USA support that?   Call of Duty 15 releases may 2014
>>> and 30 million gamers start downloading a 20 GB files.  Would the 
>>> internet collapse like a house of cards?.
>>
> 
> 
> 

RE: Craigslist outage

[Frank Bulk]

Much documented here:
http://forums.verizon.com/t5/FiOS-Internet/DNS-issues-in-SoCal/td-p/393781

The thread is titled "DNS", but just ignore and read through.  I don't
understand how Verizon FiOS hasn't resolved this after two weeks.

Frank

-Original Message-
From: Matthew Black [mailto:matthew.bl...@csulb.edu] 
Sent: Saturday, January 28, 2012 4:00 AM
To: nanog@nanog.org
Subject: RE: Craigslist outage

Confirmed that it's Verizon FIOS. I remote logged into a system at work and
had no trouble.

I'm dealing with tech support person that says "nobody blocks websites or
changes routing tables."  Big sigh.

Tech trying to get a supervisor and just came back with "he has another
customer with the same problem."

Taking a deep breath.

Thanks all for your help!

matthew black
information technology services
california state university, long beach

From: Matthew Black
Sent: Saturday, January 28, 2012 1:39 AM
To: Matthew Black; nanog@nanog.org
Subject: RE: Craigslist outage


IE diagnose connection problem suggests a firewall issue.



matthew black

information technology services

california state university, long beach





-Original Message-
From: Matthew Black [mailto:matthew.bl...@csulb.edu]
Sent: Saturday, January 28, 2012 1:32 AM
To: nanog@nanog.org
Subject: RE: Craigslist outage



Kind of supports my suspicion that a caching center (like Akamai) has gone
down.



What does nslookup return for you? I get



losangeles.craigslist.org

208.82.238.129



DOS tracert finds that IP in 9 hops (20ms, 19ms, 19ms).



Possible routing problems for http traffic with Verizon FIOS?



The about page comes up



matthew black

information technology services

california state university, long beach





-Original Message-

From: Henry Yen
[mailto:he...@aegisinfosys.com]

Sent: Saturday, January 28, 2012 1:26 AM

To: nanog@nanog.org

Subject: Re: Craigslist outage



On Sat, Jan 28, 2012 at 09:14:52AM +, Matthew Black wrote:

> It looks like www.craigslist.org redirects to
the nearest geographical

> craigslist site. Mine redirects to losangeles.craigslist.org, which is

> down.



losangeles.craigslist.org is working from here (Long Island, NY).



--

Henry Yen   Aegis Information Systems,
Inc.

Senior Systems Programmer   Hicksville, New York

Re: Fiber outage in Miami

[Randy Epstein]

>
>Anyone has seen on gotten a  RFA  or a deeper explanation of what
>happened from them ?
>
>
>Faisal Imtiaz
>Snappy Internet&  Telecom
>7266 SW 48 Street
>Miami, Fl 33155
>Tel: 305 663 5518 x 232
>Helpdesk: 305 663 5518 option 2 Email: supp...@snappydsl.net

Yes.  They blamed/burned the local crew and suggested that they fired
them.  Yes, they put this in the RFO.  I have it, but I'm having legal
determine if it can be made public record.

Randy

Re: Fiber outage in Miami

[Faisal Imtiaz]

ohh..

-

They wanted to perform the same maintenance again this weekend.

-

This is new news  to us

ok, then it makes sense

Anyone has seen on gotten a  RFA  or a deeper explanation of what 
happened from them ?



Faisal Imtiaz
Snappy Internet&  Telecom
7266 SW 48 Street
Miami, Fl 33155
Tel: 305 663 5518 x 232
Helpdesk: 305 663 5518 option 2 Email: supp...@snappydsl.net


On 1/28/2012 1:12 PM, Randy Epstein wrote:



On 1/28/12 1:07 PM, "Faisal Imtiaz"  wrote:


hmm... an what exactly does this accomplish ?

Faisal Imtiaz
Snappy Internet&   Telecom

It forces Fiberlight to follow a procedure that was outlined in the TRO
filing.  Yes, a maintenance procedure.

Oh, maybe you weren't aware.  The maintenance was never completed.  It was
reverted back.  Everyone is still feeding via Eqx-MI1.

They wanted to perform the same maintenance again this weekend.

Randy

RE: Paypal outage?

[Blake Pfankuch]

Seems to be working for me now.

-Original Message-
From: Chris [mailto:cal...@gmail.com] 
Sent: Saturday, January 28, 2012 11:11 AM
To: NANOG list
Subject: Paypal outage?

Anyone getting a 400 Bad Request from Paypal when you try to login to your 
account or make a transaction?

--
--C

"The dumber people think you are, the more surprised they're going to be when 
you kill them." - Sir William Clayton

Re: Fiber outage in Miami

[Randy Epstein]

>
>
>
>On 1/28/12 1:07 PM, "Faisal Imtiaz"  wrote:
>
>>hmm... an what exactly does this accomplish ?
>>
>>Faisal Imtiaz
>>Snappy Internet&  Telecom
>
>It forces Fiberlight to follow a procedure that was outlined in the TRO
>filing.  Yes, a maintenance procedure.

Oh, maybe you weren't aware.  The maintenance was never completed.  It was
reverted back.  Everyone is still feeding via Eqx-MI1.

They wanted to perform the same maintenance again this weekend.

Randy

Paypal outage?

[Chris]

Anyone getting a 400 Bad Request from Paypal when you try to login to
your account or make a transaction?

-- 
--C

"The dumber people think you are, the more surprised they're going to
be when you kill them." - Sir William Clayton

Re: Fiber outage in Miami

[Randy Epstein]

On 1/28/12 1:07 PM, "Faisal Imtiaz"  wrote:

>hmm... an what exactly does this accomplish ?
>
>Faisal Imtiaz
>Snappy Internet&  Telecom

It forces Fiberlight to follow a procedure that was outlined in the TRO
filing.  Yes, a maintenance procedure.

Re: Fiber outage in Miami

[Faisal Imtiaz]

hmm... an what exactly does this accomplish ?

Faisal Imtiaz
Snappy Internet&  Telecom


On 1/28/2012 12:52 PM, Randy Epstein wrote:


On 1/23/12 3:57 PM, "Jason LeBlanc"  wrote:


We are still impacted from what I understand.

On 01/23/2012 10:02 AM, Jimmy Changa wrote:

Was anyone impacted by a botched fiber move in Miami this weekend? I
lost 2 pieces of dark fiber for over almost 24 hours due to a fiber move
being performed by FiberLight. I'm curious if anyone else was impacted.

Sent from mobile device

This is what happens when you don't follow proper procedure:
http://web.hostleasing.net/~repstein/FiberlightOrder.pdf

Yes, we had to file a TRO against them.

Randy

Re: Fiber outage in Miami

[Randy Epstein]

On 1/23/12 3:57 PM, "Jason LeBlanc"  wrote:

>We are still impacted from what I understand.
>
>On 01/23/2012 10:02 AM, Jimmy Changa wrote:
>> Was anyone impacted by a botched fiber move in Miami this weekend? I
>>lost 2 pieces of dark fiber for over almost 24 hours due to a fiber move
>>being performed by FiberLight. I'm curious if anyone else was impacted.
>>
>> Sent from mobile device
>

This is what happens when you don't follow proper procedure:
http://web.hostleasing.net/~repstein/FiberlightOrder.pdf

Yes, we had to file a TRO against them.

Randy

RE: XBOX 720: possible digital download mass service.

[Nathan Eisenberg]

> Now if RFC1149 supported jumbo frames, it might give tin-cans-and-string a
> run for its money

It's a simple matter of weight ratios.  A 5 oz bird cannot carry a 9000 mtu 
coconut.

Re: US DOJ victim letter

[John Peach]

On Sat, 28 Jan 2012 16:30:47 +
bmann...@vacation.karoshi.com wrote:

> On Fri, Jan 27, 2012 at 10:20:08PM -0500, Martin Hannigan wrote:
> > On Fri, Jan 27, 2012 at 1:32 PM, Randy Epstein  
> > wrote:
> > >
[snip]
>   I missed the part where ARIN turned over its address database w/ 
> associatedd
>   registration information to the Fed ... I mean I've always advocated 
> for 
>   LEO access, but ther has been significant pushback fromm the community 
> on
>   unfettered access to that data.  As I recall, there are even policies 
> and
>   processes to limit/restrict external queries to prevent a DDos of the 
> whois
>   servers.  And some fairly strict policies on who gets dumps of the 
> address
>   space.  As far as I know (not very far) bundling the address database
>   -and- the registration data are not available to mere mortals.
> 
>   So - just how DID the Fed get the data w/o violating ARIN policy?
> 
> /bill
> 
> 

Ours came from our whois information.

-- 
John

Re: XBOX 720: possible digital download mass service.

[Lamar Owen]

On Friday, January 27, 2012 05:56:19 AM Randy Bush wrote:
> > Can internet in USA support that?   Call of Duty 15 releases may 2014
> > and 30 million gamers start downloading a 20 GB files.  Would the
> > internet collapse like a house of cards?.

> not a problem.  the vast majority of the states is like a developing
> country [0], the last mile is pretty much a tin can and a string.  so
> this will effectively throttle the load.

Being in 'the middle of nowhere' as I write, even we are a few notches above 
RFC1149 capabilities.  As one visitor to our site (who had been recently to 
NRAO Greenbank) said 'if this isn't the middle of nowhere, you can probably see 
it from here.'

Our base DSL is 7Mb/s down, 0.5Mb/s up, with 11Mb/s down and 1Mb/s up available 
to over 99% of our very rural county.  We (work) have 1Gb/s on the local loop 
fiber pair, throttled to the amount of IP we actually pay for at the ISP's PoP.

Now if RFC1149 supported jumbo frames, it might give tin-cans-and-string a run 
for its money

Re: US DOJ victim letter

[bmanning]

On Fri, Jan 27, 2012 at 10:20:08PM -0500, Martin Hannigan wrote:
> On Fri, Jan 27, 2012 at 1:32 PM, Randy Epstein  wrote:
> >
> >
> > On 1/27/12 1:23 PM, "valdis.kletni...@vt.edu" 
> > wrote:
> >
> >>On Fri, 27 Jan 2012 13:16:27 EST, Bryan Horstmann-Allen said:
> >>
> >>> Bit odd, if it's a phish. Even more odd if it's actually from the Fed.
> >>
> >>What if it's a phish from a compromised Fed box? :)
> >
> > We've spoken to folks at various FBI field offices and at 26 Plaza in New
> > York which is handling this case.  Further, John Curran (ARIN CEO) has
> > confirmed it's real via their own liaison and Paul Vixie is actually
> > working with them on this.
> >
> 
> 
> It's definitely real.
> 
> Best,
> 
> -M<
> 

I missed the part where ARIN turned over its address database w/ 
associatedd
registration information to the Fed ... I mean I've always advocated 
for 
LEO access, but ther has been significant pushback fromm the community 
on
unfettered access to that data.  As I recall, there are even policies 
and
processes to limit/restrict external queries to prevent a DDos of the 
whois
servers.  And some fairly strict policies on who gets dumps of the 
address
space.  As far as I know (not very far) bundling the address database
-and- the registration data are not available to mere mortals.

So - just how DID the Fed get the data w/o violating ARIN policy?

/bill

Re: XBOX 720: possible digital download mass service.

[Mark Tinka]

On Saturday, January 28, 2012 11:39:21 PM Roland Perry 
wrote:

> When did you last see a Windows or Office update
> available on disc?

In my experience (especially in places where Internet access 
to the home is "tight" or non-existent), Windows and Office 
is normally used in the office, where Internet access is 
"not as tight".

If folk have Windows or Office on their laptops, they'll 
take those laptops into the office and run updates from 
there. If they're using PC's at home, they'll download the 
offline copies of those updates and go home and install them 
via disc, USB or whatever.

Game consoles don't normally "make it to the office", hence 
my point earlier.

Mark.


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

Re: BDP discussion pointers: was: Re pontification bloat (was 10GE TOR port buffers (was Re: 10G switch recommendaton))

[Jim Gettys]

On 01/28/2012 10:28 AM, Jim Gettys wrote:
> On 01/27/2012 08:31 PM, Randy Bush wrote:
 for those who say bufferbloat is a problem, do you have wred enabled
 on backbone or customer links?
>>> For *most backbone networks* it is a no-op on the backbone.  To be
>>> more precise, if the backbone is at least 10x, and preferably more
>>> like 50x faster than the largest single TCP flow from any customer
>>> it will be nearly impossible to measure the performance difference
>>> between a short FIFO queue and a WRED queue.
>> when a line card is designed to buffer the b*d of a trans-pac 40g, the
>> oddities on an intra-pop link have been observed to spike to multiple
>> seconds.
> See the  CACM article Bufferbloat: Dark Buffers in the Internet, in the
> January CACM, by Kathy Nichols and myself or online at:
> http://cacm.acm.org/magazines/2012/1/144810-bufferbloat/fulltext
> The section entitled "Revisiting the Bandwidth Delay Product" is germain
> to the discussion here. Fundamentally, the b*d "rule" isn't really very
> useful under most circumstances, though it helps to understand what it
> tells you, and may be a useful upper bound under some circumstances,
> though very seldom for a network operator such as found on the NANOG list.
>
> The fundamental problem is most people don't know either the bandwidth,
> nor the delay. 
>
> The BDP is what you need for a single long lived TCP flow; as soon as
> you have multiple flows, it's over-estimating the buffering needed, even
> if you know the bandwidth and the delay...
>
> And this work in particular for routers (or potentially switches) is
> important:
>
> Appenzeller, G., Keslassy, I., McKeown, N. 2004. Sizing router buffers.
> ACM SIGCOMM, Portland, OR, (August).
> http://yuba.stanford.edu/~nickm/papers/sigcomm2004-extended.pdf
> 
>
>
> Ultimately, we need an AQM algorithm that works so well,  and requires
> no configuration, so that we can just always have it on and we can
> forget about it; (W)RED and friends aren't it; but it's the best we've
> got for the moment that you can actually use.  It's hopeless to try to
> use it in the home, where we have very highly variable bandwidth.
>
> In backbone networks, the biggest reason I can see for enabling (W)RED
> may be for robustness sake: if you have a link and it congests, you can
> quickly be in a world of hurt.  I wonder what happened in Japan after
> the earthquake  And it should always be on on congested links you
> know about, of course.

Also in particular see section 3.1 in the Sizing Router Buffers paper:
if you don't have AQM enabled, *and* your router/switch is a bottleneck
link, multiple long lived TCP flows will synchronise and you again need
a full BDP sized buffer; this is why random drop in AQM algorithms is
important.

So your millage will vary.  BDP really isn't useful most of the time,
other than thinking about the problem in the first place.
- Jim

Re: XBOX 720: possible digital download mass service.

[Roland Perry]

In article <201201282306.00569.mti...@globaltransit.net>, Mark Tinka 
 writes

Then, of course, there are those who might not be in a
position to get any kind of Internet access to their
consoles. This isn't such a terrible thing if games are
released both on digital and hard copies, but it's quite
unlikely maintenance updates for the game might be available
on disc.


When did you last see a Windows or Office update available on disc?

(And don't say "buy the latest version retail" - in my experience they 
are the ones that are hit with the biggest install-update.)

--
Roland Perry

BDP discussion pointers: was: Re pontification bloat (was 10GE TOR port buffers (was Re: 10G switch recommendaton))

[Jim Gettys]

On 01/27/2012 08:31 PM, Randy Bush wrote:
>>> for those who say bufferbloat is a problem, do you have wred enabled
>>> on backbone or customer links?
>> For *most backbone networks* it is a no-op on the backbone.  To be
>> more precise, if the backbone is at least 10x, and preferably more
>> like 50x faster than the largest single TCP flow from any customer
>> it will be nearly impossible to measure the performance difference
>> between a short FIFO queue and a WRED queue.
> when a line card is designed to buffer the b*d of a trans-pac 40g, the
> oddities on an intra-pop link have been observed to spike to multiple
> seconds.

See the  CACM article Bufferbloat: Dark Buffers in the Internet, in the
January CACM, by Kathy Nichols and myself or online at:
http://cacm.acm.org/magazines/2012/1/144810-bufferbloat/fulltext
The section entitled "Revisiting the Bandwidth Delay Product" is germain
to the discussion here. Fundamentally, the b*d "rule" isn't really very
useful under most circumstances, though it helps to understand what it
tells you, and may be a useful upper bound under some circumstances,
though very seldom for a network operator such as found on the NANOG list.

The fundamental problem is most people don't know either the bandwidth,
nor the delay. 

The BDP is what you need for a single long lived TCP flow; as soon as
you have multiple flows, it's over-estimating the buffering needed, even
if you know the bandwidth and the delay...

And this work in particular for routers (or potentially switches) is
important:

Appenzeller, G., Keslassy, I., McKeown, N. 2004. Sizing router buffers.
ACM SIGCOMM, Portland, OR, (August).
http://yuba.stanford.edu/~nickm/papers/sigcomm2004-extended.pdf



Ultimately, we need an AQM algorithm that works so well,  and requires
no configuration, so that we can just always have it on and we can
forget about it; (W)RED and friends aren't it; but it's the best we've
got for the moment that you can actually use.  It's hopeless to try to
use it in the home, where we have very highly variable bandwidth.

In backbone networks, the biggest reason I can see for enabling (W)RED
may be for robustness sake: if you have a link and it congests, you can
quickly be in a world of hurt.  I wonder what happened in Japan after
the earthquake  And it should always be on on congested links you
know about, of course.

There is hope on this front, but it's early days yet.

- Jim

Re: XBOX 720: possible digital download mass service.

[Mark Tinka]

On Saturday, January 28, 2012 09:11:24 PM Roland Perry 
wrote:

> So does Microsoft Office (if you can call that a game).

So does Mac OS X Lion (exclusively, more so).

But I guess the trend the OP was raising was this 
distribution method shifting for console games. As many have 
already mentioned, since the majority of consoles are in the 
home, the last mile to the home router is likely the choke 
point in most cases.

For consoles that will be sold outside "major" areas, one 
might not be able to get CDN coverage, so not only do they 
have to suffer with small last mile pipes, they also need to 
contend with higher latency to get to the nearest CDN (which 
may not be so close by).

Then, of course, there are those who might not be in a 
position to get any kind of Internet access to their 
consoles. This isn't such a terrible thing if games are 
released both on digital and hard copies, but it's quite 
unlikely maintenance updates for the game might be available 
on disc.

Mark.


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

Re: XBOX 720: possible digital download mass service.

[Roland Perry]

In article <201201281518.47292.mti...@globaltransit.net>, Mark Tinka 
 writes

Needless to say, a lot of games are now pushing massive
updates via the Internet; on the order of hundreds of MB.


So does Microsoft Office (if you can call that a game).
--
Roland Perry

Re: 10GE TOR port buffers (was Re: 10G switch recommendaton)

[Saku Ytti]

On (2012-01-28 21:53 +0900), Masataka Ohta wrote:
 
> 1.5MB @ 100Mbps is 120ms, which is prohibitively lengthy
> even as BE.
> 
> The solution is to have less number of classes.

The solution is to per class define max queue size, so user with fewer
queues configured will not use all available buffer in remaining queues.
JNPR MX is happy to buffer >4s on 10GE on QX interfaces. Reading some posts
on this thread seems to imply vendor is not knowing what they are doing,
but in this case there is good reason why there is potentially lot of
buffer space and it's simply operator mistake not to limit it if
application is just single class in single vlan/untagged 10G interface

-- 
  ++ytti

Re: 10GE TOR port buffers (was Re: 10G switch recommendaton)

[Masataka Ohta]

Saku Ytti wrote:

>>> And if switch does support QoS but operator configures only BE, and
>>> operator does not limit BE queue size, operator will see buffer bloat,
>>
>> 1.5MB @ 10Gbps is only 1.2ms, which is not buffer bloat.
> 
> You can't buffer these in ingress or you risk HOLB issue, you must buffer
> these in the egress 100M and drop in ingress if egress buffer is full.

1.5MB @ 100Mbps is 120ms, which is prohibitively lengthy
even as BE.

The solution is to have less number of classes.

For QoS assurance, you only need to have two classes for
infinitely many flows with different QoS, if flows in higher
priority class receive policing against reserved bandwidths
of the flow.

Masataka Ohta



> 
> But I fully agree, it's not buffer bloat. But having switch which does
> support very different traffic rates in ingress and egress (ingress could
> even be LACP, which further mandates larger buffers on egress) and if you
> also need to support QoS towards customer, the amount of buffer quickly
> reaches the level some of these vendors are supporting.
> When it becomes buffer bloat, is when inexperienced operator allows all of
> the buffer to be used for single class in matching ingress/egress rates.
> 

Re: photonic buffer bloat

[Masataka Ohta]

Eugen Leitl wrote:

> In future photonic networks (which will do relativistic cut-through
> directly in a photonic crossbar without converting photons to electrons
> and back) the fiber is not just a transport channel but also a photonic
> buffer

Yes.

> (e.g. at 10 GBit/s Ethernet a short reach fiber already buffers
> a standard 1500 MTU).

Wrong. 10Gbps is too slow for optical buffering.

At 1Tbps, you can use 100 times less lengthy fiber than at 10Gbps
to buffer packets.

A 1Tbps packet can be constructed by simultaneously encoding
100 wavelengths at 10Gbps.

> Of course photonic gates are expensive, individual delays do add up
> so even with slow light buffers

Don't try to make light slower. Slow light buffers have resonators,
which means they have very very very narrow bandwidth.

Instead, make communication speed faster, which shortens fiber
length of fiber delay line buffers.

> or optical delay loops taken into consideration
> current TCP/IP header layout has not been optimized for leading edge
> containing most significant switching/routing information, or even
> local-knowledge routing (with no global routes). It's too bad IPv6
> was not radical enough, so today's legacy protocols have to be tunneled
> through the networks of the future.

Considering that, in practice, packet headers must be processed
electrically, IPv4 at the photonic backbone is just fine, if most
routing table entries are aggregated at /24 or better, which is
the current practice. You only have to read a 16M entry SRAM.

A problem of IPv6 with 128bit addresses is that route look up
can not be performed within a constant time of a few nano
seconds, which means packets have overrun fiber delay lines.

> I presume this future is some 20-30 years away still.

Not so much. Moore's law requires much rapid bandwidth
increase.

My slides presented at IEEE photonics society 2009 summer topical

ftp://chacha.hpcl.titech.ac.jp/IEEE-ST.ppt

might be interesting for you.

Masataka Ohta

Re: 10GE TOR port buffers (was Re: 10G switch recommendaton)

[Saku Ytti]

On (2012-01-28 21:06 +0900), Masataka Ohta wrote:

> The required amount of memory is merely 150KB.

Assuming we don't support jumbo frames and switch cannot queue sub packet
sizes (normally they can't but VXR at least has 512B cell concept, so
tx-ring is packet size agnostic, but this is just PA-A3)

> If you have 10 classes, it is still 1.5MB.

Yup, that's not bad at all in 100M port, infact 10 classes would be quite
much.

> > And if switch does support QoS but operator configures only BE, and
> > operator does not limit BE queue size, operator will see buffer bloat,
> 
> 1.5MB @ 10Gbps is only 1.2ms, which is not buffer bloat.

You can't buffer these in ingress or you risk HOLB issue, you must buffer
these in the egress 100M and drop in ingress if egress buffer is full.

But I fully agree, it's not buffer bloat. But having switch which does
support very different traffic rates in ingress and egress (ingress could
even be LACP, which further mandates larger buffers on egress) and if you
also need to support QoS towards customer, the amount of buffer quickly
reaches the level some of these vendors are supporting.
When it becomes buffer bloat, is when inexperienced operator allows all of
the buffer to be used for single class in matching ingress/egress rates.

-- 
  ++ytti

Re: 10GE TOR port buffers (was Re: 10G switch recommendaton)

[Masataka Ohta]

Saku Ytti wrote:

> No, you're not crazy. If your core is higher rate than your customer, then
> you need at minimum serialization delay difference of buffering.
> If core is 10G and access 100M, you need buffer for minimum of 100 packets,
> to handle the single 10G incoming, without any extra buffering.

The required amount of memory is merely 150KB.

> Now if you add QoS on top of this, you probably need 100 per each class you
> are going to support.

If you have 10 classes, it is still 1.5MB.

> And if switch does support QoS but operator configures only BE, and
> operator does not limit BE queue size, operator will see buffer bloat,

1.5MB @ 10Gbps is only 1.2ms, which is not buffer bloat.

Masataka Ohta

photonic buffer bloat

[Eugen Leitl]

In future photonic networks (which will do relativistic cut-through 
directly in a photonic crossbar without converting photons to electrons 
and back) the fiber is not just a transport channel but also a photonic 
buffer (e.g. at 10 GBit/s Ethernet a short reach fiber already buffers 
a standard 1500 MTU). 

Of course photonic gates are expensive, individual delays do add up
so even with slow light buffers or optical delay loops taken into consideration 
current TCP/IP header layout has not been optimized for leading edge 
containing most significant switching/routing information, or even 
local-knowledge routing (with no global routes). It's too bad IPv6 
was not radical enough, so today's legacy protocols have to be tunneled 
through the networks of the future. 

I presume this future is some 20-30 years away still.

Re: Craigslist outage

[Henry Yen]

On Sat, Jan 28, 2012 at 09:59:44AM +, Matthew Black wrote:
> Confirmed that it's Verizon FIOS. I remote logged into a system at work
> and had no trouble.

FiOS connection from here to losangeles.craigslist.org works.

> What does nslookup return for you? I get
> losangeles.craigslist.org
> 208.82.238.129

Same from here, but I don't use FiOS nameservers. dig +trace returns the same.

-- 
Henry Yen   Aegis Information Systems, Inc.
Senior Systems Programmer   Hicksville, New York

Re: 10GE TOR port buffers (was Re: 10G switch recommendaton)

[Saku Ytti]

On (2012-01-27 22:40 +0100), bas wrote:

> But do you generally agree that "the market" has a requirement for a
> deep-buffer TOR switch?
> 
> Or am I crazy for thinking that my customers need such a solution?

No, you're not crazy. If your core is higher rate than your customer, then
you need at minimum serialization delay difference of buffering.
If core is 10G and access 100M, you need buffer for minimum of 100 packets,
to handle the single 10G incoming, without any extra buffering.

Now if you add QoS on top of this, you probably need 100 per each class you
are going to support.
And if switch does support QoS but operator configures only BE, and
operator does not limit BE queue size, operator will see buffer bloat, and
think it's clueless vendor dropping expensive memory there for the lulz,
while it's just misconfigured box.

When it comes to these trident+ 64x10GE/48x10GE+4x40G, your serialization
delay difference between interfaces is minimal, and so is buffering demand.

-- 
  ++ytti

RE: Craigslist outage

[Matthew Black]

Confirmed that it's Verizon FIOS. I remote logged into a system at work and had 
no trouble.

I'm dealing with tech support person that says "nobody blocks websites or 
changes routing tables."  Big sigh.

Tech trying to get a supervisor and just came back with "he has another 
customer with the same problem."

Taking a deep breath.

Thanks all for your help!

matthew black
information technology services
california state university, long beach

From: Matthew Black
Sent: Saturday, January 28, 2012 1:39 AM
To: Matthew Black; nanog@nanog.org
Subject: RE: Craigslist outage


IE diagnose connection problem suggests a firewall issue.



matthew black

information technology services

california state university, long beach





-Original Message-
From: Matthew Black [mailto:matthew.bl...@csulb.edu]
Sent: Saturday, January 28, 2012 1:32 AM
To: nanog@nanog.org
Subject: RE: Craigslist outage



Kind of supports my suspicion that a caching center (like Akamai) has gone down.



What does nslookup return for you? I get



losangeles.craigslist.org

208.82.238.129



DOS tracert finds that IP in 9 hops (20ms, 19ms, 19ms).



Possible routing problems for http traffic with Verizon FIOS?



The about page comes up



matthew black

information technology services

california state university, long beach





-Original Message-

From: Henry Yen 
[mailto:he...@aegisinfosys.com]

Sent: Saturday, January 28, 2012 1:26 AM

To: nanog@nanog.org

Subject: Re: Craigslist outage



On Sat, Jan 28, 2012 at 09:14:52AM +, Matthew Black wrote:

> It looks like www.craigslist.org redirects to the 
> nearest geographical

> craigslist site. Mine redirects to losangeles.craigslist.org, which is

> down.



losangeles.craigslist.org is working from here (Long Island, NY).



--

Henry Yen   Aegis Information Systems, Inc.

Senior Systems Programmer   Hicksville, New York

RE: Craigslist outage

[Matthew Black]

IE diagnose connection problem suggests a firewall issue.



matthew black

information technology services

california state university, long beach





-Original Message-
From: Matthew Black [mailto:matthew.bl...@csulb.edu]
Sent: Saturday, January 28, 2012 1:32 AM
To: nanog@nanog.org
Subject: RE: Craigslist outage



Kind of supports my suspicion that a caching center (like Akamai) has gone down.



What does nslookup return for you? I get



losangeles.craigslist.org

208.82.238.129



DOS tracert finds that IP in 9 hops (20ms, 19ms, 19ms).



Possible routing problems for http traffic with Verizon FIOS?



The about page comes up



matthew black

information technology services

california state university, long beach





-Original Message-

From: Henry Yen 
[mailto:he...@aegisinfosys.com]

Sent: Saturday, January 28, 2012 1:26 AM

To: nanog@nanog.org

Subject: Re: Craigslist outage



On Sat, Jan 28, 2012 at 09:14:52AM +, Matthew Black wrote:

> It looks like www.craigslist.org redirects to the 
> nearest geographical

> craigslist site. Mine redirects to losangeles.craigslist.org, which is

> down.



losangeles.craigslist.org is working from here (Long Island, NY).



--

Henry Yen   Aegis Information Systems, Inc.

Senior Systems Programmer   Hicksville, New York

RE: Craigslist outage

[Matthew Black]

Kind of supports my suspicion that a caching center (like Akamai) has gone down.

What does nslookup return for you? I get

losangeles.craigslist.org
208.82.238.129

DOS tracert finds that IP in 9 hops (20ms, 19ms, 19ms).

Possible routing problems for http traffic with Verizon FIOS?

The about page comes up

matthew black
information technology services
california state university, long beach


-Original Message-
From: Henry Yen [mailto:he...@aegisinfosys.com] 
Sent: Saturday, January 28, 2012 1:26 AM
To: nanog@nanog.org
Subject: Re: Craigslist outage

On Sat, Jan 28, 2012 at 09:14:52AM +, Matthew Black wrote:
> It looks like www.craigslist.org redirects to the nearest geographical 
> craigslist site. Mine redirects to losangeles.craigslist.org, which is 
> down.

losangeles.craigslist.org is working from here (Long Island, NY).

-- 
Henry Yen   Aegis Information Systems, Inc.
Senior Systems Programmer   Hicksville, New York

Re: Craigslist outage

[Henry Yen]

On Sat, Jan 28, 2012 at 09:14:52AM +, Matthew Black wrote:
> It looks like www.craigslist.org redirects to the nearest geographical
> craigslist site. Mine redirects to losangeles.craigslist.org, which is
> down.

losangeles.craigslist.org is working from here (Long Island, NY).

-- 
Henry Yen   Aegis Information Systems, Inc.
Senior Systems Programmer   Hicksville, New York

RE: Craigslist outage

[Matthew Black]

Thanks everyone for the updates.

It looks like www.craigslist.org redirects to the nearest geographical 
craigslist site. Mine redirects to losangeles.craigslist.org, which is down.

Is it possible that some high-volume internet caching centers have gone down?

matthew black
information technology services
california state university, long beach
562-985-5144


-Original Message-
From: Henry Yen [mailto:he...@aegisinfosys.com] 
Sent: Saturday, January 28, 2012 1:06 AM
To: nanog@nanog.org
Subject: Re: Craigslist outage

On Sat, Jan 28, 2012 at 08:56:31AM +, Matthew Black wrote:
> Accessing from Southern California.
> 
> Cannot get any pages to view, except a few "about" pages.
> http://www.craigslist.org/about/help/system-status.html
> 
> Status says runs good, but cannot pull up any city sites or the basic home 
> page http://www.craigslist.org. 
> 
> Anyone else having trouble or are you able to get in?

Works fine from Long Island, NY.

I see that www.craigslist.org immediately loads geo.craigslist.org;
maybe the latter is broken? (From here, it subsequently loads
longisland.craigslist.org.)

-- 
Henry Yen   Aegis Information Systems, Inc.
Senior Systems Programmer   Hicksville, New York

Re: Craigslist outage

[Henry Yen]

On Sat, Jan 28, 2012 at 08:56:31AM +, Matthew Black wrote:
> Accessing from Southern California.
> 
> Cannot get any pages to view, except a few "about" pages.
> http://www.craigslist.org/about/help/system-status.html
> 
> Status says runs good, but cannot pull up any city sites or the basic home 
> page http://www.craigslist.org. 
> 
> Anyone else having trouble or are you able to get in?

Works fine from Long Island, NY.

I see that www.craigslist.org immediately loads geo.craigslist.org;
maybe the latter is broken? (From here, it subsequently loads
longisland.craigslist.org.)

-- 
Henry Yen   Aegis Information Systems, Inc.
Senior Systems Programmer   Hicksville, New York

RE: Craigslist outage

[Matthew Black]

www.craigslist.org, losangeles.craigslist.org and sfo.craigslist.org all ail.

matthew black
information technology services
california state university, long beach
562-985-5144


-Original Message-
From: David [mailto:dav...@mckendrick.ca] 
Sent: Saturday, January 28, 2012 1:02 AM
To: Matthew Black
Cc: nanog@nanog.org
Subject: Re: Craigslist outage

Chicago loads, San Diego doesn't.
Interesting.

On Sat, 2012-01-28 at 08:56 +, Matthew Black wrote:
> Accessing from Southern California.
> 
> Cannot get any pages to view, except a few "about" pages.
> http://www.craigslist.org/about/help/system-status.html
> 
> Status says runs good, but cannot pull up any city sites or the basic home 
> page http://www.craigslist.org. 
> 
> Anyone else having trouble or are you able to get in?
> 
> matthew black
> information technology services
> california state university, long beach
> 
> 
> 
> 

Re: Craigslist outage

[David]

Chicago loads, San Diego doesn't.
Interesting.

On Sat, 2012-01-28 at 08:56 +, Matthew Black wrote:
> Accessing from Southern California.
> 
> Cannot get any pages to view, except a few "about" pages.
> http://www.craigslist.org/about/help/system-status.html
> 
> Status says runs good, but cannot pull up any city sites or the basic home 
> page http://www.craigslist.org. 
> 
> Anyone else having trouble or are you able to get in?
> 
> matthew black
> information technology services
> california state university, long beach
> 
> 
> 
> 

Craigslist outage

[Matthew Black]

Accessing from Southern California.

Cannot get any pages to view, except a few "about" pages.
http://www.craigslist.org/about/help/system-status.html

Status says runs good, but cannot pull up any city sites or the basic home page 
http://www.craigslist.org. 

Anyone else having trouble or are you able to get in?

matthew black
information technology services
california state university, long beach