On Feb 15, 2008, at 8:04 AM, Greg VILLAIN wrote:
Obvious as it is, if one of your peerings on an IX gets big in terms
of in/out volumes, you HAVE to secure it by PNI.
You need a way to prevent the IX's equipments from being a SPoFs
between you and that peer.
HAVE to is such a strong
Greg VILLAIN wrote:
I'm not saying one should convert every single IX peering into a PNI, as
I feel both are pretty much required: your smallest peers shall be
secured on as many IXes as possible, your biggest ones via PNI. IX
peering is mandatory to keep internet routing diversity up to par
On Feb 14, 2008, at 7:06 PM, Paul Vixie wrote:
[EMAIL PROTECTED] (Kai Chen) writes:
A typical Internet Exchange Point (IXP) consists of one or more
network
switches http://en.wikipedia.org/wiki/Network_switch, to which
each of
the participating ISPs connect. We call it the
On Thu, Feb 14, 2008 at 11:02:54AM -0600, Kai Chen wrote:
A typical Internet Exchange Point (IXP) consists of one or more network
switches http://en.wikipedia.org/wiki/Network_switch, to which each of the
participating ISPs connect. We call it the exchange-based topology. My
question is if
A typical Internet Exchange Point (IXP) consists of one or more network
switches http://en.wikipedia.org/wiki/Network_switch, to which each of the
participating ISPs connect. We call it the exchange-based topology. My
question is if some current IXPs use directly-connected topology, in
which ISPs
[EMAIL PROTECTED] (Kai Chen) writes:
A typical Internet Exchange Point (IXP) consists of one or more network
switches http://en.wikipedia.org/wiki/Network_switch, to which each of
the participating ISPs connect. We call it the exchange-based topology.
My question is if some current IXPs use
in other words there appeared to be no exchange-based topology, more
like a hybrid exchange and PNI topology.
Paul Vixie
It is interesting. Is this the common case for the IXP infrastructure?[1] I
mean the hybrid topology? It seems that it is both directly-connected and
On 14 Feb 2008, at 17:02, Kai Chen wrote:
A typical Internet Exchange Point (IXP) consists of one or more
network switches, to which each of the participating ISPs connect.
We call it the exchange-based topology. My question is if some
current IXPs use directly-connected topology, in
On Feb 14, 2008, at 3:44 PM, Andy Davidson wrote:
On 14 Feb 2008, at 17:02, Kai Chen wrote:
A typical Internet Exchange Point (IXP) consists of one or more
network switches, to which each of the participating ISPs connect.
We call it the exchange-based topology. My question is if some
Paul Vixie wrote:
i don't know what's true of other IXP's around the world.
At the Kenyan Internet Exchange Point (KIXP), we require that all
operators have a BGP-speaking router mounted on the racks at the
facility. All connections are done through the IXP switches. We have not
had a
On Fri, 17 Feb 2006, sjk wrote:
We're a small facilities based ISP in Chicago and I am looking for a
public exchange point for peering. I have been told, by someone at SBC,
that the public NAP here is no longer accepting connections and is
essentially going to shut down
We're a small facilities based ISP in Chicago and I am looking for a
public exchange point for peering. I have been told, by someone at SBC,
that the public NAP here is no longer accepting connections and is
essentially going to shut down over time. Has anyone else heard this? Are
there
On Fri, Feb 17, 2006 at 08:46:34PM -0600, sjk wrote:
We're a small facilities based ISP in Chicago and I am looking for a
public exchange point for peering. I have been told, by someone at SBC,
that the public NAP here is no longer accepting connections and is
essentially going to shut
You keep saying EMIX
and you're confusing me. Peering or no? IX naturally insinuates
yes regardless of neutrality.
Exactly. IX as a component of a name is _intended to insinuate_ the
availability of peering, _regardless of whether that's actually true or
false_.
It
On 9-Feb-2006, at 02:19, [EMAIL PROTECTED] wrote:
But back to EMIX. Maybe they do not offer any peering today
but is it true that they actively prohibit any companies
with routers at EMIX from peering?
There is no at EMIX. EMIX is an ISP, AS 8966, with network
connecting various cities in
On Thu, 9 Feb 2006 [EMAIL PROTECTED] wrote:
In hindsight, it would have been clearer to refer to these
places as peering exchanges however back in those days, the important
distinction wasn't between peering and transit.
There was a significant effort from 2001 to
On 2/7/06, Bill Woodcock [EMAIL PROTECTED] wrote:
On Tue, 7 Feb 2006, Joe Abley wrote: I would not be surprised if the toplogical centre of today's African Internet turned out to be the LINX.Yep, with 111 8th close behind.
Most of the African ISPs connect into 118th and the LINX.All the ISPs I've
At 11:08 AM 2/9/2006, Bill Woodcock wrote:
On Thu, 9 Feb 2006 [EMAIL PROTECTED] wrote:
In hindsight, it would have been clearer to refer to these
places as peering exchanges however back in those days, the important
distinction wasn't between peering and transit.
There
On 7-Feb-2006, at 23:25, Martin Hannigan wrote:
You keep saying EMIX
and you're confusing me. Peering or no? IX naturally insinuates
yes regardless of neutrality.
I'm not sure how to be more clear about this. EMIX is the name of a
transit service offered by Emirates Telecom.
Joe
On Tue, 7 Feb 2006, william(at)elan.net wrote:
And when ISP A buys access from ISP B for purpose of getting to ISP C is
that peering or transit?
I thought it was generally accepted that peering is the exhange of
routes that are not re-sent to other organisations.
Transit is when one
On Wed, 8 Feb 2006, Mikael Abrahamsson wrote:
On Tue, 7 Feb 2006, william(at)elan.net wrote:
And when ISP A buys access from ISP B for purpose of getting to ISP C is
that peering or transit?
I thought it was generally accepted that peering is the exhange of routes
that are not re-sent to
On Tue, 7 Feb 2006, william(at)elan.net wrote:
So what exactly is definition of transit that does not make it peering?
Transit is the exchange of TRANSITIVE routes to destinations which are not
the downstream customers of either of the two parties to the transaction.
And when
On Wed, 8 Feb 2006, Martin Hannigan wrote:
Guys, are you being semantic?
Yes, we're doggedly insisting that words mean what they're defined to
mean, rather than the opposite.
You keep saying EMIX
and you're confusing me. Peering or no? IX naturally insinuates
yes
On Tue, 7 Feb 2006, william(at)elan.net wrote:
On Tue, 7 Feb 2006, Bill Woodcock wrote:
different definitions. If you say transit is peering, just not by our
definitions, then you're into 1984 territory.
So what exactly is definition of transit that does not make it peering?
And
On Wed, Feb 08, 2006 at 10:45:47AM -0800, Bill Woodcock wrote:
On Wed, 8 Feb 2006, Martin Hannigan wrote:
Guys, are you being semantic?
Yes, we're doggedly insisting that words mean what they're defined to
mean, rather than the opposite.
You keep saying EMIX
and
On Feb 8, 2006, at 12:30 PM, william(at)elan.net wrote:
Transit is when one entity sends the routes on to other
organsiations, often with money involved.
More commonly understood is that transit involves one ISP sending all
of its BGP routes and allowing any traffic to be send from ISP A
At 01:45 PM 2/8/2006, Bill Woodcock wrote:
On Wed, 8 Feb 2006, Martin Hannigan wrote:
Guys, are you being semantic?
Yes, we're doggedly insisting that words mean what they're defined to
mean, rather than the opposite.
You keep saying EMIX
and you're confusing me. Peering
I know of a Cairo IXP, and possibly one in the UAE. Is there one in
Kuwait as yet?
There is one in Pakistan, and maybe Dubai. I would address this
question to the SANOG list.
Regards
Marshall
On Feb 7, 2006, at 12:48 PM, Howard C. Berkowitz wrote:
I know of a Cairo IXP, and possibly one in the UAE. Is there one
in Kuwait as yet?
Howard C. Berkowitz wrote:
I know of a Cairo IXP, and possibly one in the UAE. Is there one in
Kuwait as yet?
ISOC-IL is running the IIX for Israel.
On 2/7/06, Howard C. Berkowitz [EMAIL PROTECTED] wrote:
I know of a Cairo IXP, and possibly one in the UAE. Is there one in
Kuwait as yet?
http://www.emix.net.ae/
it's flash heavy fyi
I know of a Cairo IXP, and possibly one in the UAE. Is there one in
Kuwait as yet?
Yes, KIX. Note, there's CIX and CRIX. If you are trying to
reach African users, there's also KIX ala Kenya.
-M
--
Martin Hannigan(c) 617-388-2663
Renesys Corporation
On 7-Feb-2006, at 11:27, Aaron Glenn wrote:
On 2/7/06, Howard C. Berkowitz [EMAIL PROTECTED] wrote:
I know of a Cairo IXP, and possibly one in the UAE. Is there one in
Kuwait as yet?
http://www.emix.net.ae/
it's flash heavy fyi
Note that EMIX is a transit service, not really peering.
On 7-Feb-2006, at 11:54, Martin Hannigan wrote:
I know of a Cairo IXP, and possibly one in the UAE. Is there one
in Kuwait as yet?
Yes, KIX. Note, there's CIX and CRIX. If you are trying to
reach African users, there's also KIX ala Kenya.
The exchange point in Nairobi is called KIXP,
At 04:11 PM 2/7/2006, Joe Abley wrote:
On 7-Feb-2006, at 11:54, Martin Hannigan wrote:
I know of a Cairo IXP, and possibly one in the UAE. Is there one
in Kuwait as yet?
Yes, KIX. Note, there's CIX and CRIX. If you are trying to
reach African users, there's also KIX ala Kenya.
The
Sent: Tuesday, February 07, 2006 3:12 PM
To: Martin Hannigan
Cc: Howard C. Berkowitz; nanog@merit.edu
Subject: Re: Middle Eastern Exchange Points
On 7-Feb-2006, at 11:54, Martin Hannigan wrote:
I know of a Cairo IXP, and possibly one in the UAE. Is there one
in Kuwait as yet?
Yes, KIX. Note
, 7 Feb 2006, Howard C. Berkowitz wrote:
Middle Eastern Exchange Points
I know of a Cairo IXP, and possibly one in the UAE. Is there one in
Kuwait as yet?
All the ISPs I've talked to in Egypt claim that the Cairo IX was a failed
experiment and that they haven't heard anything about
At 10:30 PM 2/7/2006, Bill Woodcock wrote:
[ SNIP ]
Anyway, back to the conversation at hand:
On Tue, 7 Feb 2006, Howard C. Berkowitz wrote:
Middle Eastern Exchange Points
I know of a Cairo IXP, and possibly one in the UAE. Is there one in
Kuwait as yet?
All
On Tue, 7 Feb 2006, Martin Hannigan wrote:
Interconnecting in a government exchange is
still peering.
Uh, not if it's buying transit.
They are peering, even if it isn't by our
definitions.
Uh, Marty... the difference between peering and transit is that they have
At 11:55 PM 2/7/2006, Bill Woodcock wrote:
On Tue, 7 Feb 2006, Martin Hannigan wrote:
Interconnecting in a government exchange is
still peering.
Uh, not if it's buying transit.
They are peering, even if it isn't by our
definitions.
Uh, Marty... the difference
On 7-Feb-2006, at 20:50, Martin Hannigan wrote:
As Joe's pointed out, what's available in the UAE, Saudi Arabia, and
Kuwait are governmental monopoly incumbent transit services, a la
STIX, as
opposed to Internet exchanges where peering takes place. There are
several private colocation
On Tue, 7 Feb 2006, Bill Woodcock wrote:
different definitions. If you say transit is peering, just not by our
definitions, then you're into 1984 territory.
So what exactly is definition of transit that does not make it peering?
And when ISP A buys access from ISP B for purpose of getting
At 01:11 AM 2/8/2006, Joe Abley wrote:
On 7-Feb-2006, at 20:50, Martin Hannigan wrote:
As Joe's pointed out, what's available in the UAE, Saudi Arabia, and
Kuwait are governmental monopoly incumbent transit services, a la
STIX, as
opposed to Internet exchanges where peering takes place.
http://www.itu.int/ITU-D/treg/publications/AfricaIXPRep.pdf
--
Suresh Ramasubramanian ([EMAIL PROTECTED])
Aside from the Switch Data in Southfield and
the nearby Level 3 location, has anyone encountered
good locations for private peering in the metro
Detroit area?
Interesting points, and although orthogonal to the analysis in Do
ATM-based Internet Exchange Points Make Sense Anymore?, I am including
these in the appendix to show these alternate views of the world. Am I
missing any of the major (fact-based) views?
There is this small thing that higher
Hi all -
I have walked about 30 people through the Do ATM-based Internet Exchange
Points make sense anymore? white paper and have received some really good
feedback, suggestions and price points to calibrate the Peering Financial
Model. I have applied these calibrations and I am ready
Jesper Skriver wrote:
Your Cisco router (say a GSR) will go foobar if you use 10/30 seconds
timers, a IGP topology change, causing a new next-hop interface for
100k routes, will cause processes (probably CEF related) to run for so
long, that you will loose your BGP keepalives, thus loose
Thus spake Alex Rubenstein [EMAIL PROTECTED]
What functionality does PVC give you that the ethernet VLAN does not?
Shaping, for one.
There is nothing inherent in Ethernet which precludes shaping. Low- and
mid-range routers can do it just fine. If your core router doesn't, speak with
your
Thus spake Vadim Antonov [EMAIL PROTECTED]
It makes little sense to detect transient glitches. Any possible reaction
on those glitches (i.e. withdrawal of exterior routes with subsequent
reinstatement) is more damaging than the glitches themselves.
(Ignoring BGP for the moment, which has no
Thus spake Petri Helenius [EMAIL PROTECTED]
What functionality does PVC give you that the ethernet VLAN does not?
That´s quite easy. Endpoint liveness. A IPv4 host on a VLAN has no idea
if the guy on the other end died until the BGP timer expires.
FR has LMI, ATM has OAM. (and ILMI)
FR
Exchange Points make sense anymore?
On Fri, 9 Aug 2002, Nenad Trifunovic wrote:
It appears that for analysis purposes one has to separate access
from switching. How much payload one brings to the exchange depends
on port speed and protocol overhead. In that light, Frame Relay
can bring
Paul just hit on it. At how many layers do you want protection, and
will they interfere with each other. Granted not all protection
schemes overlap. If there if not a layer 1 failure, and a router
maintains link0 but the card or routers has somehow failed and is no
longer passing
I suppose the discussion is what do you want from your exchange pt
operator and what do you NOT want.
At the IXP level, bits per month always trumps bits per second,
and usually trumps pennies per bit as well. There are now a number
of companies trying to sell wide area ethernet -- even
On Fri, Aug 09, 2002 at 03:22:00PM -0700, Lane Patterson wrote:
BGP keepalive/hold timers are configurable even down to granularity of
link or PVC level keepalives, but for session stability reasons, it
appears that most ISPs at GigE exchanges choose not to tweak them down
from the
Paul Vixie wrote:
Adding complexity to a system increases its cost but not nec'ily its value.
Consider the question: how often do you expect endpoint liveness to matter?
The issue I'm trying to address is to figure out how to extend the robustness
that can be achieved with tuned IGP's with
would be
reasonable, but nobody seems compelled that this is much of an
issue.
Cheers,
-Lane
-Original Message-
From: Petri Helenius [mailto:[EMAIL PROTECTED]]
Sent: Friday, August 09, 2002 3:07 PM
To: Mikael Abrahamsson; [EMAIL PROTECTED]
Subject: Re: Do ATM-based Exchange
warning: i've had one high gravity steel reserve over my quota. hit D now.
The issue I'm trying to address is to figure out how to extend the robustness
that can be achieved with tuned IGP's with subsecond convergence across
an exchange point without suffering a one to five minute delay
Mike Hughes wrote:
With the shorter timers or fast-external-fallover, a very short
maintenance slot at a large exchange can cause ripples in the routing
table. It would be interesting to do some analysis of this - how far the
ripples spread from each exchange!
We do BGP instability
Mikael Abrahamsson [EMAIL PROTECTED] writes:
On 10 Aug 2002, Paul Vixie wrote:
why on god's earth would subsecond anything matter in a
nonmilitary situation?
It does when you start doing streaming anything, say TV or telephony. I
I submit that it doesn't matter for voice or video,
Mike Hughes wrote:
But, how does that work when you may be delivering multiple q-tags on a
single GigE port (for example)? If only one tag is affected, you don't
want to drop link, right?
So, we're back to detection at layer 3, can I ping it, do I have
adjacency, etc.
Some sort of
Paul Vixie wrote:
warning: i've had one high gravity steel reserve over my quota. hit D now.
The issue I'm trying to address is to figure out how to extend the robustness
that can be achieved with tuned IGP's with subsecond convergence across
an exchange point without suffering a one
On Sat, Aug 10, 2002 at 06:09:05PM +0300, Petri Helenius wrote:
If the software MTBF would be better, convergence would not be an issue.
As long as it's an operational hazard to run core boxes (with some
vendors anyway) with older piece of code than six months, you end up
engineering
On Sat, Aug 10, 2002 at 11:20:44AM -0400, Richard A Steenbergen wrote:
On Sat, Aug 10, 2002 at 06:09:05PM +0300, Petri Helenius wrote:
If the software MTBF would be better, convergence would not be an issue.
As long as it's an operational hazard to run core boxes (with some
vendors
On 10 Aug 2002, Paul Vixie wrote:
why on god's earth would subsecond anything matter in a nonmilitary situation?
Telemedicine, tele-robotics, etc, etc. Actually, there's a lot of cases
when you want to have subsecond recovery. The current Internet routing
technology is not up to the task;
On Fri, 9 Aug 2002, Nenad Trifunovic wrote:
Can you, please, explain why you didn't consider Frame Relay
based exchange in your analysis?
I'd imagine because no real 'high-speed' FR switch exists (as in, oc12 or
above).
-- Alex Rubenstein, AR97, K2AHR, [EMAIL PROTECTED], latency, Al
What functionality does PVC give you that the ethernet VLAN does not?
Shaping, for one.
What is the current max speed of frame relay in any common vendor
implementation (I'm talking routers here).
Doesn't OC48 POS on GSR and Jewniper do FR?
--
Mikael Abrahamssonemail: [EMAIL
and
OC48 ports are expensive, I suspect its overkill for the amount of traffic
that will actually be exchanged there.
I do wonder why most GigE exchange points are still doing single lan
segment peering instead of having a peermaker type service for dynamic
vlan configurations. Manual
-to: [EMAIL PROTECTED]
Delivered-to: [EMAIL PROTECTED]
Subject: Re: Do ATM-based Exchange Points make sense anymore?
Hi again -
A couple points (based on some interactions with folks privately).
This is not an ATM is bad, or general ATM-bashing paper. It simply applies
the same Peering Analysis
Personally, I don't believe that ATM is 'bad' for
shared-fabric exchange point. I mean, it works, and solves several
problems quite easy: a) it's easily distributed via SONET services to
folks who are not next to the ATM switch, b) it makes interconnection
between
Can you, please, explain why you didn't consider Frame Relay
based exchange in your analysis?
I don't have much insight into Frame Relay-based Internet Exchange Points ;-)
The majority of IXes around the world are ethernet-based, with some legacy
FDDI and a few ATM IXes. It is in these areas
: [EMAIL PROTECTED]
Subject: Re: Do ATM-based Exchange Points make sense anymore?
Can you, please, explain why you didn't consider Frame Relay
based exchange in your analysis?
I don't have much insight into Frame Relay-based Internet Exchange Points ;-)
The majority of IXes around the world
What functionality does PVC give you that the ethernet VLAN does not?
That´s quite easy. Endpoint liveness. A IPv4 host on a VLAN has no idea
if the guy on the other end died until the BGP timer expires.
FR has LMI, ATM has OAM. (and ILMI)
Pete
On Fri, 9 Aug 2002, William B. Norton wrote:
One point a couple other folks brought up during the review (paraphrasing)
You can't talk about a 20% ATM cell tax on the ATM-based IX side without
counting the HDLC Framing Overhead (4%) for the OC-x circuit into an
ethernet-based IX. Since
-based Exchange Points make sense anymore?
What functionality does PVC give you that the ethernet VLAN does not?
That´s quite easy. Endpoint liveness. A IPv4 host on a VLAN has no idea
if the guy on the other end died until the BGP timer expires.
FR has LMI, ATM has OAM. (and ILMI)
Pete
What functionality does PVC give you that the ethernet VLAN does not?
That´s quite easy. Endpoint liveness. A IPv4 host on a VLAN has no idea
if the guy on the other end died until the BGP timer expires.
FR has LMI, ATM has OAM. (and ILMI)
Adding complexity to a system increases its
Richard,
There are several exchange points, but their functions tend to be slightly
different from what is understood in the US. IXes such as SOX (Singapore),
HKIX (Hong Kong), JPIX NSP-IXP2 (Japan) and KIX KINX (Korea) tend to be
the more oft quoted IXes in Asia and are familiar in design
There are several exchange points, but their functions tend to be slightly
different from what is understood in the US. IXes such as SOX (Singapore),
HKIX (Hong Kong), JPIX NSP-IXP2 (Japan) and KIX KINX (Korea) tend to be
the more oft quoted IXes in Asia and are familiar
Hi Richard,
http://www.ep.net/naps_ap.html
I know this isn't quote North American, but does anyone know what major
exchange points exist in Asia? The largest one I've found so far is JPIX,
which seems to move a fair amount of traffic
(http://www.jpix.co.jp/en/techncal/traffic.html
http://www.ep.net/naps_ap.html
I was looking for more along the lines of opinions on which exchange
points are significant, without having to go through that entire list
looking for the english translations and trying to find traffic stats.
Ah. Sorry.
HKIX doesn't push the most traffic
providers show up in at least one IXP per country.
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]On Behalf Of
Richard A Steenbergen
Sent: Saturday, May 11, 2002 10:07 AM
To: Dave Curado
Cc: [EMAIL PROTECTED]
Subject: Re: Asian exchange points
On Sat, May 11, 2002
Curado [EMAIL PROTECTED]
Cc: [EMAIL PROTECTED]
Sent: Saturday, May 11, 2002 7:06 AM
Subject: Re: Asian exchange points
On Sat, May 11, 2002 at 12:59:12PM -0400, Dave Curado wrote:
Hi Richard,
http://www.ep.net/naps_ap.html
I was looking for more along the lines of opinions on which
://www.ep.net/naps_ap.html
But a word of caution - some of them are not really exchange points but
actually more like higher tiered service providers providing transit.
Jake
Singapore
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On
Behalf Of Richard
Peter,
For basic Internet style routeing you are probably
correct [and possibly even more true for MPLS style
switching/routeing], but these days customers
demand different classes of service and managed data and bandwidth
services over IP. These requires lots of packet hacking and for
that you
Note that the previous example was about end to end systems achieving line
rate across a continent, nothing about routers was mentioned.
Fair enough - for that I can see the point. Maybe I need to read more though
:)
Peter
Thus spake Peter Galbavy [EMAIL PROTECTED]
Why ?
I am still waiting (after many years) for anyone to explain to me
the issue of buffering. It appears to be completely unneccesary in
a router.
Routers are not non-blocking devices. When an output port is blocked,
packets going to that port
Sprunk
Cc: [EMAIL PROTECTED]
Subject: Re: packet reordering at exchange points
On Mon, 8 Apr 2002, Stephen Sprunk wrote:
Thus spake Iljitsch van Beijnum [EMAIL PROTECTED]
But how is packet reordering on two parallell gigabit interfaces
ever going to translate into reordered packets
points will all be operating at 10Gb/s, and interswitch trunks
at exchange points will be multiples of 10Gb/s.
Of course, I'd hope that individual heavy pairs would establish
private interconnects instead of using public switch fabric, but
I know that's not always { an option | done
On Tue, Apr 09, 2002 at 07:18:35PM +, E.B. Dreger wrote:
Date: Tue, 09 Apr 2002 11:16:24 -0700
From: Paul Vixie [EMAIL PROTECTED]
my expectation is that when the last mile goes to 622Mb/s or 1000Mb/s,
exchange points will all be operating at 10Gb/s, and interswitch trunks
beware: you're probably looking at benchmarks
(I can't resist passing this along for posterity.)
One of our guys described it thus: Engineering wants to see how fast they
can get the wheels to spin on a car. Operations wants to know how fast the
car will go. These are different.
Date: Tue, 9 Apr 2002 16:03:53 -0400
From: Richard A Steenbergen [EMAIL PROTECTED]
To transfer 1Gb/s across 100ms I need to be prepared to buffer at least
25MB of data. According to pricewatch, I can pick up a high density 512MB
[ snip ]
The problem isn't the lack of hardware, it's a
On Tue, Apr 09, 2002 at 10:51:27PM +, E.B. Dreger wrote:
But how many simultaneous connections? Until TCP stacks start
using window autotuning (of which I know you're well aware), we
must either use suboptimal windows or chew up ridiculous amounts
of memory. Yes, bad software, but
Date: Tue, 9 Apr 2002 19:17:44 -0400
From: Richard A Steenbergen [EMAIL PROTECTED]
[ snip beginning ]
Actually here's an even simpler one. Define a global limit for
this, something like 32MB would be more then reasonable. Then
instead of advertising the space remaining in individual
My
On Wed, Apr 10, 2002 at 12:22:57AM +, E.B. Dreger wrote:
My static buffer presumed that one would regularly see line rate;
that's probably an invalid assumption.
Indeed. But thats why it's not an actual allocation.
Why bother advertising space remaining? Simply take the total
space
Date: Tue, 9 Apr 2002 20:39:34 -0400
From: Richard A Steenbergen [EMAIL PROTECTED]
My suggestion was to cut out all that non-sense by simply removing the
received window limits all together. Actually you could accomplish this
goal by just advertising the maximum possible window size and
On Wed, Apr 10, 2002 at 12:57:19AM +, E.B. Dreger wrote:
Unless, again, there's some sort of limit. 32 MB total, 512
connections, each socket gets 64 kB until it proves its worth.
Sockets don't get to play the RED-ish game until they _prove_
that they're serious about sucking down
Date: Tue, 9 Apr 2002 21:12:30 -0400
From: Richard A Steenbergen [EMAIL PROTECTED]
That doesn't prevent an intentional local DoS though.
And the current stacks do? (Note that my 64 kB figure was an
example, for an example system that had 512 current connections.)
Okay, how about new
packet reordering at MAE East was extremely common a few years ago. Does
anyone have information whether this is still happening?
more to the point, does anybody still care about packet reordering at
exchange points? we (paix) go through significant effort to prevent it,
and interswitch
On Mon, 8 Apr 2002, Paul Vixie wrote:
packet reordering at MAE East was extremely common a few years ago. Does
anyone have information whether this is still happening?
more to the point, does anybody still care about packet reordering at
exchange points? we (paix) go through significant
### On Mon, 08 Apr 2002 14:18:52 -0700, Paul Vixie [EMAIL PROTECTED] casually
### decided to expound upon [EMAIL PROTECTED] the following thoughts about
### packet reordering at exchange points:
PV packet reordering at MAE East was extremely common a few years ago. Does
PV anyone have
1 - 100 of 111 matches
Mail list logo