Re: Practical guide to predicting latency effects?

[Eric Tykwinski]

There is still one in XCode tools.  It’s a alternate download: 
https://developer.apple.com/download/more/?q=Additional%20Tools%20for%20Xcode 

Of course this is limited to OSX, but it’s there.

Sincerely,

Eric Tykwinski
TrueNet, Inc.
P: 610-429-8300

> On Apr 8, 2020, at 10:33 PM, Lee  wrote:
> 
> On 4/7/20, Adam Thompson  wrote:
>> I’m looking for a practical guide – i.e. specifically NOT an academic paper,
>> thanks anyway – to predicting the effect of increased (or decreased) latency
>> on my user’s applications.
>> 
>> Specifically, I want to estimate how much improvement there will be in
>> {bandwidth, application XYZ responsiveness, protocol ABC goodput, whatever}
>> if I decrease the RTT between the user and the server by 10msec, or by
>> 20msec, or by 40msec.
>> 
>> My googling has come up with lots of research articles discussing
>> theoretical frameworks for figuring this out, but nothing concrete in terms
>> of a calculator or even a rule-of-thumb.
> 
> There used to be network simulators that claimed to figure that out for you - 
> eg
> https://opnetmodeler.wordpress.com/
>  "Predict application performance using real traffic in a simulated mode"
> 
> I suspect all that died after encryption became the norm, since you
> have to be able to see and understand what's going on before you can
> predict what will happen after changing the network.  Take a look at
> https://www.cse.wustl.edu/~jain/cse567-08/ftp/simtools/index.html
>  the date is 2008 and all the references are http://xxx  (or maybe I
> can't search worth beans & missed all the current references)
> 
> Or maybe simulation just got too expensive?  I vaguely recall sitting
> through a few OPNET sales pitches in the early 2000s & people getting
> excited about the product until they found out how much it cost :(
> 
> Regards,
> Lee
> 
> 
>> 
>> Ultimately, this goes into MY calculator – we have the usual north-american
>> duopoly on last-mile consumer internet here; I’m connected directly to only
>> one of the two.  There’s a cost $X to improve connectivity so I’m peered
>> with both, how do I tell if it will be worthwhile?
>> 
>> Anyone got anything at all that might help me?
>> 
>> Thanks in advance,
>> -Adam
>> 
>> Adam Thompson
>> Consultant, Infrastructure Services
>> [[MERLIN LOGO]]
>> 100 - 135 Innovation Drive
>> Winnipeg, MB, R3T 6A8
>> (204) 977-6824 or 1-800-430-6404 (MB only)
>> athomp...@merlin.mb.ca
>> www.merlin.mb.ca
>> 
>> 

Re: Practical guide to predicting latency effects?

[Lee]

On 4/7/20, Adam Thompson  wrote:
> I’m looking for a practical guide – i.e. specifically NOT an academic paper,
> thanks anyway – to predicting the effect of increased (or decreased) latency
> on my user’s applications.
>
> Specifically, I want to estimate how much improvement there will be in
> {bandwidth, application XYZ responsiveness, protocol ABC goodput, whatever}
> if I decrease the RTT between the user and the server by 10msec, or by
> 20msec, or by 40msec.
>
> My googling has come up with lots of research articles discussing
> theoretical frameworks for figuring this out, but nothing concrete in terms
> of a calculator or even a rule-of-thumb.

There used to be network simulators that claimed to figure that out for you - eg
https://opnetmodeler.wordpress.com/
  "Predict application performance using real traffic in a simulated mode"

I suspect all that died after encryption became the norm, since you
have to be able to see and understand what's going on before you can
predict what will happen after changing the network.  Take a look at
https://www.cse.wustl.edu/~jain/cse567-08/ftp/simtools/index.html
  the date is 2008 and all the references are http://xxx  (or maybe I
can't search worth beans & missed all the current references)

Or maybe simulation just got too expensive?  I vaguely recall sitting
through a few OPNET sales pitches in the early 2000s & people getting
excited about the product until they found out how much it cost :(

Regards,
Lee


>
> Ultimately, this goes into MY calculator – we have the usual north-american
> duopoly on last-mile consumer internet here; I’m connected directly to only
> one of the two.  There’s a cost $X to improve connectivity so I’m peered
> with both, how do I tell if it will be worthwhile?
>
> Anyone got anything at all that might help me?
>
> Thanks in advance,
> -Adam
>
> Adam Thompson
> Consultant, Infrastructure Services
> [[MERLIN LOGO]]
> 100 - 135 Innovation Drive
> Winnipeg, MB, R3T 6A8
> (204) 977-6824 or 1-800-430-6404 (MB only)
> athomp...@merlin.mb.ca
> www.merlin.mb.ca
>
>

Re: Practical guide to predicting latency effects?

[Eric Tykwinski]

The only informal paper I remember is Stuart Cheshire’s It’s the latency, 
stupid…
http://www.stuartcheshire.org/rants/Latency.html 


Given it’s from the dialup days, but latency is still the same just a lot lower.

I would thing I would recommend now is checking out SRE docs as well for 
application latency it's not network related, but does affect performance.
https://landing.google.com/sre/sre-book/toc/ 


Sincerely,

Eric Tykwinski
TrueNet, Inc.
P: 610-429-8300

> On Apr 8, 2020, at 6:36 PM, Jakob Heitz (jheitz) via NANOG  
> wrote:
> 
> My data point:
> 
> I'm working from home. My computer is connected through company VPN, over 
> wifi to Comcast.
> Comcast speed test says 18mS.
> I use VNC and Webex with voice and video through the computer.
> VNC response time and voice delay is not noticeable.
> 
> Regards,
> Jakob.
> 
> -Original Message-
> Date: Tue, 7 Apr 2020 22:52:18 +
> From: Adam Thompson 
> 
> I’m looking for a practical guide – i.e. specifically NOT an academic paper, 
> thanks anyway – to predicting the effect of increased (or decreased) latency 
> on my user’s applications.
> 
> Specifically, I want to estimate how much improvement there will be in 
> {bandwidth, application XYZ responsiveness, protocol ABC goodput, whatever} 
> if I decrease the RTT between the user and the server by 10msec, or by 
> 20msec, or by 40msec.
> 
> My googling has come up with lots of research articles discussing theoretical 
> frameworks for figuring this out, but nothing concrete in terms of a 
> calculator or even a rule-of-thumb.
> 
> Ultimately, this goes into MY calculator – we have the usual north-american 
> duopoly on last-mile consumer internet here; I’m connected directly to only 
> one of the two.  There’s a cost $X to improve connectivity so I’m peered with 
> both, how do I tell if it will be worthwhile?
> 
> Anyone got anything at all that might help me?
> 
> Thanks in advance,
> -Adam
> 
> Adam Thompson
> Consultant, Infrastructure Services
> [[MERLIN LOGO]]
> 100 - 135 Innovation Drive
> Winnipeg, MB, R3T 6A8
> (204) 977-6824 or 1-800-430-6404 (MB only)
> athomp...@merlin.mb.ca
> www.merlin.mb.ca
> 

RE: Practical guide to predicting latency effects?

[Jakob Heitz (jheitz) via NANOG]

My data point:

I'm working from home. My computer is connected through company VPN, over wifi 
to Comcast.
Comcast speed test says 18mS.
I use VNC and Webex with voice and video through the computer.
VNC response time and voice delay is not noticeable.

Regards,
Jakob.

-Original Message-
Date: Tue, 7 Apr 2020 22:52:18 +
From: Adam Thompson 

I’m looking for a practical guide – i.e. specifically NOT an academic paper, 
thanks anyway – to predicting the effect of increased (or decreased) latency on 
my user’s applications.

Specifically, I want to estimate how much improvement there will be in 
{bandwidth, application XYZ responsiveness, protocol ABC goodput, whatever} if 
I decrease the RTT between the user and the server by 10msec, or by 20msec, or 
by 40msec.

My googling has come up with lots of research articles discussing theoretical 
frameworks for figuring this out, but nothing concrete in terms of a calculator 
or even a rule-of-thumb.

Ultimately, this goes into MY calculator – we have the usual north-american 
duopoly on last-mile consumer internet here; I’m connected directly to only one 
of the two.  There’s a cost $X to improve connectivity so I’m peered with both, 
how do I tell if it will be worthwhile?

Anyone got anything at all that might help me?

Thanks in advance,
-Adam

Adam Thompson
Consultant, Infrastructure Services
[[MERLIN LOGO]]
100 - 135 Innovation Drive
Winnipeg, MB, R3T 6A8
(204) 977-6824 or 1-800-430-6404 (MB only)
athomp...@merlin.mb.ca
www.merlin.mb.ca

RE: [nanog] Traffic destined for 100.114.128.0/24

[Michel Py]

> Drew Weaver wrote :
> I've noticed over the past couple of weeks that some hosts on a network I
> manage appear to be trying to reach hosts in this network 100.114.128.0/24

It's part of 100.64.0.0/10 that is used for CGN. Possibly, this is the 
by-product of a protocol such as SIP that embeds its own IP address into the 
packet, and there is no ALG. The host on your network is trying to talk to the 
inside NAT address of the other host. It is similar to seing trafic leaving 
your network for RFC1918 addresses.

Michel.

TSI Disclaimer:  This message and any files or text attached to it are intended 
only for the recipients named above and contain information that may be 
confidential or privileged. If you are not the intended recipient, you must not 
forward, copy, use or otherwise disclose this communication or the information 
contained herein. In the event you have received this message in error, please 
notify the sender immediately by replying to this message, and then delete all 
copies of it from your system. Thank you!...

Spoofer Report for NANOG for Mar 2020

[CAIDA Spoofer Project]

In response to feedback from operational security communities,
CAIDA's source address validation measurement project
(https://spoofer.caida.org) is automatically generating monthly
reports of ASes originating prefixes in BGP for systems from which
we received packets with a spoofed source address.
We are publishing these reports to network and security operations
lists in order to ensure this information reaches operational
contacts in these ASes.

This report summarises tests conducted within usa, can.

Inferred improvements during Mar 2020:
ASNName   Fixed-By
6128   CABLE-NET-12020-03-02
11827  WSU2020-03-03
32329  MONKEYBRAINS   2020-03-04
11427  TWC-11427-TEXAS2020-03-26
11525  HRTC   2020-03-26
396073 MAJESTIC-HOSTING-012020-03-31

Further information for the inferred remediation is available at:
https://spoofer.caida.org/remedy.php

Source Address Validation issues inferred during Mar 2020:
ASNName   First-Spoofed Last-Spoofed
577BACOM 2016-03-09   2020-03-12
209CENTURYLINK-US-LEGACY-QWEST   2016-08-16   2020-03-25
6128   CABLE-NET-1   2016-09-03   2020-03-30
7459   GRANDECOM-AS1 2016-09-26   2020-03-26
20412  CLARITY-TELECOM   2016-09-30   2020-03-28
6181   FUSE-NET  2016-10-10   2020-03-31
11427  TWC-11427-TEXAS   2016-10-21   2020-03-07
174COGENT-1742016-10-21   2020-03-31
32440  LONI  2016-11-03   2020-03-28
12083  WOW-INTERNET  2016-11-09   2020-03-31
39939  RISE-CO-AS39939   2016-11-11   2020-03-02
1403   EBOX  2016-11-12   2020-03-09
701UUNET 2017-06-14   2020-03-17
6461   ZAYO-6461 2017-06-21   2020-03-04
63296  AWBROADBAND   2017-09-01   2020-03-31
546PARSONS-PGS-1 2017-11-20   2020-03-26
1  AKAMAI2018-02-14   2020-03-15
393564 SPOKANE   2018-06-05   2020-03-10
20448  VPNTRANET-LLC 2018-09-20   2020-03-23
63275  RADIOWIRE 2019-02-07   2020-03-11
8047   GCI   2019-04-11   2020-03-25
46300  HSC-WAP   2019-10-30   2020-03-26
2886   EC-813-2886   2019-11-05   2020-03-25
21859  ZNET  2019-12-26   2020-03-25
12231  CONWAYCORP2020-01-10   2020-03-26
239UTORONTO  2020-01-28   2020-03-28
13614  ALLWEST   2020-03-16   2020-03-24
51043  ASPIRE01  2020-03-17   2020-03-17
26335  MTSU  2020-03-20   2020-03-20

Further information for these tests where we received spoofed
packets is available at:
https://spoofer.caida.org/recent_tests.php?country_include=usa,can_block=1

Please send any feedback or suggestions to spoofer-i...@caida.org

Looking for contact in Sydney

[Alexandre Legrix]

 Hi NANog community,



In Sydney ASX datacentre, I am looking to perform an iperf test from one of
my transmission equipment.

For that purpose I am looking to rent a server (2 weeks or 1 month)+
installation in the datacentre with following specs:

   - Capable of running a 500M iperf 2.0.9 test
   - Network connectivity in SMF (100BASE-LX) preferred but we can
   accommodate copper

Would one of you able to provide such services and provide me a quote for
it?



Thanks in advance for your feedback,


Please contact us me and Eymeric in cc outside the ML if you can get any
proposal

Best Regards
-- 
Alexandre

Re: Traffic destined for 100.114.128.0/24

[Brandon Martin]

On 4/8/20 2:42 PM, Drew Weaver wrote:

Hello,

I’ve noticed over the past couple of weeks that some hosts on a network 
I manage appear to be trying to reach hosts in this network 100.114.128.0/24


It’s an IANA reserved block but I’m really not sure what it’s used for. 
I just notice it keeps coming up but it doesn’t have a route.


Has anyone else been seeing this?


This is part of the RFC6598 space for carrier-NAT deployments.  If 
you're seeing traffic inbound to your network to those addresses, 
someone's presumably got a default toward you and a hole in their 
internal routing table.  If you're seeing traffic outbound toward those 
addresses, some of your customers have somehow picked up a configuration 
expecting some sort of service there.


Inbound traffic toward your network from or to those addresses is 
effectively a bogon.  Outbound traffic from/to those addresses means you 
have a misconfiguration somewhere (presumably unintentional and perhaps 
some poorly behaved automatic config on a CPE).

--
Brandon Martin

Traffic destined for 100.114.128.0/24

[Drew Weaver]

Hello,

I've noticed over the past couple of weeks that some hosts on a network I 
manage appear to be trying to reach hosts in this network 100.114.128.0/24

It's an IANA reserved block but I'm really not sure what it's used for. I just 
notice it keeps coming up but it doesn't have a route.

Has anyone else been seeing this?

Thanks,
-Drew

Re: best email list?

[Matt Harris]

On Wed, Apr 8, 2020 at 1:08 PM Anne P. Mitchell, Esq. 
wrote:

>
>
> > On Apr 8, 2020, at 12:02 PM, David Funderburk 
> wrote:
> >
> > What email list companies or direct mail have you used with success?
> During this time I feel there are many companies that are or should be
> considering off-site back ups or putting in remote servers.  I'd like to
> contact some of these who could benefit from our data center.  Suggestions?
>
> You do understand that permission cannot be transferred, and that using
> purchased or rented email lists is a violation of all sorts of laws, right?
>

It's also just a bad idea. Legitimate professionals will chalk you up as a
spammer, and not want to do business with you. How many folks here with
budgets for such things explicitly avoid spammers? I know I do.

If you want to gain a positive reputation, the best way to do so is to
actually work for it. It can't be purchased and it certainly can't be
obtained by email blasting a bunch of random addresses you purchased - but
a negative reputation certainly can be obtained in those ways and very
quickly, to boot.

What you can do is put yourself out there effectively. If you own a data
center facility, make sure it's listed on the data center map website. If
you provide connectivity, make sure your network has correct information on
peeringdb and other sites where folks like us go for information on
connectivity providers. If you are providing off-site backups, make sure
your website clearly and effectively communicates your pricing model along
with the technology used to do so and your testing methodology and
frequency, for example, as well. That's the sort of information that
legitimate professionals want to see, will search for, and will hence get
you good placement within google results (there's no SEO black magic that
works, either.)

You can of course also purchase advertising space within contexts that your
potential customers are likely to visit.

Good luck!

Matt Harris|Infrastructure Lead Engineer
816-256-5446|Direct
Looking for something?
Helpdesk Portal|Email Support|Billing Portal
We build and deliver end-to-end IT solutions.

Re: best email list?

[Josh Luthman]

Facebook works infinitely better and costs way less.

We had 0 success with mailing.

Josh Luthman
Office: 937-552-2340
Direct: 937-552-2343
1100 Wayne St
Suite 1337
Troy, OH 45373


On Wed, Apr 8, 2020 at 2:06 PM Milt Aitken  wrote:

> None.
>
> I tried mass mail a long time ago, 3 rounds, no responses.
>
> Advertising & marketing is a very expensive black art.
>
>
>
>
>
>
>
> *From:* NANOG [mailto:nanog-boun...@nanog.org] *On Behalf Of *David
> Funderburk
> *Sent:* Wednesday, April 08, 2020 2:03 PM
> *To:* nanog@nanog.org
> *Subject:* best email list?
>
>
>
> What email list companies or direct mail have you used with success?
> During this time I feel there are many companies that are or should be
> considering off-site back ups or putting in remote servers.  I'd like to
> contact some of these who could benefit from our data center.  Suggestions?
>
> --
>
> Regards,
>
> David Funderburk
> GlobalVision
> 864-569-0703
>
>
> --
> This message has been scanned for viruses and dangerous content by
> *E.F.A. Project* , and is believed to be
> clean.
>

Re: best email list?

[Anne P. Mitchell, Esq.]

> On Apr 8, 2020, at 12:02 PM, David Funderburk  wrote:
> 
> What email list companies or direct mail have you used with success? During 
> this time I feel there are many companies that are or should be considering 
> off-site back ups or putting in remote servers.  I'd like to contact some of 
> these who could benefit from our data center.  Suggestions?

You do understand that permission cannot be transferred, and that using 
purchased or rented email lists is a violation of all sorts of laws, right?

Anne

--
Anne P. Mitchell, Attorney at Law
Dean of Cyberlaw & Cybersecurity, Lincoln Law School
Advisor, Colorado Innovation Response Team Task Force
CEO/President, SuretyMail Email Reputation Certification
Policy Drafting and Review for Businesses
Author: Section 6 of the CAN-SPAM Act of 2003 (the Federal anti-spam law)
Legislative Consultant, GDPR, CCPA (CA) & CCDPA (CO) Compliance Consultant
Board of Directors, Denver Internet Exchange
Chair Emeritus, Asilomar Microcomputer Workshop
Legal Counsel: The CyberGreen Institute
Former Counsel: Mail Abuse Prevention System (MAPS)
Location: Boulder, Colorado

RE: best email list?

[Milt Aitken]

None.

I tried mass mail a long time ago, 3 rounds, no responses.

Advertising & marketing is a very expensive black art.

 

 

 

From: NANOG [mailto:nanog-boun...@nanog.org] On Behalf Of David Funderburk
Sent: Wednesday, April 08, 2020 2:03 PM
To: nanog@nanog.org
Subject: best email list?

 

What email list companies or direct mail have you used with success? During 
this time I feel there are many companies that are or should be considering 
off-site back ups or putting in remote servers.  I'd like to contact some of 
these who could benefit from our data center.  Suggestions?

-- 

Regards,

David Funderburk
GlobalVision
864-569-0703


-- 
This message has been scanned for viruses and dangerous content by 
  E.F.A. Project, and is believed to be clean. 

best email list?

[David Funderburk]

What email list companies or direct mail have you used with success?
During this time I feel there are many companies that are or should be
considering off-site back ups or putting in remote servers.  I'd like to
contact some of these who could benefit from our data center. 
Suggestions?

-- 
Regards,

David Funderburk
GlobalVision
864-569-0703

--
This message has been scanned by E.F.A. Project and is believed to be clean.

RE: Telehouse North 2 Temperatures

[Phil Lavin]

> I am seeing increased temperatures in our cage in THN2 and I am curious if 
> anyone else has noticed this as well. If you have gear in THN2 could you let 
> me know if you have seen an increase in Temps over the past week or so?

Now that you mention it, yes. This is suite 260: 
https://pasteboard.co/J2T7d7k.png.

Looks like about +2.5c starting around midday on Sunday. It was warm outside 
before then so it feels unlikely to be as a result of outside temperature and 
fresh air cooling.

That said, none of our kit has alerted on temperature so it doesn't seem to be 
negatively affecting anything.

Re: Telehouse North 2 Temperatures

[Brandon Butterworth]

On Wed Apr 08, 2020 at 09:47:13AM -0700, Bradley Raymo wrote:
> I am seeing increased temperatures in our cage in THN2

What are the numbers, are they out of spec (it's in
your contract usually schedule 4)?

> and I am curious if anyone else has noticed this as well

It's become more summery the last few days (today is quite
warm). THN2 is free air cooled for efficiency so I'd expect
up but in range.

If in doubt ask operations, they're friendly and are probably
bored now we all stopped visiting.

brandon

Telehouse North 2 Temperatures

[Bradley Raymo]

Hello,

I am seeing increased temperatures in our cage in THN2 and I am curious if
anyone else has noticed this as well. If you have gear in THN2 could you
let me know if you have seen an increase in Temps over the past week or so?

Thanks
Brad

Re: Practical guide to predicting latency effects?

[Saku Ytti]

Hey Adam,

I’m looking for a practical guide – i.e. specifically NOT an academic
> paper, thanks anyway – to predicting the effect of increased (or decreased)
> latency on my user’s applications.
>

This makes answering difficult. Because you may be looking for a simpler
answer than what is available.

Specifically, I want to estimate how much improvement there will be in
> {bandwidth, application XYZ responsiveness, protocol ABC goodput, whatever}
> if I decrease the RTT between the user and the server by 10msec, or by
> 20msec, or by 40msec.
>

TCP single flow throughput is TcpWindow / RTT. But all modern stacks have
TcpWindow scaling (does not mean all devices have), allowing it to grow
beyond the default 0x. However, most TCP implementations burst window
growth, and window grows exponentially, this means if there is speed
step-down in-transit (100G => 10G, or such, which is below sender's rate)
then transit device needs to be able to slurp the window growth amount of
bytes, otherwise there is packet loss and window cannot grow and single
flow cannot attain the max_rate. This means with lower RTT you need to
buffer less, and devices with tiny buffers can be a lot cheaper than
devices with large buffers.
Even though most OS support window scaling, there is often a limit to how
large it is allowed to grow, because it's an attack vector for DRAM DOS.

Example1, no window scaling, 100ms:
0x bytes / 100ms == 5.2Mbps

Example2, no window scaling, 60ms:
0x bytes / 60ms == 8.7Mbps

Example3, no window scaling, 5ms:
0x bytes / 5ms == 104.8Mbps

I believe you can multiply the numbers by 8x, to get performance your
modern window users experience. As I believe windows restricts window-size
by limiting allowable scaling factor to 8x.

Example4, arbitrary window scaling, 100ms, 10Gbps receiver, 100Gbps sender:
100ms * 10Gbps == 125MB, you need tcp window to scale to 125MB to achieve
10Gbps on this path, and you need step-down device 100G=>10G to have 62.5MB
buffer, while window grows from 62.5MB to 125MB and sender burst that
data @ 100Gbps.

The Example4 is easy to fix, by not bursting the window growth, but by
rather doing bandwidth estimation and send the window growth at estimated
receiver rate, removing almost all need for transit buffering. However if
we were to migrate to such congestion control, classical congestion control
like reno, would out-compete it during congestion, so well behaved TCP
streams would get increasingly little capacity as their bandwidth
estimation would keep going down, and reno would win increasingly more
capacity.

Ultimately, this goes into MY calculator – we have the usual north-american
> duopoly on last-mile consumer internet here; I’m connected directly to only
> one of the two.  There’s a cost $X to improve connectivity so I’m peered
> with both, how do I tell if it will be worthwhile?
>

Based on your questions I'd estimate you do not have a business case to
latency optimize if it carries a premium. The most to benefit would
probably be for competitive gamers, but they may be bad users on average
being subsidized by light users, so it's not entirely clear if you want to
invest to attract them.


-- 
 ++ytti