Re: Guest Column: Kentik's Doug Madory, Last Call for Upcoming ISOC Course + More

[John Springer]

Inline

On Sat, Sep 9, 2023 at 09:51 Ryan Hamel  wrote:

> Martin and Tom,
>
> How is it a private marketing initiative exactly if the links go to
> stories on NANOG's website?
>

This seems deliberately obtuse. It is a private marketing initiative
exactly if the links go to private marketing stories on NANOG's website.

Are you saying the very org that brings us together, is not allowed to spur
> discussion based on newsletter content and cannot provide us with updates
> and/or reminders about various things?
>

More deliberate and fairly unhelpful tongue in cheekery. A link to The
NANOG Mailing List Usage Guidelines was cited. That was helpful and
authoritative. If the marketing arm of NANOG wishes to change the
Guidelines, that will presumably take more formalities than some snarky
remarks.

>
> Y'all have been making a mountain out of a molehill.
>

Last I looked, NANOG members have been making mountains out of any handy
materials (or none at all) for several decades now. Folksy condescension is
no more welcome or constructive than it has ever been.

And FTR, Tom and Marty make most sense to me in this thread. So far.

Springer


> Ryan
>
> --
> *From:* Tom Beecher 
> *Sent:* Saturday, September 9, 2023 9:30:13 AM
> *To:* Martin Hannigan 
> *Cc:* Ryan Hamel ; nanog@nanog.org 
>
> *Subject:* Re: Guest Column: Kentik's Doug Madory, Last Call for Upcoming
> ISOC Course + More
>
> Caution: This is an external email and may be malicious. Please take care
> when clicking links or opening attachments.
>
> What network does Nanog-news operate?
>>
>> Marketing email doesn’t  belong on an operational list.  Even if its
>> NANOG marketing itself.  (Ack Kentik non involvement).
>>
>
> This is the right comment.
>
> The NANOG Mailing List Usage Guidelines  (
> https://www.nanog.org/resources/usage-guidelines/ ) are fairly clear
> about this.
>
> Posts to NANOG’s Mailing List should be focused on operational and
>> technical content only, as described by the NANOG Bylaws.
>> Using the NANOG Mailing List as a source for private marketing
>> initiatives, or product marketing of any kind, is prohibited.
>
>
> Sending this type of message to nanog@ is not appropriate, by our own
> rules. This issue will be raised at the next members meeting.
>
>
>
>
> On Fri, Sep 8, 2023 at 9:39 PM Martin Hannigan  wrote:
>
>>
>> What network does Nanog-news operate?
>>
>> Marketing email doesn’t  belong on an operational list.  Even if its
>> NANOG marketing itself.  (Ack Kentik non involvement).
>>
>> Warm regards,
>>
>> -M<
>>
>>
>

Re: Lossy cogent p2p experiences?

[Saku Ytti]

On Sat, 9 Sept 2023 at 21:36, Benny Lyne Amorsen
 wrote:

> The Linux TCP stack does not immediately start backing off when it
> encounters packet reordering. In the server world, packet-based
> round-robin is a fairly common interface bonding strategy, with the
> accompanying reordering, and generally it performs great.

If you have
Linux - 1RU cat-or-such - Router - Internet

Mostly round-robin between Linux-1RU is gonna work, because it
satisfies the a) non congested b) equal rtt c) non-distributed (single
pipeline ASIC switch, honoring ingress order on egress),
requirements. But it is quite a special case, and of course there is
only a round-robin on one link in one direction.

Between 3.6-4.4 all multipath in Linux was broken, and I still to this
day help people with problems on multipath complaining it doesn't
perform (in LAN!).

3.6 introduced FIB to replace flow-cache, and made multipath essentially random
4.4 replaced random with hash

When I ask them 'do you see reordering', people mostly reply 'no',
because they look at PCAP and it doesn't look important to the human
observer, it is such an insignificant amount.. Invariable problem goes
away with hashing. (netstat -s is better than intuition on PCAP).


-- 
  ++ytti