Flent-users discussion archives
 help / color / mirror / Atom feed
* [Flent-users] SmokePing probe
@ 2018-02-17 23:29 Pete Heist
  2018-02-18 11:35 ` Pete Heist
  0 siblings, 1 reply; 2+ messages in thread
From: Pete Heist @ 2018-02-17 23:29 UTC (permalink / raw)
  To: flent-users

I wrote a SmokePing (https://oss.oetiker.ch/smokeping/) probe for IRTT:

Code: https://github.com/peteheist/SmokePing/blob/master/lib/Smokeping/probes/IRTT.pm

Pull request: https://github.com/oetiker/SmokePing/pull/110

I hope to use this in my ISP, which uses SmokePing for about 70 access points. Since ICMP is apparently being prioritized, I don’t think the current SmokePing graphs are telling much of a story about queueing delay.

I’ve been mesmerized for the past couple hours watching one-way delay stats. The link I’m testing is 3km NLOS point-to-point WiFi, with trees about 100 meters from my side of the link. When there is delay or loss, it’s almost always on sending (from me). Median send IPDV (jitter) is around 5x that of the receive IPDV. Presumably, the scattering due to the trees is worse on the uplink because the signal hits the trees closer to the transmitter, when it still has a longer distance to travel. This may also explain my 10/30 asymmetric throughput. I thought about trimming these trees, but this is too much fun… :)


_______________________________________________
Flent-users mailing list
Flent-users@flent.org
http://flent.org/mailman/listinfo/flent-users_flent.org

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [Flent-users] SmokePing probe
  2018-02-17 23:29 [Flent-users] SmokePing probe Pete Heist
@ 2018-02-18 11:35 ` Pete Heist
  0 siblings, 0 replies; 2+ messages in thread
From: Pete Heist @ 2018-02-18 11:35 UTC (permalink / raw)
  To: flent-users


[-- Attachment #1.1: Type: text/plain, Size: 1624 bytes --]

The author pulled the probe in pretty quickly, so it’s already upstream. Some samples:

https://www.drhleny.cz/bufferbloat/smokeping/irtt_smokeping.png <https://www.drhleny.cz/bufferbloat/smokeping/irtt_smokeping.png>

https://www.drhleny.cz/bufferbloat/smokeping/irtt_smokeping2.png <https://www.drhleny.cz/bufferbloat/smokeping/irtt_smokeping2.png>

Maybe I’ll post another image after a while if something more exciting happens… :)

> On Feb 18, 2018, at 12:29 AM, Pete Heist <peteheist@gmail.com> wrote:
> 
> I wrote a SmokePing (https://oss.oetiker.ch/smokeping/) probe for IRTT:
> 
> Code: https://github.com/peteheist/SmokePing/blob/master/lib/Smokeping/probes/IRTT.pm
> 
> Pull request: https://github.com/oetiker/SmokePing/pull/110
> 
> I hope to use this in my ISP, which uses SmokePing for about 70 access points. Since ICMP is apparently being prioritized, I don’t think the current SmokePing graphs are telling much of a story about queueing delay.
> 
> I’ve been mesmerized for the past couple hours watching one-way delay stats. The link I’m testing is 3km NLOS point-to-point WiFi, with trees about 100 meters from my side of the link. When there is delay or loss, it’s almost always on sending (from me). Median send IPDV (jitter) is around 5x that of the receive IPDV. Presumably, the scattering due to the trees is worse on the uplink because the signal hits the trees closer to the transmitter, when it still has a longer distance to travel. This may also explain my 10/30 asymmetric throughput. I thought about trimming these trees, but this is too much fun… :)
> 


[-- Attachment #1.2: Type: text/html, Size: 2605 bytes --]

[-- Attachment #2: Type: text/plain, Size: 151 bytes --]

_______________________________________________
Flent-users mailing list
Flent-users@flent.org
http://flent.org/mailman/listinfo/flent-users_flent.org

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2018-02-18 11:36 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-02-17 23:29 [Flent-users] SmokePing probe Pete Heist
2018-02-18 11:35 ` Pete Heist

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox