Skip to Content.

rare-dev - Re: [rare-dev] RES: perfSONAR on RARE/FreeRtr

Subject: Rare project developers

List archive


Re: [rare-dev] RES: perfSONAR on RARE/FreeRtr


Chronological Thread 
    < Chronological >      < Thread >
  • From: Tim Chown <>
  • To: mc36 <>
  • Cc: "" <>, Pavle Vuletić <>, Marcos Felipe Schwarz <>, Frédéric LOUI <>, Ivana Golub <>, Xavier Jeannin <>, Mohácsi János <>, Visky Balázs <>
  • Subject: Re: [rare-dev] RES: perfSONAR on RARE/FreeRtr
  • Date: Fri, 26 Aug 2022 14:33:29 +0000
  • Accept-language: en-GB, en-US
  • Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=jisc.ac.uk; dmarc=pass action=none header.from=jisc.ac.uk; dkim=pass header.d=jisc.ac.uk; arc=none
  • Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=GqruYXOvrlB8P4EdXBjayrDcb0tjdsBrdZ+OR15LMMc=; b=jKU8W8xosMiUF0O9C8BwbS6s8tGjlbwb9PdgM+EaQEHmNWbxuZ2TaXstwZ1c1b/E0c6xFl1JVNnAeBedU3aQD1CHeT32eObjRpB5dOIBty8E4i/zi7Agakn7r0h6bDAS2PNW+duwIYq6XHTPx9+Uc+kvkfZf/EQMYhgH8XE/6E4LCc3YZEU9xYQBfmcQB4+K8X+6eBClneKVKbglXaA6TQ8NmknN31LRCNvA88OHsq01fEf5nRWZ7AyE5YnKBvf7unEZRdp6CHcW4AJTOcSDU6XqzFRQbLVBT1pvwb6OIyTUuRlf56vZZ0GJGu61r1UJoWVY7rgA9IjLNs5HFy12iA==
  • Arc-seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=l//VEtfGz1NYzOAjqF96EzdHwiwKk9N8lz6Y8ieJ6g1KB3BBxPFMogjdj7TEc6oDY807IanswR/4NmRem5GY3DsAq7vZ0FtqgCzXBqzRU3tk7FbQkm2VXYZBOOYucr4OW3PaGwAYSJgPjdFV1T04yPuboh33iZPHhdcRfrtLyFLFlpO75OdVuh680Dr6krSGQvnuKSctVkBpdO+jmuLKe2GOB5E+5qWC7EY8SBXr3i2e2p938QsaOeJv9Elqp7x0VHsc/vFl9qmhnBQI7vaU3ZT1EMCy6hPCx2CahLec1joiuMmaOblRXkB7hSYtfrClcj6MZTxgQVFIPcKoELiswQ==
  • Authentication-results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=jisc.ac.uk;
:-o

Microdep - https://www.uninett.no/en/microdep

And a recent presentation:
https://www.es.net/science-engagement/ci-engineering-lunch-and-learn-series
https://youtu.be/b0SugIIsO5M

It’s pretty cool work.

Tim

> On 26 Aug 2022, at 12:11, mc36 <> wrote:
>
> microdep??? without a link???
> tim! when you first said lola, i put it to google and i got boobs :)
>
> On 8/26/22 13:02, Tim Chown wrote:
>> Well, we have different reasons for asking for new features, or for things
>> to be tested.
>> In this case, TimeMap and Microdep are work items elsewhere in WP6, and it
>> s good, especially as this project nears its end and the new one starts
>> in January, to show examples of the work streams being able to feed into
>> each other. Microdep is all about measuring and analysing changes in
>> network behaviour and paths, it s really interesting work.
>> Anyway, I ll stop there. If Fabio or Claudio don t respond on
>> TimeMap, the point is moot.
>> Tim
>>> On 26 Aug 2022, at 11:47, mc36 <> wrote:
>>>
>>> so please instead of trying to solve yourself and then pushing that,
>>> please ask for a solution to the original problem....
>>> dont get misunderstood, we're still happy to implement anything but imho
>>> this is the way to go if it comes to network monitoring...
>>> you dont need to consult the routers at all to have the full visibility
>>> and you can have arbitrary number of monitoring systems in parallel, it
>>> wont hurt the router cpus....
>>>
>>>
>>>
>>>
>>> On 8/26/22 12:17, Tim Chown wrote:
>>>> This might be interesting for Olav s microdep work in Task 3, copying
>>>> Pavle.
>>>>> On 26 Aug 2022, at 11:14, mc36 <> wrote:
>>>>>
>>>>> if you need, and since this output is good as is, if you need this in
>>>>> streaming telemetry or prometheus then that...
>>>>> in kifu we went the prometheus way and this table _graphs_ nicely when
>>>>> there is a flappy (i/e)bgp somewhere
>>>>>
>>>>> On 8/26/22 12:12, mc36 wrote:
>>>>>> or maybe a bmp demo?
>>>>>> if they shut the backup geant link then it'll become false, and the
>>>>>> change will be 2...
>>>>>> when they noshut it, then the state will be true again, but the change
>>>>>> will be 3...
>>>>>> so if you didn't listened to janos at that time, we disabled snmp for
>>>>>> years now...
>>>>>> bmp.wdcvhpc#show bmp bmp
>>>>>> from peer
>>>>>> as state change last
>>>>>> 195.111.97.83 152.66.0.124
>>>>>> 2547 true 1 5d14h
>>>>>> 195.111.97.83 195.111.103.206
>>>>>> 12301 true 1 5d14h
>>>>>> 195.111.97.108 62.40.96.23
>>>>>> 20965 true 1 5d14h
>>>>>> 195.111.97.108 62.40.96.24
>>>>>> 20965 true 1 5d14h
>>>>>> 195.111.97.108 62.40.102.26
>>>>>> 20965 true 1 5d14h
>>>>>> 195.111.97.108 62.40.124.101
>>>>>> 20965 true 1 5d14h
>>>>>> 195.111.97.108 80.239.195.56
>>>>>> 1299 true 1 5d14h
>>>>>> 195.111.97.108 81.183.2.166
>>>>>> 5483 true 1 5d14h
>>>>>> 195.111.97.108 83.97.88.81
>>>>>> 21320 true 1 5d14h
>>>>>> 195.111.97.108 94.21.255.13
>>>>>> 20845 true 1 5d14h
>>>>>> 195.111.97.108 193.188.137.1
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.108 193.188.137.2
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.108 193.188.137.53
>>>>>> 5400 true 1 5d14h
>>>>>> 195.111.97.108 193.188.137.74
>>>>>> 8708 true 1 5d14h
>>>>>> 195.111.97.108 193.188.137.125
>>>>>> 3303 true 1 5d14h
>>>>>> 195.111.97.108 193.188.137.142
>>>>>> 199524 true 1 5d14h
>>>>>> 195.111.97.108 193.188.137.175
>>>>>> 6939 true 1 5d14h
>>>>>> 195.111.97.108 193.224.231.138
>>>>>> 65012 true 1 5d14h
>>>>>> 195.111.97.108 195.191.97.254
>>>>>> 59649 true 1 5d14h
>>>>>> 195.111.97.108 213.222.185.3
>>>>>> 21334 true 1 5d14h
>>>>>> 195.111.97.108 2001:738:1040:193:224:231:136:138 65012 true
>>>>>> 1 5d14h
>>>>>> 195.111.97.108 2001:798:1::65
>>>>>> 21320 true 1 5d14h
>>>>>> 195.111.97.108 2001:798:1b:10aa::5
>>>>>> 20965 true 1 5d14h
>>>>>> 195.111.97.108 2001:7f8:35::3303:1
>>>>>> 3303 true 1 5d14h
>>>>>> 195.111.97.108 2001:7f8:35::5507:1
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.108 2001:7f8:35::5507:2
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.108 2001:7f8:35::6939:1
>>>>>> 6939 true 1 5d14h
>>>>>> 195.111.97.108 2001:2000:3080:14f5::1 1299
>>>>>> true 1 5d14h
>>>>>> 195.111.97.108 2a01:368:1fe::11
>>>>>> 20845 true 1 5d14h
>>>>>> 195.111.97.109 62.40.124.17
>>>>>> 20965 true 1 5d14h
>>>>>> 195.111.97.109 83.97.88.85
>>>>>> 21320 true 1 5d14h
>>>>>> 195.111.97.109 149.11.10.9
>>>>>> 174 true 1 5d14h
>>>>>> 195.111.97.109 193.188.137.1
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.109 193.188.137.2
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.109 193.188.137.125
>>>>>> 3303 true 1 5d14h
>>>>>> 195.111.97.109 193.188.137.142
>>>>>> 199524 true 1 5d14h
>>>>>> 195.111.97.109 193.224.231.142
>>>>>> 65012 true 1 5d14h
>>>>>> 195.111.97.109 195.191.97.254
>>>>>> 59649 true 1 5d14h
>>>>>> 195.111.97.109 213.163.3.173
>>>>>> 12301 true 1 5d14h
>>>>>> 195.111.97.109 2001:738:1040:193:224:231:140:142 65012 true
>>>>>> 1 5d14h
>>>>>> 195.111.97.109 2001:798:1::69
>>>>>> 21320 true 1 5d14h
>>>>>> 195.111.97.109 2001:798:10:10aa::15
>>>>>> 20965 true 1 5d14h
>>>>>> 195.111.97.109 2001:7f8:35::3303:1
>>>>>> 3303 true 1 5d14h
>>>>>> 195.111.97.109 2001:7f8:35::5507:1
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.109 2001:7f8:35::5507:2
>>>>>> 5507 true 1 5d14h
>>>>>> 195.111.97.109 2001:978:2:27::7:1
>>>>>> 174 true 1 5d14h
>>>>>> 195.111.97.112 81.183.245.9
>>>>>> 5483 true 1 5d14h
>>>>>> bmp.wdcvhpc#
>>>>>> On 8/26/22 12:05, mc36 wrote:
>>>>>>> im not against the perfsonar at all, the more measures the better...
>>>>>>>
>>>>>>> but to spot the routing and/or prefix changes, we have log-spf in
>>>>>>> isis, ospf and lsrp
>>>>>>>
>>>>>>> if you still use icinga, prometheus any basically anything, all these
>>>>>>> could be barked back that is:
>>>>>>> the monitoring asks regularly the single management box part of the
>>>>>>> igp,
>>>>>>> as as soon as the routing change happens, the show will differ so
>>>>>>> it'll tell you what happened
>>>>>>>
>>>>>>> frederic, could you please show tim the icinga demo from the p4lab
>>>>>>> after to let the others catch the idea?
>>>>>>> (no worries, i'll be with you to back you up if the vc will be after
>>>>>>> my lunch)
>>>>>>>
>>>>>>> imho that was the stf15 presentation about:
>>>>>>> http://www.freertr.org/present/geant-bmp.pdf
>>>>>>> we did it with niall's help, he _flapped_ 2 times the hbone backup
>>>>>>> link and we got an alert which needed to be cleared...
>>>>>>>
>>>>>>>
>>>>>>> janos, balazs, if frederic fails to find a proper timeslot, could you
>>>>>>> please help a bit here by demoing what happens when you shut
>>>>>>> szeged-debrecen for a minute or so?
>>>>>>>
>>>>>>> thanks,
>>>>>>> cs
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> On 8/26/22 11:54, Tim Chown wrote:
>>>>>>>>> On 26 Aug 2022, at 10:48, mc36 <> wrote:
>>>>>>>>>
>>>>>>>>> On 8/26/22 11:41, Tim Chown wrote:
>>>>>>>>>>> On 25 Aug 2022, at 14:56, mc36 <> wrote:
>>>>>>>>>>>
>>>>>>>>>>> hi,
>>>>>>>>>>>
>>>>>>>>>>> On 8/25/22 15:41, Marcos Felipe Schwarz wrote:
>>>>>>>>>>>> 1. supports all perfsonar test, including bandwith at 100G and
>>>>>>>>>>>> above. With 2., we'll be limited by the CPU resources of the
>>>>>>>>>>>> switch and cpu-todataplane performance, which normally are very
>>>>>>>>>>>> limited.
>>>>>>>>>>> so true, moreover, if you do 100g measurements in every 10ms then
>>>>>>>>>>> the user traffic will be heavily suppressed...
>>>>>>>>>>> imho doing a twamp measurements in every 10ms should give good
>>>>>>>>>>> enough results
>>>>>>>>>> perfSONAR usually runs three types of test - throughput, latency
>>>>>>>>>> (including loss), and path. Latency is run continuously (but is
>>>>>>>>>> very lightweight), but throughput is only by default run once
>>>>>>>>>> every 6 hours, for 30 seconds, so it will not generally affect
>>>>>>>>>> user traffic, and with TCP tests, it will be fair in
>>>>>>>>>> competing for bandwidth.
>>>>>>>>> which is partially true as we all know about the bandwidth*delay
>>>>>>>>> product
>>>>>>>>>
>>>>>>>>> consider that you'll perform it over a very long distances
>>>>>>>>
>>>>>>>> Yes, some tests will be intercontinental, but the R&E backbones are
>>>>>>>> generally not congested, so any loss, and thus drop in performance
>>>>>>>> (unless maybe using BBR) is likely caused by issues in the end
>>>>>>>> sites. There s a few hundred CERN experiment sites running
>>>>>>>> perfSONAR with these sorts of tests, usually between countries or
>>>>>>>> continents.
>>>>>>>>
>>>>>>>> Tim


Archive powered by MHonArc 2.6.19.

Top of Page