[00:18] brycec: looks like its O.K now : ping wolfman.devio.us [00:18] PING wolfman.devio.us (66.7.199.108) 56(84) bytes of data. [00:18] 64 bytes from devio.us (66.7.199.108): icmp_seq=1 ttl=244 time=35.3 ms [00:29] *** Arenlor has quit IRC (Ping timeout: 264 seconds) [01:05] *** zhangxiaobao has joined #arpnetworks [01:09] *** zhangxiaobao has quit IRC (Read error: Connection reset by peer) [01:21] *** zhangxiaobao has joined #arpnetworks [01:27] I wonder what can explain this: https://smokeping.cobryce.com/?displaymode=n;start=2014-10-18%2013:26;end=now;target=Internet.VoipMS.toronto3voipms [01:27] latency drop from 160ms to about 70ms [01:28] are you experiencing periodic abnormal latencies on ipv6? [01:29] every 8 or so pings has very high latency [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=1 ttl=64 time=20.8 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=2 ttl=64 time=29.8 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=3 ttl=64 time=0.527 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=4 ttl=64 time=0.847 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=5 ttl=64 time=0.496 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=6 ttl=64 time=0.512 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=7 ttl=64 time=9.80 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=8 ttl=64 time=25.5 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=9 ttl=64 time=11.1 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=10 ttl=64 time=0.795 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=11 ttl=64 time=0.736 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=12 ttl=64 time=0.709 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=13 ttl=64 time=0.548 ms [01:29] 64 bytes from 2607:f2f8:acd0::1: icmp_seq=14 ttl=64 time=1.32 ms [01:30] zhangxiaobao: use pastebin for multi line messages [01:31] ok, sorry [01:31] I have not noticed anything, you are probably experiencing ICMP de-prioritization [01:33] and looking glass seem to have lost ipv6 connectivity, can't ping anywhere? [01:39] *** zhangxiaobao has quit IRC (Remote host closed the connection) [01:47] I don [01:48] I don't think they set up Ipv6 on the looking glass as yet [01:50] *** zhangxiaobao has joined #arpnetworks [02:05] *** zhangxiaobao has quit IRC (Remote host closed the connection) [04:30] *** pjs has quit IRC (Read error: Network is unreachable) [04:31] *** pjs has joined #arpnetworks [04:31] *** up_the_irons has quit IRC (Ping timeout: 260 seconds) [04:31] *** pjs is now known as Guest20602 [04:32] *** up_the_irons has joined #arpnetworks [04:32] *** ChanServ sets mode: +o up_the_irons [04:38] mercutio: i fixed ipv6 on the lg [04:55] oh cool [04:55] heh traceroute6 to www.arpnetworks.com shows as www [04:56] maybe take the search path out in resolv.conf? [05:17] lol [05:17] yeah go for it [05:57] *** Guest20602 is now known as pjsg [05:57] *** pjsg is now known as pjs [08:54] mnathani: That is interesting about the voip.ms hosts. If you look at the "Last 7 days" you'll see it's consistent, same times every day for the last week, coinciding with packet loss too. Apparently there's congestion along the route. Here's an mtr, you can clearly see it's the Level3/NTT handoff http://sprunge.us/dDNW [10:37] *** pjs has quit IRC (*.net *.split) [10:37] *** toddf has quit IRC (*.net *.split) [10:37] *** SpaceDump has quit IRC (*.net *.split) [10:37] *** m0unds has quit IRC (*.net *.split) [10:37] *** toddf has joined #arpnetworks [10:37] *** ChanServ sets mode: +o toddf [10:37] *** SpaceDump has joined #arpnetworks [10:37] *** m0unds has joined #arpnetworks [10:38] *** pjs has joined #arpnetworks [10:39] *** pjs is now known as Guest72906 [11:20] *** Seji has quit IRC () [11:24] *** Seji has joined #arpnetworks [14:22] hmm that didn't seem to work [15:35] brycec: I would think its more like a shift in routing, in a schedule like that rather than congestion. I plan to compare mtr reports from times of lower latency to higher latency to see if I can figure it out [15:36] mnathani: well you have my mtr from the high latency time period :) [15:36] I do indeed [15:38] if there is actual congestion usuallyt iperf in udp mode at low bandwidth over a long period of the time is best way to monitor [15:38] you can usually get it to report every 0.5 seconds, but you can hack the source to report every 100 msec. [15:38] mercutio: you probably need access to a box at each end to test that out? [15:38] mnathani: yeah. [15:38] that's the annoying part. [15:39] remote end being monitored is a Toronto Voip.ms POP [15:39] is there a way to get a reverse trace route without access to a looking glass or the remote end? [15:41] oh. [15:41] nope [15:41] you could email them [15:41] is it level 3 outbound? [15:41] hopefully level3 inbound is turned on soon and fixes it. [15:44] * staticsafe is slightly concerned [15:44] i use Toronto's voip.ms POP [15:56] i tried google hangouts outbound voice thingy before. the free thing. it seemed laggy. [15:56] skype worked better. [15:57] i dunno how skype manages so well tbh. for international calls it seems to have some great jitter correction or something - it doesn't feel like it breaks up and jitters heaps. [15:58] and the echo cancellation seems superb. [16:17] +1 for Skype [16:17] connection has to be really poor for quality to degrade [16:19] i kind of hate skype, but it works well for actual calls. [16:19] it seems to be quite buggy though, especially on android. [16:19] and uses way too much cpu on android, linux, macos etc. [16:20] it never seems jabber really got as well functioning for every day users as i would have liked :( [16:22] I use Skpe all the time on Windows, no complaints [16:33] From an ARP VPS? That would be really silly. 15:44:40 staticsafe | i use Toronto's voip.ms POP [16:36] oh nope [16:36] from home [16:36] heh [16:36] Bear in mind that latency is being measured from an ARP vps... you're probably fine :p [16:37] er, bare [16:38] im 10ms away from it, peering at the local IX [16:39] staticsafe: looking at the smokeping graphs, it seems toronto, toronto2 and toronto3 are the ones where latency changes drastically every day. ie: toronto4 seems unaffected [16:40] as brycec mentioned, this is latency to an ARP VPS [16:40] (I don't think I knew there was a toronto4...) [16:41] toronto4 goes over Cogent [16:41] * brycec never imagined he'd see Cogent actually be the better route [16:42] although the return traffic might be different as level3 is not announcing ARP IP space at the moment [16:51] eww cogent [16:51] mnathani: on windows it works better than other platforms. [16:53] http://lg.arpnetworks.com/cgi-bin/bgplg?cmd=show+ip+bgp&req=184.75.213.210 [16:53] http://lg.arpnetworks.com/cgi-bin/bgplg?cmd=show+ip+bgp&req=184.75.215.146 [16:53] first is toronto4, second toronto3 [16:54] oh, that's nlayer [16:54] i'm surprised it's going to nlayer via level3 [16:56] so cogent is a better route if dual advertised, .. so they're avoiding cogent by not even advertising to cogent, or prepending [16:57] i like to add a prepend to cogent routes myself. [16:57] cogent often have short as-paths. but intermittent performance. [16:57] although on-net is a lot better than it was. [16:57] it's mostly their peering/transit that sucks. [17:37] mercutio: what do you mean by 'on-net' ? [18:01] mnathani: cogent at both ends [18:01] like cogent -> at&t is crap etc. [18:46] *** sga0 has joined #arpnetworks [18:46] *** sga0_ has quit IRC (Ping timeout: 255 seconds) [19:26] *** zhangxiaobao has joined #arpnetworks [19:28] *** zhangxiaobao has quit IRC (Remote host closed the connection) [20:42] *** Guest72906 is now known as pjs [21:58] *** vissborg has quit IRC (Remote host closed the connection) [21:59] *** vissborg has joined #arpnetworks [23:57] *** novae has joined #arpnetworks [23:57] *** novae has quit IRC (Changing host) [23:57] *** novae has joined #arpnetworks