***: m0unds has joined #arpnetworks
novae has quit IRC (Ping timeout: 264 seconds)
qbit has quit IRC (Quit: leaving)
novae has joined #arpnetworks
qbit has joined #arpnetworks
qbit has quit IRC (Client Quit)
qbit has joined #arpnetworks
qbit is now known as Guest14252
Guest14252 is now known as qbit
qbit has quit IRC (Quit: leaving)
qbit has joined #arpnetworks
qbit is now known as Guest37399
Guest37399 is now known as qbit
mkb has quit IRC (Remote host closed the connection)
mkb has joined #arpnetworks mkb: At first glance it seemed that ARP had engaged in this newfangled Twitter thing with a hashtag on the front page, but I was pleasantly surprised to see that it was actually an IRC channel. mercutio: haha
irc had # first. mkb: I think they took it from IRC mercutio: most people don't know what irc are these days up_the_irons: yeah we own the # mercutio: do the kvm nodes emulate cirrus logic video?
looks like they do hmm brycec: (that's what mine says - it's a pretty common default for kvm/qemu) ***: jcv_ has quit IRC (Quit: leaving)
jcv has joined #arpnetworks
mkb has quit IRC (Ping timeout: 260 seconds)
mkb has joined #arpnetworks
mkb has quit IRC (Read error: Connection reset by peer)
mkb has joined #arpnetworks
mkb has quit IRC (Ping timeout: 245 seconds)
mkb has joined #arpnetworks mhoran: up_the_irons: I'm still getting terrible IPv6 throughput from my native IPv6 connection, while speedtests show 85 Mbps.
Any thoughts?
73 Mbps to a speedtest in San Jose. But 440 Kbps via SCP to matthoran.com. acf_: mhoran: ipv6 connection from arp? mhoran: I have native IPv6 at home, to my ARP VPS. acf_: what ISP? mhoran: Time Warner. acf_: ah. Comcast here, also with native IPv6 mhoran: Nice. acf_: do you know if it's a congested ISP link?
ie, packet loss to ARP mhoran: I don't see any packet loss, just low throughput.
I pretty much have an open SSH connection to my server 24/7 and I never really have a problem with it, just when I try to transfer data over v6. acf_: do you have a traceroute you'd be willing to share? mhoran: Looks like it takes HE.net most of the way, though Inever had a problem with my HE.net tunnel. mercutio: mhoran: try a udp test maybe? acf_: hm. I'm pretty sure HE <-> ARP is okay ***: toeshred has quit IRC (Quit: WeeChat 1.0.1) mhoran: Hmm. acf_: -6 -O /dev/null http://ec2.acfsys.net/videos/comme_un_enfant.webm mhoran: acf_: https://gist.github.com/mhoran/ef24133f089cfa996d74 BryceBot: Gist: "https://gist.github.com/ef24133f089cfa996d74" mercutio: i'll see what my ipv6 thrroughput is like acf_: wget^
that's an HE tunnel to Amazon AWS mhoran: Getting faster and faster.
Almost 80 Mbps.
Around the same latency on a traceroute to that EC2 host. mercutio: hmm how do you go to ipv6 address with iperf
i'm putting it in square brakcets
and it's not working mhoran: Hmm. I'm not sure. mercutio: i'm doing the -V to set ipv6 too
meh i'll make a name acf_: did you escape the square brackets? mhoran: Route to that EC2 host hits the same exit node from Time Warner, so I don't think that's what's overloaded, or where the problem is. acf_: traceroute back to you: http://paste.unixcube.org/k/9873d0 mercutio: i'm getting 8 to 10 megabit
well i tried ' and "'
that's sending from arp
now i'll test receiving to arp
10 megabit send
i'm hitting he.net in palo alto through to arp it seems
and ntt back from arp acf_: mercutio: this is your native ipv6? mercutio: this is native ipv6 at both ends yes.
openbsd to openbsd acf_: root@phoenix:/home/acf# wget -6 -O /dev/null http://www.arpnetworks.com/100mb.bin
8.08MB/s
from Comcast mercutio: bah iperf udp mode is binding to a diff address mhoran: Yeah I get < 100KB/s from here. Same as my VPS.
Compared to wget -4 which reaches 7 MB/s.
So something on HE.net between NYC and LAX is terrible. But Seattle is fine. mercutio: i'm getting 0% packet loss with udp
oh i got 1 packet out of 8494 dropped
i'mg etting shit loads of packet dsropps uploading udp from arp
hmm
80% + packet loss at 4 megabit
and 0% at 1 megabit
i have the ipv4 udp limit lifted on my vps
i dunno if it's separate for ipv6, but even that is at 5 megabit by default i thik... acf_: there is a limit on IPv6? mercutio: not sure acf_: are you going via NYC also? mercutio: ohn it may be ip i am using
willi switch to a diff ip
yeah 10 megabit is fine on other ip
not via nyc, via palo alto for me
oh this address is he.net both directions
so yeah it may be he.net have difficulties in some locations.
hmm i have a vm in uk with ipv6 i think
that should be via new york acf_: mhoran: wget -6 -O /dev/null http://[2605:2700:0:5::4713:9574]/100mb.bin
another IPv6 endpoint on HE in LAX mhoran: Speedy! mercutio: blodoy hell
it's vultr and it wants me to use router discovery
i'll try another one mhoran: Not incrediblyspeedy, but 5 times faster.
500Kb/s instead of 100.
Still not great ... acf_: how different are the traceroutes? mercutio: my other uk host gets 2.7mb/sec over arp ipv6
to that odwnlaod file. mhoran: Quite different actually.
https://gist.github.com/mhoran/89125af09f10232223a5 BryceBot: Gist: "https://gist.github.com/89125af09f10232223a5" mercutio: http://ipv6.uk.meh.net.nz/testfile.zip
what do you guys get to that?
from arp i'm only geting 100k/sec
but that host downloads fast from arp mhoran: Just under 7 MB/s. mercutio: hmm mhoran: Pretty good to that one. mercutio: oh wow :) acf_: mercutio: does that go to arp via NTT? mercutio: nope acf_: ok good. return path is NTT.. mercutio: http://pastebin.com/vmNF2SYK
heh you can see return path is ntt
from hop 6 :)
but also, traceroute works with ipv6 automatically on linux now acf_: how long has this been going on for? mhoran: I only switched to native about 6 months ago but things got unbearably slow maybe a month ago. acf_: oh :/
have we confirmed that it's likely HE?
their NOC is fantastic... mhoran: Sure seems it.
I'll send a support ticket tomorrow if up_the_irons doesn't notice this. But it's bed time for me now. mercutio: i really should switch ipv6 on at home again ***: acf_ has quit IRC (Ping timeout: 256 seconds)