High packet loss to IPv6 DNS servers

Hi, I have been using Cloudflare’s IPv6 DNS service for some time, but starting today there has been very high packet loss to the IPv6 DNS servers from AT&T ISP in California. No issues with any other IPv6 sites. From a test I just did

— 2606:4700:4700::1111 ping statistics —
115 packets transmitted, 13 packets received, 88% packet loss
round-trip min/avg/max = 180.571/190.622/203.624 ms

Traceroute:

$ traceroute6 2606:4700:4700::1111
traceroute6 to 2606:4700:4700::1111 (2606:4700:4700::1111) from 2600:1700:3ec0:5238:fd:d00e:e413:f6ed, 64 hops max, 12 byte packets
1 2600:1700:3ec0:5238::1 4.292 ms 1.495 ms 1.157 ms
2 2600:1700:3ec0:5230::1 2.496 ms 1.934 ms 2.190 ms
3 2001:506:6000:11b:71:156:212:155 7.857 ms 9.574 ms 8.973 ms
4 * * *
5 * *
sffca401igs.ipv6.att.net 8.337 ms
6 2001:1890:1fff:41e:192:205:32:222 10.787 ms 9.753 ms 10.527 ms
7 * *
cloudflare-ic-328258-sjo-b21.c.telia.net 209.788 ms
8 * *
2400:cb00:4:1024::ac44:bf8d 182.624 ms

No one has a comment? Something really is wrong here, as the IPv4 DNS servers are fine. No one cares about IPv6?

[email protected]:/etc/resolver/dns_servers# ping 1.1.1.1
PING 1.1.1.1 (1.1.1.1): 56 data bytes
64 bytes from 1.1.1.1: seq=0 ttl=53 time=7.504 ms
64 bytes from 1.1.1.1: seq=1 ttl=53 time=7.311 ms
64 bytes from 1.1.1.1: seq=2 ttl=53 time=7.271 ms
64 bytes from 1.1.1.1: seq=3 ttl=53 time=7.257 ms
64 bytes from 1.1.1.1: seq=4 ttl=53 time=7.077 ms
64 bytes from 1.1.1.1: seq=5 ttl=53 time=7.283 ms
64 bytes from 1.1.1.1: seq=6 ttl=53 time=7.290 ms
64 bytes from 1.1.1.1: seq=7 ttl=53 time=8.659 ms
64 bytes from 1.1.1.1: seq=8 ttl=53 time=6.912 ms

We are experiencing same issues. It appears to be more widespread and multiple IPSs. We have had Verizon, ATT and Sprint tested with same issue of page time-outs orPartial loading, then time-out. You replied on other thread on this but wanted to provide some further info. We have a trouble ticket in and awaiting a proper response. Someone reporting that Switzerland has had similar if not same issue.

Thanks @user648. I thought it couldn’t just be me, thanks for verifying.

Hi @tonyquan and @user648,
Sorry for the issues you are currently experiencing.

Could you please access https://cloudflare-dns.com/help and share the generated link?

@dmz if I use 1.1.1.1 (CloudFlare IPv4) as the DNS, I get this

However if I use 2606:4700:4700::1111 (CloudFlare IPv6) as the DNS, I get this and the test never finishes. CloudFlare IPv6 used to work for me in the past. as I mentioned above, since today there are numerous dropped packets and high latency when trying to ping 2606:4700:4700::1111

I assume what you were asking is to be on data services click that link to share the results.

If that is the case, just like our websites with data service on I cannot access that page that you sent the link to.

Paul

I set up a ping test to 2606:4700:4700::1111 (Cloudflare IPv6 DNS) from my AT&T connection in California. As you can see from 23:30 UTC (when I set up the test) until now, Cloudflare IPv6 DNS was only reachable for about 15 minutes between 01:00 UTC and 01:15 UTC. The rest of the time the ping test either failed (red color) or had ping times of nearly 200ms which is much higher than normal, it is unlikely that the DNS service was usable in those windows.

is anyone actually working on this issue? I haven’t seen any change and there’s been no update here.

Had to open a new account as I hit the limit on posts in one day :slight_smile: This issue appears to have been fixed by Cloudflare as mentioned here Site unreachable from specific mobile provider