Page MenuHomePhabricator

urldownloader1003's network is unresponsive
Closed, ResolvedPublic

Description

urldownloader1003 (VM on ganeti1027) has no network connectivity, causing problems to any service using it to fetch data from the outside world

Event Timeline

jijiki triaged this task as High priority.Feb 27 2024, 3:43 PM

After issuing a restart, the VM came back to life normally.

Looking into the issue, we found that around 26th Feb @ ~21:45 UTC, the urldownloader1003 (ganeti VM running on ganeti1027 ie cluster master) lost network connectivity

image.png (608×1 px, 122 KB)

I was able to login to the VM via ganeti, where nothing seemed out of order, from the machine's perspective. Running ip a yielded that it believed its network interface was UP. After issuing a systemctl restart networking, it found its network interface as DOWN.

From the outside, we were getting

PING urldownloader1003.wikimedia.org(urldownloader1003.wikimedia.org (2620:0:861:3:208:80:154:75)) 56 data bytes
From ae4-1020.cr2-eqiad.wikimedia.org (2620:0:861:107:fe00::3) icmp_seq=1 Destination unreachable: Address unreachable

We found nothing odd in the ganeti logs, or the machine's logs. We will see if such a thing resurfaces.

tx @akosiaris for offering a hand