Connection timed out to baobab2.hpc.unige.ch

[Volodymyr.Savchenko]

Hello,

since today I am unable to login on baobab2.hpc.unige.ch, with a “connection timed out” (not refused) message.

I tried from different locations, it’s not my network issue.

Regards

Volodymyr

[Aurelie.Hintermann]

Same thing for me. I am trying since this morning.

[David.Droz]

It seems Baobab does not respond to ping:

david@LAPTOP-PBOM84A7:~$ ping baobab2.unige.ch
PING baobab2.unige.ch (129.194.9.190) 56(84) bytes of data.
^C
--- baobab2.unige.ch ping statistics ---
11 packets transmitted, 0 received, 100% packet loss, time 10038ms

[Volodymyr.Savchenko]

Even though it seems to be, technically, loaded:

Edit: as pointed out by @Yann.Sagon , this picture here is live - updated from ganglia when the post is viewed. This may or may not serve the purpose I intended by the comment, but it is clearly not guaranteed to be coherent with the text I put in the post.

here is the snapshot as I saw it (presumably) at the time of posting:

[Simone.Bavera]

Same for me. Since yesterday morning I cannot login anymore…

[Yann.Sagon]

Hello, issue fixed.

Current issues on Baobab and Yggdrasil

2020-04-04T07:40:00Z (UTC) → 2020-04-05T09:15:00Z (UTC)- Baobab Login2 unreachable. Baobab login node2 was powered off automatically due to a thermal issue Saturday morning. Restarted now and available again.

[Pierre.Megevand]

I still can’t login, Haven’t been able to through the weekend.

[Silas.Kieser]

So I’m not the only one. This forum is very useful for such errors.

[Volodymyr.Savchenko]

I was able to login - the issue was indeed fixed, but the problem started again yesterday evening (~20h).

[Yann.Sagon]

update:

Current issues on Baobab and Yggdrasil

2020-04-05T17:35:00Z (UTC) Baobab Login2 unreachable. I restarted it this morning. We have a lot of warning about high temperature on one of the CPU package. We need to investigate but for this we need to shutdown the server. We are currently preparing a replacement login node and let you know when we’ll do the swap.

[Yann.Sagon]

Ahahah, I just realized that the picture here is live, I was pretty sure the load curve was not the same when you published it. It’s better to publish a static picture for this kind of information.