[Ekhi-users] Ekhi nodes draining

[Inigo Aldazabal Mensa]

Hola de nuevo,

No había puesto en copia a la lista, ahí va.

Iñigo

On Mon, 9 Jun 2025 12:15:05
+0200 Inigo Aldazabal Mensa <inigo.aldazabalm at ehu.eus> wrote:

> Hola Manex,
> 
> Disculpad el retraso pero he estado fuera hasta hoy.
> 
> Efectivamente ekhi11 tenía el /scratch desmontado y al intentar entrar
> para correr los trabajos cascaba. Ya está solucionado.
> 
> Un saludo,
> 
> Iñigo
> 
> 
> 
> On Thu, 5 Jun 2025 10:15:01 +0200
> Manex Alkorta <manexalk at gmail.com> wrote:
> 
> > Hola Iñigo,
> > 
> > Creo que ekhi11 no está funcionando correctamente. Es algo raro,
> > porque he entrado al nodo y no he
> > encontrado ningún calculo zombie... pero al mandar un trabajo entra
> > en ekhi11 y crashea. No es algo
> > que me este pasando ami solo, ahora mismo la cola se ha vaciado
> > porque a todos nos ha fallado el
> > nodo.
> > 
> > Gracias,
> > Manex
> > 
> > Hau idatzi du Inigo Aldazabal Mensa (inigo.aldazabalm at ehu.eus)
> > erabiltzaileak (2025 eka. 4(a), az. (12:39)):
> >   
> > > Hi Dorde,
> > >
> > > Oh! I thought I had put everything online again in Ekhi but I see
> > > that I powered the nodes up last Friday and moved away to other
> > > cluster as they were powering on (they take a while) and with the
> > > mess I forgot to go back to Ekhi in order to put them up again in
> > > the queue system!
> > >
> > > Totally my fault, sorry for this!!
> > >
> > > Thanks for the heads up, they are online now except for ekhi19
> > > which does not respond remotely (I'm away in a conference for the
> > > whole week).
> > >
> > > Bests,
> > >
> > > Iñigo
> > >
> > >
> > >
> > >  On Wed, 4 Jun 2025 07:55:08 +0000
> > > DORDE DANGIC <dorde.dangic at ehu.eus> wrote:
> > >    
> > > > Hello Inigo,
> > > >
> > > > Are there any updates regarding the status of EKHI?
> > > >
> > > > Kind regards,
> > > >
> > > > Đorđe
> > > > ________________________________
> > > > From: Inigo Aldazabal Mensa <inigo.aldazabalm at ehu.eus>
> > > > Sent: Friday, May 30, 2025 12:41 PM
> > > > To: DORDE DANGIC <dorde.dangic at ehu.eus>; ekhi-users at ehu.eus
> > > > <ekhi-users at ehu.eus> Subject: Re: Ekhi nodes draining
> > > >
> > > > Hi Dorde, all,
> > > >
> > > > Yes, we are having some problems with the cooling system and I
> > > > had to drain Ekhi yesterday night in order to avoid the data
> > > > center to overheat.
> > > >
> > > > I'll put everything back online quite likely tonight, or perhaps
> > > > along tomorrow should more problems arise.
> > > >
> > > > Bests,
> > > >
> > > > Iñigo
> > > >
> > > > On Fri, 30 May 2025 08:32:15 +0000
> > > > DORDE DANGIC <dorde.dangic at ehu.eus> wrote:
> > > >    
> > > > > Hello Inigo,
> > > > >
> > > > > I noticed the majority of EKHI nodes are in DRAIN status. Is
> > > > > this some regular procedure, or is the cluster down?
> > > > >
> > > > > Kind regards,
> > > > >
> > > > > Đorđe
> > > > >    
> > > _______________________________________________
> > > Ekhi-users mailing list
> > > Ekhi-users at list.ehu.eus
> > > http://list.ehu.eus/mailman/listinfo/ekhi-users
> > >