[Beowulf] Timeout on eth0 when booting disk less

[Jon]

Yes, should've mentioned that we are running CentOS-7. However, as a first test I ran the setup on virtual machines (without any issues). This led me to believe the problem I see is at least partly connected to the switch.

Also, the problem persists even if I only boot a single node.

Thanks,
/jon 

Skickat från min iPhone

> 13 mars 2017 kl. 21:15 skrev mathog <mathog at caltech.edu>:
> 
> On 12-Mar-2017 12:00, Jon Tegner <tegner at renget.se> wrote
>> This could possibly be a problem with the switch, but one remedy would
>> seem to be to extend the time before the timeout kicks in (it seems to
>> be a few seconds at the moment). Any hints on how to achieve this?
> 
> That would depend on what you are booting.  I suggest you ask in the forum for the particular OS variant you are using.  (Or at least tell us what it is!)
> 
> Have a look at this
> 
>  https://help.ubuntu.com/community/DisklessUbuntuHowto
> 
> especially the "gotchas" section and see if anything applies.  My best guess is that the NFS mount is taking too long to complete.  It doesn't sound like a switch issue if there is no problem with the PXE or tftp parts.
> 
> Are you booting a bunch of nodes at once or one at a time, staggered?  All at once could bog down the head node so much that some compute nodes time out.
> 
> Regards,
> 
> David Mathog
> mathog at caltech.edu
> Manager, Sequence Analysis Facility, Biology Division, Caltech
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf