Scheduler, feeder

Message boards : Server backend and mirrors : Scheduler, feeder
Message board moderation

To post messages, you must log in.

AuthorMessage
JZD

Send message
Joined: 30 Dec 11
Posts: 103
Credit: 3,498,559
RAC: 274
Message 15407 - Posted: 27 Jul 2018, 5:09:41 UTC

What happened? Everything looks good http://burp.renderfarming.net/status.php, but sending tasks is stopped.
ID: 15407 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Janus
Volunteer moderator
Project administrator
Avatar

Send message
Joined: 16 Jun 04
Posts: 4571
Credit: 2,100,463
RAC: 8
Message 15408 - Posted: 27 Jul 2018, 8:24:30 UTC

Looking into the issue, it looks like the homogenous redundancy system for the entire "Blender (CPU)" part of the farm crashed because some workunits were still in flight for the old client version when the new client version was pushed out.

Temporarily switching to GPU rendering and clearing out the queue.
ID: 15408 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Janus
Volunteer moderator
Project administrator
Avatar

Send message
Joined: 16 Jun 04
Posts: 4571
Credit: 2,100,463
RAC: 8
Message 15413 - Posted: 27 Jul 2018, 11:19:46 UTC

Taking the site down for a few hours to investigate the scheduling issues without workunits flowing through it at the same time.
ID: 15413 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Janus
Volunteer moderator
Project administrator
Avatar

Send message
Joined: 16 Jun 04
Posts: 4571
Credit: 2,100,463
RAC: 8
Message 15416 - Posted: 29 Jul 2018, 10:16:18 UTC
Last modified: 29 Jul 2018, 10:18:14 UTC

Update: Still looking into scheduler issues. Fixed the issue with CPU units not going out and now instead have an issue with reported results not getting properly registered as having come back.
ID: 15416 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile PDW

Send message
Joined: 2 Nov 16
Posts: 8
Credit: 1,388,148
RAC: 2,003
Message 15417 - Posted: 29 Jul 2018, 11:06:28 UTC - in response to Message 15416.  

... an issue with reported results not getting properly registered as having come back.

Looking good, thanks.
ID: 15417 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Janus
Volunteer moderator
Project administrator
Avatar

Send message
Joined: 16 Jun 04
Posts: 4571
Credit: 2,100,463
RAC: 8
Message 15423 - Posted: 29 Jul 2018, 20:03:06 UTC

Most of the scheduling issues have been fixed and the service restarted.

I'll look into the remaining issue with a few stuck WUs tomorrow afternoon.
ID: 15423 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote

Message boards : Server backend and mirrors : Scheduler, feeder