Message boards : Number crunching : SERVER PROBLEMS.
Previous · 1 . . . 9 · 10 · 11 · 12
Author | Message |
---|---|
bill Johnson@GMU Send message Joined: 5 Aug 09 Posts: 5 Credit: 1,356,008 RAC: 0 |
I looked at the server status and it says everything is running, but 0 queued jobs and only 120 ready to send. Does that mean that one or more of the servers are running but simply overloaded? |
AMD_is_logical Send message Joined: 20 Dec 05 Posts: 299 Credit: 31,460,681 RAC: 0 |
On the Server Status page, all but the first two programs are currently listed as "Not running". |
AMD_is_logical Send message Joined: 20 Dec 05 Posts: 299 Credit: 31,460,681 RAC: 0 |
I see the Server Status page is all green again. Thanks. |
robertmiles Send message Joined: 16 Jun 08 Posts: 1232 Credit: 14,281,662 RAC: 1,150 |
I looked at the server status and it says everything is running, but 0 queued jobs and only 120 ready to send. Only that many ready to send usually means that only one of the two programs for creating workunits is running, and it can't keep up with the demand. No queued jobs probably means something worse - the list of instructions for what workunits to create has run out, so until one of the scientists specifies some more, that only workunits that can be created are repeats of those that reached their deadlines and those that failed, but in a way that indicates that another try is worthwhile. The last I looked, two of the machines in the server cluster had no programs at all listed as running, so I'd guess that those two machines are either not running, or running but unable to exchange data with the other machines in the cluster. At this time of the year, I wouldn't be surprised if it takes a few more days for enough of the staff to return from Christmas/New Year vacation to fix all of the server problems; past history suggests the Monday after New Year's Day as likely this year, though. |
Message boards :
Number crunching :
SERVER PROBLEMS.
©2024 University of Washington
https://www.bakerlab.org