| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
| World Community Grid Forums
|
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 53
|
|
| Author |
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
Thanks for letting us know, are you able to elaborate on the server/storage upgrades e.g. are you changing to SSD's (solid state drives) & the size old drives of verse new drives & what server hardware is changing? Thanks for working on the weekend. All the best with the upgrade Sure, We did some work about 2 months ago to migrate the data to larger SSD drives that were about 3 years newer. This left us with the old drives still on the devices which we were paying for. The old drives when migrating the data from them to the new drives reported 1.6GB of data being still on those drives and we spent the past 2 months trying to figure out where that was coming from. It was caused by an incorrect reporting of values in that migration tool but we spent many days attempting to confirm the data was all migrated. Now since the drives have been removed from the cluster file system, we are physically removing them. But to be extra paranoid on my end, after they are removed, I am rebooting the machine they are rebooted from. This is to confirm that during system updates that happen about once a month, we don't encounter data issues. However to do these steps, takes about 17 hours from start to completion. We will be performing these actions for the next few days. Thanks, -Uplinger |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
I'm not sure if this is related to your maintenance, but a number of machines in my fleet are hung up on downloading new work units. The BOINC client log reports a "transient HTTP error", and when I update the project, I receive the log message: "Not requesting tasks: some download is stalled". I can clear the stalled downloads by restarting the BOINC client service, but as I'm sure you can imagine, having clients stall and run out of work until someone manually restarts it is not ideal. With the updates, we put extra load on the systems which seems to have caused some load issues but cleared on their own. I will be monitoring this as we continue the changes. Thanks for reporting! Also, thanks for your patience. -Uplinger |
||
|
|
Sgt.Joe
Ace Cruncher USA Joined: Jul 4, 2006 Post Count: 7846 Status: Offline Project Badges:
|
Looks like the validators are down sometime between 13:07 and 13:34 UTC across the board.
----------------------------------------Edit: Looks like somebody gave them a kick. I just had several pages of pending validation units change to valid. Thanks Cheers
Sgt. Joe
----------------------------------------*Minnesota Crunchers* [Edit 1 times, last edit by Sgt.Joe at Oct 26, 2020 2:21:02 PM] |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
Yeah, the backend processes are something I shut down to help migrate them off the host that is being manipulated. However, we are still in the middle of the changes and uploads/downloads may be disrupted due to this.
Thanks, -Uplinger |
||
|
|
BladeD
Ace Cruncher USA Joined: Nov 17, 2004 Post Count: 28976 Status: Offline Project Badges:
|
So, is this why the stats are late tonight?
---------------------------------------- |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
Thanks for the heads up. You are correct, stats are late.
I will look into starting them. Thanks, -Uplinger |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
Stats have been started.
Thanks again for the heads up. -Uplinger |
||
|
|
BladeD
Ace Cruncher USA Joined: Nov 17, 2004 Post Count: 28976 Status: Offline Project Badges:
|
You're welcome! Thanks for the quick response!
---------------------------------------- |
||
|
|
Mike.Gibson
Ace Cruncher England Joined: Aug 23, 2007 Post Count: 12594 Status: Offline Project Badges:
|
Keith
We seem to have skipped about 1500 batches of opn1. Is this anything to do with the server changes? Mike |
||
|
|
TPCBF
Master Cruncher USA Joined: Jan 2, 2011 Post Count: 2173 Status: Offline Project Badges:
|
Stats have been started. Looks like the generation of the external stats files needs a kick in the buns as well...Thanks again for the heads up. -Uplinger Ralf |
||
|
|
|