| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Official Messages
Forum: News
Thread: Downtime warning |
| Member(s) browsing this thread: PMH_UK , Link64 |
|
Thread Status: Active Thread Type: Global Announcement Thread Total posts in this thread: 96
|
|
| Author |
|
|
savas
Cruncher Joined: Sep 21, 2021 Post Count: 29 Status: Offline |
- IMPORTANT: We have been notified of an extended downtime at SHARCNET facility for construction lasting from December 9th, 2024, to January 3rd, 2025. There will be no power and no cooling during this time. We are exploring temporary migration to another site. We will provide an update on what downtime if any can be expected to start on December 9th, 2024. Overall, this upgrade should provide further improvements to the WCG capacity.
----------------------------------------- Bandwidth has been improved thanks to hosting staff at SHARCNET. In addition, we have more and better hardware devoted to handling downloads and uploads, and a more competent load balancer. - ARP1 will resume in limited quantities over the next few days. We will make an effort to focus on extremes as suggested in the forums and test the imposed rate limits on workunit production as well as total bandwidth of all clients and number of connections per client for ARP1 file transfer specifically. - Forums were down earlier today for an extended period, they are back up now and we apologize for the slow response. [Edit 1 times, last edit by savas at Nov 27, 2024 3:28:24 AM] |
||
|
|
Boca Raton Community HS
Advanced Cruncher Joined: Aug 27, 2021 Post Count: 113 Status: Offline Project Badges: 
|
Thanks for letting us know! Hopefully it all goes smoothly and further improves the WCG.
|
||
|
|
Mike.Gibson
Ace Cruncher England Joined: Aug 23, 2007 Post Count: 12120 Status: Offline Project Badges: 
|
savas
Thanks for the warning. As for restarting ARP1 with some extremes, might it be a good idea to try the 3 ultras languishing in generations 21 & 22? With a limited quantity being released, they could be monitored more easily and they will take a lot of time to catch up with the other extremes. Mike |
||
|
|
TPCBF
Master Cruncher USA Joined: Jan 2, 2011 Post Count: 1928 Status: Offline Project Badges: 
|
- IMPORTANT: We have been notified of an extended downtime at SHARCNET facility for construction lasting from December 9th, 2024, to January 3rd, 2025. There will be no power and no cooling during this time. We are exploring temporary migration to another site. We will provide an update on what downtime if any can be expected to start on December 9th, 2024. It really seems as if WCG his haunted by either Gremlins or Mr.Murphy...  - ARP1 will resume in limited quantities over the next few days. We will make an effort to focus on extremes as suggested in the forums and test the imposed rate limits on workunit production as well as total bandwidth of all clients and number of connections per client for ARP1 file transfer specifically. I hope that any rate limits are all "per client" based (using the BOINC/host ID) and not IP based, as it was mentioned in the update on the Jurisica update page. Don't mind the limit on WUs per host, but I run most of my clients NAT'ed behind one router/firewall, so they all have the same public IP... - Forums were down earlier today for an extended period, they are back up now and we apologize for the slow response.  Ralf  |
||
|
|
ADDIE2014
Cruncher Joined: Apr 13, 2019 Post Count: 31 Status: Offline Project Badges:
|
Thanks for the info savas.Hoping all goes well.
|
||
|
|
Mike.Gibson
Ace Cruncher England Joined: Aug 23, 2007 Post Count: 12120 Status: Offline Project Badges:
|
Enjoy your Christmas Holiday.
|
||
|
|
gj82854
Advanced Cruncher Joined: Sep 26, 2022 Post Count: 57 Status: Offline Project Badges: 
|
With a pending 1 month outage it wouldn't seem prudent not to release any APR1 work units. In fact, the next ten days might be better used to stop MCM and let those work units come back prior to the shutdown or they will expire on the contributors machines during the outage period.
|
||
|
|
Link64
Advanced Cruncher Joined: Feb 19, 2021 Post Count: 116 Status: Recently Active Project Badges: 
|
With a pending 1 month outage it wouldn't seem prudent not to release any APR1 work units. In fact, the next ten days might be better used to stop MCM and let those work units come back prior to the shutdown or they will expire on the contributors machines during the outage period. Why do you think, that sending out long running tasks before the outage instead of the short running ones is a good idea? If the temporary migration to another site won't be possible, best send only MCM out and increase the deadline 2 or 3 days before shutdown to around 40 days, so everyone can fill up their cache to the maximum of 10+10 days. Once the dust settles down after the outage, slowly start sending ARP again and see what the systems can handle after all the changes. Considering that "this upgrade should provide further improvements to the WCG capacity", it's pointless to experiment now, just keep it running without any interruptions. [Edit 1 times, last edit by Link64 at Nov 29, 2024 3:35:08 PM] |
||
|
|
BobbyB
Veteran Cruncher Canada Joined: Apr 25, 2020 Post Count: 598 Status: Offline Project Badges: 
|
I was thinking the same. Should we let our queues empty out before December 9 and stop accepting new tasks a few days before? It would be useless to process WUs in the queue after the 9th if the deadline is 3-5 days later.
This should be a boon the all the other Boinc projects if they could get their stuff together. |
||
|
|
gj82854
Advanced Cruncher Joined: Sep 26, 2022 Post Count: 57 Status: Offline Project Badges:
|
With a pending 1 month outage it wouldn't seem prudent not to release any APR1 work units. In fact, the next ten days might be better used to stop MCM and let those work units come back prior to the shutdown or they will expire on the contributors machines during the outage period. Why do you think, that sending out long running tasks before the outage instead of the short running ones is a good idea? If the temporary migration to another site won't be possible, best send only MCM out and increase the deadline 2 or 3 days before shutdown to around 40 days, so everyone can fill up their cache to the maximum of 10+10 days. Once the dust settles down after the outage, slowly start sending ARP again and see what the systems can handle after all the changes. Considering that "this upgrade should provide further improvements to the WCG capacity", it's pointless to experiment now, just keep it running without any interruptions.Sorrry, the word not shouldn't have been in the sentence. Should really be draining work. |
||
|
|
|