| 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: 72
|
|
| Author |
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
It looks like the large result files for MCM are returning. So far it is the 3828 and 3829 sets that are 1.73MB in size which is larger than what caused issues the last time.
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Long as everything remains in production flow, specially the assimilation to continue clearing space used by complete quorums, there's no reason to irk the nerves.
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Since the large datasets caught WCG off guard, I thought it was prudent to give them a heads up so they can at least keep an eye on the systems. It is easier to prevent a meltdown than to deal with one.
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
If they get caught off guard again on , when these sizes are actually specified as possible on the system requirement page, they may have to think about a career change.
![]() |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
The average size is usually below .5MB and right now the sizes are 1.74MB. When the issue happened before they were 1.34MB in size. So given that these are even larger, the potential is there for the issue to resurface.
So would you rather no one says anything and when *IT* hits the fans then we can all deal with it? That is the tone of your post. My post was to inform the admins that large results are coming. What have you contributed? |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
Currently the system is caught up on all assimilation as well as the file system sitting at 44% full. We are not running MCM at full speed right now so that helps keep the filesystem with more space. We are still working with the researchers to help them keep the file return size low.
We do appreciate the information and hopefully there is not a career change in the future :) Thanks, -Uplinger |
||
|
|
Seoulpowergrid
Veteran Cruncher Joined: Apr 12, 2013 Post Count: 823 Status: Offline Project Badges:
|
@Uplinger
----------------------------------------Thanks for your positive attitute and all the updates in all of this :) BTW, what does "the file system sitting at 44% full" mean? Thanks! ![]() |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
So we have multiple file systems that are utilized behind the scenes. Each file system can be considered at a high level like a C: drive or D: drive on windows (they are a little bit more sophisticated than that). But the file system where members upload results to which is shared between 3 upload servers is sitting at 44% full. If there is say 1TB of storage for that filesystem, then we are using 440GB of storage out of the 1000GB total.
During assimilation we take results that have been validated and move them to another filesystem that has more storage and is used for more than the purpose of upload and download of work units/results. Thanks, -Uplinger |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Uplinger
Is there an update about the servers and the problem?? When goes the server at full speed again? Thanks |
||
|
|
Speedy51
Veteran Cruncher New Zealand Joined: Nov 4, 2005 Post Count: 1326 Status: Offline Project Badges:
|
As of the latest statistics update (5/4/14 00:06:03 UTC) (5 hours ago) was not returned today was 265,693. I am unsure whether or not the project is back to full speed but it is clipping along at a reasonable pace. Statistic information was found under the Community tab
----------------------------------------![]() |
||
|
|
|