Minirosetta 3.73-3.78

Message boards : Number crunching : Minirosetta 3.73-3.78

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 11 · Next

AuthorMessage
Profile Michael H.W. Weber
Avatar

Send message
Joined: 18 Sep 05
Posts: 8
Credit: 3,633,490
RAC: 1
Message 79555 - Posted: 16 Feb 2016, 15:06:58 UTC

On my systems and those of other team members, all WUs carrying the phrase \"backrub\" are breaking down with computation errors. Often after having consumed quite some CPU time.

@Baker Lab:
Please take a look at this WU series.
Thanks.

Michael.
Michael H.W. Weber
Chairman and scientific advisor of Rechenkraft.net e.V.

http://www.rechenkraft.net - The world's first and largest distributed computing association. We make those things possible that supercomputers don't.
ID: 79555 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile David E K
Volunteer moderator
Project administrator
Project developer
Project scientist

Send message
Joined: 1 Jul 05
Posts: 1001
Credit: 2,869,947
RAC: 3,628
Message 79558 - Posted: 16 Feb 2016, 17:59:14 UTC - in response to Message 79555.  

On my systems and those of other team members, all WUs carrying the phrase \"backrub\" are breaking down with computation errors. Often after having consumed quite some CPU time.

@Baker Lab:
Please take a look at this WU series.
Thanks.

Michael.


These are my jobs and I do realize that many of them are failing with memory issues on some platforms. I will definitely look into this. The batch is almost complete so I\'m going to let them continue since they are producing results which I\'m very interested in. Credit should still be granted for the jobs that fail.
ID: 79558 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile Timo
Avatar

Send message
Joined: 9 Jan 12
Posts: 174
Credit: 15,237,629
RAC: 21,162
Message 79566 - Posted: 20 Feb 2016, 17:06:46 UTC
Last modified: 20 Feb 2016, 17:11:40 UTC

Two of my systems have started intermittently falling into \'project backoff\' for 10-40 hour periods after getting this message in the logs (If I go and do a manual \'request new tasks\' they successfully get more tasks but I noticed because their work queues dry out:


2/20/2016 2:07:54 AM | rosetta@home | Reporting 5 completed tasks
2/20/2016 2:07:54 AM | rosetta@home | Requesting new tasks for CPU
2/20/2016 2:07:57 AM | rosetta@home | Scheduler request completed: got 0 new tasks
2/20/2016 2:07:57 AM | rosetta@home | No work sent
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Is this perhaps a result of higher \'memory requirements\' attached to some of those jobs? If so, no worries, I\'ll just keep an eye on it until that batch finishes :)

.. a side note though, the backrub type jobs seem to be completing successfully on my boxes - maybe it\'s something to do with my target runtime being short (4 hours) and it not getting a chance to chew through so much memory? (Speculation ftw!) If that\'s the case maybe jobs like this should be limited to a shorter target runtime?
ID: 79566 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile Chilean
Avatar

Send message
Joined: 16 Oct 05
Posts: 676
Credit: 16,000,334
RAC: 9,938
Message 79567 - Posted: 20 Feb 2016, 18:25:12 UTC - in response to Message 79566.  

Two of my systems have started intermittently falling into \'project backoff\' for 10-40 hour periods after getting this message in the logs (If I go and do a manual \'request new tasks\' they successfully get more tasks but I noticed because their work queues dry out:


2/20/2016 2:07:54 AM | rosetta@home | Reporting 5 completed tasks
2/20/2016 2:07:54 AM | rosetta@home | Requesting new tasks for CPU
2/20/2016 2:07:57 AM | rosetta@home | Scheduler request completed: got 0 new tasks
2/20/2016 2:07:57 AM | rosetta@home | No work sent
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Is this perhaps a result of higher \'memory requirements\' attached to some of those jobs? If so, no worries, I\'ll just keep an eye on it until that batch finishes :)

.. a side note though, the backrub type jobs seem to be completing successfully on my boxes - maybe it\'s something to do with my target runtime being short (4 hours) and it not getting a chance to chew through so much memory? (Speculation ftw!) If that\'s the case maybe jobs like this should be limited to a shorter target runtime?


Or you could just... you know... buy 60 gigs of RAM lol

ID: 79567 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile robertmiles

Send message
Joined: 16 Jun 08
Posts: 671
Credit: 5,256,446
RAC: 7,669
Message 79569 - Posted: 20 Feb 2016, 19:23:21 UTC - in response to Message 79567.  

Two of my systems have started intermittently falling into \'project backoff\' for 10-40 hour periods after getting this message in the logs (If I go and do a manual \'request new tasks\' they successfully get more tasks but I noticed because their work queues dry out:


2/20/2016 2:07:54 AM | rosetta@home | Reporting 5 completed tasks
2/20/2016 2:07:54 AM | rosetta@home | Requesting new tasks for CPU
2/20/2016 2:07:57 AM | rosetta@home | Scheduler request completed: got 0 new tasks
2/20/2016 2:07:57 AM | rosetta@home | No work sent
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Is this perhaps a result of higher \'memory requirements\' attached to some of those jobs? If so, no worries, I\'ll just keep an eye on it until that batch finishes :)

.. a side note though, the backrub type jobs seem to be completing successfully on my boxes - maybe it\'s something to do with my target runtime being short (4 hours) and it not getting a chance to chew through so much memory? (Speculation ftw!) If that\'s the case maybe jobs like this should be limited to a shorter target runtime?


Or you could just... you know... buy 60 gigs of RAM lol


I\'d do just that for both of my computers if their motherboards could handle more memory. They can\'t.
ID: 79569 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
fractal

Send message
Joined: 12 Dec 08
Posts: 2
Credit: 1,000,245
RAC: 0
Message 79570 - Posted: 20 Feb 2016, 19:32:45 UTC - in response to Message 79566.  

Two of my systems have started intermittently falling into \'project backoff\' for 10-40 hour periods after getting this message in the logs (If I go and do a manual \'request new tasks\' they successfully get more tasks but I noticed because their work queues dry out:


2/20/2016 2:07:54 AM | rosetta@home | Reporting 5 completed tasks
2/20/2016 2:07:54 AM | rosetta@home | Requesting new tasks for CPU
2/20/2016 2:07:57 AM | rosetta@home | Scheduler request completed: got 0 new tasks
2/20/2016 2:07:57 AM | rosetta@home | No work sent
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Is this perhaps a result of higher \'memory requirements\' attached to some of those jobs? If so, no worries, I\'ll just keep an eye on it until that batch finishes :)


I found two of my machines in that state this morning and several yesterday.

2/19/2016 5:54:25 PM | rosetta@home | Computation for task rb_11_07_60457_104894__t000__0_C1_beta_nov15_cart_fa_wt_0.40_SAVE_ALL_OUT_IGNORE_THE_REST_327108_852_1 finished
2/19/2016 5:54:25 PM | rosetta@home | Starting task rb_02_18_60756_107222_ab_stage0_t000___robetta_IGNORE_THE_REST_10_15_329934_9_0
2/19/2016 5:54:28 PM | rosetta@home | Started upload of rb_11_07_60457_104894__t000__0_C1_beta_nov15_cart_fa_wt_0.40_SAVE_ALL_OUT_IGNORE_THE_REST_327108_852_1_0
2/19/2016 5:54:33 PM | rosetta@home | Finished upload of rb_11_07_60457_104894__t000__0_C1_beta_nov15_cart_fa_wt_0.40_SAVE_ALL_OUT_IGNORE_THE_REST_327108_852_1_0
2/19/2016 5:56:48 PM | rosetta@home | Sending scheduler request: To report completed tasks.
2/19/2016 5:56:48 PM | rosetta@home | Reporting 1 completed tasks
2/19/2016 5:56:48 PM | rosetta@home | Requesting new tasks for CPU
2/19/2016 5:56:50 PM | rosetta@home | Scheduler request completed: got 0 new tasks
2/19/2016 5:56:50 PM | rosetta@home | No work sent
2/19/2016 5:56:50 PM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6922.61 MB is available for use.
2/19/2016 5:56:50 PM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/19/2016 5:56:50 PM | rosetta@home | Rosetta Mini needs 9536.74 MB RAM but only 6922.61 MB is available for use.

That machine had 18 hours of backoff when I found it this morning. it still had one work unit running out of four cores.
2/20/2016 3:04:19 AM | rosetta@home | Computation for task foldit_2001101_s003_fold_and_dock_SAVE_ALL_OUT_328024_8728_0 finished
2/20/2016 3:04:19 AM | rosetta@home | Starting task TL_QTS_S_nuc_elbow_0072_0328_0047_0006_0487_0021_0997_0006_1669_0001_1503_0001_fold_SAVE_ALL_OUT_326891_2874_0
2/20/2016 3:04:21 AM | rosetta@home | Started upload of foldit_2001101_s003_fold_and_dock_SAVE_ALL_OUT_328024_8728_0_0
2/20/2016 3:04:26 AM | rosetta@home | Finished upload of foldit_2001101_s003_fold_and_dock_SAVE_ALL_OUT_328024_8728_0_0
2/20/2016 3:24:47 AM | rosetta@home | Computation for task rb_02_17_62203_107217_ab_stage0_t000___robetta_IGNORE_THE_REST_03_09_329939_184_0 finished
2/20/2016 3:24:47 AM | rosetta@home | Starting task FFD__adba9af95181d2f6c2e74c99f922bf95_abinitioDocking_16_02_12_21_37_globalDocking_7_SAVE_ALL_OUT_330008_6_0
2/20/2016 3:24:50 AM | rosetta@home | Started upload of rb_02_17_62203_107217_ab_stage0_t000___robetta_IGNORE_THE_REST_03_09_329939_184_0_0
2/20/2016 3:24:57 AM | rosetta@home | Finished upload of rb_02_17_62203_107217_ab_stage0_t000___robetta_IGNORE_THE_REST_03_09_329939_184_0_0
2/20/2016 4:05:08 AM | rosetta@home | Sending scheduler request: To report completed tasks.
2/20/2016 4:05:08 AM | rosetta@home | Reporting 2 completed tasks
2/20/2016 4:05:08 AM | rosetta@home | Requesting new tasks for CPU
2/20/2016 4:05:11 AM | rosetta@home | Scheduler request completed: got 0 new tasks
2/20/2016 4:05:11 AM | rosetta@home | No work sent
2/20/2016 4:05:11 AM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/20/2016 4:05:11 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 5670.64 MB is available for use.

This machine was completely out of work when I found it at the same time with over 24 hours of backoff. It got work as soon as I manually refreshed the project. My priority 0 backup project was not getting work either, but that never seems to work..
2/20/2016 7:10:56 AM | Universe@Home | Sending scheduler request: To report completed tasks.
2/20/2016 7:10:56 AM | Universe@Home | Reporting 1 completed tasks
2/20/2016 7:10:56 AM | Universe@Home | Not requesting tasks: don\'t need (job cache full)
2/20/2016 7:10:59 AM | Universe@Home | Scheduler request completed


I don\'t mind not getting a work unit that needs 60 GiB of RAM but please don\'t refuse to give my meager machine more bite sized work just because of that.
ID: 79570 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Link
Avatar

Send message
Joined: 4 May 07
Posts: 260
Credit: 338,704
RAC: 0
Message 79576 - Posted: 21 Feb 2016, 12:22:21 UTC - in response to Message 79566.  

2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Maybe it\'s time to remove \"mini\" from the app name... ;-)

On the serious side, considering that most PCs are still sold with 8GB or less, maybe creating another app name for this type of work would indeed be a good idea, so that only people who have much RAM can activate it in their profile while others won\'t be stopped from getting work (if that can\'t be solved in another way).
.
ID: 79576 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile robertmiles

Send message
Joined: 16 Jun 08
Posts: 671
Credit: 5,256,446
RAC: 7,669
Message 79577 - Posted: 21 Feb 2016, 15:32:47 UTC - in response to Message 79576.  

2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Maybe it\'s time to remove \"mini\" from the app name... ;-)

On the serious side, considering that most PCs are still sold with 8GB or less, maybe creating another app name for this type of work would indeed be a good idea, so that only people who have much RAM can activate it in their profile while others won\'t be stopped from getting work (if that can\'t be solved in another way).


I decided to buy another of my favorite brand of computers yesterday. They didn\'t offer any with more than 32 GB that fit my other requirements.
ID: 79577 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
fractal

Send message
Joined: 12 Dec 08
Posts: 2
Credit: 1,000,245
RAC: 0
Message 79578 - Posted: 21 Feb 2016, 23:07:15 UTC - in response to Message 79577.  
Last modified: 21 Feb 2016, 23:08:46 UTC

2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Maybe it\'s time to remove \"mini\" from the app name... ;-)

On the serious side, considering that most PCs are still sold with 8GB or less, maybe creating another app name for this type of work would indeed be a good idea, so that only people who have much RAM can activate it in their profile while others won\'t be stopped from getting work (if that can\'t be solved in another way).


I decided to buy another of my favorite brand of computers yesterday. They didn\'t offer any with more than 32 GB that fit my other requirements.

You generally need server class hardware to get more than 32 GiB of memory. <begin wry humor>And, since the project shuts you down if you fail for ANY work unit, you need 60 GiB of RAM per core. That\'s 240 GiB for a quad core. You can get that with AMD Opterons or Intel Xeons using registered ECC RDIM\'s. This is not a viable approach for most volunteers.<end wry humor>

That aside, I had to manually update 8 stuck machines yesterday. I was about to say that I didn\'t have to restart any today but just found one on a 20 hour backoff. Fortunately I increased my buffer from a half a day to a full day to give me time to find them before they run dry.

Oh, and why is it called \"mini rosetta?\" See https://www.rosettacommons.org/content/what-minirosetta
ID: 79578 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile robertmiles

Send message
Joined: 16 Jun 08
Posts: 671
Credit: 5,256,446
RAC: 7,669
Message 79579 - Posted: 22 Feb 2016, 0:03:42 UTC - in response to Message 79578.  

2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


Maybe it\'s time to remove \"mini\" from the app name... ;-)

On the serious side, considering that most PCs are still sold with 8GB or less, maybe creating another app name for this type of work would indeed be a good idea, so that only people who have much RAM can activate it in their profile while others won\'t be stopped from getting work (if that can\'t be solved in another way).


I decided to buy another of my favorite brand of computers yesterday. They didn\'t offer any with more than 32 GB that fit my other requirements.

You generally need server class hardware to get more than 32 GiB of memory. <begin wry humor>And, since the project shuts you down if you fail for ANY work unit, you need 60 GiB of RAM per core. That\'s 240 GiB for a quad core. You can get that with AMD Opterons or Intel Xeons using registered ECC RDIM\'s. This is not a viable approach for most volunteers.<end wry humor>

That aside, I had to manually update 8 stuck machines yesterday. I was about to say that I didn\'t have to restart any today but just found one on a 20 hour backoff. Fortunately I increased my buffer from a half a day to a full day to give me time to find them before they run dry.

Oh, and why is it called \"mini rosetta?\" See https://www.rosettacommons.org/content/what-minirosetta


I might be able to afford server class hardware, but I don\'t feel like learning a server operating system - I\'ve already learned enough operating systems. Also, I have rather strong electrical power limitations here.

As for removing mini from minirosetta, it looks like someone doesn\'t know enough of the history of Rosetta@home to remember that the main application was rosetta a few years ago. Do the want the renamed application to be easily confused with the application of a few years ago?
ID: 79579 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
jjch

Send message
Joined: 10 Nov 13
Posts: 9
Credit: 212,883,956
RAC: 257,732
Message 79582 - Posted: 22 Feb 2016, 5:44:59 UTC

It looks like there are two different things going on here but they may be related.

I have a number of servers and workstations that are being used for CPU and GPU computing. These were recently set to primarily to run rosetta for CPU work to help out that project.

The rosetta Task status shows Ready to report but the Project Status goes to Communication Deferred for multiple hours (ex. 18 hrs) and the server runs dry.

What I am seeing is that the project happily goes along for a while Requesting new tasks for CPU and gets the Scheduler request completed: got 1 task message.

Then after a few hours it gets the Scheduler request completed: got 0 tasks. No work sent. Rosetta Mini for Android is not available for your type of computer.

Finally, the message Rosetta Mini needs 57220.46 MB RAM but only 7363.62 MB is available for use. After that it stops updating. Remaining tasks will continue to upload until it runs out.

Rosetta does not automatically download any more tasks or report any that were finished. You can manually update and get it to reset and start again however it will just run through to the same result in a few hours.

I\'m not going to baby sit all of these servers everyday to keep running rosetta. Also, these were purposefully only populated with 8GB memory to save on power and cooling requirements. CPU and GPU computing remember.

Please look into this and provide a resolution soon or I will have to move on to other projects. Let me know if I can be of assistance or provide any more detailed information.

Thanks.




ID: 79582 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile robertmiles

Send message
Joined: 16 Jun 08
Posts: 671
Credit: 5,256,446
RAC: 7,669
Message 79584 - Posted: 22 Feb 2016, 15:34:07 UTC - in response to Message 79582.  

It looks like there are two different things going on here but they may be related.

I have a number of servers and workstations that are being used for CPU and GPU computing. These were recently set to primarily to run rosetta for CPU work to help out that project.

The rosetta Task status shows Ready to report but the Project Status goes to Communication Deferred for multiple hours (ex. 18 hrs) and the server runs dry.

What I am seeing is that the project happily goes along for a while Requesting new tasks for CPU and gets the Scheduler request completed: got 1 task message.

Then after a few hours it gets the Scheduler request completed: got 0 tasks. No work sent. Rosetta Mini for Android is not available for your type of computer.

Finally, the message Rosetta Mini needs 57220.46 MB RAM but only 7363.62 MB is available for use. After that it stops updating. Remaining tasks will continue to upload until it runs out.

Rosetta does not automatically download any more tasks or report any that were finished. You can manually update and get it to reset and start again however it will just run through to the same result in a few hours.

I\'m not going to baby sit all of these servers everyday to keep running rosetta. Also, these were purposefully only populated with 8GB memory to save on power and cooling requirements. CPU and GPU computing remember.

Please look into this and provide a resolution soon or I will have to move on to other projects. Let me know if I can be of assistance or provide any more detailed information.

Thanks.






It looks like all of your computers run some version of Windows and none of them run Android
ID: 79584 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
jjch

Send message
Joined: 10 Nov 13
Posts: 9
Credit: 212,883,956
RAC: 257,732
Message 79593 - Posted: 22 Feb 2016, 19:50:13 UTC

All of the systems are running Windows, either 2012/R2, 7 or 8.1. There isn\'t any that have an android emulator either. Had to give up my Linux servers.

There were a couple of these that were left with more than 8GB memory. I am going to check if those also have the same problem.

I will also check if one might already have 64 GB memory or upgrade it and see if it makes any difference.
ID: 79593 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile Timo
Avatar

Send message
Joined: 9 Jan 12
Posts: 174
Credit: 15,237,629
RAC: 21,162
Message 79594 - Posted: 22 Feb 2016, 20:38:19 UTC - in response to Message 79593.  

All of the systems are running Windows, either 2012/R2, 7 or 8.1. There isn\'t any that have an android emulator either. Had to give up my Linux servers.

There were a couple of these that were left with more than 8GB memory. I am going to check if those also have the same problem.

I will also check if one might already have 64 GB memory or upgrade it and see if it makes any difference.


I think your (very impressive) fleet of servers is being affected by the same memory allocation messages I posted about (seen as follows in my logs):


2/20/2016 2:07:54 AM | rosetta@home | Reporting 5 completed tasks
2/20/2016 2:07:54 AM | rosetta@home | Requesting new tasks for CPU
2/20/2016 2:07:57 AM | rosetta@home | Scheduler request completed: got 0 new tasks
2/20/2016 2:07:57 AM | rosetta@home | No work sent
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


The above causes the box to head into \'project standoff\' for 20-40 hours. Hoping David sees this thread and can take a peak sooner than later :).
ID: 79594 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile David E K
Volunteer moderator
Project administrator
Project developer
Project scientist

Send message
Joined: 1 Jul 05
Posts: 1001
Credit: 2,869,947
RAC: 3,628
Message 79595 - Posted: 22 Feb 2016, 21:00:04 UTC - in response to Message 79594.  

All of the systems are running Windows, either 2012/R2, 7 or 8.1. There isn\'t any that have an android emulator either. Had to give up my Linux servers.

There were a couple of these that were left with more than 8GB memory. I am going to check if those also have the same problem.

I will also check if one might already have 64 GB memory or upgrade it and see if it makes any difference.


I think your (very impressive) fleet of servers is being affected by the same memory allocation messages I posted about (seen as follows in my logs):


2/20/2016 2:07:54 AM | rosetta@home | Reporting 5 completed tasks
2/20/2016 2:07:54 AM | rosetta@home | Requesting new tasks for CPU
2/20/2016 2:07:57 AM | rosetta@home | Scheduler request completed: got 0 new tasks
2/20/2016 2:07:57 AM | rosetta@home | No work sent
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini for Android is not available for your type of computer.
2/20/2016 2:07:57 AM | rosetta@home | Rosetta Mini needs 57220.46 MB RAM but only 6842.83 MB is available for use.


The above causes the box to head into \'project standoff\' for 20-40 hours. Hoping David sees this thread and can take a peak sooner than later :).


thanks for the heads up. I\'ll track this down and try to fix it on our end.
ID: 79595 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile robertmiles

Send message
Joined: 16 Jun 08
Posts: 671
Credit: 5,256,446
RAC: 7,669
Message 79596 - Posted: 22 Feb 2016, 21:01:41 UTC - in response to Message 79593.  

All of the systems are running Windows, either 2012/R2, 7 or 8.1. There isn\'t any that have an android emulator either. Had to give up my Linux servers.

There were a couple of these that were left with more than 8GB memory. I am going to check if those also have the same problem.

I will also check if one might already have 64 GB memory or upgrade it and see if it makes any difference.


Something that MIGHT be worth trying: See if your account settings allow you to turn off Android workunits, since none of your computers run Android instead of Windows.
ID: 79596 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
jjch

Send message
Joined: 10 Nov 13
Posts: 9
Credit: 212,883,956
RAC: 257,732
Message 79597 - Posted: 22 Feb 2016, 23:18:20 UTC

I\'m not seeing an option to change that setting in rosetta. It is available on a few other BOINC projects though.
ID: 79597 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
jjch

Send message
Joined: 10 Nov 13
Posts: 9
Credit: 212,883,956
RAC: 257,732
Message 79600 - Posted: 23 Feb 2016, 6:38:51 UTC

Update - Several of the servers that had 0 work left yesterday started up again today and began processing Rosetta tasks. Probably after the communication deferred timer ran out.

Seems that if you manually update the project it triggers the loop but if you leave it alone it might sort it out by itself. There are a few that still are stuck so I can check on those tomorrow.

Several servers already have 32GB memory so those are reporting a similar message with slightly different memory size available.

Also, there are three servers one each with 64, 128 and 256GB of memory. They need patching and BOINC updates to 7.6.22 anyway. When I restart them I will watch how they behave.
ID: 79600 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile Chilean
Avatar

Send message
Joined: 16 Oct 05
Posts: 676
Credit: 16,000,334
RAC: 9,938
Message 79607 - Posted: 24 Feb 2016, 2:02:49 UTC - in response to Message 79600.  

Update - Several of the servers that had 0 work left yesterday started up again today and began processing Rosetta tasks. Probably after the communication deferred timer ran out.

Seems that if you manually update the project it triggers the loop but if you leave it alone it might sort it out by itself. There are a few that still are stuck so I can check on those tomorrow.

Several servers already have 32GB memory so those are reporting a similar message with slightly different memory size available.

Also, there are three servers one each with 64, 128 and 256GB of memory. They need patching and BOINC updates to 7.6.22 anyway. When I restart them I will watch how they behave.


Not to be nosy, but how do you handle the heat from the servers?
You\'re pulling over a quarter million of credit per day, that\'s very impressive!
ID: 79607 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
jjch

Send message
Joined: 10 Nov 13
Posts: 9
Credit: 212,883,956
RAC: 257,732
Message 79608 - Posted: 24 Feb 2016, 2:24:58 UTC

The servers are all in a lab room that has an AC cooling unit but I\'m actually close to the limit it will handle. Works pretty well during the winter and cooler months but when the weather gets hot outside I have to throttle them back during that day and only run at night.

If it gets past 90 F I have had to just let them run out of work units and idle. If we get to 100+ F I have had to shut them off and let the weather cool down a bit before starting back up again. Gives me a chance to update things and reset them anyway.
ID: 79608 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 11 · Next

Message boards : Number crunching : Minirosetta 3.73-3.78



©2017 University of Washington
http://www.bakerlab.org