log in

Advanced search

Message boards : Number crunching : Native Java 1.7 Application requires 1.97 KB/sec download bandwidth...

Author Message
boinc127
Send message
Joined: 7 Nov 13
Posts: 3
Credit: 56,828
RAC: 0
Message 3304 - Posted: 4 Nov 2014, 5:39:07 UTC
Last modified: 4 Nov 2014, 5:40:17 UTC

Why do I keep getting this error:


11.03.2014 23.30.11 | MindModeling@Beta | Message from server: Native Java 1.7 Application (Cross Platform) requires 1.97 KB/sec download bandwidth. Your computer has been measured at 1.96 KB/sec.

My internet speed is quite adequate. (I just tested it... it downloads at 30 Mbps and uploads at 21 Mbps). The only way I have found to reset this issue is by removing the project and rejoining it. Its quite an irritation. Anyone have any advice on how to fix this?

P.S. It seems the speed in which these particular workunits are being crunched (less than 12 seconds each) may have something to do with it. Uploading and downloading multiple workunits obviously has slowed the bandwidth down.

Matthias Lehmkuhl
Send message
Joined: 29 Mar 08
Posts: 27
Credit: 394,772
RAC: 274
Message 3305 - Posted: 4 Nov 2014, 7:58:37 UTC

I've more than 500 Native Java 1.7 Application (Cross Platform) results with Validation pending.

All results with runtime less than 1 minute.
Most have a runtime less 30 seconds
Some are there with a CPU time of 0.00 seconds

Looks like there is something wrong with the results or application

Native Java 1.7 Application (Cross Platform) v1.08 (sse2)

Actual I'll set mindmodeling to NNW
____________
Matthias

Matthias Lehmkuhl
Send message
Joined: 29 Mar 08
Posts: 27
Credit: 394,772
RAC: 274
Message 3307 - Posted: 4 Nov 2014, 11:26:35 UTC - in response to Message 3305.

I've more than 500 Native Java 1.7 Application (Cross Platform) results with Validation pending.

All results with runtime less than 1 minute.
Most have a runtime less 30 seconds
Some are there with a CPU time of 0.00 seconds

Looks like there is something wrong with the results or application

Native Java 1.7 Application (Cross Platform) v1.08 (sse2)

Actual I'll set mindmodeling to NNW


add a example output
<core_client_version>7.4.22</core_client_version>
<![CDATA[
<stderr_txt>
wrapper: starting
Setting up task
Checking if I should run task...
1415094796 - Task Done Found at E:\Public\BoincData/projects/mindmodeling.org\java-1.7_1.0_env_done
Skipping task
Setting up task
10:53:16 (10924): wrapper: running 7za.exe (x -y dist.zip)
Setting up task
10:53:17 (10924): wrapper: running E:\Public\BoincData/projects/mindmodeling.org\java-1.7_1.0_env\java-1.7\bin\java.exe (-cp .;dist;dist\Simulator.jar;dist\lib\beansbinding-1.2.1.jar;dist\lib\cobra.jar;dist\lib\js.jar;dist\lib\swing-layout-1.0.4.jar MMJavaBridge com.grid.simulations.simworld.worlds.swamp.SwampNR staticRun 2)
Acquiring IV names: numFemales meanPulsesPCall nBestN maleDistributionInt strategyParameterDistInt seed mm_samples mm_sample_offset
Running IV Values: 10 6 4 0 0 -244693141
Updating Fraction Done to: 1.98
Updating Fraction Done to: 1.98
Done!
10:53:23 (10924): called boinc_finish

</stderr_txt

http://mindmodeling.org/result.php?resultid=19836852
all my short run results have this output
____________
Matthias

Profile Tom
Volunteer moderator
Avatar
Send message
Joined: 23 Jun 08
Posts: 490
Credit: 238,767
RAC: 0
Message 3308 - Posted: 4 Nov 2014, 16:08:07 UTC - in response to Message 3307.

Hi all,

Our workunits are typically scheduled to run an hour. When the system detects that results are not returning, it will reduce the size of any newly created workunits to a more manageable amount. Unfortunately, the work was returning from the clients fine, but the validator was broken. The work generator, not detecting this, continued to reduce the size of the workunits until they reached a threshold of only a few seconds. This lead to all the follow-on issues described above, which can be attributed to our Validator not running. It has since been fixed and workunits are processing again (albeit slowly).

I hope that helps explain the situation. You may need to reset (or detach/reattach) your project to get it back into a normal state again.

Derion
Send message
Joined: 22 Nov 15
Posts: 30
Credit: 1,203,307
RAC: 1,437
Message 3742 - Posted: 13 May 2016, 0:59:26 UTC
Last modified: 13 May 2016, 0:59:26 UTC

Seems the issue is happening again. Had to reset the project to obtain new tasks, otherwise it cannot fetch new ones.

Could explain why there's a buildup of tasks ready to send, but a lowering number of tasks in progress.

Profile Brandon
Project administrator
Project developer
Project tester
Avatar
Send message
Joined: 5 Jan 15
Posts: 261
Credit: 1,456,117
RAC: 0
Message 3743 - Posted: 13 May 2016, 13:31:09 UTC
Last modified: 13 May 2016, 13:31:09 UTC

Thanks for the heads up Derion.

We will take a look at this job and see what is going on.

Thanks for your support and happy crunching,

Brandon

Derion
Send message
Joined: 22 Nov 15
Posts: 30
Credit: 1,203,307
RAC: 1,437
Message 3751 - Posted: 24 May 2016, 13:20:53 UTC
Last modified: 24 May 2016, 13:20:53 UTC

What does this mystic message mean?

Tasks won't finish in time: BOINC runs 35.3% of the time; computation is enabled 96.1% of that

Gunde
Send message
Joined: 8 Feb 15
Posts: 26
Credit: 7,169,421
RAC: 0
Message 3752 - Posted: 24 May 2016, 13:47:34 UTC - in response to Message 3751.
Last modified: 24 May 2016, 13:47:34 UTC

It is summery from the settings you have in boinc manager for usage limits and schedules.
So if set to run all cores at 100% and 100% cpu time and never suspend at anytime of week/day it will be 100% in eventlog.

Derion
Send message
Joined: 22 Nov 15
Posts: 30
Credit: 1,203,307
RAC: 1,437
Message 3855 - Posted: 8 Aug 2016, 0:44:56 UTC
Last modified: 8 Aug 2016, 0:44:56 UTC

The issue appeared again. Re-setting the project did the job.

Derion
Send message
Joined: 22 Nov 15
Posts: 30
Credit: 1,203,307
RAC: 1,437
Message 3884 - Posted: 26 Aug 2016, 14:30:32 UTC
Last modified: 26 Aug 2016, 14:30:32 UTC

Still happening from time to time, would there be a permenent fix?

AEM74
Send message
Joined: 5 Mar 14
Posts: 17
Credit: 286,834
RAC: 0
Message 3887 - Posted: 27 Aug 2016, 18:44:53 UTC
Last modified: 27 Aug 2016, 18:44:53 UTC

8/27/2016 2:42:40 PM | MindModeling@Beta | Message from server: Native R v2.15.1 Application (Cross Platform) requires 1.97 KB/sec download bandwidth. Your computer has been measured at 1.94 KB/sec.

At least 75 down and 18 up. Any solutions?

Profile Brandon
Project administrator
Project developer
Project tester
Avatar
Send message
Joined: 5 Jan 15
Posts: 261
Credit: 1,456,117
RAC: 0
Message 3893 - Posted: 29 Aug 2016, 17:48:41 UTC
Last modified: 29 Aug 2016, 17:48:41 UTC

Hey Guys,

I am wondering if issues with the bandwidth had to do with issues with the upload server last week.

We will look to see if there could be another issue but that would be my guess.

The quick fix is to reattach your project. However if this happens again please let me know.

Thanks for your support and happy crunching,

Brandon

Derion
Send message
Joined: 22 Nov 15
Posts: 30
Credit: 1,203,307
RAC: 1,437
Message 4065 - Posted: 27 Oct 2017, 11:14:52 UTC
Last modified: 27 Oct 2017, 11:14:52 UTC

Still happening now, can't find any triggers to this

Profile Brandon
Project administrator
Project developer
Project tester
Avatar
Send message
Joined: 5 Jan 15
Posts: 261
Credit: 1,456,117
RAC: 0
Message 4066 - Posted: 27 Oct 2017, 12:44:26 UTC
Last modified: 27 Oct 2017, 12:44:26 UTC

Hey Derion,

We have done a couple of deployments over the past week or so. During 2 of the deployments, the system was unavailable for less than ten minutes. You may have been trying to upload results at that time which is what reduced your BOINC Client's bandwidth value which is causing this issue. If you reset the project, that should reset which will fix this for you.

If not we will look into other possibilities as to why this happened.

Hope this helps!

Best,

Brandon

xii5ku
Send message
Joined: 4 Sep 17
Posts: 6
Credit: 4,728,116
RAC: 60,890
Message 4068 - Posted: 3 Nov 2017, 12:06:54 UTC - in response to Message 4066.
Last modified: 3 Nov 2017, 12:11:35 UTC

We have done a couple of deployments over the past week or so. During 2 of the deployments, the system was unavailable for less than ten minutes. You may have been trying to upload results at that time which is what reduced your BOINC Client's bandwidth value which is causing this issue.

This is *not* the cause.

The problem with bogus bandwidth measurements is a general one, caused by your project server. Probably linked to (a) your network connection being chronically swamped, (b) by far most of the transferred files being merely a few bytes small.

The problem occurred on *all* clients which I ever used at MindModeling. On a 22C/44T client it occured several times a day. On a 6C/12T client a few times a week. On a 4C/8T laptop roughly once a week. I had these on different internet connections, and fairly good ones.

The problem is solely on your end, and it is a *permanent* one. (Well, the repeated posts about it here should already tell you so.)

If you reset the project, that should reset which will fix this for you.

It is not a fix, only a temporary workaround until it happens again. But it is so far the only known working workaround.

If not we will look into other possibilities as to why this happened.

Can you disable bandwidth limits? You don't need them anyway; the only time when networking bandwidth is used is when a client starts working on a new dataset/ new application. After that, you distribute almost only those few-bytes transfers, whose transfer performance depends on networking latency (and maybe on *your* networking bandwidth), but not on the client's networking bandwidth.

Or if you cannot disable this limit, then you must not measure networking bandwidth of the small transfers, you should only measure large transfers.

Edit:
I.e. I suppose the solution is either in the boinc server config, or in boinc server program code (which would be troublesome).

Profile Brandon
Project administrator
Project developer
Project tester
Avatar
Send message
Joined: 5 Jan 15
Posts: 261
Credit: 1,456,117
RAC: 0
Message 4072 - Posted: 6 Nov 2017, 16:38:23 UTC
Last modified: 6 Nov 2017, 16:38:23 UTC

Hi xii5ku,

Thanks for the help. We are currently investigating how the boinc server is measuring bandwidth and attempting to find a solution to fix this issue for you guys.

As soon as I have more information I will let you guys know.

Thanks again!

Best,

Brandon

Message boards : Number crunching : Native Java 1.7 Application requires 1.97 KB/sec download bandwidth...


Main page · Your account · Message boards


Copyright © 2018 MindModeling.org