1) Message boards : Number Crunching : 3k~ tasks hogged by someone (Message 6382)
Posted 20 Sep 2016 by Profile Charles Dennett
Strange. His computer is listed as an 8 processor android. I don't recall what the limit is for outstanding tasks per processor for this project but over 3000 tasks seems excessive.

Anyway, I see they are expiring as the oldest ones reach and pass their deadlines. As they reach their deadlines, the project will automatically cancel them and resend them to others. Looks like the oldest are expiring now. The more recent ones will reach their deadlines in a bit over 2 days from now.

Charlie
2) Message boards : Number Crunching : Workunit Memory Estiimates (Message 6189)
Posted 14 Apr 2016 by Profile Charles Dennett
Thanks, Travis. My concern was that the smaller tasks and the larger tasks all say they have the same memory requirement but in reality the larger tasks use a lot more memory. My little cruncher can handle all but the largest tasks. If the memory estimate was closer to what each task actually required, I could turn this one back on for the project. As it is, I have it turned off because every time it gets one of the large tasks, it uses all the memory and swap. and freezes.

Charlie
3) Message boards : Number Crunching : Workunit Memory Estiimates (Message 6181)
Posted 13 Apr 2016 by Profile Charles Dennett
Just wanted to bump this up to see if someone would respond.
4) Message boards : Number Crunching : Workunit Memory Estiimates (Message 6129)
Posted 7 Feb 2016 by Profile Charles Dennett
One of my crunchers is an old laptop with only 1 GB of memory. For most tasks here and on other projects it's ok. Slow, but ok. However, there are some tasks here where it uses all the memory and starts swapping. This freezes the system so I have to power cycle it and abort the task before it starts again.

The last time this happened I looked at the workunit in the client-state.xml file and it looks like the memory estimate for the task was only 50 MB. A couple of other tasks not the same type as the one that used all the memory had the same estimate. However, they did not use the same amount of memory when they ran as the one that froze.

Would it be possible to get a better memory estimate of the tasks? The system is set to allow only 75% of the memory to be used for a task and BOINC will reject a task if it does not have enough memory. I know this works because BOINC rejects some tasks from another project I crunch for for this reason. That project also has tasks of varying memory requirements.

Thanks for your consideration of this.
5) Message boards : Number Crunching : Memory usage (Message 4931)
Posted 29 Dec 2014 by Profile Charles Dennett
I'm running into the same problem. There is one type of task that I've found has this rather large memory footprint. Task name is of the type gibbs_snail_hg19_1000fa_3motifs. On my 4 core/4 GB/Linux system I've had to create an app_config.xml file down in /var/lib/boinc/projects/volunteer.cs.und.edu_csg to limit the system to 2 tasks max for CSG. The file looks like this:

<app_config> <app> <name>gibbs</name> <max_concurrent>2</max_concurrent> </app> </app_config>


I also have an old HP pavillion notebook with two cores and only 1 GB of memory. It can handle one of these at a time but not two. I usually have to manually abort these tasks if I see them. Otherwise the thing locks up. I have a start delay in the tasks so I can reboot, start boinc and get in there if needed to abort a task before it actually starts. The delay is a line in cc_config.xml that I added:

<cc_config> <options> <start_delay>180</start_delay> </options> </cc_config>


The 4 core system is also crunching for POEM@Home. It's only 64 bit Linux so my other crunchers are only doing CSG for now. The other project I am currently crunching - FiND@Home - is currently down.
6) Message boards : Number Crunching : Running multiple tasks on a multi-core system takes longer. (Message 4906)
Posted 16 Dec 2014 by Profile Charles Dennett
Looks like the same problem does not exist for the POEM project. Tasks take the same amount of time no matter how many cores I use.

When I get some time I can play with a kernel setting called vm.swappiness. It adjusts when the kernel starts using swap space. If my memory is correct, the default is 60. (Ranges 0-100). 60 means that it will start using swap space when 60% of the memory is free. Setting it lower will allow it to use more memory before it starts using swap.

-Charlie
7) Message boards : Number Crunching : Running multiple tasks on a multi-core system takes longer. (Message 4904)
Posted 16 Dec 2014 by Profile Charles Dennett
Disk activity on the system is very low. It only has 4 GB of memory, the most the MB will support. Could be memory pressure. Also, just one piece of silicon with 4 cores so it could be some shared component on the processor chip or other hardware. Anyway, running tests now with another BOINC app (POEM) to see how it behaves. Just started tests with a one task at a time. It will be a while. I'll report back.

-Charlie
8) Message boards : Number Crunching : Running multiple tasks on a multi-core system takes longer. (Message 4899)
Posted 16 Dec 2014 by Profile Charles Dennett
Using the snail_hg19_1000fa_1motif type of task, I've run these with 1,2,3 and 4 cores on my system. Only these tasks were running. No other boinc projects were active. Total run time per task is just a bit longer than cpu time per task.

1 core: Takes about 46 minutes each . Get about 21 credits
2 cores: Takes about 1 hour 7 minutes each - Gets about 21 credits
3 cores: Takes about 1 hour 40 minutes each - Gets about 22 credits
4 cores: Takes about 2 hours 29 minutes each - Gets about 23 credits

The system is running Fedora 20 with a KDE desktop but it's not actively used most of the day so close to 100% of the cpu is used for DNA@Home.

Is this normal behavoir? I have not run the same tests on other projects. Perhaps I will. Now that SIMAP is done I might go back to POEM and see how that behaves (but I will come back to DNA@Home after those tests.)

-Charlie
9) Message boards : Number Crunching : Running multiple tasks on a multi-core system takes longer. (Message 4891)
Posted 15 Dec 2014 by Profile Charles Dennett
Running some tests. I've limited DNA@Home to only 1 core. No other project is crunching. So far it's only completed a couple of small snail (10fa) tasks. With two cores they used to take about 44 seconds. The two done with only 1 core in use took 30 seconds. It's working on a large snail (1000fa) now. Normally that take 1 hour 7 minutes. It competed 10% in 4 minutes 42 seconds which if my math is correct extrapolates to 47 minutes for the whole thing.

-Charlie
10) Message boards : Number Crunching : Running multiple tasks on a multi-core system takes longer. (Message 4890)
Posted 15 Dec 2014 by Profile Charles Dennett
One of my crunchers is a 4 core 64 bit Linux box, Typically I was giving equal time to SIMAP and DNA@Home which meant I was running 2 SIMAP tasks and 2 DNA@Home tasks at the same time. I've run out ot SIMAP work as that project is shutting down and is now out of work. So, this cruncher is now running 4 DNA@Home tasks at a time.

I've noticed a funny thing. DNA@Home tasks now take about twice as long with 4 tasks at a time as when only 2 are running. In other words, a task that would take 40 seconds when DNA@Home used 2 cores now takes 80 seconds when all 4 cores are used for DNA@Home. Likewise a 6 minute task now takes 12 minutes. Why would that be?

Now the question is, with the doubled time, will the credit double or stay the same?

-Charlie
11) Message boards : Number Crunching : Limit of 2 tasks per processing core. (Message 4791)
Posted 3 Nov 2014 by Profile Charles Dennett
I don't know the history, but what is the reason for limiting a user to 2 tasks per processing core? For example, on my 4 core cruncher, I can have at most 8 tasks downloaded at any one time. Is there any chance this limit could be either increased or eliminated? At least one project I've participated in starts out with a low limit on tasks. As the user returns valid tasks the limit is increased while returning invalid tasks lowers the limit. Sorry, but I don't recall which project that is.
12) Message boards : Number Crunching : No new work! (Message 4765)
Posted 30 Oct 2014 by Profile Charles Dennett
Yes. No new work plus the DNA_validator is not running according to the server status page.
13) Message boards : News : [dna] invalid workunits? (Message 4757)
Posted 29 Oct 2014 by Profile Charles Dennett
Just checked my tasks. No invalid ones listed. I have 4 systems with a total of 9 cores crunching (4,2,2,1) evenly divided between CSG, SIMAP and WCG. Looking good from my end!
14) Message boards : Number Crunching : How accurate is the server status page? (Message 4741)
Posted 23 Oct 2014 by Profile Charles Dennett
Just wondering. How accurate is the server status page as it relates to DNA@Home? It seems that there are usually just a few tasks ready to send and the tasks in progress keeps getting smaller and smaller (it's now down to under 500.) Also, the workunits waiting for validation seems to be stuck at 4 and the workunits waiting for assimilation is stuck at 1892. I have not been watching the numbers under Users and Computers so I really can't comment on them other than to note that it is reporting 4066 users registered in the past 24 hours. Not sure if that means new users or just total users who have contacted the server in that time.

Thanks for any insight.

Charlie


This is my question that started this thread but it morphed into the problem with all the spam accounts. I'm still curious on the constant 4 WUs waiting for validation and the 1892 waiting for assimilation . Those numbers never change.

Charlie
15) Message boards : News : deleting spam accounts (Message 4695)
Posted 16 Oct 2014 by Profile Charles Dennett
Seems reasonable to me.
16) Message boards : Webpage and Application Code Discussion : Unable to read a lot of profiles (Message 4688)
Posted 16 Oct 2014 by Profile Charles Dennett
Travis is aware of the problem.
17) Message boards : Webpage and Application Code Discussion : Unable to read a lot of profiles (Message 4687)
Posted 16 Oct 2014 by Profile Charles Dennett
I went to the http://cs.und.edu website and found Travis' email address. Sent him an email and gave a quick description of the problem Conan discovered.

Charlie
18) Message boards : Webpage and Application Code Discussion : Unable to read a lot of profiles (Message 4686)
Posted 16 Oct 2014 by Profile Charles Dennett
Take a look at this URL showing number of users over the past 60 days:

http://boincstats.com/en/stats/156/project/detail/user

it was pretty flat until the October 9 when it suddenly jumped and has been steadily rising since.

Likewise, http://boincstats.com/en/stats/156/project/detail/host shows the total number of hosts. It is a similar graph.

Something unusual going on here.

Charlie
19) Message boards : Webpage and Application Code Discussion : Unable to read a lot of profiles (Message 4685)
Posted 16 Oct 2014 by Profile Charles Dennett
Went to a bunch of other random profiles. Where the user adds information about themselves, they all had URLs listed. Bet those URLs are bad in one form or another (ads, malware downloads, etc.)

Travis, can you suspend new account creation until you can figure out how to prevent this?

Charlie
20) Message boards : Webpage and Application Code Discussion : Unable to read a lot of profiles (Message 4684)
Posted 16 Oct 2014 by Profile Charles Dennett
Interesting. Went to the M page, selected an arbitrary page number, then selected an arbitrary user. Did this several times. None had credit and none had any computers listed. Potential spammer accounts? Something else? Also , the comments seemed all of a similar type. Something funny's going on here.

Charlie


Next 20