Jump to content
SpencerJ

Help Take the Fight to COVID-19 with BOINC and Folding@home

313 posts in this topic Last Reply

Recommended Posts

26 minutes ago, PSYCHOPATHiO said:

Folding@Home Now More Powerful Than World's Seven Top Supercomputers Combined - Join TPU!

https://www.techpowerup.com/265018/folding-home-now-more-powerful-than-worlds-seven-top-supercomputers-combined-join-tpu

Umm, is this how skynet gets started?!?

 

We were so preoccupied with whether or not we could, we didn’t stop to think if we should. 😜

Share this post


Link to post
Posted (edited)
18 minutes ago, aptalca said:

Umm, is this how skynet gets started?!?

Never came to mind, its actually scary if it was being used for AI.

At least if Skynet did happen the end user has the power to take their own PCs/Servers offline.

 

EDIT: This virus might be called CoronaNet Extra 🤣

Edited by PSYCHOPATHiO

Share this post


Link to post

Hmmm

Maybe THAT's where this new hardware came from!

(perhaps the voices too?)

😵

Share this post


Link to post
On 3/22/2020 at 6:57 PM, jsdoc said:

Just caught onto this today (Thx @SpaceInvaderOne !), saw we're "only" #2, which just won't do --- Just "remembered" I have a Threadripper 2950x new in box - was going to sell the old dual Xeon E5 V2s and upgrade, but now going to bring this out & join the fray with the I9-9900 Hackintosh [AMD 580] and Ryzen 3700x.  The threadripper will have to go "benchtop bare" for now, but that's OK.    Should probably just use the office for a sauna now 🥵.   Think the UPS is sweating a tad....  

 

I am regional medical director for a company that does home medical visits on the sickest of the (US Medicare) population, IE top tier risk for COVID, avg. patient age 80+.  We have offices in all the top affected cities in US so far.   We're working nonstop to try to keep our patients safe at home.   We've had to retreat temporarily to mostly telephonic visits due to shortage of PPE (protective gear) til our supply improves so we don't spread it to them - very frustrating.   Now I can feel better about being stuck at home, still helping on the compute side as well til we get to get back safely in their homes. 

 

I wanted to thank everyone here for being so eager to take part / take action and with such impressive results.   It means alot in the medical world to see folks being resourceful and doing their part.   Please stay home, stay safe, and round up some more CPU's for this !

 

Is it just me but how come there is a shortage?  It can't be because people are panic buying is it?  Sorry I'm generally curious but without the political agendas hidden in any of the messaging which I feel is a damn shame.  

Share this post


Link to post
13 hours ago, cbr600ds2 said:

 

Is it just me but how come there is a shortage?  It can't be because people are panic buying is it?  Sorry I'm generally curious but without the political agendas hidden in any of the messaging which I feel is a damn shame.  

The shortage is caused by the hoarding and I guess most of the hospitals don't have a large stock as they weren't prepared for this. The whole world wants to buy, so it's no wonder it's hard to get protective gear.

Share this post


Link to post
11 minutes ago, saarg said:

The shortage is caused by the hoarding and I guess most of the hospitals don't have a large stock as they weren't prepared for this. The whole world wants to buy, so it's no wonder it's hard to get protective gear.

That, and they're all one use only.

Share this post


Link to post
Posted (edited)

Is anyone else experiencing "out of memory" errors for the lsio BOINC docker? I've tried limiting the amount of memory available to the container (and also lowering the maximum memory usage in the BOINC manager settings) and now it's not bringing my whole server down when it fills up all the memory available to it, but I'm still getting these out of memory errors and the kernel is killing Rosetta as a result.

 

Also, I don't believe this is related but every Rosetta Mini task assigned to me is failing by way of computational error. Is anyone else experiencing these issues? Or maybe have a fix?

Edited by arwaldman
added additonal information

Share this post


Link to post

i having issue with the grcpool  where you supposed to get bitcoins for running it.. but the admin isnt replying there anyone else having same issue  with BONIC and the grcpool for getting credit to running  i been running BONIC on 3 computers for 10 days non stop  but its doing nothing

Share this post


Link to post
53 minutes ago, arwaldman said:

Is anyone else experiencing "out of memory" errors for the lsio BOINC docker? I've tried limiting the amount of memory available to the container (and also lowering the maximum memory usage in the BOINC manager settings) and now it's not bringing my whole server down when it fills up all the memory available to it, but I'm still getting these out of memory errors and the kernel is killing Rosetta as a result.

 

Also, I don't believe this is related but every Rosetta Mini task assigned to me is failing by way of computational error. Is anyone else experiencing these issues? Or maybe have a fix?

I think the more cores you use the more ram it requires.

I installed Hyper-v on my windows 10 and installed a windows vm with BOINC I noticed when I limited the ram I started having issues as task failing and out of memory also the more cores I added the more memory it consumed.

 

you can limit the number of cores if you dont want it to conume all the memory

Share this post


Link to post
12 minutes ago, comet424 said:

i having issue with the grcpool  where you supposed to get bitcoins for running it.. but the admin isnt replying there anyone else having same issue  with BONIC and the grcpool for getting credit to running  i been running BONIC on 3 computers for 10 days non stop  but its doing nothing

Please don't take offense at this, but you probably will anyway.

 

If the only or overriding reason you are running this is to be directly compensated in some way, don't run it.

  • Like 2
  • Thanks 1

Share this post


Link to post

no   as  you assumed wrong..  when you install it they say also  add grcpool

why would you think  grcpool had anything to do with bonic...  since that wasnt the reason to install. but bonic is linked to grcpool when it your going through the settings.. and it says  you can get credit for doing it.. but i cant seem to get that part to work..

never said i was only doing it for that reason...  i also been doing SETI crunching for 20 years..  and i dont get credit for it

 

Share this post


Link to post

in an another community were i am active they said, 1G per task (1 task is 1 core/thread) but i have also seen some trouble with rosetta mini tasks in the docker container, were on my VM (same machine) it finished without problems.

Share this post


Link to post
Posted (edited)

 

15 minutes ago, comet424 said:

no   as  you assumed wrong..  when you install it they say also  add grcpool

why would you think  grcpool had anything to do with bonic...  since that wasnt the reason to install. but bonic is linked to grcpool when it your going through the settings.. and it says  you can get credit for doing it.. but i cant seem to get that part to work..

never said i was only doing it for that reason...  i also been doing SETI crunching for 20 years..  and i dont get credit for it

 

It's a two-year-old post but BOINC warns against using grcpool as a manager.

 

https://boinc.berkeley.edu/forum_thread.php?id=12245

Edited by Hoopster

Share this post


Link to post

i currently running 3 computers  12cores 8 cores 6 cores  and that includes my desktop  so i just run my 2 unraids and desktop 24 7 at 100%

also good for bench marking the cpu too

i also have Folding @ home  on my desktop but my video card not the best..  and i done the crunching for cancer in the past because i have gone through cancer twice  both times nearly killed me  and i have crunched seti 20 yrs using a Dial up internet connectioned a 3.1kbps speeds back then   man those days

and i only looked at the grcpool as after you follow the instrucstion to install  bionic etc from the unraid page    thats also where i found the grcpool  

 

but from the link above more like seems grcpool is a scam..  i just figured what the heck try doing it and see what i can get at the same time.. but was never my first interest..  as initially you dont see the grcpool  till following the instructions then it pops up  i forget exactly  ...

 

but from what i read seems like a gimic  like Sea Monkeys lol

 

Share this post


Link to post

now i know where i saw it      in bonic  in the account manager   they offer BAM, grcpool,gridrepublic,science united.. thats how i found it playing with the settings..       wish you guys had this program long time ago for unraid... 

 

not a big deal like i mentioned..

hope everyone is staying safe and self iscolating and stayng your 6 feet away. and we all will recover the best we can 🙂 .  thanks guys for getting back to me 🙂

 

Share this post


Link to post

F@H starting to drop more CPU jobs for COVID-19 projects, previously only really seeing GPU jobs.

Team Unraid also just hit 1100 donors :)

 

Share this post


Link to post

Anyone gettting transfer errors?  For some reason its holding a bunch of files that need to transfer- I run diskspeed and its showing close to 300 Gbps down and up.  I'm not sure what else to check

Share this post


Link to post
15 hours ago, Squid said:

That, and they're all one use only.

Yeah but that's not like that's new, you know?  Goes with the territory kind of thing.  I wonder how many actual plants are actually making such items or if they're like all coming from like 2-3 plants which seems...dumb.

Share this post


Link to post
12 hours ago, arwaldman said:

Is anyone else experiencing "out of memory" errors for the lsio BOINC docker?

Just did last night on one my servers, it killed a VM, going to lower allocated RAM for all VMs to see if having some more free RAM is enough, I have another server running it without VMs/dockers and no issue on that one.

Share this post


Link to post
Posted (edited)

Some considerations on using the BOINC docker for Rosetta@Home. Performance and Memory concerns.

 

BOINC defaults to using 100% of the CPUs.  Also, by default, Rosetta will process 1 task per cpu core/thread.  So if you have an 8 core machine (16 with HT) it will attempt to process 16 tasks at once.  Even if you set docker pinning to specific cores, the docker image will see all available cores and begin 1 task per core/thread.  If you want to limit the number of tasks being processed, change the setting for using % of CPUs. 

 

So using the 8 core machine example above, setting it to 50% would process 8 tasks at a time.  Regardless of how you set up CPU pinning.  

 

RAM and out of memory errors.

Some of the Rosetta jobs can consume a lot of RAM.  I have noticed individual tasks consuming anywhere between 500Mb-1.5Gb of RAM. You can find the memory a task is using by selecting the task, and clicking the properties button. If the task runs out of memory, it may get killed, wasting the work done or delaying it.  It is helpful to balance the number of tasks you have running to the amount of RAM you have available.  In the example machine above, if I am processing 8 tasks, I might expect the RAM usage to be anywhere from 4Gb to 10Gb.  The docker FAQ has instructions on limiting the amount of memory the docker container uses, but be aware that processing too many tasks and running out of memory will just kill them and delay processing.

 

My real world example.

CPU: 3900X 12-core (24 w/ Hyperthreading)

RAM 32GB

Usage limit set to 50%, so processing only 12 tasks at a time.

image.png.47cfb54cb8cf9b9f28f2f0d8d46321ab.png

 

RAM limited to 14G, I could go a little higher, but havent needed to.  Most tasks stay under 1Gb

image.png.9befc97d64d709a71dd689e8d48e9647.png

 

CPU pinning to almost all available cores

image.png.46db184a736b469394ca29299a303fa9.png

 

Actual CPU usage looks like

image.png.25827446fb6246880bc50a902a48d259.png

 

Since putting those restrictions on, I have had very stable processing and no out of memory errors.

Edited by mattekure
  • Like 2
  • Thanks 1

Share this post


Link to post

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Restore formatting

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.