Welcome to MilkyWay@home

Posts by WMD

1) Message boards : News : Nbody WU Flush (Message 73364)
Posted 7 May 2022 by WMD
One reason you might get that is if you don't have at least two CPUs allocated to BOINC. (I had that problem once.)
2) Message boards : News : New Poll Regarding GPU Application of N-Body (Message 73144)
Posted 28 Apr 2022 by WMD

Any progress on this?
3) Message boards : News : Nbody WU Flush (Message 72988)
Posted 19 Apr 2022 by WMD
Update: I hadn't been getting any Separation tasks all day, so I opted to also try nbody on my main machine. A few people have had issues getting Separation CPU tasks that they didn't want, but, I was able to fetch 100 nbody tasks by themselves, for 16 CPUs. So far so good... but wouldn't you know it? I got more Separation tasks several minutes later, including a bunch of CPU ones. >.< I aborted those, and it's doing GPU work at the moment, but if it keeps trying to get Separation CPU work I'll just have to turn that off. Oh well... (That particular CPU has been doing distributed.net OGR for a while, but either way, it's going back to WCG once they come back online.)

EDIT: Looks like the Separation tasks were a one-time thing, for CPU and GPU. It's steadily getting nbody only, at least for now. I'll keep an eye on it...

I get the feeling that we'll just have to keep chipping away at the nbody backlog, slowly but surely, until it's under control and the server can handle things again.
4) Message boards : News : Nbody WU Flush (Message 72985)
Posted 18 Apr 2022 by WMD
I added a spare PC to nbody for the first time, to help out. It's only two Sandy Bridge cores, but, it seems to get through a work unit every 16 minutes :)
5) Message boards : News : Server Downtime March 25, 2022 (24 hours starting 17:00 UTC) (Message 72261)
Posted 27 Mar 2022 by WMD
I don't know if the drive is rebuilt yet, but I did turn off the WU generators.

Did you, actually? The number of "Tasks ready to send" is higher than it was yesterday, so it seems more work is still being generated.
6) Message boards : News : Server Trouble (Message 72082)
Posted 20 Mar 2022 by WMD
My main desktop's data drive is a 4TB 7200rpm (TV and security camera and software installers) is 3/4 full and that only takes 5.5 hours to backup, so should be similar for a rebuild.

Rebuild times don't match the transfer rate of the drives, especially when rebuilding from parity. I've heard stories of multiple-day rebuilds of very large drives. (Larger than MW probably has or needs.)

I've never run a server with a 7200 drive!

It's actually more common than you think... or at least it was when I worked on that stuff several years back. Most commonly, they were the "capacity" tier of hybrid SAN arrays. One array I maintained had a full 3U tray of 3TB 7.2k disks, and rebuilding one of them once took over a day. They still use 7.2k in file servers, too - heck, AWS even offers them for cloud file servers, if you were to set one up.

But if he's still running validations and serving us at the same time, the rebuild will be slower.

Considering the validations weren't going at all when the failed drive was removed, I'm inclined to think the rebuild finished already. (Unless the validation pace picks up massively in the next several hours, in which case, I guess not!)

Tom seems embarrassed to say! He really ought to get some SSDs.

I doubt MW has the money. I mean, just a few years ago they were begging for money just to keep the research team going. I don't think they have funding for new hardware.

I love this one because it's the only double precision one, and I have cards very good at that, I bought them for MW on purpose, since I like the science topic.

Yeah, I have a Titan V myself... it's a pretty good performer for normal FP32 things, but so are cards a fifth of the price! So for other projects it's at least pretty productive, but still a waste overall.

If I leave my computers alone, sometimes I spot they've got a full batch of 300 per GPU. If I pester them I get nothing.

That's funny... I only got 300 tasks today by pestering it. Otherwise, getting nothing. :D

I've acquired five R9 280X cards now. I love it when they reduce the price from £130 to £50 because they "don't work". No display output? Don't care! Some of the VRAM broken, won't run big programs like Einstein, but MW is ok!

Nice :D the 280X is a pretty good FP64 card, especially at those prices.
7) Message boards : News : Server Trouble (Message 72075)
Posted 19 Mar 2022 by WMD
Hallo together, hallo Tom, how long make your server trouble???? I have many works done for this group,but the points I don't get. The last work I don't have get my points for work, because by the server crash!!!

Please repair the server and give me my workpoints.!!!Thanks Tom.....!!!

Please check out the Server Status page. Right now it says "Workunits waiting for validation: 3423883". This is why you don't have your points yet. This number is slowly decreasing now, so you will get your points within the next few days.
8) Message boards : News : Server Trouble (Message 72073)
Posted 19 Mar 2022 by WMD
Hmm, I see that the status page hasn't updated in a few hours. Normally it updates once or twice an hour...

Disk rebuild times obviously vary depending on the disk, but I've seen as low as an hour or two for a 300GB 10k rpm drive, to two days for 4TB 720rpm. No idea what MW's disk specs are. The validation queue was consistently going up until Tom announced he'd replaced the drive, so the rebuild was probably quick. I get the feeling the validation queue is lower now, but the page simply isn't updating for some reason.

As far as other GPU projects go, I've been pretty happy with MLC@Home. Amicable Numbers also worked well, but that requires a ton of system RAM.

EDIT: Got exactly one new task, just now (19:06 UTC). So it's working, just light-years (heh heh) behind. Lots for it to still catch up on. EDIT 2: And 299 more 90 seconds later! So it's kind of working, here and there.
9) Message boards : News : Server Trouble (Message 72071)
Posted 19 Mar 2022 by WMD
I'm not getting any workunits either... but I notice on the status page there are 3,591,958 workunits to waiting for validation right now. It may be trying to churn through these before it starts handing out new work. It's down by about a million since the new drive was installed, so, if I'm right, it could be a few more days before new units start going out.

I don't mind though... my GPU is just churning through my backup project. :)
10) Message boards : News : New Poll Regarding GPU Application of N-Body (Message 71018)
Posted 23 Jul 2021 by WMD
I've been waiting for this for years! I only run MilkyWay on GPU, as the CPU is used for other things - generally, projects that don't have a GPU version. And I do have a Titan V, so, I imagine the performance will be quite good. :) The performance differential between CPU and GPU won't matter so much to me, though, since GPU is all I do here. Would just be nice to be able to contribute to both applications!

As an aside, if the workunits do take longer, it'll at least be able to help with the never-fixed problem this project has with sending workunits - namely, the one where you get 300 tasks, it runs through them all without receiving any more, and then it sits for almost 15 minutes with nothing to do (since the server has a bad setting somewhere related to intervals between sending units, and the BOINC client backs off for ~10 minutes upon hitting up against that). Was tolerable with my old video card, but when your Titan V can do 300 tasks in about 35 minutes, it becomes kind of a pain. I've set up some backup projects with a work share of 0 to keep the system busy during that time, but... when you spend the money on an FP64 card, you want to do FP64 work! :)
11) Message boards : Application Code Discussion : N-Body on GPU? (Message 68233)
Posted 8 Mar 2019 by WMD
I second this. I only run MW@H on my GPU, the CPU is reserved for WCG. And there seems to be a lot more development these days on n-body, so I assume it's more interesting to the project. I'd certainly like to contribute if such a client is feasible.
12) Message boards : News : Mac OS X Support For Separation (Message 66465)
Posted 26 May 2017 by WMD
Yay! My D700 is BACK! :)

It seems that the new work units take considerably longer to run (and have longer estimated times). Do they contain more work? (Old time: 16 seconds, new time: 66 seconds).
13) Message boards : Number crunching : Mac GPU apps - any plans? (Message 66000)
Posted 11 Dec 2016 by WMD
There used to be such apps, but I think Jake said the Mac they used for builds died. So the new versions for Mac are delayed.
14) Message boards : News : Updated Server Daemons and Libraries (Message 65370)
Posted 2 Oct 2016 by WMD
To follow up on my previous post...I have fixed my problem, sort of. It turns out that my project prefs had everything disabled except for Separation (Modified Fit). I honestly don't remember why I did that...so, I turned the basic app back on (leaving n-body off), and I began to receive some work units. At first, it seemed like I could only make that happen without my custom app_info.xml (which means Jake got it to read newer GPUs after all! :) ) but after that I put the app_info.xml back, and it's still working. Which is good, because that way I can crunch 3 WUs at a time :)

In spite of this, new WUs are still sporatic. Some updates don't give me anything, and then a minute later, I'll get a few. I'm not getting anything from Separation still.
15) Message boards : News : Updated Server Daemons and Libraries (Message 65346)
Posted 29 Sep 2016 by WMD
I'm not getting any work units either, on the Mac version. Here is a log of one attempt:

Wed Sep 28 20:17:27 2016 | Milkyway@Home | Sending scheduler request: To fetch work.
Wed Sep 28 20:17:27 2016 | Milkyway@Home | Requesting new tasks for AMD/ATI GPU
Wed Sep 28 20:17:29 2016 | Milkyway@Home | Scheduler request completed: got 0 new tasks
Wed Sep 28 20:17:29 2016 | Milkyway@Home | No tasks sent
Wed Sep 28 20:17:29 2016 | Milkyway@Home | No tasks are available for Milkyway@Home Separation (Modified Fit)
Wed Sep 28 20:17:29 2016 | Milkyway@Home | Message from server: Your app_info.xml file doesn't have a usable version of MilkyWay@Home N-Body Simulation.
Wed Sep 28 20:17:29 2016 | Milkyway@Home | Tasks for CPU are available, but your preferences are set to not accept them
Wed Sep 28 20:17:29 2016 | Milkyway@Home | Tasks for NVIDIA GPU are available, but your preferences are set to not accept them

That error from N-Body is from my custom app_info.xml; I'm simply too lazy to fix it. ;) Otherwise I'm using the regular 1.37 binary for Mac ATI opencl. I figured maybe this was the cause, so I temporarily renamed the app_info.xml and started up without it, but this had no effect (other than removing my self-inflicted n-body error, of course).

©2024 Astroinformatics Group