Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
![]() |
World Community Grid Forums
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
No member browsing this thread |
Thread Status: Active Total posts in this thread: 781
|
![]() |
Author |
|
spRocket
Senior Cruncher Joined: Mar 25, 2020 Post Count: 274 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() |
Everything's running smoothly here - just got back from being out a bit and no errors in the log, and no invalid, pending verification, or pending validation units.
|
||
|
kittyman
Advanced Cruncher Joined: May 14, 2020 Post Count: 140 Status: Offline Project Badges: ![]() ![]() ![]() |
The kitties aren't having any problems either. The new supersized WUs seem to have calmed the servers down.
----------------------------------------Meow ![]() |
||
|
Seth Karlinsey
Cruncher Joined: Apr 19, 2020 Post Count: 15 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
@William Albert
----------------------------------------I see 2 thing that could possibly be issues Apr 27 22:55:45 redacted-hostname boinc[7688]: 27-Apr-2021 15:55:45 [World Community Grid] Your settings do not allow fetching tasks for CPU. To fix this, you can change Project Preferences on the project's web site. Device profile? This notes that settings aren't allowing gpu work. You may want to check that the profile has those checkboxes ticked. Apr 27 22:55:47 redacted-hostname boinc[7688]: dir_open: Could not open directory 'locale' from '/var/lib/boinc-client'. And you may want to double check your permissions here. ![]() ![]() [Edit 1 times, last edit by Seth Karlinsey at Apr 28, 2021 2:39:29 AM] |
||
|
William Albert
Cruncher Joined: Apr 5, 2020 Post Count: 39 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() |
Apr 27 22:55:45 redacted-hostname boinc[7688]: 27-Apr-2021 15:55:45 [World Community Grid] Your settings do not allow fetching tasks for CPU. To fix this, you can change Project Preferences on the project's web site. Device profile? This notes that settings aren't allowing gpu work. You may want to check that the profile has those checkboxes ticked. Note that this is only for CPU WUs. WCG has a profile setting that allows a machine to request only GPU work, which is the configuration for the machine in question. These are the key log lines of interest: Apr 27 22:55:45 redacted-hostname boinc[7688]: 27-Apr-2021 15:55:45 [World Community Grid] Requesting new tasks for Intel GPU ...which is my machine asking for Intel GPU WUs, and WCG telling it that it has nothing. That being said, you may be on to something. The only machines that are consistently getting Intel WUs are machines that were either already crunching CPU WUs, or also had Nvidia or AMD GPUs. Intel-only machines that I brought online exclusively to crunch Intel GPU WUs for this stress test have largely sat around waiting for WUs to come. In any case, the Intel GPUs are visible to BOINC, meet the OpenCL version requirements, and my BOINC client is asking for WUs and not getting any. Not sure what else WCG wants me from. ![]() Apr 27 22:55:47 redacted-hostname boinc[7688]: dir_open: Could not open directory 'locale' from '/var/lib/boinc-client'. And you may want to double check your permissions here. I see a similar message on the first project update after a BOINC client restart from a fully-working machine, so it's unlikely to be related. |
||
|
Seth Karlinsey
Cruncher Joined: Apr 19, 2020 Post Count: 15 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Ah, misread the first one.
----------------------------------------Second one stood out because I've never seen any of my linux hosts throw that one. You may want to set a chronjob to force a fetch until you get some. I know a few of my hosts were stubborn about getting tasks. Been fine since I got some initially. Even weirder, some of my atom hosts got WAY too many tasks to be reasonable, yet my core machines barely get enough to keep the queue fed. anyone else here running baytrail or similar atoms and running into the same thing? ![]() ![]() [Edit 1 times, last edit by Seth Karlinsey at Apr 28, 2021 3:28:18 AM] |
||
|
Andrew80431
Cruncher Joined: Nov 25, 2005 Post Count: 36 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
I noticed that GPU usage is different for the newer batches. As soon as batches above 13000 started, the GPU usage of my GTX-1660S was not at 100% anymore. Please note that I'm running 4 WUs concurrently via app_config.xml:
----------------------------------------<app_config> <app> <name>opng</name> <fraction_done_exact/> <gpu_versions> <gpu_usage>0.25</gpu_usage> <cpu_usage>0.25</cpu_usage> </gpu_versions> </app> </app_config> See here for a larger image. Why is the GPU usage not at 100% anymore all the time? How do those batches differ? ![]() |
||
|
Crystal Pellet
Veteran Cruncher Joined: May 21, 2008 Post Count: 1322 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
I saw this morning that the real stress test tasks from 2 BOINC clients were running now on my single Radeon 7770. Estimated times left are way off.
----------------------------------------OPNG_0014015_00015_0 - 1 hour and 21 minutes in: [07:01:54] Start AutoDock for OB3ZINC000001629851--7jji_002_mgltools--TYR380_inert.dpf(Job #208)... out of 363 Jobs and OPNG_0014100_00065_0 47 minutes running: [07:01:31] Start AutoDock for OB3ZINC001231052074_1--7jji_002_mgltools--TYR380_inert.dpf(Job #89)... out of 134 Jobs Edit: The long runner over 2 hours elapsed time finally ready. Upload file 6589kB OPNG_0014015_00015_0 Valid 27-4-21 13:01:10 28-4-21 05:54:48 0,56 / 2,10 2,7 / 1.680,0 [Edit 1 times, last edit by Crystal Pellet at Apr 28, 2021 5:58:32 AM] |
||
|
erich56
Senior Cruncher Austria Joined: Feb 24, 2007 Post Count: 295 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
|
||
|
erich56
Senior Cruncher Austria Joined: Feb 24, 2007 Post Count: 295 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Sometime yesterday, someone in this thread here mentioned that about 40MB/sec are being written to the SSD by this application.
In general, the high write to SSD rate was mentioned here several times. I was wondering by what tool this is measured. So I started the Windows Ressources Monitor - but this tool definitely does not show what I am looking for; although WCG is listed, it shows only a write rate of about 2 kb/s. Can anyone recommend a tool which shows the correct write rates of any application? |
||
|
William Albert
Cruncher Joined: Apr 5, 2020 Post Count: 39 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() |
Can anyone recommend a tool which shows the correct write rates of any application? "Perfmon" comes with Windows, and pulls directly from the OS's performance counters. It's tedious to use, but it will be the most accurate. That being said, the performance tab of Windows Task Manager should show reasonably-accurate disk throughput if you're just looking for a point-in-time snapshot. |
||
|
|
![]() |