Posts by mmonnin

21) Message boards : Theory Application : Installation of CVMFS (Message 38368) Posted 21 Mar 2019 by mmonnin Post: Well, thanks for the tips but I couldn't get this damn CVMFS installed at all no matter what I tried meanwhile. :-\ I'm too inexperienced with Linux to dig into this even more and don't have the time either so I give up here. Too bad... I hope a Windows app for this will come out sooner or later, if not then so be it... If you want to try Ubuntu you can use the instructions I gave to my team. It's worked for me on several 18.04 installs. The instructions given at LHC forums are way overly complicated for no reason when CVFMS can be installed from a repository. It's also much quicker than compiling it. https://www.overclock.net/forum/365-overclock-net-boinc-team/1721752-projects-month-march-2019-a.html#post27876964
22) Message boards : Theory Application : Issues Native Theory application (Message 38329) Posted 20 Mar 2019 by mmonnin Post: The task is set to use 2 CPUs by default and barely over 1 is used and the reported time has run time = exactly CPU time. To the second on every task. At most I see 1.5 cores when the task is really short. 6min run time, 8 min CPU time. Don't trust the values reported in the results, specially when they are equal. Example your task: https://lhcathome.cern.ch/lhcathome/result.php?resultid=219459914 It reported 51m 1 sec, that is exactly the reported cpu time at the end of the result. 06:18:02 (32596): cranky exited; CPU time 3061.446043, but when you calculate job finish time minus the job start time (the job should have ran in one flow) 06:18:02 (32596): cranky exited; CPU time 3061.446043 05:38:19 (32596): wrapper (7.15.26016): starting you'll find the elapsed time is 2383 seconds, so 1 cpu is used far over 100% or 2 cpu's are partial used. I am looking at BOINCTasks history for the correct run/CPU times. And my statement is still true. At BEST 1.5 threads used but average is like 1.1 threads per task. I set it use 1 per task with app_config so the CPU would be fully used.
23) Message boards : Theory Application : Issues Native Theory application (Message 38284) Posted 19 Mar 2019 by mmonnin Post: The setup went without error, thanks Ivan for the great directions. The directions are actually by Laurence ;) 2 X rivetvm.exe, 1 at 65% CPU, 1 at ~45% CPU 2 X pythia8.exe, 1 at ~80% CPU, 1 at ~65% CPU Wahoo!! Very nice to see pythia running native but was hoping to see it using closer to 100% CPU? To each job there are a lot of processes. Each job needs 1 rivetvm.exe and e.g. pythia8, agile-runmc (=pythia6), sherpa, herwig etc. So you have to sum 1 jobname-process with a rivetvm and you see they are together >100%, what happens when you have idle cpu's. The task is set to use 2 CPUs by default and barely over 1 is used and the reported time has run time = exactly CPU time. To the second on every task. At most I see 1.5 cores when the task is really short. 6min run time, 8 min CPU time.
24) Message boards : ATLAS application : Atlas Simulation 1.01 (Vbox64) will not finish (Message 38227) Posted 12 Mar 2019 by mmonnin Post: Something whacky happened..I don't know how another CPU project got activated, but it did. I shut it down and got ATLAS back and running, everything seemed ok for awhile, but now at 90 some odd percent, while BOINC still counts off the time and the percent and the usual sluggish remaining time vs real time is happening, the log has not update with new target information for 20 mins now. Not sure what happened. The log refreshes, but no new information comes through. Note: Due to the interruption by another project switching from GPU to CPU (damn I need to get that second host going, but no time right now) this task I am running now will run another 3hrs before finishing. Looks like log file caught up finally. Anyway....dropped ATLAS for now until I can get this host thing set up. All remaining tasks will be finished (2 more). I run a separate GPU BOINC client on all my PCs. https://www.overclock.net/forum/18056-boinc-guides-tutorials/1628924-guide-setting-up-multiple-boinc-instances.html
25) Message boards : ATLAS application : No tasks available (Message 38161) Posted 8 Mar 2019 by mmonnin Post: In the past 2 days I've had ~10 native ATLAS canceled by the server on 3 different hosts. None were anywhere near expiry date. Most had run for several hours. This is definitely not a case of caching too many tasks. My watchdog script showed 5 were processing events. I didn't check the other 5. I had a couple as well.
26) Message boards : ATLAS application : ATLAS issues (Message 38109) Posted 5 Mar 2019 by mmonnin Post: So true. Tired of having my laptop on for hours for random results... You may read Don Quixote by Cervantes (a well known author in your locale) followed by Yeti's Checklist. Pay special attention to item #21. Did you mean another # as the list only goes to 19.
27) Message boards : ATLAS application : Guide for building everything from sources to run native ATLAS on Debian 9 (Stretch) (Message 35420) Posted 3 Jun 2018 by mmonnin Post: From what I recall there was a long setup time. I compared CPU time which doesn't even include setup time where runtime goes up and CPU time does not. The only benefit I saw was lower memory. I can't run all 32 threads with vbox or native Altas with 32gb of memory so theres basically no benefit at all and only credit penalties with a complicated, incomplete setup. It is the same app, either setup yourself or bundled in a .vdi. I've never seen an app vary by 19x due to the credit system. Runtime and credit of native and vbox versions was pretty consistent when comparing within version.
28) Message boards : ATLAS application : Guide for building everything from sources to run native ATLAS on Debian 9 (Stretch) (Message 35417) Posted 2 Jun 2018 by mmonnin Post: How are others seeing performance between Native/VBox Altas apps? Native is 19x slower than VBox on the same PC. https://lhcathome.cern.ch/lhcathome/results.php?userid=485872&offset=0&show_names=0&state=0&appid=14 Native: 2,892.54 25,856.68 324.96 ----0.75 Point/Min Vbox: 1,027.45 509.98 121.48 ---- 14.29 Point/Min
29) Message boards : Number crunching : Tips for optimizing BOINC file transfers for LHC@home (Message 35409) Posted 1 Jun 2018 by mmonnin Post: That would only work if you could put the ISP router in bridge mode. Otherwise, the ISP router will still keep track of all connections because it will see all of the different destinations and different source ports and still perform NAT on each connection. I still don't have dropped connections with the VZ router not in bridge mode and I've added more connections since when I was using it as the main router. Shouldn't the VZ router only see one device, the aftermarket router since everything else is behind that NAT?
30) Message boards : ATLAS application : Guide for building everything from sources to run native ATLAS on Debian 9 (Stretch) (Message 35408) Posted 1 Jun 2018 by mmonnin Post: Followup: Several tasks completed following the setup. Skipped: su testing Added sudo apt install git sudo apt-get install libtool m4 automake Modified per later post: CVMFS_HTTP_PROXY=DIRECT Very nice. thanks for the instructions. Well above my head in Linux.
31) Message boards : ATLAS application : Guide for building everything from sources to run native ATLAS on Debian 9 (Stretch) (Message 35405) Posted 31 May 2018 by mmonnin Post: I just went through the setup. I needed this to get through the 1st git download. 18.04 min install. sudo apt install git Then I also needed this: sudo apt-get install libtool m4 automake before this: ./autogen.sh Now to try and get some work.
32) Message boards : Sixtrack Application : 2nd Returned Result is Always Invalid (Message 35396) Posted 28 May 2018 by mmonnin Post: It was quite a few days w/o a reply on that forum so I posted here. The same user can also get the wingman validation so you can be guaranteed to get an invalid task. https://lhcathomedev.cern.ch/lhcathome-dev/forum_thread.php?id=415#5430 It is working fine here.
33) Message boards : Sixtrack Application : 2nd Returned Result is Always Invalid (Message 35384) Posted 26 May 2018 by mmonnin Post: The 2nd user to return the quorum is always invalid at LHC dev. Can this be fixed?
34) Message boards : Sixtrack Application : EXIT_DISK_LIMIT_EXCEEDED (Message 35102) Posted 28 Apr 2018 by mmonnin Post: https://lhcathome.cern.ch/lhcathome/result.php?resultid=188317371 Getting some of these with the tasks released today. Errors around 20min for everyone. 15 completed (13 of those very short) and 9 errors so a poor ratio and ever worse when considering the time.
35) Message boards : News : Server upgrade - file uploads paused (Message 34798) Posted 29 Mar 2018 by mmonnin Post: Sunday was the last stats-transfer to BOINCSTATS.COM or FREE-DC.ORG. Maybe, it is because of the storage-backend change. Thank you for help. Came here to ask about this. Seems to be only post about it.
36) Message boards : Sixtrack Application : Inconclusive results (Message 34773) Posted 27 Mar 2018 by mmonnin Post: Getting tons of these today out of the blue. Suspending work.
37) Message boards : ATLAS application : ATLAS native app (Message 34723) Posted 24 Mar 2018 by mmonnin Post: Wouldn't it be time to add the native app to the app list and spend an additional checkbox for it as it has already been requested by a couple of volunteers? Is now there in the app list. :-)) Thank you Atlas-Team. I think the request was to have it in the preferences as it's own app Run only the selected applications SixTrack: yes sixtracktest: yes CMS Simulation: yes LHCb Simulation: yes Theory Simulation: yes ATLAS Simulation: yes ALICE Simulation: yes Benchmark Application: yes Add Native ATLAS as an option.
38) Message boards : Sixtrack Application : 6track balance with other LHC apps (Message 34722) Posted 24 Mar 2018 by mmonnin Post: Your requirements can't be fulfilled with a single BOINC client instance. As you already stated the problem would be that you either can configure it to run a couple of SixTracks or to limit the number of concurrently running VMs. Jerome_C2005 wrote: ... if I set it to 1 I'll only get one 6track, and if I set it to 8 I may have various VM (different) apps at the same time ... You may think about to setup an additional BOINC client, with all it's advantages and disadvantages. The most "dangerous" pitfall would be to convince the project server to generate a second hostid. Otherwise the server will try to merge both instances and purges running work. A couple of howtos can be found in web, e.g. http://www.overclock.net/forum/365-overclock-net-boinc-team/1628924-guide-setting-up-multiple-boinc-instances.html I was about to link my own guide. :) The forum transition screwed up the layout of the guide, in particular the code tags. I haven't had the issue described. Of the projects I've setup on multiple clients on the same PC, GPUgrid just doesn't seem to keep the multiple home/work/school locations saved on the server even if used on separate PCs.
39) Message boards : Number crunching : Tips for optimizing BOINC file transfers for LHC@home (Message 34705) Posted 20 Mar 2018 by mmonnin Post: That sounds like issues with a small NAT table that comes with the VZ Actiontec routers for FioS. Too many connections and it trips over itself as it doesn't have enough of a NAT table to keep up with the connections. Even if your ISP requires a certain router, there's nothing stopping you from putting your own router behind it. The only device the ISP router sees is your own router so the NAT table doesn't fill up. This is how I have mine setup. Just assign your router a different IP besides the typical 192.168.1.1 that might come with the ISP router.
40) Message boards : Number crunching : Hyperthreading vice no hyperthreading for VM tasks (Message 34652) Posted 14 Mar 2018 by mmonnin Post: Most apps do gain with HT on and can do more work in the same amount of time. If there is a branch hit or info is requested from memory on one thread, the other can still utilize some the CPU cycles that would have been otherwise wasted. There was one BOINC app where I saw that turning HT off on my 2670v1 actually did produce more work but that is by far in the minority of apps. WUProp data does include if CPUs have HT On or Off and might indicate if an app is better with it on or off.

Previous 20 · Next 20

LHC@home