41)
Message boards :
Number crunching :
Credit Award Consistency?
(Message 1980)
Posted 3 Feb 2023 by hoarfrost Post: ... 5 days later. Computer 44629. Task 77739116, CPU time = 110042.80, credit = 1489.44 or 48.72 CS/hour. Task 77738339, CPU time 110473.30, credit = 1500.22 or 48.90 CS/hour. |
42)
Message boards :
Number crunching :
Credit Award Consistency?
(Message 1977)
Posted 30 Jan 2023 by hoarfrost Post: In general, the algorithm has been described in article Anderson, D.P. BOINC: A Platform for Volunteer Computing. J Grid Computing 18, 99–122 (2020) (pdf version is available). Some examples below (identical Hardware): 1st task (1332.88 CS): 77700534, computer # 41727, 48.24 CS/hour, host registered at 24 Oct 2022, host total credit = 1100243, Windows; 2nd task (1074.65 CS): 77697586, computer # 41587, 45.96 CS/hour, host registered at 19 Oct 2022, host total credit = 1168437, Windows; 3rd task (1259.42 CS): 77699183, computer # 44629, 83.24 CS/hour, host registered at 4 Jan 2023, host total credit = 247415, Linux; 4th task (660.01 CS): 77697810, computer # 42812, 45.96 CS/hour, host registered at 16 Nov 2022, host total credit = 1032098, Linux. A good set for future observations, also! |
43)
Message boards :
Number crunching :
Credit Award Consistency?
(Message 1973)
Posted 30 Jan 2023 by hoarfrost Post: For granting a fair credit to a computer, BOINC server must have a fair benchmark and have gathered appropriate statistics based on the set of tasks completed on this computer. You can look, for instance, at my computer (# 4). Credits awarded per hour do not vary much because it has relatively large statistics of computing with cmdock-l 2.02 application version. This illustrates what value of granted credit is fair, too. |
44)
Message boards :
Cafe :
Russia and Ukraine
(Message 1964)
Posted 29 Jan 2023 by hoarfrost Post: ... I've found if I shutdown my computer,the progress willl turn to zero. ... Hello! At this moment, checkpoint performs for each 0.2% for cmdock-l and previous applications. Inside my VM with Windows 10 and BOINC 7.16.11 it works. I will try to test 7.20.2 also. |
45)
Message boards :
Number crunching :
how long can "long tasks" be?
(Message 1962)
Posted 29 Jan 2023 by hoarfrost Post: Could you please add at least a day or two for user ID 8110? It's been running for days, was due the 24th and still says it has around 8.5 hours left. I just restarted BOINC for the second time since it's been running. I added 4 days. :) |
46)
Message boards :
Number crunching :
Credit Award Consistency?
(Message 1961)
Posted 29 Jan 2023 by hoarfrost Post: On one of my hosts Credit dropped from 955.43Cr to 390.61Cr , same runtime : Hi! Very unusual results! How many cores of this CPU used for computing? Could you run benchmark over used cores and post the result? And what frequency of CPU cores during computing? Thank you! |
47)
Message boards :
Number crunching :
Credit Award Consistency?
(Message 1957)
Posted 28 Jan 2023 by hoarfrost Post: I also observed some very strange issues. Task 77677176. Attribute "Device peak FLOPS": 4.20 GFLOPS. Credit: 1084.29. Task 77677199. Attribute "Device peak FLOPS": 1.00 GFLOPS. Credit: 109.03. Benchmark 1.00 GFLOPS usually is a consequence of absence of benchmark. Now as I see benchmark is present and credit for tasks completed more recently is appropriate relatively time and machine power. Good "machines"! |
48)
Message boards :
News :
СmDock "long" and "short" tasks applications
(Message 1956)
Posted 28 Jan 2023 by hoarfrost Post: Hi there! Hi! My steps. Maybe not all of them is needed for you. Good luck! P.S. And de-select all applications except "CurieMarieDock 0.2.0 short tasks" in project preferences for "venue" of RPi computers. |
49)
Message boards :
Number crunching :
how long can "long tasks" be?
(Message 1952)
Posted 26 Jan 2023 by hoarfrost Post: Please add 3 days for all tasks for user id: 4871 2 tasks found, added. :) |
50)
Message boards :
News :
СmDock "long" and "short" tasks applications
(Message 1942)
Posted 24 Jan 2023 by hoarfrost Post: We will check what is happening with this files (docking_out.progress and docking_out.chk). Maybe something changed in OS API, maybe not. Inside my VM with Windows 10 metadata of this files is not stalled during computing, but changes performs not in the same time that other files. Maybe it is normal, maybe not. |
51)
Message boards :
Number crunching :
checkpointing
(Message 1937)
Posted 23 Jan 2023 by hoarfrost Post: ...has been running 2d 19h on my 2700X with 3d 17h reported to go and only a checkpoint at the 1st second. ... The algorithm is common for all tasks: If you see, that last checkpoint been too long (for example one hour ago), the best solution - perform restart a BOINC client. Or drop tasks simply. Restart is more better, I think. Tasks linked to version 2.02 presumably will not face this problem. |
52)
Message boards :
Number crunching :
how long can "long tasks" be?
(Message 1936)
Posted 23 Jan 2023 by hoarfrost Post: Are we getting lazy in our old days there ol buddy? LOL!!! You're right, Mikey! Hope, than some of us remember what is really long tasks - CPDN at ~ 2006. More than one year of most advanced Pentium 4 @ 3.06 GHz HT per pair of tasks! P.S. New tasks was supplied with two weeks deadline. Nature is amazing that expectations, as usual. :D |
53)
Message boards :
News :
СmDock "long" and "short" tasks applications
(Message 1935)
Posted 23 Jan 2023 by hoarfrost Post: SiDock has a beta test server that one of my machines is still waiting on tasks from. Looks, that I need to repeat. SiDock@home never had a separate project for wide tests (like Albert@Home). In the first phase, project did not export statistics and due of this it was called SiDockTest. After a while, we turned on export and renamed the project to SiDock@home. Later, we migrate to another infrastructure and first server was shutdown and saved as image file only. New (at this moment not latest) version of application, initially was tested by developers, then it was used for internal computing over sample set and then was deployed. And only in real environment, this unexpected behavior was caught. And ~ 15 hours after detection, at January 9th, was posted a recommendation for usage a BOINC restart as more reliable option for problem solving. There was no to need to do "babysitting" with tasks, because you could restart BOINC client on machines 1 or 2 times per day, simply. Moreover, you could made this by Windows Scheduler. You were afraid that CPU time before last checkpoint on your computers not be saved? You could test it on one of your machine, and then - restart BOINC at all others, instead of "forum sitting" in several threads simultaneously, during next two weeks. <hr> What we have with application at this moment: 3 days ago we deploy new subversion of application (# 2.02) with excluding usage of one of new features, which presumably, leads to hangs. If any faced any problems with this application please post about this. Most of tasks that linked to previous version will be processed during next several days and problem will leave, I hope. Of course, the absence of problem is much better than having one. But if we detected "the problem habitat" rightly, the hang is not predetermined, depends on random numbers and due this it is not reproduce after restart. Great thanks for all crunchers for catching of this problem. |
54)
Message boards :
Number crunching :
how long can "long tasks" be?
(Message 1934)
Posted 23 Jan 2023 by hoarfrost Post: If you can, please add some time, maybe 5 days to my wu's User ID 7207 Hi! :) Added! You can check tasks on hanging. Also you can stop and start BOINC again, simply. |
55)
Message boards :
Number crunching :
how long can "long tasks" be?
(Message 1923)
Posted 21 Jan 2023 by hoarfrost Post: At least it's not 10 credit; not what you'd expect for 309k sec but over 1k. Ryzen 3900X @ 4.0 GHz got 1004.96 CS for 85211.20 seconds of computations or 1004.95 CS / 23.67 hours / 4.0 GHz = 10.61 CS/(hour*GHz). i5-8250U @ 1.60GHz got 1129.15 CS for 298826.10 seconds of computations or 1129.15 CS / 83.01 hours / 1.60 GHz = 8.50 CS/(hour*GHz). But SMT of Ryzens much more efficient than Hyper-Threading of Intel. |
56)
Message boards :
News :
СmDock "long" and "short" tasks applications
(Message 1922)
Posted 21 Jan 2023 by hoarfrost Post: SiDock has a beta test server that one of my machines is still waiting on tasks from. First server of SiDock@home (sidocktest) was frozen after credit was moved in main project and now is stopped. Before deploy this application was tested during several days and no any problems were found. For example: where one short ("Sprot") task is hung on my computer, I perform a run of several dozens (~40) of copies of this task on my machine and all of them were completed successfully, without any problem. Only with help of auxiliary server, we were able to get a similar task hung for a long ("RdRp_v2") task. Actually, finding of this problem is a side, but very important result of our project also, received already now. |
57)
Message boards :
News :
СmDock "long" and "short" tasks applications
(Message 1921)
Posted 21 Jan 2023 by hoarfrost Post: After special "restart test" under Ubuntu, I did the same test for Windows 10 + BOINC 7.16.11. Before ~ 1 hour of tasks completion I restart a VM with Windows. First task, for workunit 49655115 is complete. And as you see, CPU time does not lost: 77614604 49655066 20 Jan 2023, 19:14:36 UTC 21 Jan 2023, 20:29:48 UTC Completed and validated 85,387.91 85,211.20 1,004.96 CurieMarieDock 0.2.0 long tasks v2.00 windows_x86_64 77614663 49655123 20 Jan 2023, 19:14:36 UTC 21 Jan 2023, 20:00:16 UTC Completed and validated 76,331.40 76,198.72 898.37 CurieMarieDock 0.2.0 long tasks v2.00 windows_x86_64 77614655 49655115 20 Jan 2023, 19:14:35 UTC 21 Jan 2023, 18:28:11 UTC Completed and validated 76,226.16 76,041.19 897.14 CurieMarieDock 0.2.0 long tasks v2.00 windows_x86_64 77614657 49655117 20 Jan 2023, 19:14:35 UTC 21 Jan 2023, 20:29:20 UTC Completed and validated 81,194.31 80,985.95 955.61 CurieMarieDock 0.2.0 long tasks v2.00 windows_x86_64 Maybe it does not work under some systems, but under nearest for me Windows system it works. |
58)
Message boards :
Number crunching :
how long can "long tasks" be?
(Message 1918)
Posted 21 Jan 2023 by hoarfrost Post: Actually, all of the WU's that are progressing have: Post name of this task and restart BOINC. If this result does not get appropriate credit, I simply add it. :) |
59)
Message boards :
News :
СmDock "long" and "short" tasks applications
(Message 1913)
Posted 21 Jan 2023 by hoarfrost Post: Hi folks! Some news: It was decided to exclude the use of one of new functions of the application. New "sub-version" of application cmdock-l with number 2.02 are deployed. Please report if problems occurs. |
60)
Message boards :
Number crunching :
how long can "long tasks" be?
(Message 1905)
Posted 20 Jan 2023 by hoarfrost Post: Hi! :) Running on a 5900x. Before Long/Short tasks I used to crunch a unit in maybe under 3hrs. not they are averaging 1-2days with a couple running past the deadline with 4-6day estimates. Still crunching, but i've stopped new tasks for now. Added. :) New tasks is really long. Most of them between 20 and 32 hours. But if you see tasks with estimation like "days" you can check it properties in BOINC Manager: "CPU time at last checkpoint" and "CPU time". If it values very differs (for 1 hour, for example) - task is hung and need a restart. (For example - stop BOINC and start it again). Also, in beginning of task it can be a rough estimation. Good luck! |
©2024 SiDock@home Team