|
Message boards :
Number crunching :
New work Discussion
Message board moderation
Previous · 1 . . . 44 · 45 · 46 · 47 · 48 · 49 · 50 . . . 91 · Next
Author | Message |
---|---|
Send message Joined: 15 Jan 06 Posts: 637 Credit: 26,751,529 RAC: 653 |
Still no news as to when they might make the main site but more testing is happening with the OpenIFS tasks. Works for me. I built an i7-9700 (eight full cores) with 32 GB of memory for it, and never thought I would live to see it. (I can do 64 GB easily enough too with a little swapping.) It may beat the next Ice Age yet. |
Send message Joined: 11 Dec 19 Posts: 108 Credit: 3,012,142 RAC: 0 |
OpenIFS v2.19 If you get more would you please let us know how many you are running at once and post the output of "free -mw && cat /proc/meminfo"? I would like to know a little bit more what the kernel is actually doing. I may have to reconfigure things to add more swap space in a worst case scenario. Thanks! |
![]() Send message Joined: 15 May 09 Posts: 4439 Credit: 17,707,089 RAC: 27,575 |
If you get more would you please let us know how many you are running at once and post the output of "free -mw && cat /proc/meminfo"? I would like to know a little bit more what the kernel is actually doing. I may have to reconfigure things to add more swap space in a worst case scenario. Thanks! This was while running two at once. I suspended my N216's from the main site. Watching top, each task peaks at about 30% of Ram for a few seconds and then drops back down to about 9%. At one point I did let it run four at once but started at different times so hoped the peaks wouldn't all come at once. Another thing I noticed was that %work done against time isn't constant but the task slows down a lot after about 75% complete. dave@swarm:~$ free total used free shared buff/cache available Mem: 32853368 23005584 2512156 151960 7335628 9238792 Swap: 41972728 0 41972728 |
Send message Joined: 18 Jul 13 Posts: 438 Credit: 25,105,641 RAC: 12,214 |
It would be great if someone could post system requirements for the OpenIFS once more WUs are tested. It seems my i7-4790 with 16Gb and 21 Gb var space and 5.6 Gb swap may not be able to handle more than two WUs at once |
Send message Joined: 5 Sep 04 Posts: 7629 Credit: 24,240,330 RAC: 0 |
Testing has only just started, so it'll be a while before there's anything firm to talk about. But it does seem that these require more than just "rolling up your sleeves". More like "strip to the waist and put your backs into it". :) But you're right; lots of requirements are going to need to be posted. |
![]() Send message Joined: 7 Aug 04 Posts: 2172 Credit: 64,679,970 RAC: 3,208 |
If they get to the main site, there should be something in preferences like WCG where the default number that can be run at a time by a host is 1, and that can be changed by the user on a webpage if the system has 24 GB or more of RAM. Otherwise it's going to be a mess. |
![]() Send message Joined: 22 Feb 06 Posts: 487 Credit: 30,300,034 RAC: 6,617 |
Could it be done through the cc-config file with a max download flag? |
Send message Joined: 5 Sep 04 Posts: 7629 Credit: 24,240,330 RAC: 0 |
Best if it was a server setting, so fiddlers can't put things back to the way they are already. |
![]() Send message Joined: 15 May 09 Posts: 4439 Credit: 17,707,089 RAC: 27,575 |
It would be great if someone could post system requirements for the OpenIFS once more WUs are tested. It seems my i7-4790 with 16Gb and 21 Gb var space and 5.6 Gb swap may not be able to handle more than two WUs at once Based on what happened on my laptop which had 8GB RAM with the earlier tests where the tasks took up about 5GB RAM more would probably run but the use of swap memory would slow them down a lot. |
![]() Send message Joined: 15 May 09 Posts: 4439 Credit: 17,707,089 RAC: 27,575 |
There will be some more resends on batch 877 as they had gone out with the default of three strikes and out rather than the five to allow for the number that fail due to missing 32bit libs. Don't know when Sarah will do this. About 120 so far have failed three times and these will be sent out again. |
Send message Joined: 15 Jan 06 Posts: 637 Credit: 26,751,529 RAC: 653 |
About 120 so far have failed three times and these will be sent out again. I suppose we have mentioned this before, but if you had a "reliable machine" program, they would be sent to only machines that can do them. It is implemented on some BOINC projects, so I think it is a standard BOINC thing. |
![]() Send message Joined: 22 Feb 06 Posts: 487 Credit: 30,300,034 RAC: 6,617 |
Have these been sent out as batch 878? Snaflled 2 of them! |
Send message Joined: 5 Sep 04 Posts: 7629 Credit: 24,240,330 RAC: 0 |
Batch 878 are similar to batch 877. |
Send message Joined: 11 Dec 19 Posts: 108 Credit: 3,012,142 RAC: 0 |
I see over 1000 N216's in the queue. Are those bounced tasks or new? |
Send message Joined: 5 Sep 04 Posts: 7629 Credit: 24,240,330 RAC: 0 |
New. Different experiment. |
Send message Joined: 11 Dec 19 Posts: 108 Credit: 3,012,142 RAC: 0 |
With any luck I'll be able to crunch a few of them. I set WGC to "No New Tasks" on half of a Ryzen 7. |
![]() Send message Joined: 15 May 09 Posts: 4439 Credit: 17,707,089 RAC: 27,575 |
I haven't checked all of them yet but at least one of those I have downloaded is already on its third attempt. |
![]() Send message Joined: 15 May 09 Posts: 4439 Credit: 17,707,089 RAC: 27,575 |
#877 and #878 have had all tasks waiting to go out withdrawn as many produce uploads greater than the limit allowed causing some to fail at 100% completion. They will be re-issued shortly. Edit: Those already sent out will be left to run. Credit will be granted. |
![]() Send message Joined: 15 May 09 Posts: 4439 Credit: 17,707,089 RAC: 27,575 |
There were two new batches of sam50 tasks for Windows but if you blinked, you missed them. |
![]() Send message Joined: 17 Jan 09 Posts: 121 Credit: 1,751,638 RAC: 3,278 |
Yoo Hoo .. got one !!! Bill F In October 1969 I took an oath to support and defend the Constitution of the United States against all enemies, foreign and domestic; There was no expiration date. ![]() |
©2024 climateprediction.net