Posts by Brent Norman

1) Message boards : Number crunching : Don't know where it should go? Stick it here! (Message 1956238)
Posted 16 hours ago by Profile Brent Norman Special Project $250 donor
Post:
For Sog tasks I found it also helps to add the -hp switch so the task gets a High Priority CPU thread.
2) Message boards : Number crunching : Setting up Linux to crunch CUDA90 and above for Windows users (Message 1955653)
Posted 3 days ago by Profile Brent Norman Special Project $250 donor
Post:
You will be happy with that SmartUPS.
We had dozens of them at work from 5000W down and they just don't fail. Just replace batteries every 2+ years. The consumer products do. My last purchase was an APC BX1500 900W. I only had 2 days of testing with it before my #2 computer had it's meltdown, but it did trip on overload once already. The latest 'sauce' has definitely put more load on my UPSs!

The biggest problems we had with the low end UPS (Say >500W Consumer, where we only needed low use for a hub or radio supply) was that after an extended outage they just wouldn't go back to line. Once the batteries ran out - toast. replace battery and it was the same.
3) Message boards : Number crunching : Twin GPU Motherboard advice (Message 1955329)
Posted 5 days ago by Profile Brent Norman Special Project $250 donor
Post:
An Intel S5520HC may be worth looking at, they can be found quite cheap with up to 96Gb. I have one that came with 2xE5630 and 12Gb RAM, upgraded it to X5680. I was quite impressed with the E5630s originally in it for the $200 CAD it cost me. It's my NAS box so I don't push it too hard with big cards (1050/750Ti). It was a bit of a pain with the CPU coolers (2 x MasterCooler D92) since the 'pads' aren't standard - I used VGA/Serial I/O shield standoffs and some scavenged M3 screws.

EDIT1: And I took a Dremel to the other two PCIe slots to allow for a 16x card.
EDIT2: It has no sound BTW.
EDIT3: It is a BIG board SSI/CEB I believe, so a bigger case is needed.

A $110 USD example: Intel S5520HC S5520HCR, LGA 1366,with 2 x Xeon L5640, 12GB
4) Message boards : Number crunching : RenderBoxx 10100 and Linux BOINC/SETI computational errors (Message 1955262)
Posted 5 days ago by Profile Brent Norman Special Project $250 donor
Post:
I only see 1 of those computers that have processed 3 tasks and they errored with:
<core_client_version>7.9.3</core_client_version>
<![CDATA[
<message>
process exited with code 193 (0xc1, -63)</message>
<stderr_txt>
boinc-app-seti is invoked with the following arguments: 
--start
--end.
I: boinc_parse_init_data_file
I: boinc_get_init_data
I: boinc_init
I: worker
I: worker() - common_init
I: worker() - read_wu_state
SIGSEGV: segmentation violation
Stack trace (10 frames):
/usr/lib/x86_64-linux-gnu/libboinc.so.7(boinc_catch_signal+0x1d8)[0x7ff6b01151ab]
/lib/x86_64-linux-gnu/libc.so.6(+0x3ef20)[0x7ff6b05daf20]
../../projects/setiathome.berkeley.edu/setiathome_v8(+0x23b31)[0x56113d3d2b31]
../../projects/setiathome.berkeley.edu/setiathome_v8(+0x2bee6)[0x56113d3daee6]
../../projects/setiathome.berkeley.edu/setiathome_v8(+0x5521e)[0x56113d40421e]
../../projects/setiathome.berkeley.edu/setiathome_v8(+0x2e9bc)[0x56113d3dd9bc]
../../projects/setiathome.berkeley.edu/setiathome_v8(+0x2ec38)[0x56113d3ddc38]
../../projects/setiathome.berkeley.edu/setiathome_v8(+0xea68)[0x56113d3bda68]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xe7)[0x7ff6b05bdb97]
../../projects/setiathome.berkeley.edu/setiathome_v8(+0xf4fa)[0x56113d3be4fa]

Exiting...

</stderr_txt>
]]>

One other computer has downloaded a handful of tasks but not returned anything yet.

I would check for dependencies for the Anonymous app you installed as well as the execute attribute for the app.
And of course if you're trying to run a AVX app on a non-AVX CPU.

If you don't have any GPUs in them, there isn't really any need for the Anonymous platform for non AVX CPUs, just delete your app_info.xml and let the server give you an app.
5) Message boards : Number crunching : No start tag in scheduler reply (Message 1954962)
Posted 7 days ago by Profile Brent Norman Special Project $250 donor
Post:
If I recall correctly, BitDefender was a bad one for screwing with BOINCs DNS mapping and would cause problems similar to described.
6) Message boards : Number crunching : Don't know where it should go? Stick it here! (Message 1954960)
Posted 7 days ago by Profile Brent Norman Special Project $250 donor
Post:
Better add a case of earplugs to your budget.
7) Message boards : Number crunching : Anything relating to AstroPulse (2) tasks (Message 1954908)
Posted 7 days ago by Profile Brent Norman Special Project $250 donor
Post:
64 here for the 11th.
8) Message boards : Number crunching : Watching the LeaderBoard? We have a former BitMiner on the first page (Message 1954761)
Posted 8 days ago by Profile Brent Norman Special Project $250 donor
Post:
I see that host earlier too. I think he is just messin' with the drivers.
He has less than 300 tasks In Progress still ...
9) Message boards : Number crunching : Arecibo Overflow Tasks Run With CUDA Special App Sometimes Filled With Triplets Only (Message 1954545)
Posted 9 days ago by Profile Brent Norman Special Project $250 donor
Post:
One that you might want to look at
http://setiathome.berkeley.edu/workunit.php?wuid=3131317505
10) Message boards : Number crunching : Setting up Linux to crunch CUDA90 and above for Windows users (Message 1954450)
Posted 10 days ago by Profile Brent Norman Special Project $250 donor
Post:
. . They are essentially the same platform, Lubuntu is kind of Ubuntu lite ...
Exactly, That is why some things like dropping file onto a terminal don't work. Because it doesn't have all the features or ability.
11) Message boards : Number crunching : Arecibo Overflow Tasks Run With CUDA Special App Sometimes Filled With Triplets Only (Message 1954013)
Posted 13 days ago by Profile Brent Norman Special Project $250 donor
Post:
Just a comment,
I been thinking about 'Noise is noise, it's garbage' line of thought and IF they even track overflowed tasks and/or their results. So why does it matter if they just toss everything with a resut_overflow as had been said.

Then I think, about overclocking, heat issues, etc. that also produce this type of a result ... so yes it does matter that the applications agree with each other in a specific way and not just categorize it as 'noise'.

Just my 2 cents worth.
12) Message boards : Number crunching : Setting up Linux to crunch CUDA90 and above for Windows users (Message 1954007)
Posted 13 days ago by Profile Brent Norman Special Project $250 donor
Post:
The important thing in app_info to avoid changing and making ghosts is the <plan_class> whatever it is originally has to match your tasks in progress, which are listed in the client_state file. If the <plan_class> changes, all your tasks will disappear.

That is why it is recommended to empty your cache first. As long as that doesn't change, your tasks are safe.

My #1 computer is still on
<plan_class>cuda80</plan_class>
Two computers have cuda60. It doesn't matter the number, just as long as they match.
13) Message boards : Number crunching : Don't know where it should go? Stick it here! (Message 1953972)
Posted 13 days ago by Profile Brent Norman Special Project $250 donor
Post:
Petri only has 4 GPUs (1080, 1080, 1080Ti, Titan V) but he works the snot out of them :D
Other people on the list like Zalster, is slowing down, resources allocated elsewhere.
14) Message boards : Number crunching : Intel 16 core/32T discusssion (Message 1953970)
Posted 13 days ago by Profile Brent Norman Special Project $250 donor
Post:
There are hundreds available. They were popular, but on the pricy side for good ones. Lots of China boards as you know.
Try "2011 DDR3 motherboard"
15) Message boards : Number crunching : GTX is dead long live RTX !! (Message 1953863)
Posted 14 days ago by Profile Brent Norman Special Project $250 donor
Post:
Petri has said he is happy with his Titan V and is not looking to upgrade to Turing.
Yes, but those 3 - 1080 series cards are getting worn out by now :D
16) Message boards : Number crunching : Panic Mode On (113) Server Problems? (Message 1953821)
Posted 14 days ago by Profile Brent Norman Special Project $250 donor
Post:
Interesting. There was a lack of file deleter backlog after maintenance this time.
The graphs seem to indicate they ran the purge and deleter before they brought the system back up to give the system a running head start on recovery.
17) Message boards : Number crunching : Panic Mode On (113) Server Problems? (Message 1953817)
Posted 14 days ago by Profile Brent Norman Special Project $250 donor
Post:
Yea, The blc16 noise seems to be better now. More like <30% noise now.
Which is good.
18) Message boards : Number crunching : Panic Mode On (113) Server Problems? (Message 1953813)
Posted 14 days ago by Profile Brent Norman Special Project $250 donor
Post:
Thanks again Jord, your trick to get a stuck upload to go through worked again :)
My Ryzen has had one stuck for 3 days, wouldn't upload or abort.

It took me a bit to find the reference info from a year ago.
https://setiathome.berkeley.edu/forum_thread.php?id=82054&postid=1895643
19) Message boards : Number crunching : Panic Mode On (113) Server Problems? (Message 1953782)
Posted 14 days ago by Profile Brent Norman Special Project $250 donor
Post:
I ran another 32 blc16 tasks ... 13 good ones.
"Captain, How to you expect warp speed when all we have to feed the hamsters is tofu!"
20) Message boards : Number crunching : Panic Mode On (113) Server Problems? (Message 1953778)
Posted 14 days ago by Profile Brent Norman Special Project $250 donor
Post:
good news... they loaded more data files to be split...
The new blc16 is from the same day (58227) as the data bomb blc11 files. Is that a problem?? what does the number after the blc denote??
Not so good news ... I just ran a sample 19 BLC16 tasks through ... 9 were not noise.

So we have a LOT more of this crap now :(


Next 20


 
©2018 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.