Message boards :
Number crunching :
Panic Mode On (116) Server Problems?
Message board moderation
Previous · 1 . . . 38 · 39 · 40 · 41 · 42 · 43 · 44 . . . 47 · Next
Author | Message |
---|---|
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Well I've suspended GPU processing on my 2 rigs until I can get a bit of a buffer downloaded, but it's not fun downloading all this work when most of it is just garbage. :-(Well all that crap that I downloaded has exceeded my peak internet allowance so I'm on a slow boat now until the end of the month during the day. :-( . . Well if the blc41/42 tasks prove to be long and slow it may balance out a bit. Here's hoping :) Stephen :) |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Results returned per hour just hit 217K. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Results returned per hour just hit 217K. . . That would be all the unreported noise bombs finally getting uploaded (particularly with Windows hosts). It should drop now with the blc41/42 tasks. Stephen :( |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Results returned per hour just hit 217K. That would be me finally getting all my 27,700 BLC24 Linux tasks finally uploaded. The BLC42 tasks aren't going to be any help. Processing them in 30 minutes on the cpu and 45 seconds on the gpus. AR=0.55 Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13727 Credit: 208,696,464 RAC: 304 |
And now the splitters have fallen on their face with the downloads finally working. RTS basically nil. And it appears the splitters are continuing to have issues. After hitting 50/s for a while, they then fell over & were just hitting 20/s, when they hadn't stopped completely. Ready_to_send was rapidly heading for 0 again till their latest burst over 40/s. WU awaiting deletion are accumulating. And things were going so well even with the huge server load, till everything came crashing down once again. And 18dc09aa still sits there, taunting us. Grant Darwin NT |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13727 Credit: 208,696,464 RAC: 304 |
. . Well if the blc41/42 tasks prove to be long and slow it may balance out a bit. Here's hoping :) A rather mixed bag. I've had 2 that took 3 times as long to crunch, and another 2 that got done in almost half the usual time. Grant Darwin NT |
Bernie Vine Send message Joined: 26 May 99 Posts: 9954 Credit: 103,452,613 RAC: 328 |
Just doing my "first of the day checks" all uploads uploaded and all 6 machines with full caches even the Win ones ;-) Looking at the ready to report, out of the 18 that have passed through while I watched, only one that took 11 secs, the rest seem to be nearer normal times, hoping it stays that way. Nope I was wrong, just had 22 "noise bombs" but they were all on the slowest of the 2 Win machines so maybe it has just "caught up" |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
Some are non-vlar tasks, so I guess they are BLC shorty\ies.. . Well if the blc41/42 tasks prove to be long and slow it may balance out a bit. Here's hoping :)A rather mixed bag. I've had 2 that took 3 times as long to crunch, and another 2 that got done in almost half the usual time. |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Results returned per hour just hit 217K. . . See I said you were the guilty party :) . . I have noticed the short run times on the Blc41/42 tasks. That was what I was getting first time around as well except now and then I would see the really slow ones at 3 x normal time. I am guessing those were the usual GBT VLAR types. I haven't gotten around to checking out the stderr details to see what the AR's actually were ( I was afraid I would discover they were noisy overflows). Well at least the rigs are back into productivity. That noise bomb storm really put a crimp in things. Stephen :( |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
. . Well if the blc41/42 tasks prove to be long and slow it may balance out a bit. Here's hoping :) . . Apparently Keith checked the results and they are shorties with ARs around 0.55. That would explain the consistency in run times I am seeing, usually noisy overflows are more erratic in times. So the super long ones are the actual VLAR tasks. Stephen < shrug > |
Tom M Send message Joined: 28 Nov 02 Posts: 5124 Credit: 276,046,078 RAC: 462 |
I am getting "aborted runtime limit" on blc41/blc42 tasks on what appear to be gpu tasks. They are running 41 odd minutes and then hitting this error. They are also hanging in my task list. Is this me or them? Tom A proud member of the OFA (Old Farts Association). |
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
So I went for a walk in my neighborhood a couple weeks ago and there was a computer out for trash, along with a destroyed Ikea desk. I peeked inside the case to see what all was there--I was really only after mobo+cpu+ram, all of which was still there. GPU and drives were gone. That's fine by me. Brought it home, used the new build of Hiren's win10 PE to see what I was working with. The Sempron 3500 that it replaced was doing these MBs in about 5.5 hours and was single-core. 4770K is doing them in about 1 hour, and I've got it set for 4 at a time. So that's what.. 20-22x faster? Well it's been a month now and that's enough time for things to settle out. I have a verdict. Lunar orbit has been reached (click for full-size on imgur) The old Sempron machine had been on a pretty stable RAC average of ~375. Sitting at ~7150 for the past few days now, so I think that's the new stable figure. 7150/375 = 19.066667. So my rough napkin math of ~5.5x faster * 4 at a time was pretty accurate. I'm pretty pleased with this machine, especially since someone just....threw it out. The CPU alone is on ebay for $120-175. Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
That's on par with my i5-4590 @3.3GHz which is at 7400 right now. https://stats.free-dc.org/charts/hostdaily.php?proj=sah&hostid=8457417 Your could definitely run more than 4 tasks on that machine though. When you found that machine I mentioned that is a good overclock chip. I real quick look shows 4.7GHz on it :) |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
I am getting "aborted runtime limit" on blc41/blc42 tasks on what appear to be gpu tasks. They are running 41 odd minutes and then hitting this error. It would be easier if you at least listed the host you are referring. I would say it is you since I have not had any issues with any of the BLC41/42 tasks. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
Exceeded runtime limit is usually a result of excessive rescheduling in my experience. |
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 65738 Credit: 55,293,173 RAC: 49 |
Now if only We can clear this Shorty Storm... The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's |
Tom M Send message Joined: 28 Nov 02 Posts: 5124 Credit: 276,046,078 RAC: 462 |
I am getting "aborted runtime limit" on blc41/blc42 tasks on what appear to be gpu tasks. They are running 41 odd minutes and then hitting this error. Later I discovered two gpu tasks in the taskmanager that were unkillable. Had to reboot to get rid of them. It was this machine: https://setiathome.berkeley.edu/show_host_detail.php?hostid=8684146 Since I am running two new to me gpu's it is entirely likely it was me. I re-jiggered the bios settings and had to re-install the All-in-One because it wouldn't start after the 2nd app crash. So will go away and see what happens. Tom A proud member of the OFA (Old Farts Association). |
Jeff Cobb Send message Joined: 1 Mar 99 Posts: 122 Credit: 40,367 RAC: 0 |
Apologies for the upload issue yesterday. As many here properly guessed, this was fallout from the shortie / fast runner / noise bomb file set that was being split. I moved this file set out of the way but it took a few hours to work through the already split data. We are hoping to replace the upload server (bruno) before too long with a machine that is both faster and will store the results on SSDs. |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Hi Jeff, good to see you around still. Thanks for the update and news of a possible new upload server. [Edit] We ran across another noisy file set earlier this year. Any idea of why you are generating noisy files? Bad data recorder channel or something. Target location in the sky coinciding with a satellite constellation or something? Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Unixchick Send message Joined: 5 Mar 12 Posts: 815 Credit: 2,361,516 RAC: 22 |
Thanks for the info Jeff. Always nice to hear about what is going on and what is planned. |
©2024 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.