Panic Mode On (86) Server Problems?

Author	Message
Richard Haselgrove Volunteer tester Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874	Message 1461588 - Posted: 7 Jan 2014, 23:18:34 UTC - in response to Message 1461475. 100 validate errors and counting. What is going on! Corrupted upload diskspace?, maybe some diskcs have failed?, validator can't find the uploaded files. Claggy My 47 invalids are gone but I don't know if they are now valids or simply gone I had 13 invalids on one host before maintenance, but the few I spot-checked afterwards (like WU 1396570209) have been validated and the extra copies marked "didn't need". ID: 1461588 ·

Wiggo Send message Joined: 24 Jan 00 Posts: 34744 Credit: 261,360,520 RAC: 489	Message 1461597 - Posted: 7 Jan 2014, 23:35:47 UTC I see that the MB splitters still arn't getting up to speed. :-( Cheers. ID: 1461597 ·

Richard Haselgrove Volunteer tester Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874	Message 1461599 - Posted: 7 Jan 2014, 23:40:30 UTC - in response to Message 1461597. I see that the MB splitters still arn't getting up to speed. :-( Cheers. Things are always slow while the disk heads are thrashing and the database tables are being loaded into RAM. ID: 1461599 ·

Claggy Volunteer tester Send message Joined: 5 Jul 99 Posts: 4654 Credit: 47,537,079 RAC: 4	Message 1461604 - Posted: 7 Jan 2014, 23:48:58 UTC - in response to Message 1461569. I wonder whats happend of late. After the colo move we were running pretty smooth. But the last few weeks has seen one thing after another. Is it hardware or software problems. I do miss Matts weekly tech posts. +1 +2 Claggy Matt is Back. Claggy ID: 1461604 ·

Fred E. Volunteer tester Send message Joined: 22 Jul 99 Posts: 768 Credit: 24,140,697 RAC: 0	Message 1461651 - Posted: 8 Jan 2014, 2:54:52 UTC Guess the sun has set in California and the Servers are acting up again. Ready to send has been drained - only 515 S@H v7 at the 2:50:04 UTC update. That's down from 29K 10 minutes earlier. Another Fred Support SETI@home when you search the Web with GoodSearch or shop online with GoodShop. ID: 1461651 ·

S@NL Etienne Dokkum Volunteer tester Send message Joined: 11 Jun 99 Posts: 212 Credit: 43,822,095 RAC: 0	Message 1461680 - Posted: 8 Jan 2014, 5:36:35 UTC - in response to Message 1461569. I wonder whats happend of late. After the colo move we were running pretty smooth. But the last few weeks has seen one thing after another. Is it hardware or software problems. I do miss Matts weekly tech posts. +1 +2 Claggy +3 ID: 1461680 ·

Jean Labrecque Send message Joined: 4 Jun 03 Posts: 77 Credit: 14,518,927 RAC: 0	Message 1461683 - Posted: 8 Jan 2014, 5:49:02 UTC Last modified: 8 Jan 2014, 5:50:28 UTC check the technical news ....something new there from MATT jean http://setiathome.berkeley.edu/tech_news.php ID: 1461683 ·

Wiggo Send message Joined: 24 Jan 00 Posts: 34744 Credit: 261,360,520 RAC: 489	Message 1461685 - Posted: 8 Jan 2014, 5:59:03 UTC - in response to Message 1461599. I see that the MB splitters still arn't getting up to speed. :-( Cheers. Things are always slow while the disk heads are thrashing and the database tables are being loaded into RAM. Sorry Richard, but the problem with the MB splitters not getting up to speed has been going on for quite some time now and they are still not (ready to send under 10K now). :-( Cheers. ID: 1461685 ·

James Sotherden Send message Joined: 16 May 99 Posts: 10436 Credit: 110,373,059 RAC: 54	Message 1461687 - Posted: 8 Jan 2014, 6:03:55 UTC - in response to Message 1461680. I wonder whats happend of late. After the colo move we were running pretty smooth. But the last few weeks has seen one thing after another. Is it hardware or software problems. I do miss Matts weekly tech posts. +1 +2 Claggy +3 LOL, Ask and you shall receive. So if I read Matts post right, It is software and hardware. When it rains it pours as they say. Im glad Matt is back in the lab. [/quote] Old James ID: 1461687 ·

Wiggo Send message Joined: 24 Jan 00 Posts: 34744 Credit: 261,360,520 RAC: 489	Message 1461706 - Posted: 8 Jan 2014, 7:02:46 UTC MB ready to send down to under 300 now. Cheers. ID: 1461706 ·

rob smith Volunteer moderator Volunteer tester Send message Joined: 7 Mar 03 Posts: 22200 Credit: 416,307,556 RAC: 380	Message 1461707 - Posted: 8 Jan 2014, 7:09:27 UTC Expected impact of the long project back-off - will stay low for a couple of hours and then gradually climb back to 300k. So long as it remains above zero then its happy, worry when it goes negative..... Bob Smith Member of Seti PIPPS (Pluto is a Planet Protest Society) Somewhere in the (un)known Universe? ID: 1461707 ·

Grant (SSSF) Volunteer tester Send message Joined: 19 Aug 99 Posts: 13736 Credit: 208,696,464 RAC: 304	Message 1461727 - Posted: 8 Jan 2014, 7:39:45 UTC - in response to Message 1461707. Expected impact of the long project back-off - will stay low for a couple of hours and then gradually climb back to 300k. So long as it remains above zero then its happy, worry when it goes negative..... Nope, it's a result of the problem with the PFB splitters. Prior to the introduction of the PFB splitters, the old splitters were able to pump out 40 WU/s no problems at all. Now they struggle to put out much more than 25/s. Often they struggle to even produce 20/s. There are the odd bursts of 90/s+, but that's all they are- odd bursts. Grant Darwin NT ID: 1461727 ·

Filipe Send message Joined: 12 Aug 00 Posts: 218 Credit: 21,281,677 RAC: 20	Message 1461742 - Posted: 8 Jan 2014, 8:23:18 UTC Matt Wrote: Maybe we'll create a new client. (which will require much larger workunits). ID: 1461742 ·

Wiggo Send message Joined: 24 Jan 00 Posts: 34744 Credit: 261,360,520 RAC: 489	Message 1461746 - Posted: 8 Jan 2014, 8:32:24 UTC - in response to Message 1461742. Matt Wrote: Maybe we'll create a new client. (which will require much larger workunits). That has been on the table for over a year now, but still hasn't shown up. Cheers. ID: 1461746 ·

Batter Up Send message Joined: 5 May 99 Posts: 1946 Credit: 24,860,347 RAC: 0	Message 1461803 - Posted: 8 Jan 2014, 13:58:05 UTC Well here's another fine mess you've gotten me into. I use my machine for heat in an unheated room. It was 30Â°F (-1.11 Â°C), I assume the "C" stands for Canadian, yesterday morning with no GPU WUs. I bit the bullet and went with Einstein. They uploaded about four days worth of work but there code doesn't heat up the room; SETI used to get the GPUs up to 82Â°C with external cooling, Einstein only 59Â°C with no external cooling. ID: 1461803 ·

Josef W. Segur Volunteer developer Volunteer tester Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0	Message 1461910 - Posted: 8 Jan 2014, 20:03:43 UTC - in response to Message 1461727. ... Prior to the introduction of the PFB splitters, the old splitters were able to pump out 40 WU/s no problems at all. Now they struggle to put out much more than 25/s. Often they struggle to even produce 20/s. There are the odd bursts of 90/s+, but that's all they are- odd bursts. What is shown is result record creation. The splitters produce workunit files and records, it is the Transitioners which add the result records. Those odd bursts of high creation rate occur when the Transitioners got behind for some reason and are catching up. Joe ID: 1461910 ·

Grant (SSSF) Volunteer tester Send message Joined: 19 Aug 99 Posts: 13736 Credit: 208,696,464 RAC: 304	Message 1462055 - Posted: 9 Jan 2014, 7:10:04 UTC - in response to Message 1461910. ... Prior to the introduction of the PFB splitters, the old splitters were able to pump out 40 WU/s no problems at all. Now they struggle to put out much more than 25/s. Often they struggle to even produce 20/s. There are the odd bursts of 90/s+, but that's all they are- odd bursts. What is shown is result record creation. The splitters produce workunit files and records, it is the Transitioners which add the result records. Those odd bursts of high creation rate occur when the Transitioners got behind for some reason and are catching up. Joe So you're saying the problem isn't the splitters, but the transitioners, even though this issue has come about since the introduction of the PFB splitters? Grant Darwin NT ID: 1462055 ·

Robert M. Deller Send message Joined: 23 Apr 05 Posts: 407 Credit: 176,454,252 RAC: 0	Message 1462090 - Posted: 9 Jan 2014, 13:00:27 UTC - in response to Message 1461803. Well here's another fine mess you've gotten me into. I use my machine for heat in an unheated room. It was 30Â°F (-1.11 Â°C), I assume the "C" stands for Canadian, yesterday morning with no GPU WUs. I bit the bullet and went with Einstein. They uploaded about four days worth of work but there code doesn't heat up the room; SETI used to get the GPUs up to 82Â°C with external cooling, Einstein only 59Â°C with no external cooling. C=Celcius ID: 1462090 ·

Richard Haselgrove Volunteer tester Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874	Message 1462106 - Posted: 9 Jan 2014, 14:44:23 UTC - in response to Message 1462090. C=Celcius ID: 1462106 ·

Batter Up Send message Joined: 5 May 99 Posts: 1946 Credit: 24,860,347 RAC: 0	Message 1462116 - Posted: 9 Jan 2014, 15:42:45 UTC - in response to Message 1462090. C=Celcius Way back in the last century we called it centigrade. Anyway we all know that water freezes at 32 and boils at 212 degrees. Of course that is all academic when one is deep in a "polar vortex". Well Ernestine is now crashing my machine except for the GPU fans; they all spin at maximum until I cut power. So it is back to ET and my computer room is once again warm and toasty. ID: 1462116 ·

©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.