Message boards :
Number crunching :
Panic Mode On (103) Server Problems?
Message board moderation
Previous · 1 . . . 17 · 18 · 19 · 20 · 21 · 22 · 23 . . . 34 · Next
Author | Message |
---|---|
betreger Send message Joined: 29 Jun 99 Posts: 11366 Credit: 29,581,041 RAC: 66 |
Caches pretty much back to full now. Amazing how much WU demand has grown, if my perception is correct. Right, the splitters churning out 55+/sec is not enough to keep up with demand. That's huge ... That Einstein does not have any GPU data could very well explain it. |
Al Send message Joined: 3 Apr 99 Posts: 1682 Credit: 477,343,364 RAC: 482 |
Some people's caches are huge... My GPU caches are huge, the project could probably be down for close to a day before those run dry. But on my bigger crunchers, the first of the CPU cores seem to run out of work about an hour or two before the average outage completes, and progressively more and more of them idle out, until they are all just loafing around. Whatta bunch of lazy so and so's! ;-) |
Jeff Buck Send message Joined: 11 Feb 00 Posts: 1441 Credit: 148,764,870 RAC: 0 |
Seems like you could use a rescheduler option that would move GPU tasks to your CPUs on an as needed basis when the CPUs run out. Something like that could perhaps keep them all busy through the outage. |
Al Send message Joined: 3 Apr 99 Posts: 1682 Credit: 477,343,364 RAC: 482 |
I am using I believe the latest version of the rescheduler, running every 30 minutes, is this the one that you are referring to? Also, was it just me or was the website just down? |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1855 Credit: 268,616,081 RAC: 1,349 |
I am using I believe the latest version of the rescheduler, running every 30 minutes, is this the one that you are referring to? Also, was it just me or was the website just down? Yeah, web site has been struggling. The rescheduler we have doesn't address a lot of options we would all like to see, I think. This is one of them. No knock on anyone who's written such is intended! If you want to go into more depth, let's move this to the Rescheduling queue ... |
Jeff Buck Send message Joined: 11 Feb 00 Posts: 1441 Credit: 148,764,870 RAC: 0 |
I am using I believe the latest version of the rescheduler, running every 30 minutes, is this the one that you are referring to? Sorry, I was just mentioning that such an option would be one you could use, if it existed. I'm guessing that efMer's old Rescheduler, which has been mentioned several times recently in other threads, had such capability, but I've never tried using it myself. Also, was it just me or was the website just down? I think it's been up and down a couple times today. Besides that, the Replica DB is currently (a/o 6 Oct 2016, 2:00:05 UTC) 85,743 seconds behind the Master, which does not bode well for the task detail pages. It does appear to be catching up, though. |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1855 Credit: 268,616,081 RAC: 1,349 |
Looks like the Replica is down again ... |
Jeff Buck Send message Joined: 11 Feb 00 Posts: 1441 Credit: 148,764,870 RAC: 0 |
Looks like the Replica is down again ... Well, if we're lucky, perhaps it finally got caught up and now they're backing it up. Probably just wishful thinking, though. |
WezH Send message Joined: 19 Aug 99 Posts: 576 Credit: 67,033,957 RAC: 95 |
Looks like the Replica is down again ... Nope, it did not. I was about 40.000 sec behind master, then went offline... |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
Looks like the Replica is down again ... I saw 53,000 sec behind master then it went offline.... And its still offline, maybe they will switch the web to the master, one would hope..... |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
come on replica! Breathe! (Need data for some code polishing :D) "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Jeff Buck Send message Joined: 11 Feb 00 Posts: 1441 Credit: 148,764,870 RAC: 0 |
come on replica! Breathe! (Need data for some code polishing :D) Would be nice if someone in Berkeley at least let us know if they're working on it and/or what the issue might be. Then again, communicating useful information to the great unwashed masses is not their strong suit. |
betreger Send message Joined: 29 Jun 99 Posts: 11366 Credit: 29,581,041 RAC: 66 |
come on replica! Breathe! (Need data for some code polishing :D) With Eric ill plus the longstanding manpower shortage it is quite understandable. I really, really miss the replica. |
Dimly Lit Lightbulb 😀 Send message Joined: 30 Aug 08 Posts: 15399 Credit: 7,423,413 RAC: 1 |
come on replica! Breathe! (Need data for some code polishing :D) I have a shower every time it rains. Member of the People Encouraging Niceness In Society club. |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1855 Credit: 268,616,081 RAC: 1,349 |
Starting to be a problem with more than stats. I have a box I changed venues on from "AP only" to "all tasks" almost 24 hours ago, still have not been able to get that change to stick. Web acknowledges the change, says its happened, but next web query doesn't reflect it. So, no new work and machine is now empty. |
Kevin Olley Send message Joined: 3 Aug 99 Posts: 906 Credit: 261,085,289 RAC: 572 |
Starting to be a problem with more than stats. I have a box I changed venues on from "AP only" to "all tasks" almost 24 hours ago, still have not been able to get that change to stick. Web acknowledges the change, says its happened, but next web query doesn't reflect it. So, no new work and machine is now empty. Edit preferences is still working but it will effect all computers that use that location. Kevin |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1855 Credit: 268,616,081 RAC: 1,349 |
Starting to be a problem with more than stats. I have a box I changed venues on from "AP only" to "all tasks" almost 24 hours ago, still have not been able to get that change to stick. Web acknowledges the change, says its happened, but next web query doesn't reflect it. So, no new work and machine is now empty. Turns out it was a client problem not related to the servers. Something was stuck, but a reboot solved it. Sorry for the mis-info ... |
Kieron Walsh Send message Joined: 2 Mar 00 Posts: 74 Credit: 43,502,325 RAC: 112 |
come on replica! Breathe! (Need data for some code polishing :D) Is Eric the only one who can add a message? Has nobody had even 30 seconds during the last several days to at least acknowledge the issue? Maybe they've found ET, decided they're not helpful, job done, shut down commenced, all gone home! For a project so reliant on 'us' it sometimes appears that we are not deemed very important. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
come on replica! Breathe! (Need data for some code polishing :D) Unfortunately its more about funding, and at the moment Eric is ill |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
come on replica! Breathe! (Need data for some code polishing :D) . . I hope he is not terribly ill and I wish him a speedy recovery. . . Then when he is better we can hassle him about our concerns :) Stephen . { not that that will offer much incentive to get better :) } . |
©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.