Message boards :
Number crunching :
Panic Mode On (34) Server Problems
Message board moderation
Previous · 1 . . . 6 · 7 · 8 · 9 · 10 · 11 · Next
Author | Message |
---|---|
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 66336 Credit: 55,293,173 RAC: 49 |
Oh no, starting to see weird connection notices and the boards are on and off...or my internet is going down.... I think It might be Your connection hiamps or at least somewhere between You and Seti@Home, Good Luck. Savoir-Faire is everywhere! The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST |
hiamps Send message Joined: 23 May 99 Posts: 4292 Credit: 72,971,319 RAC: 0 |
Oh no, starting to see weird connection notices and the boards are on and off...or my internet is going down.... Lets hope.... Official Abuser of Boinc Buttons... And no good credit hound! |
kittyman Send message Joined: 9 Jul 00 Posts: 51478 Credit: 1,018,363,574 RAC: 1,004 |
Ooops.... Just checked the cricket graph, and it looks like outbound traffic has gone away. "Time is simply the mechanism that keeps everything from happening all at once." |
Uli Send message Joined: 6 Feb 00 Posts: 10923 Credit: 5,996,015 RAC: 1 |
Mark go to bed Pluto will always be a planet to me. Seti Ambassador Not to late to order an Anni Shirt |
Terror Australis Send message Joined: 14 Feb 04 Posts: 1817 Credit: 262,693,308 RAC: 44 |
[stamp, pout] Not fair - they went down 20 hours early on the downloads and are now off altogether [/stamp, pout] :-) |
Miep Send message Joined: 23 Jul 99 Posts: 2412 Credit: 351,996 RAC: 0 |
No, they went down exactly at midnight Tuesday morning Berkeley time, if you look at the server graphs. That's not 20 hours early, that's right on schedule. If you look closely outbound went down just a tad before the dateline. Server status is frozen at 4:30 UTC. As of 10:30 UTC upload, report and validate was still working (for me). Looks rather like something in the download pipe went AWOL. In praxi doesn't make a difference - no downloads and unlikely to be fixed and turned on again before the outage. In any case it's only 8 hours early ;) Carola ------- I'm multilingual - I can misunderstand people in several languages! |
Terror Australis Send message Joined: 14 Feb 04 Posts: 1817 Credit: 262,693,308 RAC: 44 |
No, they went down exactly at midnight Tuesday morning Berkeley time, if you look at the server graphs. That's not 20 hours early, that's right on schedule. So you think someone's in there doing science at midnight. Now that's enthusiasm. Allowing time for a morning coffee, I would have thought somewhere between 8am and 9am Berkeley time would have been the start time. The 20 hours (ok 18 to be precise) is from the time downloads disappeared at around 1400 PST Monday till then. BTW I'm only being a smart alec, afterall this is a notified planned outage and I have WCG units on standby :-) |
Bill Walker Send message Joined: 4 Sep 99 Posts: 3868 Credit: 2,697,267 RAC: 0 |
So you think someone's in there doing science at midnight. Now that's enthusiasm. Maybe not someone, but something. Freed up CPU cycles could start on other things, like the big backlog waiting to assimilated, even without a human there. |
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
Two AP splitters were shut off early Monday, leaving just one. It has made the odds of picking up an AP three times more difficult. I'm definitely going to run out of my AP-only cache now. Would have been fine if the splitters stayed up all of Monday. [/semi-sarcasm] Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
At the time of the last server status page update there were 74709 "Results ready to send" and 4 mb_splitter processes running. The ready to send by itself would have sustained about 25Mb/s download until midnight, letting the splitter processes continue to the end of the channels they were working on wouldn't quite have provided enough additional tasks to give the near 50Mb/s which actually flowed. But with one ap_splitter running maybe there would have been enough. Still, I would estimate that if the rundown of ready to send was intentional they probably didn't inhibit starting on new channels until 10 or 10:30 pm PDT. If it was done that way, running out slightly before midnight makes sense because it wouldn't be possible to predict accurately in advance the total work requests which would come in. Although there is code in the mb_splitters which is intended to allow starting and stopping within a channel, when it was tried at SETI Beta the new splitter process often didn't get the right starting point and produced redundant WUs from an earlier part of the channel. Since then all mb_splitter runs at Beta have been full channels. The ap_splitters at Beta do produce partial channels, usually about 100 WUs at a time. Joe |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
Forewarned is forearmed, so I took a look at the Arecibo observing schedule for the "tapes" from the 3rd, 4th, and 5th of November 2009. (Those ready to be split as shown on Server status). The P2030 PALFA project was allocated a couple of 3 hour observing blocks, and produces mostly VLARs. But the A2010 project had a couple of 6 hour observing blocks, and produces midrange work exclusively (except possibly during setup or teardown at the ends of the blocks). The number of "tapes" isn't sufficient to cover as much time as was scheduled for those two projects. I can't really predict what we'll get, those schedules are made up several weeks before the observing time and don't necessarily show what was actually done. For instance, work I got from 03no09aa and 03no09ab was recorded late in that day during a period originally scheduled for x-band radar work. The 03no09ac through 03no09ae "tapes" may all be from the next day. Joe |
Roundel Send message Joined: 1 Feb 06 Posts: 21 Credit: 6,850,211 RAC: 0 |
So... I noticed on the front page that the weekly tuesday outage takes 3 days... was that a slip or have the outage times been extended quite a bit. I'm unable to upload.... and checking the servers, it seems that everything is disabled. Did I miss something? |
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 66336 Credit: 55,293,173 RAC: 49 |
So... I noticed on the front page that the weekly tuesday outage takes 3 days... was that a slip or have the outage times been extended quite a bit. It is No slip, This is the new norm(3 days), 3-4 hours(or so) was the old one, Now their analyzing signals, So they need uninterrupted access to the database, So there are No uploads or downloads from Tuesday to Thursday, On Friday upload and downloads should resume, At least the Forums are up most of the time. Savoir-Faire is everywhere! The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST |
hiamps Send message Joined: 23 May 99 Posts: 4292 Credit: 72,971,319 RAC: 0 |
So... I noticed on the front page that the weekly tuesday outage takes 3 days... was that a slip or have the outage times been extended quite a bit. It's all true, 3 day is the norm from now till ? Official Abuser of Boinc Buttons... And no good credit hound! |
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 66336 Credit: 55,293,173 RAC: 49 |
So... I noticed on the front page that the weekly tuesday outage takes 3 days... was that a slip or have the outage times been extended quite a bit. Until someone donates $100,000.00 to Seti@Home, Until then I suppose this will be normal here. Savoir-Faire is everywhere! The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST |
hiamps Send message Joined: 23 May 99 Posts: 4292 Credit: 72,971,319 RAC: 0 |
So... I noticed on the front page that the weekly tuesday outage takes 3 days... was that a slip or have the outage times been extended quite a bit. Out of that much it would be interesting to know how much would actually channel down thru Berkeley... Official Abuser of Boinc Buttons... And no good credit hound! |
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 66336 Credit: 55,293,173 RAC: 49 |
So... I noticed on the front page that the weekly tuesday outage takes 3 days... was that a slip or have the outage times been extended quite a bit. Yes It would indeed. Savoir-Faire is everywhere! The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
So... I noticed on the front page that the weekly tuesday outage takes 3 days... was that a slip or have the outage times been extended quite a bit. I have no reason to doubt the FAQ on the Donate to SETI@home page: Q: How much of my donation actually goes to you? I'm really glad they have electricity to run those servers, any of you California residents care to estimate the monthly cost? Space for the servers and someplace for the staff to sit is nice too. Joe |
FiveHamlet Send message Joined: 5 Oct 99 Posts: 783 Credit: 32,638,578 RAC: 0 |
Rig on a Bench has no work left and has earned a rest. Maybe this room will be cooler for a while. Dave |
Roundel Send message Joined: 1 Feb 06 Posts: 21 Credit: 6,850,211 RAC: 0 |
I hate to complain... I don't like complainers... But I see this as a major issue. It would seem that there maybe alot of trouble actually getting uploads and downloads during the times the servers are available... almost like what happens after an extended outage, the servers are bombarded and it takes alot of time for things to calm down. It would seem now that every weekend is now a race to get as much resources exchanged as possible... |
©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.