Message boards :
Number crunching :
Panic Mode On (79) Server Problems?
Message board moderation
Previous · 1 . . . 14 · 15 · 16 · 17 · 18 · 19 · 20 . . . 22 · Next
Author | Message |
---|---|
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 65842 Credit: 55,293,173 RAC: 49 |
I've gone back to x41zb as a test as the previous post was ll under x41zc, why did that happen? I don't know. The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's |
Team kizb Send message Joined: 8 Mar 01 Posts: 219 Credit: 3,709,162 RAC: 0 |
|
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 65842 Credit: 55,293,173 RAC: 49 |
|
Claggy Send message Joined: 5 Jul 99 Posts: 4654 Credit: 47,537,079 RAC: 4 |
Well from 12:07am on My PC was told, sorry You have plenty to work on, so You get no more, yet there was nothing to crunch here... Sounds like a VLAR storm, or just AP Wu's going out, but you were also sat on your 100 task limit, Claggy |
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 65842 Credit: 55,293,173 RAC: 49 |
Well from 12:07am on My PC was told, sorry You have plenty to work on, so You get no more, yet there was nothing to crunch here... Well as long as the PC is able to report, the limit isn't per day I'd hope. The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13765 Credit: 208,696,464 RAC: 304 |
Network traffic is looking rather odd over the last few hours. Grant Darwin NT |
kittyman Send message Joined: 9 Jul 00 Posts: 51469 Credit: 1,018,363,574 RAC: 1,004 |
That's because most hosts have all the MB tasks that the current cache limits will allow. And I wonder what's gonna happen when the MB splitting stops. The server status page stopped updating almost 3 hours ago, but at that time there were only 3 channels of MB data left splitting. And 37 channels of AP data that have not even started to split yet. I suspect there might be a lotta tears and empty GPUs if they split nothing but AP for days to clear that data out. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14656 Credit: 200,643,578 RAC: 874 |
Network traffic is looking rather odd over the last few hours. Yes, we do seem to lurch from one extreme to the other. I'm one of the people who suggested cutting down the number of AP splitters, so that the AP side didn't consistently finish a long way ahead. But cutting down to just two splitters (on an old, slow, server at that) is a bigger correction than was needed. |
Cliff Harding Send message Joined: 18 Aug 99 Posts: 1432 Credit: 110,967,840 RAC: 67 |
According to the server status page Lando has been disabled for several days, must still be having a problem with it even though Matt said it was rebuilt from spares. 2 MB splitters & 2 AP are down and out until fixed. I don't buy computers, I build them!! |
kittyman Send message Joined: 9 Jul 00 Posts: 51469 Credit: 1,018,363,574 RAC: 1,004 |
Network traffic is looking rather odd over the last few hours. Yup.... And I wouldn't give it a second thought except that now of course I can't cache enough work to ride it out due to the dang limit solution to band-aid past whatever the true problems are. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Khangollo Send message Joined: 1 Aug 00 Posts: 245 Credit: 36,410,524 RAC: 0 |
|
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 65842 Credit: 55,293,173 RAC: 49 |
So this is how S@H would work without AP and 10-day cachers. Yep, Lurching along... The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13765 Credit: 208,696,464 RAC: 304 |
So this is how S@H would work without AP and 10-day cachers. Smooth? I suggest you look at the netwrok traffic. Also what was the outage we had just the other day? The splitters (for some reason) are still struggling to produce work & the assimilators appear to now be working, sometimes, at an increadibly slow pace. Limiting tasks hasn't fixed anything- the problems are still there. It just makes them less noticable. Grant Darwin NT |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13765 Credit: 208,696,464 RAC: 304 |
The limits would have been hit several times since they were introduced, but this is the first time i've seen those data spikes in the outbound traffic & the ripples in the inbound. Grant Darwin NT |
tbret Send message Joined: 28 May 99 Posts: 3380 Credit: 296,162,071 RAC: 40 |
Your typo made me think of the "regular Tuesday outrage." Maybe we should rename this "netwrek traffic." |
David S Send message Joined: 4 Oct 99 Posts: 18352 Credit: 27,761,924 RAC: 12 |
I just had to restart my i7's Boinc Manager because it said it couldn't connect to the internet. Once I did, it flushed out huge numbers of uploads for both Seti and Einstein. Then it downloaded a huge number of new tasks for Einstein. When it asks Seti, it gets "no tasks are available for SETI@home v7." Well, what about any other Seti project? Right now I have four (yes, 4) Seti units for CPU and none (0) for GPU. At least they're on board; no ghosts. I believe I have all Seti projects enabled for all processors (aside: I just set up new venue rules for GPU only, but there is only one computer in that venue and it's not this one). Yes, I believe the work request was for both CPU and GPU. I can't really tell whether it's the kitty or the tail that's getting wagged. Is it getting lots of Einstein because it can't get Seti, or is it asking for limited amounts of Seti because it has so much Einstein? It's done so much Einstein lately, there should be a huge debt to Seti. This machine's Seti tasks in progress are always 104. It reports some, it downloads more, it always has 104. When I check the manager, that breaks down to 100 GPU and 4 CPU, but whenever I look it's always running Einstein. [edit] P.S. Now that this thread has gone to a 5th page, I can see it at work again. Whatever our security or nanny filter was barfing on must have been specific to that page. Probably an image's filename or host server. David Sitting on my butt while others boldly go, Waiting for a message from a small furry creature from Alpha Centauri. |
Gary Charpentier Send message Joined: 25 Dec 00 Posts: 30734 Credit: 53,134,872 RAC: 32 |
I can't really tell whether it's the kitty or the tail that's getting wagged. Is it getting lots of Einstein because it can't get Seti, or is it asking for limited amounts of Seti because it has so much Einstein? It's done so much Einstein lately, there should be a huge debt to Seti. To see the debt go to the projects tab and select a project. Click on the properties button. Might need to scroll the box down. <ed> on 6.x Both the work fetch and CPU priority numbers are displayed. On 7.x a single priority number is displayed. IIRC they run from zero to negative infinity. |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
If they were to do that it would be interesting to see how long it would take to split all AP tapes |
kittyman Send message Joined: 9 Jul 00 Posts: 51469 Credit: 1,018,363,574 RAC: 1,004 |
It would appear that they took the unsplit AP datasets out of the splitter queue and loaded a bunch of new ones. Because when I look now, after getting home from work, there is once again much MB work to split, and very little AP being split. They must be setting aside the AP work for a time when better server solutions are in place. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
It looks that way yes. See what happens after this weeks outage |
©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.