Message boards :
Number crunching :
New outage schedule....
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 9 · Next
Author | Message |
---|---|
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 66334 Credit: 55,293,173 RAC: 49 |
There will be forums and stats during the outage days. Basically just no uploads/downloads. That's the plan now, at any rate, and subject to change (the goal is to keep the web site as active/interesting as possible during any extended outages). Yeah, We were just tossed a rare and juicy tidbit there, nice. Savoir-Faire is everywhere! The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST |
soft^spirit Send message Joined: 18 May 99 Posts: 6497 Credit: 34,134,168 RAC: 0 |
There will be forums and stats during the outage days. Basically just no uploads/downloads. That's the plan now, at any rate, and subject to change (the goal is to keep the web site as active/interesting as possible during any extended outages). The board gets a bit TOO "active/interesting" when the outages are surprises one after another. I still say a planned 3 day beats a surprise 2 day any time. Janice |
Byron Leigh Hatch @ team Carl Sagan Send message Joined: 5 Jul 99 Posts: 4548 Credit: 35,667,570 RAC: 4 |
There will be forums and stats during the outage days. Basically just no uploads/downloads. That's the plan now, at any rate, and subject to change (the goal is to keep the web site as active/interesting as possible during any extended outages). thank you Matt, for that info :-) |
Scarecrow Send message Joined: 15 Jul 00 Posts: 4520 Credit: 486,601 RAC: 0 |
Goodbye, cruel World. There will be forums and stats during the outage days. Whew.... Standing down. |
TheFreshPrince a.k.a. BlueTooth76 Send message Joined: 4 Jun 99 Posts: 210 Credit: 10,315,944 RAC: 0 |
How is the upload-server going to survive when we return millions of WU's at once, next thursday? And what about my "Crunchy" who's "quotum of 218" is increasing without getting any work? I'll have 0 WU's left tonight and there's nothing coming for 3 days... Here, this is what it looks like for 2 days now: 28-6-2010 22:18:12 SETI@home Scheduler request completed: got 0 new tasks 28-6-2010 22:18:12 SETI@home Message from server: No work sent 28-6-2010 22:18:12 SETI@home Message from server: Your app_info.xml file doesn't have a usable version of SETI@home Enhanced. 28-6-2010 22:18:12 SETI@home Message from server: This computer has finished a daily quota of 218 tasks) 28-6-2010 22:19:27 SETI@home Sending scheduler request: To fetch work. 28-6-2010 22:19:27 SETI@home Requesting new tasks for GPU 28-6-2010 22:19:29 SETI@home Scheduler request completed: got 0 new tasks 28-6-2010 22:19:29 SETI@home Message from server: No work sent 28-6-2010 22:19:29 SETI@home Message from server: Your app_info.xml file doesn't have a usable version of SETI@home Enhanced. 28-6-2010 22:19:29 SETI@home Message from server: This computer has finished a daily quota of 218 tasks) 28-6-2010 22:20:44 SETI@home Sending scheduler request: To fetch work. 28-6-2010 22:20:44 SETI@home Requesting new tasks for CPU 28-6-2010 22:20:46 SETI@home Scheduler request completed: got 0 new tasks 28-6-2010 22:20:46 SETI@home Message from server: Project has no tasks available 28-6-2010 22:22:01 SETI@home Sending scheduler request: To fetch work. 28-6-2010 22:22:01 SETI@home Requesting new tasks for GPU 28-6-2010 22:22:04 SETI@home Scheduler request completed: got 0 new tasks 28-6-2010 22:22:04 SETI@home Message from server: Project has no tasks available This really <explicit word>... This is going on for weeks now... Can't we just fix this before doing a "3 day scheduled outage"??? Rig name: "x6Crunchy" OS: Win 7 x64 MB: Asus M4N98TD EVO CPU: AMD X6 1055T 2.8(1,2v) GPU: 2x Asus GTX560ti Member of: Dutch Power Cows |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14679 Credit: 200,643,578 RAC: 874 |
I wonder if it's strictly necessary to disable the upload server? After all, it normally ran during the previous Tuesday-only outages, and the uploading process itself doesn't impinge on the database servers which will be taking the internal hit during the scientific activity mid-week. It's possible that they are worried about internal bandwidth, but it seems unlikely that 20Mb max would be noticeable on an exclusively gigabit internal network. Perhaps - and I'm speculating here, not trying to put words into Matt's mouth when he actually said something different - that he was referring to work allocation and reporting, rather than downloading and uploading. We'll just have to wait and see what happens on the day. |
kittyman Send message Joined: 9 Jul 00 Posts: 51478 Credit: 1,018,363,574 RAC: 1,004 |
I wonder if it's strictly necessary to disable the upload server? After all, it normally ran during the previous Tuesday-only outages, and the uploading process itself doesn't impinge on the database servers which will be taking the internal hit during the scientific activity mid-week. It's possible that they are worried about internal bandwidth, but it seems unlikely that 20Mb max would be noticeable on an exclusively gigabit internal network. That would make a lot of sense, Richard....and save a lotta bandwidth and 'no connect' errors when everybody is trying to report work after a 3 day outage. "Time is simply the mechanism that keeps everything from happening all at once." |
Gary Charpentier Send message Joined: 25 Dec 00 Posts: 31006 Credit: 53,134,872 RAC: 32 |
I wonder if it's strictly necessary to disable the upload server? After all, it normally ran during the previous Tuesday-only outages, and the uploading process itself doesn't impinge on the database servers which will be taking the internal hit during the scientific activity mid-week. It's possible that they are worried about internal bandwidth, but it seems unlikely that 20Mb max would be noticeable on an exclusively gigabit internal network. I can see it now. Server comes back and everyone hits the update button at once. Server goes down for the rest of the week ... |
zoom3+1=4 Send message Joined: 30 Nov 03 Posts: 66334 Credit: 55,293,173 RAC: 49 |
I wonder if it's strictly necessary to disable the upload server? After all, it normally ran during the previous Tuesday-only outages, and the uploading process itself doesn't impinge on the database servers which will be taking the internal hit during the scientific activity mid-week. It's possible that they are worried about internal bandwidth, but it seems unlikely that 20Mb max would be noticeable on an exclusively gigabit internal network. Yeah, I can see It now, Someone call Doctor Freud, The Server has had a metal breakdown after being offline for 3 days. :D But We'll have to wait and see. Savoir-Faire is everywhere! The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST |
JohnDK Send message Joined: 28 May 00 Posts: 1222 Credit: 451,243,443 RAC: 1,127 |
Is it old habit they have the normal Tuesday morning 3-4 hour outage on the front page? |
Qui-Gon Send message Joined: 15 May 99 Posts: 2940 Credit: 19,199,902 RAC: 11 |
I'm all out of work and the servers are SNAFU, so it looks like no work until at least Friday. |
kittyman Send message Joined: 9 Jul 00 Posts: 51478 Credit: 1,018,363,574 RAC: 1,004 |
I think I have enough on most rigs to keep up to speed until the first of the extended outages is over. I can only hope that when the system comes back online things have been untangled enough that the servers can handle the load without crashing right away. And that the Boinc changes have been corrected so the quota works without dropping like a stone any time a simple Cuda WU error occurs. And the DCF thingy doesn't keep whacking one or two of my rigs into thinking a 10 minute Cuda job is gonna take 2 days.......LOL. "Time is simply the mechanism that keeps everything from happening all at once." |
SciManStev Send message Joined: 20 Jun 99 Posts: 6658 Credit: 121,090,076 RAC: 0 |
The other day I was just watching BOINC as it changed the completion times, jumped be high priority and normal, and abandoned wu's that were 99% complete to start a new one. It would do all of this is just a few minutes. Quite comical actually, but I have a feeling a cache is not as big as the number of days says it is. The last time I looked, it had my cuda tasks completing in 45 minutes, rather than the 7 to 10 it actually takes. Times would bounce up and down with me just looking at it. Steve Warning, addicted to SETI crunching! Crunching as a member of GPU Users Group. GPUUG Website |
hiamps Send message Joined: 23 May 99 Posts: 4292 Credit: 72,971,319 RAC: 0 |
I hope I have enough but doubt it. The estimated completion times kept me in High Priority mode most of the time limiting downloads. Changed DCF but it would change back when I downloaded so some CPU units showed they could finish in 1:25 while others showed 56:35:24.... 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 |
The other day I was just watching BOINC as it changed the completion times, jumped be high priority and normal, and abandoned wu's that were 99% complete to start a new one. It would do all of this is just a few minutes. Quite comical actually, but I have a feeling a cache is not as big as the number of days says it is. The last time I looked, it had my cuda tasks completing in 45 minutes, rather than the 7 to 10 it actually takes. Times would bounce up and down with me just looking at it. That's probably the DCF adjustment thingy I was referring to....which was put into place and then retracted when it was found out how whacko it was. It would be nice if that was worked out during the outage. But we probably won't know until it suddenly appears again and Richard or Joe can comment on how it is working out. "Time is simply the mechanism that keeps everything from happening all at once." |
Bill G Send message Joined: 1 Jun 01 Posts: 1282 Credit: 187,688,550 RAC: 182 |
I have no SETI WUs to run. I do not know what is happening to me but on a quad processor I get 2 SETI running, along with Rosetta, and no more SETI WUs will download. This is not a new thing. When one of the WUs finishes another will be requested and will download. Which means I will shortly be out of SETI WU to run during the outage. I do nothing to BOINC, just let it run as in the past it always seemed to run. My daily numbers, and that is not just SETI, but totals have been falling for a month now. I can not figure it out as nothing else has changed. SETI@home classic workunits 4,019 SETI@home classic CPU time 34,348 hours |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
For all of us running anonymous platform it will have a similar up-front effect as last time it was turned on, getting much more work than requested. After that, it will take at least a day or two on fast hosts to know if they have the averaging working OK. My 200MHz Pentium MMX won't stabilize before late August at best. I agree it would be nice if they can get it worked out during the outage, then most hosts will have recovered before the next week's outage. And if it does a good enough job of fitting estimates to the host app version then it will turn out to have been one of the most helpful BOINC changes in recent times. Joe |
kittyman Send message Joined: 9 Jul 00 Posts: 51478 Credit: 1,018,363,574 RAC: 1,004 |
Joe.... I'm afraid it did not have that effect for me the last time around, because the silly-ass new quota system kept quashing my work requests..... That must be fixed as well.....it is not right to cut the quota back to 100 on a high performing rig just because of a Cuda error here and there. The number of errors has to be reconciled with the amount of valid work returned. 5 errors on a host returning several hundred valid results a day should not be cut back that far, if at all. 5 errors on a host that does 10 WUs a month might mean something different. And the system needs to be able to differentiate between the two situations. "Time is simply the mechanism that keeps everything from happening all at once." |
Qui-Gon Send message Joined: 15 May 99 Posts: 2940 Credit: 19,199,902 RAC: 11 |
What? No outage this week? It's past 11:00 am in California and everything is still running. The front page messages are just confusing. |
Qui-Gon Send message Joined: 15 May 99 Posts: 2940 Credit: 19,199,902 RAC: 11 |
I haven't tried uploading, because I have nothing to upload, but the status page shows everything running and over 100,000 work units ready to send out. Also, here we are posting in NC, which we could never do during prior outages. |
©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.