Message boards :
Number crunching :
Panic Mode On (104) Server Problems?
Message board moderation
Previous · 1 . . . 8 · 9 · 10 · 11 · 12 · 13 · 14 . . . 42 · Next
Author | Message |
---|---|
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
The kitties are wondering if the GPUs are gonna run outta work if today's outrage is another 8 hour saga. At a guess I would say it is just the tapes that they loaded to process not expecting to not be splitting GBT data. I like the idea of shorter runtimes because to me it feels as more work is getting done. I am reasonably confident that people will have different opinions on that sentence. In no way am I wanting to start a debate Did your GPUs manage to hold their own? |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
The kitties are wondering if the GPUs are gonna run outta work if today's outrage is another 8 hour saga. . . 8 hours? I wish! It was at least 10 hours by my reckoning. But worse still, while I was expecting a flood of guppies, even worse has occured ... a flood of "Project has no tasks!" .... . . AAARRRGGG! . . The Baby ran out of work nearly 6 hours before the system came back up, and now, still no work :( Stephen :( |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13854 Credit: 208,696,464 RAC: 304 |
Out of GPU work, and still unable to get any. And I notice Centurion is still down. EDIT- should have posted this sooner. 3 seconds after posting, I got some work. Hopefully it will be enough to not run out before the next batch becomes available. EDIT- not looking good, the first 3 WUs were noisy. And probably half the WUs downloaded are all shorties. Grant Darwin NT |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Out of GPU work, and still unable to get any. . . Hi Grant, . . Like you, within a short time of posting that there were no new tasks I got about 20 or so on The Baby, but still a long way short of a full cache of 200. Hopefully there will be more before that little bit runs out. . . Also like you I was expecting a flood of Guppies with Centurion restored during the outage but it must have a serious problem :( Still only Arecibo tasks when you can get them. Stephen . |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1856 Credit: 268,616,081 RAC: 1,349 |
My fault! My caches are now full (lol). Must have been a long outage today, my "heavy hitter" actually ran out of CPU work today, and that almost never happens ... |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Quit stealing all my work !! ;-^ } I have been only to get a single task per machine every hour or so since the project came back. I'm still running backup projects because of a lack of SETI work. These latest outages take a full day to build up my normal 200 task cache per machine. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13854 Credit: 208,696,464 RAC: 304 |
I've just about got a full cache again. Luckily I got hit with a whole slab of Guppie resends, so that will help keep the system busy between eventual successful requests for work. Grant Darwin NT |
marsinph Send message Joined: 7 Apr 01 Posts: 172 Credit: 23,823,824 RAC: 0 |
Only one task received since Seti came back !!! It will say about 6 hours ago. No work available !? But on server status the creation rate is about 37WU/sec !?!? Who can explain ? |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1856 Credit: 268,616,081 RAC: 1,349 |
Quit stealing all my work !! ;-^ } I have been only to get a single task per machine every hour or so since the project came back. I'm still running backup projects because of a lack of SETI work. These latest outages take a full day to build up my normal 200 task cache per machine. SETI loves me This I know Cause my caches tell me so lol Interesting twist here is that since it's all Aricebo stuff coming out, and mostly not VLARs right now, every time GR runs it slams all the jobs over to the GPU and the CPUs get empty and have to ask for more work. Terrible thing! |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1856 Credit: 268,616,081 RAC: 1,349 |
Only one task received since Seti came back !!! Market economics aka demand vs. supply We're all slamming the scheduler asking for work, and it's getting handed out as fast as it's created. Won't see a surplus until all the caches get filled up on folks machines. edit For a bit more background, the BL splitter server died, so no BLC stuff from Greenbank until they get it fixed. Basically, 50-75% reduction in capacity to generate work right now coupled with demand from weekly maintenance equals very slow to get caught up. |
kittyman Send message Joined: 9 Jul 00 Posts: 51478 Credit: 1,018,363,574 RAC: 1,004 |
The kitties are wondering if the GPUs are gonna run outta work if today's outrage is another 8 hour saga. Dunno if they ran out or not, as I was gone to work. I am assuming they did at some point, but my RAC still went up, so it may not have been too bad. Caches not full at present, but all rigs appear to have work. With the extended outage and the splitter output all short Aerecibo tasks, it will take some time for things to catch up, for sure. "Time is simply the mechanism that keeps everything from happening all at once." |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
Don't see this often, 4 inconclusives http://setiathome.berkeley.edu/result.php?resultid=5423396047 Lets see if I can make it 5 :) EDIT: One more http://setiathome.berkeley.edu/workunit.php?wuid=2331080925 |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
I've just about got a full cache again. . . I never thought I would hear these words leave my fingers under such circumstances but ... lucky you! :) Stephen . |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
Is it my imagination or are pages loading very slowly? I am in New Zealand |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Well, this has been interesting. My Windows 10 machine has a full cache of work. My Windows 7 machines have zero GPU work. Looks like the outrage is going to cause at least a 3-4 day lack of GPU work for my fast machines. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Dr Grey Send message Joined: 27 May 99 Posts: 154 Credit: 104,147,344 RAC: 21 |
Well, this has been interesting. My Windows 10 machine has a full cache of work. My Windows 7 machines have zero GPU work. Looks like the outrage is going to cause at least a 3-4 day lack of GPU work for my fast machines. Current result creation rate: 30.4548/sec Results received in last hour: 110,406. 110,406 / 3600 = 30.668 / sec So it looks like the splitters can't keep up. |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13854 Credit: 208,696,464 RAC: 304 |
So it looks like the splitters can't keep up. It's been a long standing issue with the PFB splitters; several of them end up on the one file, and that slows the splitting down significantly. Grant Darwin NT |
rob smith Send message Joined: 7 Mar 03 Posts: 22526 Credit: 416,307,556 RAC: 380 |
The splitting rate shown is an instantaneous figure, compared to the long (hour?) sample used to generate the return rate. As I type the splitting rate is over 35/sec, so should be "more than capable" of keeping up with the demand (based on the results returned), which is just over 31/sec. Bob Smith Member of Seti PIPPS (Pluto is a Planet Protest Society) Somewhere in the (un)known Universe? |
Dr Grey Send message Joined: 27 May 99 Posts: 154 Credit: 104,147,344 RAC: 21 |
The splitting rate shown is an instantaneous figure, compared to the long (hour?) sample used to generate the return rate. As I type the splitting rate is over 35/sec, so should be "more than capable" of keeping up with the demand (based on the results returned), which is just over 31/sec. So generating a surplus of 4/sec which is enough to fill a 100 wu cache every 25 seconds. That's fast. But with 162,000 active hosts, it will take a while to get ahead of the pack. |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13854 Credit: 208,696,464 RAC: 304 |
So generating a surplus of 4/sec which is enough to fill a 100 wu cache every 25 seconds. That's fast. But with 162,000 active hosts, it will take a while to get ahead of the pack. As long as it continues to produce work at that rate. Sometimes it's faster, but at other times (like the most recent update) it's slower. Only 26/sec. Nowhere near faster enough. Grant Darwin NT |
©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.