Panic Mode On (81) Server Problems? |
![]() |
| log in |
Message boards : Number crunching : Panic Mode On (81) Server Problems?
Previous · 1 . . . 3 · 4 · 5 · 6 · 7 · 8 · 9 . . . 21 · Next
| Author | Message |
|---|---|
They don't normally swap tapes until they have been split for both MB & AP, so we could have some wait given the current rate of (not) splitting the APs :-( The question is, that is doing automaticaly (wait of few hours) or manualy (wait almost a day)? ____________ | |
| ID: 1334416 · | |
They don't normally swap tapes until they have been split for both MB & AP, so we could have some wait given the current rate of (not) splitting the APs :-( If some are still in the pipe automatically. If not .......... ____________ | |
| ID: 1334423 · | |
|
My faster rigs are already running out of GPU tasks. The slower ones will hang in there for some hours yet. | |
| ID: 1334424 · | |
|
Im running on SETI drayland too, 100WU on a 2x690 host takes less than 2hr to finish. I realy hate the 100WU limit, they need to change it soon at least to 100WU per GPU. | |
| ID: 1334429 · | |
|
Before doing that they need to sort the ability to deliver the >100 work units per hour that many of the more modern crunchers manage. | |
| ID: 1334432 · | |
Before doing that they need to sort the ability to deliver the >100 work units per hour that many of the more modern crunchers manage. Well, I do find it rather frustrating when I can't cache enough work to ride out anything much more than a few hours of server problems on my better crunchers. ____________ ****** "Ask not, what your kitty can do for you. Ask what you can do for your kitty." As it is kitten, so shall it be done. | |
| ID: 1334433 · | |
Actually I just received 3 GPU work units. Someone must be working on it at the lab. Results ready to send now shows as 1. Here's the name of one of the work units. The others had similar long names. No x_0 or x_1 or x_2 or x_3. 28no12ad.22646.124880.140733193388038.10.113 ____________ | |
| ID: 1334454 · | |
Actually I just received 3 GPU work units. Someone must be working on it at the lab. Results ready to send now shows as 1. That's the Workunit name, what about the task name? There are Multiple tasks to a workunit, from 2 to 10. Claggy | |
| ID: 1334458 · | |
Actually I just received 3 GPU work units. Someone must be working on it at the lab. Results ready to send now shows as 1. OK, this should be what you're looking for. 1140189392 ____________ | |
| ID: 1334460 · | |
I'm going to guess that this is your computer. http://setiathome.berkeley.edu/show_host_detail.php?hostid=6896017 ____________ | |
| ID: 1334483 · | |
Yep. I'm still in the process of putting this cruncher together and need more parts. It's running with the mobo sitting on a wooden table and fans blowing on it. ____________ | |
| ID: 1334484 · | |
|
Well I did just notice that with 5 AP splitters running and no new MB work being produced.. cricket shows that we are not at max capacity. | |
| ID: 1334545 · | |
If we could get our pipe to be increased to 150mbit (since my understanding is that it is connected via a gigabit connection, but we're only allowed to use 100mbit of it), that should pretty much "fix" the throughput problem. It'd be good to push for a minimum of 250Mb/s. No more traffic jams after outages, and it would give room for growth. Be a bit of a pain to finally get an extra 50Mb/s, only to have to argue for it all over again in a matter of months. ____________ Grant Darwin NT. | |
| ID: 1334556 · | |
|
Don“t forget the limits, MB uses 70% of the avaiable BW with them, or more without. | |
| ID: 1334560 · | |
|
I have been crunching for a few years now without ever actually bothering about how long it takes for the discs to be recorded and how/when it gets transported from Arecibo to Berkeley. | |
| ID: 1334590 · | |
|
Work is being split again, unfortunately most Scheduler requests result in "Couldn't connect to server" messages. | |
| ID: 1334649 · | |
Work is being split again, unfortunately most Scheduler requests result in "Couldn't connect to server" messages. Not ALL requests... Very hard to get through right now, but the kitties have managed on a few rigs, and have started to get just a bit of GPU work here and there. But, yes, the scheduler is tied pretty tight right now. ____________ ****** "Ask not, what your kitty can do for you. Ask what you can do for your kitty." As it is kitten, so shall it be done. | |
| ID: 1334655 · | |
Work is being split again, unfortunately most Scheduler requests result in "Couldn't connect to server" messages. Must be the distance thing again then. 45min & not a single request has gotten through on either of my systems. ____________ Grant Darwin NT. | |
| ID: 1334658 · | |
Work is being split again, unfortunately most Scheduler requests result in "Couldn't connect to server" messages. Well, I have 9 rigs making the attempt, so I would have a few more chances to connect. I tried the update button on a couple of them, but it's pretty useless to do so. Just have to let the kitties keep trying whilst I am gone to work and count on random chance to have some work get through. ____________ ****** "Ask not, what your kitty can do for you. Ask what you can do for your kitty." As it is kitten, so shall it be done. | |
| ID: 1334659 · | |
|
Hmm... so they dumped once again lots of unsplited AP. Is AP not worth crunching or how shall we understand that? | |
| ID: 1334663 · | |
Message boards : Number crunching : Panic Mode On (81) Server Problems?
| Copyright © 2013 University of California |