Panic Mode On (89) Server Problems?


log in

Advanced search

Message boards : Number crunching : Panic Mode On (89) Server Problems?

1 · 2 · 3 · 4 . . . 24 · Next
Author Message
Profile arkaynProject Donor
Volunteer tester
Avatar
Send message
Joined: 14 May 99
Posts: 4087
Credit: 51,542,028
RAC: 1,774
United States
Message 1556228 - Posted: 13 Aug 2014, 16:39:43 UTC

Them stuck tapes are getting old!!
____________

Darth Beaver
Avatar
Send message
Joined: 20 Aug 99
Posts: 6305
Credit: 14,950,020
RAC: 19,273
Australia
Message 1556237 - Posted: 13 Aug 2014, 17:02:57 UTC - in response to Message 1556228.

I agree getting pissed off not even getting v7 for the cpu i have no work at all for the CPU
____________

msattler - meow!!
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 45388
Credit: 805,569,404
RAC: 112,258
United States
Message 1556241 - Posted: 13 Aug 2014, 17:12:30 UTC - in response to Message 1556237.
Last modified: 13 Aug 2014, 17:12:58 UTC

I agree getting pissed off not even getting v7 for the cpu i have no work at all for the CPU

You'll have to be patient. Ready to send is around zero for both MB and AP.
Hopefully somebody can get a message through to whoever is in the lab. I have sent a couple of messages to Eric this week, but I believe he is out of town.

Meowsigh.
____________
Meow, and the world meows with you. Bark, and you bark alone.

Have made a few friends in life.
Most were cats.

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 5985
Credit: 153,408,350
RAC: 543
United States
Message 1556320 - Posted: 13 Aug 2014, 18:39:54 UTC

To makes things even worse. The other splitters that are not stuck seem to be moving through mud or something. The same other 4 tapes have been at it since we came back yesterday. Normally they would have ripped though those tapes and started at the top where the finished AP tapes are long ago.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

juan BFP
Volunteer tester
Avatar
Send message
Joined: 16 Mar 07
Posts: 5830
Credit: 330,028,949
RAC: 12,441
Panama
Message 1556323 - Posted: 13 Aug 2014, 18:43:30 UTC

I´m disapointed, seem's like no one in the lab read antyhing we post here, the tape is stuck for more than 24 hrs now and aparently nobody see that. Where are they?

That rises a question: If we found an ET call would be anyone in the lab to acknowledgue that?
____________

Richard HaselgroveProject Donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 10937
Credit: 80,829,510
RAC: 38,365
United Kingdom
Message 1556325 - Posted: 13 Aug 2014, 18:44:56 UTC - in response to Message 1556320.

To makes things even worse. The other splitters that are not stuck seem to be moving through mud or something. The same other 4 tapes have been at it since we came back yesterday. Normally they would have ripped though those tapes and started at the top where the finished AP tapes are long ago.

And the WUs which are split off them are almost all shorties. I don't know if there's any technical reason making the splitters work harder if the source data was recorded at high ARs.

Profile Bernie Vine
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 26 May 99
Posts: 8498
Credit: 41,720,034
RAC: 13,928
United Kingdom
Message 1556327 - Posted: 13 Aug 2014, 18:46:05 UTC - in response to Message 1556323.

I´m disapointed, seem's like no one in the lab read antyhing we post here, the tape is stuck for more than 24 hrs now and aparently nobody see that. Where are they?

That rises a question: If we found an ET call would be anyone in the lab to acknowledgue that?

As far as I am aware no one in the lab does or has ever read these boards.
____________

Richard HaselgroveProject Donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 10937
Credit: 80,829,510
RAC: 38,365
United Kingdom
Message 1556335 - Posted: 13 Aug 2014, 18:53:33 UTC - in response to Message 1556327.

I´m disapointed, seem's like no one in the lab read antyhing we post here, the tape is stuck for more than 24 hrs now and aparently nobody see that. Where are they?

That rises a question: If we found an ET call would be anyone in the lab to acknowledgue that?

As far as I am aware no one in the lab does or has ever read these boards.

That's a little cynical, Bernie. Try message 1514606.

Profile Julie
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 28 Oct 09
Posts: 33164
Credit: 8,421,405
RAC: 8,088
Belgium
Message 1556381 - Posted: 13 Aug 2014, 20:29:37 UTC

Woohoo!! The RAC on Lisa's computer just hit the sky:))
____________

rOZZ
MUSIC

juan BFP
Volunteer tester
Avatar
Send message
Joined: 16 Mar 07
Posts: 5830
Credit: 330,028,949
RAC: 12,441
Panama
Message 1556443 - Posted: 13 Aug 2014, 23:28:12 UTC - in response to Message 1556335.

Cynical or not the dam tape remains stuck after almost 2 days.
____________

Grant (SSSF)
Volunteer tester
Send message
Joined: 19 Aug 99
Posts: 7345
Credit: 87,818,009
RAC: 40,544
Australia
Message 1556494 - Posted: 14 Aug 2014, 1:18:02 UTC - in response to Message 1556443.
Last modified: 14 Aug 2014, 1:18:49 UTC

A few things I'm curious about that msattler with his contacts may be able to get information on.

1 There are 7 PFB splitters, but I have only ever seen 5 of them running. PFB splitters 0 & 14 are always disabled. Any particular reason?
2 There are SAH Validate & SAH validate (v7) validators, as well as SAH assimilator & SAH assimilator (v7) assimilators. I'm guessing the ones without (v7) are for the older applications, and I'm pretty sure they've finally cleared all of the old WUs out.
Wouldn't removing those older Validators & assimilators free up resources? That would allow for more PFB splitters, and also allow them to run.

Things will still get stuck, but if there were 10 PFB splitters running we could lose half of them & it would have no effect on work availability. As things are, just losing one can be enough to stop the Ready-to-send buffer from re-filling & limit work available for download.
____________
Grant
Darwin NT

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 5985
Credit: 153,408,350
RAC: 543
United States
Message 1556512 - Posted: 14 Aug 2014, 2:25:21 UTC - in response to Message 1556494.
Last modified: 14 Aug 2014, 2:30:11 UTC

A few things I'm curious about that msattler with his contacts may be able to get information on.

1 There are 7 PFB splitters, but I have only ever seen 5 of them running. PFB splitters 0 & 14 are always disabled. Any particular reason?
2 There are SAH Validate & SAH validate (v7) validators, as well as SAH assimilator & SAH assimilator (v7) assimilators. I'm guessing the ones without (v7) are for the older applications, and I'm pretty sure they've finally cleared all of the old WUs out.
Wouldn't removing those older Validators & assimilators free up resources? That would allow for more PFB splitters, and also allow them to run.

Things will still get stuck, but if there were 10 PFB splitters running we could lose half of them & it would have no effect on work availability. As things are, just losing one can be enough to stop the Ready-to-send buffer from re-filling & limit work available for download.

From Moving on... (Apr 08 2013)
"...it seems that our result storage server can't handle much higher a load."

Since the old validators/assimilators are not doing any work. So just sit idle taking up little to no resources that would be of use.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Grant (SSSF)
Volunteer tester
Send message
Joined: 19 Aug 99
Posts: 7345
Credit: 87,818,009
RAC: 40,544
Australia
Message 1556515 - Posted: 14 Aug 2014, 2:49:49 UTC - in response to Message 1556512.

From Moving on... (Apr 08 2013)
"...it seems that our result storage server can't handle much higher a load."

Maybe time for another specific fund raiser?
____________
Grant
Darwin NT

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 5985
Credit: 153,408,350
RAC: 543
United States
Message 1556516 - Posted: 14 Aug 2014, 2:58:57 UTC - in response to Message 1556515.

From Moving on... (Apr 08 2013)
"...it seems that our result storage server can't handle much higher a load."

Maybe time for another specific fund raiser?

I think the current hardware priority is for the Green Bank recorder stuff, but that might be finished. There have not been any updates in a while on http://www.gpuug.org/ about the status.
If that is complete they may have other needs that are more important then a faster disk array.

On the plus side MB RTS is growing once again!
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Grant (SSSF)
Volunteer tester
Send message
Joined: 19 Aug 99
Posts: 7345
Credit: 87,818,009
RAC: 40,544
Australia
Message 1556529 - Posted: 14 Aug 2014, 3:33:26 UTC - in response to Message 1556516.

On the plus side MB RTS is growing once again!

Probably due to the amount of AP work that's been going out.
Splitter output is still borked.
____________
Grant
Darwin NT

juan BFP
Volunteer tester
Avatar
Send message
Joined: 16 Mar 07
Posts: 5830
Credit: 330,028,949
RAC: 12,441
Panama
Message 1556653 - Posted: 14 Aug 2014, 9:22:56 UTC - in response to Message 1556529.

On the plus side MB RTS is growing once again!

Probably due to the amount of AP work that's been going out.
Splitter output is still borked.

The dam 18fe09ag tape still stucked at the channel #3...
____________

Grant (SSSF)
Volunteer tester
Send message
Joined: 19 Aug 99
Posts: 7345
Credit: 87,818,009
RAC: 40,544
Australia
Message 1556658 - Posted: 14 Aug 2014, 9:43:33 UTC - in response to Message 1556653.

On the plus side MB RTS is growing once again!

Probably due to the amount of AP work that's been going out.
Splitter output is still borked.

The dam 18fe09ag tape still stucked at the channel #3...


Yeah,
18fe09ag is a bit of a problem child.
____________
Grant
Darwin NT

Richard HaselgroveProject Donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 10937
Credit: 80,829,510
RAC: 38,365
United Kingdom
Message 1556661 - Posted: 14 Aug 2014, 9:50:46 UTC - in response to Message 1556658.

On the plus side MB RTS is growing once again!

Probably due to the amount of AP work that's been going out.
Splitter output is still borked.

The dam 18fe09ag tape still stucked at the channel #3...

Yeah,
18fe09ag is a bit of a problem child.

But with fewer shorties being pulled down, the remaining splitters are enough to slowly rebuild the ready-to-send buffer. Perhaps helped by the AP crowd not muscling in on the act ;)

Grant (SSSF)
Volunteer tester
Send message
Joined: 19 Aug 99
Posts: 7345
Credit: 87,818,009
RAC: 40,544
Australia
Message 1556666 - Posted: 14 Aug 2014, 10:23:52 UTC - in response to Message 1556661.

But with fewer shorties being pulled down, the remaining splitters are enough to slowly rebuild the ready-to-send buffer. Perhaps helped by the AP crowd not muscling in on the act ;)

I reckon the AP feeding frenzy would be having the biggest impact.
____________
Grant
Darwin NT

juan BFP
Volunteer tester
Avatar
Send message
Joined: 16 Mar 07
Posts: 5830
Credit: 330,028,949
RAC: 12,441
Panama
Message 1556669 - Posted: 14 Aug 2014, 10:40:03 UTC - in response to Message 1556666.
Last modified: 14 Aug 2014, 10:45:45 UTC

I´m not sure about that. Why? Simply because the slow down of the splitting process happening before the AP frenzy starts, the problem starts when any tape is stuck. At that time 3 days ago there where no AP splitters running, just remember the last monday.

On the contrary when we have AP spliting the intensity of the problem is smaller because less hosts ask for MB WU, releasing some of the remaining MB splitters workload.

A simple kick o the stuck WU normaly clears the problem. What i can understand why that is not automatic.
____________

1 · 2 · 3 · 4 . . . 24 · Next

Message boards : Number crunching : Panic Mode On (89) Server Problems?

Copyright © 2016 University of California