Panic Mode On (34) Server Problems

Message boards : Number crunching : Panic Mode On (34) Server Problems
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 . . . 11 · Next

AuthorMessage
Profile soft^spirit
Avatar

Send message
Joined: 18 May 99
Posts: 6497
Credit: 34,134,168
RAC: 0
United States
Message 1007471 - Posted: 23 Jun 2010, 18:02:02 UTC - in response to Message 1007466.  

it does since reboot.

And nothing is going to stop the cheap shots. It will not stop me from sharing what could be useful information. Maybe not.

The timing was suspicious. But that is a stretch. Depending on where the units landed, might be no cause for alarm. If others are having vanishing units.. Could be cause for concern.







Janice
ID: 1007471 · Report as offensive
Robert Ribbeck
Avatar

Send message
Joined: 7 Jun 02
Posts: 644
Credit: 5,283,174
RAC: 0
United States
Message 1007475 - Posted: 23 Jun 2010, 18:09:35 UTC - in response to Message 1007464.  

Total cash donations since 1 June 2008 have been $ 217770.11 so about half that annually. It amounts to about 1/5 of a reasonable budget, so perhaps we should consider anything more than 20% uptime a testament to the skills and dedication of project staff.
                                                               Joe


Guess you can't count the continuing grant money they receive
or hardware donations to the contributions

That's exactly why I said "cash donations". Certainly the grant Eric managed to get after that budget changes the picture somewhat, though I don't know how much. I doubt there's any significant amount from the old Astropulse grant. The hardware donations by Overland Storage and Intel, and continuing support from Sun are certainly important too.

Will 1/10 of the 1 GBit line being run to SSL cover S@H needs? Perhaps so, the ALFA receiver sytem at Arecibo is being used less than they had hoped. But if enough had been donated to fund a S@H specific 1 GBit line being run up the hill as well as the 1GBit for the rest of the Space Sciences Lab, the capacity would be there if they can get enough funding to record more than 1/100 of the ALFA bandwidth.

If they had been able to get another staff member, would that have improved the uptime? Maybe, and maybe it would have meant more posts initiated by staff members.
                                                              Joe


I guess I missed the "cash" part I meant no slight was just pointing out
It's not just the cash donations that keep this going

I've been here since the classic days and nothing surprises me or troubles me
Sure things could be better .. where couldn't they be
It's just a shame we can't all respect each other's opinions and not resort to
slamming people we disagree with

On another note something I've thought about for a while
This is all about distributed computing

Could not something be done to distribute the load of handling the "seti@home"
project via distribution instead of all being done in a server room at berkley
splitting verifications & creating the master data base over several volunteers computers on the internet
ID: 1007475 · Report as offensive
Berserker
Volunteer tester

Send message
Joined: 2 Jun 99
Posts: 105
Credit: 5,440,087
RAC: 0
United Kingdom
Message 1007476 - Posted: 23 Jun 2010, 18:12:30 UTC
Last modified: 23 Jun 2010, 18:13:15 UTC

it does since reboot.

And nothing is going to stop the cheap shots. It will not stop me from sharing what could be useful information. Maybe not.

The timing was suspicious. But that is a stretch. Depending on where the units landed, might be no cause for alarm. If others are having vanishing units.. Could be cause for concern.

Same. While I do get frustrated with people making demands and claiming rights they don't have, I don't pretend for one moment that there aren't issues to be resolved - and bugs too.

Given that the scheduling server has been off for most of the day, it's fairly unlikely to be anything server-side. Unless of course it happened in the brief window when the project was up and you just didn't notice at the time. That's plausible (I've had crunchers sat idle for a week because I didn't notice stuff). Maybe the logs (see BOINC data directory) might reveal something useful.
Stats site - http://www.teamocuk.co.uk - still alive and (just about) kicking.
ID: 1007476 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 1007477 - Posted: 23 Jun 2010, 18:13:11 UTC - in response to Message 1007475.  


On another note something I've thought about for a while
This is all about distributed computing

Could not something be done to distribute the load of handling the "seti@home"
project via distribution instead of all being done in a server room at berkley
splitting verifications & creating the master data base over several volunteers computers on the internet

It seems to me that this has been proposed before, but it was determined at the time that any benefit in doing so would be lost in the complexities of transferring data back and forth between a master database and external hosts, verifying integrity of data, maintaining scientific integrity of same, etc., etc., etc..
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1007477 · Report as offensive
DJStarfox

Send message
Joined: 23 May 01
Posts: 1066
Credit: 1,226,053
RAC: 2
United States
Message 1007478 - Posted: 23 Jun 2010, 18:18:45 UTC - in response to Message 1007477.  


On another note something I've thought about for a while
This is all about distributed computing

Could not something be done to distribute the load of handling the "seti@home"
project via distribution instead of all being done in a server room at berkley
splitting verifications & creating the master data base over several volunteers computers on the internet

It seems to me that this has been proposed before, but it was determined at the time that any benefit in doing so would be lost in the complexities of transferring data back and forth between a master database and external hosts, verifying integrity of data, maintaining scientific integrity of same, etc., etc., etc..


This problem of distributed validation is being researched generally by a few universities... but to my knowledge (as of late last year when I was in research), there is no solution that works at the scale of SETI@Home. IOW, no solution any time soon.
ID: 1007478 · Report as offensive
Berserker
Volunteer tester

Send message
Joined: 2 Jun 99
Posts: 105
Credit: 5,440,087
RAC: 0
United Kingdom
Message 1007479 - Posted: 23 Jun 2010, 18:19:43 UTC - in response to Message 1007477.  

It seems to me that this has been proposed before, but it was determined at the time that any benefit in doing so would be lost in the complexities of transferring data back and forth between a master database and external hosts, verifying integrity of data, maintaining scientific integrity of same, etc., etc., etc..


This. Given that the source data is in 50GB 'blobs', the internet isn't up to distributing them. Peer-to-peer distribution of workunits might help with download bandwidth, but also opens up a whole can of network issue worms - not to mention security concerns.

Besides, all the results have to get back to Berkeley somehow eventually to be validated, assimilated, and NTPCkr'd over (assuming that gets to operational status in due course). So the databases at least end up just as big as they are now.
Stats site - http://www.teamocuk.co.uk - still alive and (just about) kicking.
ID: 1007479 · Report as offensive
Robert Ribbeck
Avatar

Send message
Joined: 7 Jun 02
Posts: 644
Credit: 5,283,174
RAC: 0
United States
Message 1007482 - Posted: 23 Jun 2010, 18:27:07 UTC - in response to Message 1007478.  


On another note something I've thought about for a while
This is all about distributed computing

Could not something be done to distribute the load of handling the "seti@home"
project via distribution instead of all being done in a server room at berkley
splitting verifications & creating the master data base over several volunteers computers on the internet

It seems to me that this has been proposed before, but it was determined at the time that any benefit in doing so would be lost in the complexities of transferring data back and forth between a master database and external hosts, verifying integrity of data, maintaining scientific integrity of same, etc., etc., etc..


This problem of distributed validation is being researched generally by a few universities... but to my knowledge (as of late last year when I was in research), there is no solution that works at the scale of SETI@Home. IOW, no solution any time soon.


Well it wasn't really that long ago that boinc wasn't possible either
as home computers get better & better thing theat wern't possible now are

Maybe getting the message boards off local servers ?
or just a raid array of disk space accross the internet
Now there's something

ID: 1007482 · Report as offensive
Berserker
Volunteer tester

Send message
Joined: 2 Jun 99
Posts: 105
Credit: 5,440,087
RAC: 0
United Kingdom
Message 1007483 - Posted: 23 Jun 2010, 18:30:52 UTC

Update: Our upload server disk array crashed last night, but has been recovered. However, the project will remain down until we process a large backlog of results.

Looks like a resync did the trick. Clearing the pipes before opening up for more punishment seems like a sound idea.
Stats site - http://www.teamocuk.co.uk - still alive and (just about) kicking.
ID: 1007483 · Report as offensive
W-K 666 Project Donor
Volunteer tester

Send message
Joined: 18 May 99
Posts: 18996
Credit: 40,757,560
RAC: 67
United Kingdom
Message 1007484 - Posted: 23 Jun 2010, 18:31:31 UTC - in response to Message 1007482.  


On another note something I've thought about for a while
This is all about distributed computing

Could not something be done to distribute the load of handling the "seti@home"
project via distribution instead of all being done in a server room at berkley
splitting verifications & creating the master data base over several volunteers computers on the internet

It seems to me that this has been proposed before, but it was determined at the time that any benefit in doing so would be lost in the complexities of transferring data back and forth between a master database and external hosts, verifying integrity of data, maintaining scientific integrity of same, etc., etc., etc..


This problem of distributed validation is being researched generally by a few universities... but to my knowledge (as of late last year when I was in research), there is no solution that works at the scale of SETI@Home. IOW, no solution any time soon.


Well it wasn't really that long ago that boinc wasn't possible either
as home computers get better & better thing theat wern't possible now are

Maybe getting the message boards off local servers ?
or just a raid array of disk space accross the internet
Now there's something

It's a problem that has been discussed many times, probably too many. In the end all the data has to though one fairly small connection and that makes it virtually impossible. Even if the rest of the resources were provided gratis.
ID: 1007484 · Report as offensive
Robert Ribbeck
Avatar

Send message
Joined: 7 Jun 02
Posts: 644
Credit: 5,283,174
RAC: 0
United States
Message 1007488 - Posted: 23 Jun 2010, 18:41:42 UTC - in response to Message 1007484.  


It's a problem that has been discussed many times, probably too many. In the end all the data has to though one fairly small connection and that makes it virtually impossible. Even if the rest of the resources were provided gratis.


Ok as per usual the nay sayers have the majority

It's always easier to say WHY NOT than to come up with the solutions

I'm too old to fight any more
Just remember yesterdays dreams are todays reality
ID: 1007488 · Report as offensive
DJStarfox

Send message
Joined: 23 May 01
Posts: 1066
Credit: 1,226,053
RAC: 2
United States
Message 1007491 - Posted: 23 Jun 2010, 18:44:41 UTC - in response to Message 1007484.  

It's a problem that has been discussed many times, probably too many. In the end all the data has to though one fairly small connection and that makes it virtually impossible. Even if the rest of the resources were provided gratis.

The next step is to make the quorum and validation distributed. Then, the SETI@Home servers can simply poll for the result via DHT mechanism. The only disadvantage that is certain is the increased latency between work distribution and storing the canonical result. However, no intermediate storage is needed server-side (no upload server).

I expect we'll see this architecture available as soon as 3-5 years from now, or longer if no one pursues any applications. It's a waste to discuss changing the SETI@Home architecture until technology and/or resources are greatly improved.

But if anyone really wants to beat the dead horse some more, I suggest starting a new thread instead of filling this one up.
ID: 1007491 · Report as offensive
W-K 666 Project Donor
Volunteer tester

Send message
Joined: 18 May 99
Posts: 18996
Credit: 40,757,560
RAC: 67
United Kingdom
Message 1007497 - Posted: 23 Jun 2010, 19:07:07 UTC - in response to Message 1007488.  


It's a problem that has been discussed many times, probably too many. In the end all the data has to though one fairly small connection and that makes it virtually impossible. Even if the rest of the resources were provided gratis.


Ok as per usual the nay sayers have the majority

It's always easier to say WHY NOT than to come up with the solutions

I'm too old to fight any more
Just remember yesterdays dreams are todays reality

As I said it has been discussed many times and there has been a even greater number of suggestions, all of which have been rejected, mainly by people who have a lot more knowledge that I on the subject.

Some of the knowledgeable were Ned and Ozzfan, who have retired. On of the reasons being because they got tired of repeating explanations to people who wouldn't look to see if there were any previous posts on the subject.
ID: 1007497 · Report as offensive
Robert Ribbeck
Avatar

Send message
Joined: 7 Jun 02
Posts: 644
Credit: 5,283,174
RAC: 0
United States
Message 1007500 - Posted: 23 Jun 2010, 19:17:20 UTC - in response to Message 1007497.  
Last modified: 23 Jun 2010, 19:24:22 UTC


It's a problem that has been discussed many times, probably too many. In the end all the data has to though one fairly small connection and that makes it virtually impossible. Even if the rest of the resources were provided gratis.


Ok as per usual the nay sayers have the majority

It's always easier to say WHY NOT than to come up with the solutions

I'm too old to fight any more
Just remember yesterdays dreams are todays reality

As I said it has been discussed many times and there has been a even greater number of suggestions, all of which have been rejected, mainly by people who have a lot more knowledge that I on the subject.

Some of the knowledgeable were Ned and Ozzfan, who have retired. On of the reasons being because they got tired of repeating explanations to people who wouldn't look to see if there were any previous posts on the subject.


thank YOU O WIZARD FOR YOUR WORDS OF WISDOM
I'm out of here
If i wanted trolls & bs I'd turn my time machine back to the 60's
These forum threads are not invitations to flame other posters or post
what you think you know
It's apparent nothing useful can be accomplished
BYE
ID: 1007500 · Report as offensive
KB7RZF
Volunteer tester
Avatar

Send message
Joined: 15 Aug 99
Posts: 9549
Credit: 3,308,926
RAC: 2
United States
Message 1007505 - Posted: 23 Jun 2010, 19:43:03 UTC - in response to Message 1007500.  


It's a problem that has been discussed many times, probably too many. In the end all the data has to though one fairly small connection and that makes it virtually impossible. Even if the rest of the resources were provided gratis.


Ok as per usual the nay sayers have the majority

It's always easier to say WHY NOT than to come up with the solutions

I'm too old to fight any more
Just remember yesterdays dreams are todays reality

As I said it has been discussed many times and there has been a even greater number of suggestions, all of which have been rejected, mainly by people who have a lot more knowledge that I on the subject.

Some of the knowledgeable were Ned and Ozzfan, who have retired. On of the reasons being because they got tired of repeating explanations to people who wouldn't look to see if there were any previous posts on the subject.


thank YOU O WIZARD FOR YOUR WORDS OF WISDOM
I'm out of here
If i wanted trolls & bs I'd turn my time machine back to the 60's
These forum threads are not invitations to flame other posters or post
what you think you know
It's apparent nothing useful can be accomplished
BYE

I really don't see how WinterKnight was being a troll, and throwing BS around. He simply stated a fact, and why those who have a great knowledge of things going on around here have left. Nothing of that was being a troll, or feeding BS. And maybe heeding to your own words, these forums aren't an invitation to flame other posters, just as you said yourself. Good day sir.
ID: 1007505 · Report as offensive
Profile Geek@Play
Volunteer tester
Avatar

Send message
Joined: 31 Jul 01
Posts: 2467
Credit: 86,146,931
RAC: 0
United States
Message 1007507 - Posted: 23 Jun 2010, 19:50:06 UTC - in response to Message 1007500.  
Last modified: 23 Jun 2010, 19:50:48 UTC

thank YOU O WIZARD FOR YOUR WORDS OF WISDOM
I'm out of here
If i wanted trolls & bs I'd turn my time machine back to the 60's
These forum threads are not invitations to flame other posters or post
what you think you know
It's apparent nothing useful can be accomplished
BYE


Everyone here have dreams of what could be.
We all must live under the constraints of limited time, limited personel, limited funds for Boinc and Seti. It is what it is.
Boinc....Boinc....Boinc....Boinc....
ID: 1007507 · Report as offensive
Profile Allie in Vancouver
Volunteer tester
Avatar

Send message
Joined: 16 Mar 07
Posts: 3949
Credit: 1,604,668
RAC: 0
Canada
Message 1007511 - Posted: 23 Jun 2010, 19:56:15 UTC

How's about everyone just takes a calming step back from the brink, shall we?
Pure mathematics is, in its way, the poetry of logical ideas.

Albert Einstein
ID: 1007511 · Report as offensive
nemesis
Avatar

Send message
Joined: 12 Oct 99
Posts: 1408
Credit: 35,074,350
RAC: 0
Message 1007512 - Posted: 23 Jun 2010, 19:56:25 UTC

setizens.
lets keep this a positive place.
we are all concerned about the current problems,
getting angry with one another solves absolutely nothing.

if your frustration level is at a high point,
consider cutting your computers off for awhile.
at least until the mess is demessified.
you'll save money on your next power bill also.





ID: 1007512 · Report as offensive
Iona
Avatar

Send message
Joined: 12 Jul 07
Posts: 790
Credit: 22,438,118
RAC: 0
United Kingdom
Message 1007517 - Posted: 23 Jun 2010, 20:17:35 UTC - in response to Message 1007512.  

setizens.
lets keep this a positive place.
we are all concerned about the current problems,
getting angry with one another solves absolutely nothing.

if your frustration level is at a high point,
consider cutting your computers off for awhile.
at least until the mess is demessified.
you'll save money on your next power bill also.







Well, I usually find the 'off' switch to be a pretty good solution, when things can't upload and downloads are not happening. I also acknowledge that it is unreasonable to expect a project as large as this one, with resources limited in the way they are, to be 100% functional 24/7 all year. Is that called, being realistic (no connection to Tandy....lol)?




Don't take life too seriously, as you'll never come out of it alive!
ID: 1007517 · Report as offensive
KB7RZF
Volunteer tester
Avatar

Send message
Joined: 15 Aug 99
Posts: 9549
Credit: 3,308,926
RAC: 2
United States
Message 1007533 - Posted: 23 Jun 2010, 21:14:10 UTC - in response to Message 1007516.  



Current problems? What current problems? I bet that most people here still have jobs running from their caches. The download and upload doesn't work, but that isn't any problems until the computers doesn't have any jobs at all to crunch.

Edit, added: Take as an example someone who have his computers set to connect to SETI every 5 days. That person wouldn't have noticed any problems at all. So, there is no problems yet, is there?

So I'd say that so far we do NOT have any problems whatsoever. That is apart from some people without any patience.

LOL I'm right there with ya, although I crunch for more than 1 project. My computers stay toasty warm regardless of what happens on any of the projects. My laptop I'm attached to 17, 3 of which rarely have work, LHC, Pirates, and Orbit@home. My desktop is connected to pretty much everything in my sig. So 1 goes down, start another. :-) No problems EVER here. LOL
ID: 1007533 · Report as offensive
Profile perryjay
Volunteer tester
Avatar

Send message
Joined: 20 Aug 02
Posts: 3377
Credit: 20,676,751
RAC: 0
United States
Message 1007557 - Posted: 23 Jun 2010, 22:05:13 UTC

For those complaining about no news see Matt's post in Tech News.

Sten....These things have off buttons???


PROUD MEMBER OF Team Starfire World BOINC
ID: 1007557 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 . . . 11 · Next

Message boards : Number crunching : Panic Mode On (34) Server Problems


 
©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.