looks like we are down for the weekend

Message boards : Number crunching : looks like we are down for the weekend
Message board moderation

To post messages, you must log in.

1 · 2 · Next

AuthorMessage
Lionel

Send message
Joined: 25 Mar 00
Posts: 680
Credit: 563,640,304
RAC: 597
Australia
Message 1035851 - Posted: 25 Sep 2010, 0:21:21 UTC


25/09/2010 10:19:27 AM SETI@home [error] Error reported by file upload server: Server is out of disk space

ID: 1035851 · Report as offensive
Iona
Avatar

Send message
Joined: 12 Jul 07
Posts: 790
Credit: 22,438,118
RAC: 0
United Kingdom
Message 1035854 - Posted: 25 Sep 2010, 0:24:20 UTC

Not looking good. Oh well, I'm on holiday for a week, so I'll be back in time for another (extended) 'outage'! You've just got to love it....



Don't take life too seriously, as you'll never come out of it alive!
ID: 1035854 · Report as offensive
Zebra3
Avatar

Send message
Joined: 22 Oct 01
Posts: 186
Credit: 13,658,148
RAC: 0
Canada
Message 1035859 - Posted: 25 Sep 2010, 0:49:34 UTC

Time to dust off off some of those other BOINC projects I guess...I need to keep the house warm still!
http://www.novascotia.com
ID: 1035859 · Report as offensive
Profile James Sotherden
Avatar

Send message
Joined: 16 May 99
Posts: 10436
Credit: 110,373,059
RAC: 54
United States
Message 1035885 - Posted: 25 Sep 2010, 2:26:59 UTC

I turned the p4 off yesterday for no work, I have 3 AP's good for 20 more hours and 5 MB left. Then milkyway gets to run free on the i7.
[/quote]

Old James
ID: 1035885 · Report as offensive
Profile BANZAI56
Volunteer tester

Send message
Joined: 17 May 00
Posts: 139
Credit: 47,299,948
RAC: 2
United States
Message 1035896 - Posted: 25 Sep 2010, 2:56:47 UTC - in response to Message 1035885.  

I turned the p4 off yesterday for no work, I have 3 AP's good for 20 more hours and 5 MB left. Then milkyway gets to run free on the i7.




With an empty cache, it might be a good time for a detach/reattach to set them ghosts free... ;)


ID: 1035896 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1035906 - Posted: 25 Sep 2010, 3:41:35 UTC - in response to Message 1035896.  

I turned the p4 off yesterday for no work, I have 3 AP's good for 20 more hours and 5 MB left. Then milkyway gets to run free on the i7.


With an empty cache, it might be a good time for a detach/reattach to set them ghosts free... ;)


Sounds like a good idea, but I think the scheduler needs to be able to respond for such an action. :p
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1035906 · Report as offensive
Zebra3
Avatar

Send message
Joined: 22 Oct 01
Posts: 186
Credit: 13,658,148
RAC: 0
Canada
Message 1035907 - Posted: 25 Sep 2010, 3:46:15 UTC

Well one way we can look at it...with 500,00 MB and 25,000 AP's now we wont run out of WU's for at least an hour or so when it does come up...lol
http://www.novascotia.com
ID: 1035907 · Report as offensive
Zebra3
Avatar

Send message
Joined: 22 Oct 01
Posts: 186
Credit: 13,658,148
RAC: 0
Canada
Message 1035920 - Posted: 25 Sep 2010, 4:42:54 UTC - in response to Message 1035916.  

This SETI thing is getting all f'd up


Right now the project is suffering some growing pains...the new server will hopefully bring more stability...If you run out of SETI work just move on to another project temporarily until things get back online. You have been around long enough to have seen this go on before. It is frustrating at times but keep hanging in as things will get better I am sure!

http://www.novascotia.com
ID: 1035920 · Report as offensive
Vlad
Avatar

Send message
Joined: 23 May 99
Posts: 8
Credit: 5,538,965
RAC: 0
United States
Message 1035926 - Posted: 25 Sep 2010, 5:14:14 UTC

One thing has become very clear to me. Seti@Home is a dying project. These constant server issues (scheduled and non-scheduled) prove it. Fifty to seventy five percent of the time (or more) the servers are down for one reason or another. It may be time to pull the plug. My stated opinions will be very unpopular with many of you, but they have merit. How many of you really believe we will ever find alien signals this way? Other Boinc projects have gotten results. For instance, Einstein@Home recently discovered it's first radio pulsar. What has Seti@home found? I'm sure you all know the answer to this question. I will be ending my involvement with Seti@home. It's been a interesting/frustrating 11 years 5 months.

Vlad
ID: 1035926 · Report as offensive
TheFreshPrince a.k.a. BlueTooth76
Avatar

Send message
Joined: 4 Jun 99
Posts: 210
Credit: 10,315,944
RAC: 0
Netherlands
Message 1035943 - Posted: 25 Sep 2010, 6:21:49 UTC - in response to Message 1035926.  

One thing has become very clear to me. Seti@Home is a dying project. These constant server issues (scheduled and non-scheduled) prove it. Fifty to seventy five percent of the time (or more) the servers are down for one reason or another. It may be time to pull the plug. My stated opinions will be very unpopular with many of you, but they have merit. How many of you really believe we will ever find alien signals this way? Other Boinc projects have gotten results. For instance, Einstein@Home recently discovered it's first radio pulsar. What has Seti@home found? I'm sure you all know the answer to this question. I will be ending my involvement with Seti@home. It's been a interesting/frustrating 11 years 5 months.

Vlad


If you look outside your window (instead of MS Windows) and take a look at the sky, try to imagine how big it is ;)
It can take another 100 years to find something, so I guess we are just at the beginning...
And I'll be around here as long as Seti is here (and my electric bills are paid)...

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
ID: 1035943 · Report as offensive
OzzFan Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Apr 02
Posts: 15688
Credit: 84,761,841
RAC: 28
United States
Message 1035948 - Posted: 25 Sep 2010, 7:07:03 UTC - in response to Message 1035926.  

One thing has become very clear to me. Seti@Home is a dying project. These constant server issues (scheduled and non-scheduled) prove it.


Constant server issues does not mean a dying project. It only means difficulty with the success of CUDA. The only way the project will die is if they do not have enough money to afford running the servers.

Fifty to seventy five percent of the time (or more) the servers are down for one reason or another.


Even if that were true (and it's not), I still don't recall a promise of higher uptime. They do what they can to keep things running smoothly. They don't need our pessimistic discouragement.

It may be time to pull the plug. My stated opinions will be very unpopular with many of you, but they have merit.


I can't speak to the popularity, but I can tell you your opinions really don't have the merit you think they do. Your opinions are particularly one-sided, even if shared by other frustrated people.

How many of you really believe we will ever find alien signals this way?


It's better than not looking at all.

Other Boinc projects have gotten results. For instance, Einstein@Home recently discovered it's first radio pulsar. What has Seti@home found? I'm sure you all know the answer to this question.


The difference is that SETI@Home can only have two answers: 1) We've found them! 2) We haven't found them.

Einstein is merely making other discoveries that don't require a singular answer (i.e. is there intelligent life out there). Big difference in goals, larger difference in comparing successes.

I will be ending my involvement with Seti@home. It's been a interesting/frustrating 11 years 5 months.

Vlad


I've been with the project almost as long, yet I don't suffer from the same frustration. I suppose it has a lot to do with my level of patience, realistic expectations, and an eye toward the bigger picture.

Good luck in your endeavors.
ID: 1035948 · Report as offensive
Profile soft^spirit
Avatar

Send message
Joined: 18 May 99
Posts: 6497
Credit: 34,134,168
RAC: 0
United States
Message 1035951 - Posted: 25 Sep 2010, 7:20:13 UTC

You know.. I do get frustrated. There been yet again a lot of unscheduled down time. And it would go a long way if someone from the project popped in and said "yes we are aware we have a problem.".

But there ARE a lot of changes being made, server swaps and upgrades and re-balancing, it is a very small wonder that more code has not gotten mis-placed, mis-routed, and just plain broken. The current outtage might simply be in IP routing, a cable in the wrong spot, or 1,001 other things. While it is frustrating, it is not surprising.

The full disks have been under-reacted to. This is not the first time they became an issue, and with more work continuing to be pumped out it is not likely to go away without some major changes. And major changes may mean more outtages. And the corrections might not be painless either.

So.. I will quietly grumble with the rest of the malcontents and wait. Fresh hardware is on its way. And more changes are in store. Take a deep breath, mutter dirty words and hang on.
Janice
ID: 1035951 · Report as offensive
OzzFan Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Apr 02
Posts: 15688
Credit: 84,761,841
RAC: 28
United States
Message 1035952 - Posted: 25 Sep 2010, 7:24:25 UTC - in response to Message 1035951.  

And it would go a long way if someone from the project popped in and said "yes we are aware we have a problem.".


Matt and Jeff have been doing exactly that lately, with a reasonable frequency.
ID: 1035952 · Report as offensive
Profile soft^spirit
Avatar

Send message
Joined: 18 May 99
Posts: 6497
Credit: 34,134,168
RAC: 0
United States
Message 1035953 - Posted: 25 Sep 2010, 7:36:55 UTC - in response to Message 1035952.  

And it would go a long way if someone from the project popped in and said "yes we are aware we have a problem.".


Matt and Jeff have been doing exactly that lately, with a reasonable frequency.

If there has been anything since this morning, I missed it.
Janice
ID: 1035953 · Report as offensive
OzzFan Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Apr 02
Posts: 15688
Credit: 84,761,841
RAC: 28
United States
Message 1035954 - Posted: 25 Sep 2010, 7:38:49 UTC - in response to Message 1035953.  
Last modified: 25 Sep 2010, 7:56:08 UTC

And it would go a long way if someone from the project popped in and said "yes we are aware we have a problem.".


Matt and Jeff have been doing exactly that lately, with a reasonable frequency.

If there has been anything since this morning, I missed it.


Does there really need to be more? Matt's post from Thursday pretty much addresses all these issues we've been having since they brought up the servers this week:

There have been some interesting unexpected consequences due to these extended weekly outages. For example, the amount of results hanging out in the mysql database has pretty much doubled (growing slowly but consistently over the past two months), which is causing minor indigestion: the database backups and re-orgs take much longer, and workunits and results are hanging out on disk much longer (and filling up their respective disks). But also some power users are trying to return hundreds, perhaps thousands, of results in a single scheduler request.


(My emphasis added)

And I still see no reason to be frustrated.
ID: 1035954 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15183
Credit: 4,362,181
RAC: 3
Netherlands
Message 1035958 - Posted: 25 Sep 2010, 7:57:43 UTC - in response to Message 1035926.  
Last modified: 25 Sep 2010, 8:00:54 UTC

For instance, Einstein@Home recently discovered it's first radio pulsar.

Which isn't the primary thing for Einstein to search for; they only added that option 'recently' and it's an opt-in option. Their primary function, the one they get the grant for, is to find gravitational waves from spinning neutron stars (also called pulsars) using data from the LIGO gravitational wave detector. So far they've discovered none of those.

Compare that to Seti which has been collecting data for 11 years and has never checked through all the data they have collected whether or not the Wow! signal was actually present. As that's what they are doing now during those 3 days of outage, check for possible signals in the data, see what needs revisiting.
ID: 1035958 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6324
Credit: 106,370,077
RAC: 121
Russia
Message 1035959 - Posted: 25 Sep 2010, 8:01:44 UTC

Well, looks like we should be happy that upload disk is full.
There is simple solution for this problem - to free up space.
But if we could still upload tasks the second problem would become much more important - more and more hosts would have too many tasks to report in single request. While BOINC client can do partial upload, it seems it can't do partial report. That is, from some point host will be not able to report already completed and uploaded tasks at all.
So it's better not to upload anything until aleady uploaded tasks will be reported successfully and size of report transaction will be small enough.
ID: 1035959 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15183
Credit: 4,362,181
RAC: 3
Netherlands
Message 1035962 - Posted: 25 Sep 2010, 8:06:31 UTC - in response to Message 1035959.  

While BOINC client can do partial upload, it seems it can't do partial report.

With the new scheduler in place, Vyper can attest that it does. It'll take your reports in blocks of 1,000 to be reported tasks.
ID: 1035962 · Report as offensive
Roger Parsons

Send message
Joined: 26 Dec 99
Posts: 7
Credit: 2,052,430
RAC: 1
United Kingdom
Message 1035965 - Posted: 25 Sep 2010, 8:10:14 UTC

I have been more than happy with the info provided by Jeff, Matt, volunteer Scarab and Soft-spirit. Thanks. Enough to satisfy my curiosity and confirm it is not a problem at my end. Withdrawal symptoms notwithstanding, most of us value and appreciate your efforts. Keep up the good work. BTW It was helpful to have updated news on the homepage to save picking through the Notice Boards. Roger
Rogerp
http://www.rogerparsons.info/

E pur si muove - And yet it does move (Galileo Galilei)
ID: 1035965 · Report as offensive
FiveHamlet
Avatar

Send message
Joined: 5 Oct 99
Posts: 783
Credit: 32,638,578
RAC: 0
United Kingdom
Message 1035969 - Posted: 25 Sep 2010, 8:19:08 UTC

My Rig on a Bench has at the moment 2150 tasks to report and another 400 to upload.
It still has 2300 tasks in its cache and is continuing to crunch them,each day another 500 will be added.
It is in the top ten rigs so there are other rigs trying to report more tasks than it.
If there is a problem that power crunchers cause by trying to report to many tasks at one time,then a solution should be found sooner rather than later.
More and more rigs are starting to power crunch with the the new fermi cards.

Dave
ID: 1035969 · Report as offensive
1 · 2 · Next

Message boards : Number crunching : looks like we are down for the weekend


 
©2022 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.