Welcome to MilkyWay@home

Aaargh! Server out of new work!

Message boards : Number crunching : Aaargh! Server out of new work!
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 6 · 7 · 8 · 9 · 10 · 11 · 12 . . . 22 · Next

AuthorMessage
Profile Werkstatt

Send message
Joined: 19 Feb 08
Posts: 350
Credit: 141,284,369
RAC: 0
Message 41377 - Posted: 10 Aug 2010, 16:46:33 UTC - in response to Message 41374.  


With DNetC now available which provides largely the same GPU support as Collatz, MW will drop down to my number three project in terms of TC within a couple of months. It is interesting the sort of reliability that Collatz and Dnetc can provide with quite limited resources (of course with lower user counts).

I guess we can hope that Travis is able to pass on the torch here to someone at RPI who will be 'invested' in the project as he was in the past. My other hope is that additional 'low end' GPU projects, particularly ATI GPU projects, start showing as well.


BarryAZ,
I'm afraid you're right. My hope is that someone follows his footsteps.

As I've learned from GPUGRID, cal is an 'outdated' programming tool. They are working on OpenCL Apps, which should be a step to an independency of the type of your card as long as it supports OpenCL.

Two or three month's ago somebody posted here in this forum, that other projects are working on GPU-Apps. Let's see if I can find that again.

Alexander
ID: 41377 · Rating: 0 · rate: Rate + / Rate - Report as offensive
BarryAZ

Send message
Joined: 1 Sep 08
Posts: 520
Credit: 302,525,188
RAC: 0
Message 41379 - Posted: 10 Aug 2010, 18:00:11 UTC - in response to Message 41375.  

Yes, I got that -- if that is the 'permanent' plan for SETI, then the folks most affected by that are the 'SETI uber alles' crowd -- for that group, the self-imposed 'only one project' makes them dependent on a project that, aside from the newsgroups, runs only 50% of the time and is pretty well stressed with folks crowding into the 'half-space' for uploads and downloads.

The plus side is that the much smaller active BOINC crowd that might have originally been brought into distributed processing by SETI and doesn't have a 'SETI only' DP world view might well help out other projects which are not half time.




As I understand it, the 3 day outage is to let Nitpicker run on 10 years worth of results to sift for likely candidates to re-examine. When they tried it in real time it zonked the servers and the database out. You can't upload or download work for 3 days, but the message boards are only out for 9-12 hours as they were before.



ID: 41379 · Rating: 0 · rate: Rate + / Rate - Report as offensive
Profile David Glogau*
Avatar

Send message
Joined: 12 Aug 09
Posts: 172
Credit: 645,240,165
RAC: 0
Message 41380 - Posted: 10 Aug 2010, 18:17:43 UTC
Last modified: 10 Aug 2010, 18:24:52 UTC

I run a GTX260 24/7 on Seti. it is no big deal. I needed to adjust my cache to 4 days to assure constant work, but that's no big deal.

As to DnetC, I find it makes an excellent backup project for me. I am running it now on two, twin 5790 computers. One 5790 and 4770 computer. And one single 5790 computer, so it is pretty adaptable from my point of view.

OK must go MW just downloaded on one of the boxes, so lets see if I can get the others back!
ID: 41380 · Rating: 0 · rate: Rate + / Rate - Report as offensive
Cartoonman

Send message
Joined: 10 Dec 09
Posts: 18
Credit: 9,456,111
RAC: 0
Message 41381 - Posted: 10 Aug 2010, 18:23:04 UTC

hmm, i got some WU's, assimilation seems to be up and running. have to wait though. AFAICS, there are a small bunch ready to send.
ID: 41381 · Rating: 0 · rate: Rate + / Rate - Report as offensive
John Clark

Send message
Joined: 4 Oct 08
Posts: 1734
Credit: 64,228,409
RAC: 0
Message 41382 - Posted: 10 Aug 2010, 19:24:30 UTC

Work is avilable again
Go away, I was asleep


ID: 41382 · Rating: 0 · rate: Rate + / Rate - Report as offensive
Profile skildude
Avatar

Send message
Joined: 13 Jan 08
Posts: 52
Credit: 59,823,507
RAC: 0
Message 41383 - Posted: 10 Aug 2010, 19:33:59 UTC

no validation though
Blah blah blah you know the rest
ID: 41383 · Rating: 0 · rate: Rate + / Rate - Report as offensive
John Clark

Send message
Joined: 4 Oct 08
Posts: 1734
Credit: 64,228,409
RAC: 0
Message 41384 - Posted: 10 Aug 2010, 19:47:04 UTC - in response to Message 41383.  

no validation though



It may have still been catshing up with the backlog when you looked. The Validator backlog now reads 6,287 WUs
Go away, I was asleep


ID: 41384 · Rating: 0 · rate: Rate + / Rate - Report as offensive
BarryAZ

Send message
Joined: 1 Sep 08
Posts: 520
Credit: 302,525,188
RAC: 0
Message 41385 - Posted: 10 Aug 2010, 21:02:24 UTC

Looks like the root cause is either winning or being looked into -- web pages are on -- sort of in a SETI emulation mode we are at the moment.

ID: 41385 · Rating: 0 · rate: Rate + / Rate - Report as offensive
John Clark

Send message
Joined: 4 Oct 08
Posts: 1734
Credit: 64,228,409
RAC: 0
Message 41387 - Posted: 10 Aug 2010, 22:52:37 UTC

Back to Collatz, which has good uptime since Comcast repaired/replaced parts of the BB line.
Go away, I was asleep


ID: 41387 · Rating: 0 · rate: Rate + / Rate - Report as offensive
Profile mdhittle*
Avatar

Send message
Joined: 25 Jun 10
Posts: 284
Credit: 260,490,091
RAC: 0
Message 41390 - Posted: 11 Aug 2010, 1:42:11 UTC
Last modified: 11 Aug 2010, 1:43:21 UTC

I just setup Collatz to be my primary project and Milky Way to be my backup. I really like Milky Way, but when you average in the downtime and the almost nonexistant cache, I am getting much better credit returns at Collatz.

If only I could get DNETC working om my system, I would set up as #1=DNETC, #2=Collatz, and #3=Milky Way.

I will keep checking back with the hope that I will find that the reliabilty of this project has improved.

Mike...
ID: 41390 · Rating: 0 · rate: Rate + / Rate - Report as offensive
BarryAZ

Send message
Joined: 1 Sep 08
Posts: 520
Credit: 302,525,188
RAC: 0
Message 41407 - Posted: 12 Aug 2010, 3:16:57 UTC

OK -- so could we PLEASE get some feedback from folks at the project as to what is going (or not going) on?

One thing more troublesome than outages is outages in a vacuum.

ID: 41407 · Rating: 0 · rate: Rate + / Rate - Report as offensive
Profile The Gas Giant
Avatar

Send message
Joined: 24 Dec 07
Posts: 1947
Credit: 240,884,648
RAC: 0
Message 41410 - Posted: 12 Aug 2010, 9:53:00 UTC - in response to Message 41407.  

OK -- so could we PLEASE get some feedback from folks at the project as to what is going (or not going) on?

One thing more troublesome than outages is outages in a vacuum.

Erm..front page.
ID: 41410 · Rating: 0 · rate: Rate + / Rate - Report as offensive
John Clark

Send message
Joined: 4 Oct 08
Posts: 1734
Credit: 64,228,409
RAC: 0
Message 41529 - Posted: 17 Aug 2010, 11:49:19 UTC
Last modified: 17 Aug 2010, 12:28:37 UTC

Now the Server Status page is beginning to look ominous regarding another validatior backing up problem.

When all is running smoothly the status page Workunits waiting for validation usually runs with between 6,250 and 6,4000 results waiting. I see the status now gives us with 12,139 waiting validation. If this continues then the whole shebang will be down again.

I have PMed Matthew as a precaution, which I hope I am wrong about.


[Edit mode on - 35 minutes after first posting this potential panic]

Thanks Matthew.

The validator is back to it's usual numbers waithing for validation.

PANIC avoided

[Edit mode off]

Go away, I was asleep


ID: 41529 · Rating: 0 · rate: Rate + / Rate - Report as offensive
Profile KWSN Checklist
Avatar

Send message
Joined: 12 Aug 08
Posts: 253
Credit: 275,593,872
RAC: 0
Message 41625 - Posted: 21 Aug 2010, 3:05:44 UTC

Knock knock!

    ID: 41625 · Rating: 0 · rate: Rate + / Rate - Report as offensive
    Profile The Gas Giant
    Avatar

    Send message
    Joined: 24 Dec 07
    Posts: 1947
    Credit: 240,884,648
    RAC: 0
    Message 41626 - Posted: 21 Aug 2010, 4:35:45 UTC
    Last modified: 21 Aug 2010, 4:36:46 UTC

    Sending scheduler request: To fetch work.
    Requesting new tasks for GPU
    Scheduler request completed: got 0 new tasks
    Message from project server: No work sent
    Message from project server: Your app_info.xml file doesn't have a version of MilkyWay@Home N-Body Simulation.

    Is N-Body the only style of work being assigned now? Or is this just a glitch in the matrix?
    ID: 41626 · Rating: 0 · rate: Rate + / Rate - Report as offensive
    Profile mdhittle*
    Avatar

    Send message
    Joined: 25 Jun 10
    Posts: 284
    Credit: 260,490,091
    RAC: 0
    Message 41627 - Posted: 21 Aug 2010, 4:50:07 UTC - in response to Message 41626.  
    Last modified: 21 Aug 2010, 4:51:09 UTC

    Sending scheduler request: To fetch work.
    Requesting new tasks for GPU
    Scheduler request completed: got 0 new tasks
    Message from project server: No work sent
    Message from project server: Your app_info.xml file doesn't have a version of MilkyWay@Home N-Body Simulation.

    Is N-Body the only style of work being assigned now? Or is this just a glitch in the matrix?


    I was getting the same thing, so I reset the project. It didn't help. The server page shows workunits available, but I am unable to get any of them.

    They could be CPU N-Body workunits. But, the validator is backed up and looks like it is about to crash, also.
    ID: 41627 · Rating: 0 · rate: Rate + / Rate - Report as offensive
    TJ

    Send message
    Joined: 12 Aug 09
    Posts: 262
    Credit: 92,631,041
    RAC: 0
    Message 41628 - Posted: 21 Aug 2010, 5:50:02 UTC

    No panic boys, it is weekend....

    Servers and validators have some days of too every now and then.
    Greetings from,
    TJ
    ID: 41628 · Rating: 0 · rate: Rate + / Rate - Report as offensive
    BarryAZ

    Send message
    Joined: 1 Sep 08
    Posts: 520
    Credit: 302,525,188
    RAC: 0
    Message 41629 - Posted: 21 Aug 2010, 6:03:16 UTC - in response to Message 41627.  

    OK -- so this problem -- which has shown up every week or so remains unresolved -- frankly, not really a surprise.

    Sending scheduler request: To fetch work.
    Requesting new tasks for GPU
    Scheduler request completed: got 0 new tasks
    Message from project server: No work sent
    Message from project server: Your app_info.xml file doesn't have a version of MilkyWay@Home N-Body Simulation.

    Is N-Body the only style of work being assigned now? Or is this just a glitch in the matrix?


    I was getting the same thing, so I reset the project. It didn't help. The server page shows workunits available, but I am unable to get any of them.

    They could be CPU N-Body workunits. But, the validator is backed up and looks like it is about to crash, also.


    ID: 41629 · Rating: 0 · rate: Rate + / Rate - Report as offensive
    John Clark

    Send message
    Joined: 4 Oct 08
    Posts: 1734
    Credit: 64,228,409
    RAC: 0
    Message 41630 - Posted: 21 Aug 2010, 7:40:30 UTC

    It's the validator again - it has backed up with 59K worth of work to knock off.
    Go away, I was asleep


    ID: 41630 · Rating: 0 · rate: Rate + / Rate - Report as offensive
    John Clark

    Send message
    Joined: 4 Oct 08
    Posts: 1734
    Credit: 64,228,409
    RAC: 0
    Message 41637 - Posted: 21 Aug 2010, 15:08:55 UTC

    Are the servers dishing up nBody work ATM?
    Go away, I was asleep


    ID: 41637 · Rating: 0 · rate: Rate + / Rate - Report as offensive
    Previous · 1 . . . 6 · 7 · 8 · 9 · 10 · 11 · 12 . . . 22 · Next

    Message boards : Number crunching : Aaargh! Server out of new work!

    ©2024 Astroinformatics Group