Panic Mode On (28) Server problems

Message boards : Number crunching : Panic Mode On (28) Server problems
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 8 · 9 · 10 · 11 · 12 · 13 · 14 . . . 15 · Next

AuthorMessage
Profile John Fluth

Send message
Joined: 6 Oct 99
Posts: 22
Credit: 164,030,648
RAC: 153
United States
Message 971042 - Posted: 18 Feb 2010, 1:57:47 UTC

Able to submit some tasks about five minutes ago. Did not receive any tasks.
ID: 971042 · Report as offensive
Profile Pappa
Volunteer tester
Avatar

Send message
Joined: 9 Jan 00
Posts: 2562
Credit: 12,301,681
RAC: 0
United States
Message 971068 - Posted: 18 Feb 2010, 3:26:50 UTC

This recovery will take a while! Go read the Tech News!

All things considered it is doing okay.

Regards


Please consider a Donation to the Seti Project.

ID: 971068 · Report as offensive
1mp0£173
Volunteer tester

Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 971084 - Posted: 18 Feb 2010, 4:26:40 UTC - in response to Message 971006.  

I gave up on SETI when I ran out of tasks and turned everything over to Collatz. I normally only run Collatz in the GPU on my iMac since SETI won't provide GPU tasks. I just shut the HP down until I see transfers working again.

There are lots of things we can complain about, like a lack of funding, servers running at high loads, and while I don't think that's justified (you may be upset about a lack of uploads, but BOINC doesn't care), I can understand it.

... but if you have to blame someone, the A/C is maintained by campus facilities, not SETI@Home.

Besides, if you add a project (instead of "giving up") and just let BOINC manage it through resource shares, life will be good.
ID: 971084 · Report as offensive
Profile Pappa
Volunteer tester
Avatar

Send message
Joined: 9 Jan 00
Posts: 2562
Credit: 12,301,681
RAC: 0
United States
Message 971092 - Posted: 18 Feb 2010, 4:51:51 UTC
Last modified: 18 Feb 2010, 4:52:50 UTC

As near as I can "GUESS" there are roughly 1.4+ million results to upload (28+ hours of outage for MB and AP). Or try stuffing about 200 pounds of cooked spagetti in your mouth and swallowing it in a couple of hours (that could cause a PANIC).

Looking at my Logs, the scheduler is still having issues. So while it appears there is work. "Little" is getting out. I did have one machine that "did" manage to get a request through and it got work. That was while I was out in the yard doing things. Go figure, I did not have to push buttons. Boinc worked just as it supposed to.

I suspect that before someone goes to bed to night something will turn on (be restarted) and in the morning things will look brighter.

So yes, "offically" my one day cache failed me. Although I do have other projects that are keeping things warm. This messes up the numbers I have been collecting for a months now for Pendings and RAC. Over the next week or so, they will show the dip and increase...

Patience, as things are sorted.

Regards

I forgot, somewhere in all this I am not Panic'd (I know I am sipposed to be). I am conecerned...

Regards
Please consider a Donation to the Seti Project.

ID: 971092 · Report as offensive
Rasputin
Volunteer tester

Send message
Joined: 13 Jun 02
Posts: 1764
Credit: 6,132,221
RAC: 0
Russia
Message 971101 - Posted: 18 Feb 2010, 5:32:28 UTC

I've read the technical news and it still doesn't explain why some of us haven't been able to connect to the servers since early monday.

Ok, that's not totally correct. I managed to upload half of two different wu's today. LOL Only several hundred more to go.

I think (based on what some people have said here) that there is a problem with Berkeley's internet service.




ID: 971101 · Report as offensive
Rick
Avatar

Send message
Joined: 3 Dec 99
Posts: 79
Credit: 11,486,227
RAC: 0
United States
Message 971111 - Posted: 18 Feb 2010, 6:51:50 UTC

Seem to be getting connected to the scheduler now but just getting "Project has no jobs available"
ID: 971111 · Report as offensive
Profile [B^S] madmac
Volunteer tester
Avatar

Send message
Joined: 9 Feb 04
Posts: 1175
Credit: 4,754,897
RAC: 0
United Kingdom
Message 971118 - Posted: 18 Feb 2010, 7:41:13 UTC

I am getting http errors which means a server going wrong I think this morning. So I will just sit and wait and see if my uploads go up on both my machines. Just got a new one a couple of months ago, so that has a few to upload this one I am typing on has 6 waiting to upload
ID: 971118 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51511
Credit: 1,018,363,574
RAC: 1,004
United States
Message 971119 - Posted: 18 Feb 2010, 7:41:22 UTC
Last modified: 18 Feb 2010, 7:43:43 UTC

I am getting almost nothing but HTTP errors on upload attempts...a few do manage to make it, but very few.
And 'scheduler request failed, couldn't connect to server' when attempting to report those uploads that did squeak through.

Something is obviously still very wrong here....and this problem is happening on all of my rigs.
"Time is simply the mechanism that keeps everything from happening all at once."

ID: 971119 · Report as offensive
_heinz
Volunteer tester

Send message
Joined: 25 Feb 05
Posts: 744
Credit: 5,539,270
RAC: 0
France
Message 971123 - Posted: 18 Feb 2010, 7:52:48 UTC

hi,
the same from here, cant no upload work
18.02.2010 08:51:05 SETI@home Started upload of 15fe07ac.10146.290720.11.10.4_0_0
18.02.2010 08:51:26 SETI@home Temporarily failed upload of 15fe07ac.10146.290720.11.10.4_0_0: HTTP error
18.02.2010 08:51:26 SETI@home Backing off 44 min 32 sec on upload of 15fe07ac.10146.290720.11.10.4_0_0

D5400XS V8-Xeon
ID: 971123 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51511
Credit: 1,018,363,574
RAC: 1,004
United States
Message 971125 - Posted: 18 Feb 2010, 7:55:55 UTC - in response to Message 971123.  
Last modified: 18 Feb 2010, 7:56:09 UTC

hi,
the same from here, cant no upload work
18.02.2010 08:51:05 SETI@home Started upload of 15fe07ac.10146.290720.11.10.4_0_0
18.02.2010 08:51:26 SETI@home Temporarily failed upload of 15fe07ac.10146.290720.11.10.4_0_0: HTTP error
18.02.2010 08:51:26 SETI@home Backing off 44 min 32 sec on upload of 15fe07ac.10146.290720.11.10.4_0_0

And yet, the Cricket graphs show total bandwidth at a very lazy pace....does not make sense to me. Have never seen quite this scenario that I can remember.

These kinds of comms problems are usually seen when the bandwidth is saturated.

Maybe it will get sorted tomorrow. Until then, I got two of my prime rigs with no Cuda work. Sigh.
"Time is simply the mechanism that keeps everything from happening all at once."

ID: 971125 · Report as offensive
Profile Fred J. Verster
Volunteer tester
Avatar

Send message
Joined: 21 Apr 04
Posts: 3252
Credit: 31,903,643
RAC: 0
Netherlands
Message 971142 - Posted: 18 Feb 2010, 9:35:53 UTC - in response to Message 971125.  

Hi, still got a day, I guess, of work for SETI, but also can't upload about 100 task's.
Probably a good time, to clean out the dust in all rig's and reseat a heatsink which doesn't make much contact with the CPU, as it get's too hot (96C) and only has a mild (10%) OC.
BOINC doesn't even try to UPLoad, since yesterday!

ID: 971142 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51511
Credit: 1,018,363,574
RAC: 1,004
United States
Message 971143 - Posted: 18 Feb 2010, 9:41:14 UTC
Last modified: 18 Feb 2010, 9:43:21 UTC

I still wish answers as to just WTF is going on.......

Seti server problems, or external inet comms problems.

These have both bean postulated, but not answered.
"Time is simply the mechanism that keeps everything from happening all at once."

ID: 971143 · Report as offensive
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14687
Credit: 200,643,578
RAC: 874
United Kingdom
Message 971146 - Posted: 18 Feb 2010, 9:50:17 UTC - in response to Message 971068.  

Pappa wrote:

This recovery will take a while! Go read the Tech News!

All things considered it is doing okay.

Regards

No it isn't.

The sequence was:

1) Uploads stopped (problem with HTTP service on Bruno)
2) Regular backup/compression maintenance
3) A/C failure

They've dealt with (3): (2) is history, as it always is by the following day: but reading Matt's posts, I honestly don't think he's noticed (1) yet. First day back after vacation, everything showing green on the monitors, just enough uploads trickling in to make it look like a normal/quiet day.

I'm running a very lean mix at the moment, for testing. CUDA cards switched to GPUGrid ages ago, and even big steady old Octo has finished the 2-day CPU cache. So all I'm doing at the moment is grinding through a backlog of rebranded VLARs on CPUs. But I've still got 303 uploads waiting to go through - about 20 more than when I went to bed last night.

If the uploader can't even keep up with CPU production, it's broken: I tried to say as much in Technical News last night, but it got buried in an avalanche of 15-year old UPSs. Somebody else can try using back-channels to attract attention if they want.
ID: 971146 · Report as offensive
Dave

Send message
Joined: 29 Mar 02
Posts: 778
Credit: 25,001,396
RAC: 0
United Kingdom
Message 971147 - Posted: 18 Feb 2010, 9:53:29 UTC

I'm out of work on this main machine for the 1st time since I started 6 mnths ago. Secondary machine has about an hour of work to go.
ID: 971147 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51511
Credit: 1,018,363,574
RAC: 1,004
United States
Message 971148 - Posted: 18 Feb 2010, 9:54:06 UTC
Last modified: 18 Feb 2010, 9:56:13 UTC

There is a basic comms problem going on here..........

It may be within Seti, it may be not.


All I know, is it is starting to piss me off. LOL.
"Time is simply the mechanism that keeps everything from happening all at once."

ID: 971148 · Report as offensive
PhonAcq

Send message
Joined: 14 Apr 01
Posts: 1656
Credit: 30,658,217
RAC: 1
United States
Message 971162 - Posted: 18 Feb 2010, 12:51:14 UTC

Monitoring my upload process, I see a very few making it through at present. What is frustrating is that I see a lot that get as far as 100% uploaded to be subsequently rejected and queued up to try again. The last bit of handshaking fails and causes the system to repeat work (upload) that appears to have been completed. This is not an new observation.

Because it obviously takes bandwidth and server resources to execute this type of failure, and because the behavior has been around 'forever', has any effort been made to remedy it? (Doning manager hat: If not why not?!)
ID: 971162 · Report as offensive
Profile the silver surfer
Avatar

Send message
Joined: 24 Feb 01
Posts: 131
Credit: 3,739,307
RAC: 0
Austria
Message 971164 - Posted: 18 Feb 2010, 12:57:40 UTC - in response to Message 971142.  

Hi, still got a day, I guess, of work for SETI, but also can't upload about 100 task's.
Probably a good time, to clean out the dust in all rig's and reseat a heatsink which doesn't make much contact with the CPU, as it get's too hot (96C) and only has a mild (10%) OC.
BOINC doesn't even try to UPLoad, since yesterday!



Hi Fred,

To be correct, it isn`t BOINC, it`s SETI. I`m on some other projects right now,
and uploads/downloads are doing just fine.

All the best !

Kurt

ID: 971164 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51511
Credit: 1,018,363,574
RAC: 1,004
United States
Message 971165 - Posted: 18 Feb 2010, 13:00:14 UTC - in response to Message 971162.  
Last modified: 18 Feb 2010, 13:33:09 UTC

Monitoring my upload process, I see a very few making it through at present. What is frustrating is that I see a lot that get as far as 100% uploaded to be subsequently rejected and queued up to try again. The last bit of handshaking fails and causes the system to repeat work (upload) that appears to have been completed. This is not an new observation.

Because it obviously takes bandwidth and server resources to execute this type of failure, and because the behavior has been around 'forever', has any effort been made to remedy it? (Doning manager hat: If not why not?!)

All comms are wrecked here for now too.......
[rant]This is rather frustrating, as no acknowledgment has been made of the problem as of yet.......so I don't know WTF is going on. Nothing is happening on Cricket, nor the server status page to give a clue...
WHERE ARE THE FISH?????[/rant]
"Time is simply the mechanism that keeps everything from happening all at once."

ID: 971165 · Report as offensive
Profile Bill Walker
Avatar

Send message
Joined: 4 Sep 99
Posts: 3868
Credit: 2,697,267
RAC: 0
Canada
Message 971171 - Posted: 18 Feb 2010, 13:29:43 UTC

I'm actually out of SETI work, for the first time in months.

Uploaded 5 out of 8 completed WUs overnight, oldest of these these have been trying to transfer for about 48 hours. No downloads, messages like this:

18/02/2010 8:26:04 AM|SETI@home|Sending scheduler request: Requested by user. Requesting 259200 seconds of work, reporting 1 completed tasks
18/02/2010 8:26:26 AM||Project communication failed: attempting access to reference site
18/02/2010 8:26:27 AM||Internet access OK - project servers may be temporarily down.
18/02/2010 8:26:29 AM|SETI@home|Scheduler request failed: Couldn't connect to server

Cricket graphs appear virtually dead. Definitely a communications problem somewhere....

Fortunately all my other projects are running nicely.

ID: 971171 · Report as offensive
Profile ccappel
Avatar

Send message
Joined: 27 Jan 00
Posts: 362
Credit: 1,516,412
RAC: 0
United States
Message 971176 - Posted: 18 Feb 2010, 13:40:28 UTC

After many many retry attempts (automatic, not manual), I finally have all my uploads completed and tasks reported. Haven't downloaded anything for a while, but thank god for the 10 day cache. Considering myself lucky.
"Life is a tragedy for those who feel, and a comedy for those who think."

"I never get into an argument that I cannot win."
ID: 971176 · Report as offensive
Previous · 1 . . . 8 · 9 · 10 · 11 · 12 · 13 · 14 . . . 15 · Next

Message boards : Number crunching : Panic Mode On (28) Server problems


 
©2025 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.