Panic Mode On (81) Server Problems?


log in

Advanced search

Message boards : Number crunching : Panic Mode On (81) Server Problems?

Previous · 1 . . . 15 · 16 · 17 · 18 · 19 · 20 · 21 · Next
Author Message
msattlerProject donor
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38863
Credit: 577,336,168
RAC: 522,342
United States
Message 1338884 - Posted: 16 Feb 2013, 15:28:35 UTC
Last modified: 16 Feb 2013, 15:31:22 UTC

No problemos here.
I got all 1800 tasks I can get. The kitties have been sniffing 'em out and crunching 'em down.

The chinks in the upload bandwidth on the Cricket are a little worrisome though.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

I have met a few friends in my life.
Most were cats.

Profile BMaytum
Volunteer tester
Avatar
Send message
Joined: 3 Apr 99
Posts: 98
Credit: 3,603,176
RAC: 5,256
United States
Message 1338911 - Posted: 16 Feb 2013, 17:31:20 UTC - in response to Message 1335768.
Last modified: 16 Feb 2013, 17:48:04 UTC

Bandwidth ... than useless server chatter with no results.

Yes, we need more bandwidth to fully sort comms difficulties, but Matt has proven that proper server configuration can also go a long ways toward fully utilizing what we now have.


Whatever tweaks or adjustments Matt applied recently have really IMPROVED the DL /UL /Report throughput (and now few stalls) for me, just over the hill from SSL. Prior to those tweaks, I seriously contemplated pulling my plug on SAH from so much communications frustration. Now greatly improved, I'll stick around to atleast reach my 14th SAH Anniversary in April.

Kudos MATT!
____________
Sabertooth Z77, i7-3770K@4.2GHz, GTX680, W8.1Pro x64
P5N32-E SLI, C2D E8400@3Ghz, GTX580, Win7SP1Pro x64 & PCLinuxOS2014 x86

Cosmic_Ocean
Avatar
Send message
Joined: 23 Dec 00
Posts: 2245
Credit: 8,584,096
RAC: 4,165
United States
Message 1338921 - Posted: 16 Feb 2013, 18:21:35 UTC

My comms are doing fairly well, too. Every now and then I need to use a proxy to push the AP downloads along, but usually just 3-5 re-tries without a proxy and they'll go all the way through.

My single-core machine oddly doesn't have that issue at all. In BOINC Land, nothing ever makes sense, and nothing is predictable.
____________

Linux laptop uptime: 1484d 22h 42m
Ended due to UPS failure, found 14 hours after the fact

Profile ivan
Volunteer tester
Avatar
Send message
Joined: 5 Mar 01
Posts: 600
Credit: 135,105,094
RAC: 123,986
United Kingdom
Message 1338976 - Posted: 16 Feb 2013, 23:01:28 UTC - in response to Message 1338921.

I thought I had a way to fix the bandwidth problem this morning -- National Lottery sent me a message saying, "We've good news about your ticket in last night's Euromillions draw!" Alas, it was only £5, not £500,000...
____________

Profile KWSN Ekky Ekky Ekky
Avatar
Send message
Joined: 25 May 99
Posts: 922
Credit: 11,332,972
RAC: 13,032
United Kingdom
Message 1339044 - Posted: 17 Feb 2013, 1:27:10 UTC
Last modified: 17 Feb 2013, 1:30:27 UTC

The curious Cricket blue line hiccups continue:
http://fragment1.berkeley.edu/newcricket/grapher.cgi?target=%2Frouter-interfaces%2Finr-250%2Fgigabitethernet2_3;view=Octets;ranges=d%3Aw
I wonder if this a symptom of a problem or whatever was done to cure the greater difficulties?
Looks like another downward cycle is starting at present.
____________

msattlerProject donor
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38863
Credit: 577,336,168
RAC: 522,342
United States
Message 1339079 - Posted: 17 Feb 2013, 5:40:18 UTC - in response to Message 1339044.

The curious Cricket blue line hiccups continue:
http://fragment1.berkeley.edu/newcricket/grapher.cgi?target=%2Frouter-interfaces%2Finr-250%2Fgigabitethernet2_3;view=Octets;ranges=d%3Aw
I wonder if this a symptom of a problem or whatever was done to cure the greater difficulties?
Looks like another downward cycle is starting at present.

Might be a bit wonky, but so far the rigs seem to be able to keep the work flowing.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

I have met a few friends in my life.
Most were cats.

ExchangeMan
Volunteer tester
Send message
Joined: 9 Jan 00
Posts: 108
Credit: 131,378,654
RAC: 210,869
United States
Message 1339083 - Posted: 17 Feb 2013, 5:58:22 UTC - in response to Message 1339079.

The curious Cricket blue line hiccups continue:
http://fragment1.berkeley.edu/newcricket/grapher.cgi?target=%2Frouter-interfaces%2Finr-250%2Fgigabitethernet2_3;view=Octets;ranges=d%3Aw
I wonder if this a symptom of a problem or whatever was done to cure the greater difficulties?
Looks like another downward cycle is starting at present.

Might be a bit wonky, but so far the rigs seem to be able to keep the work flowing.

Acting a little wierd here too. Been able to keep going with some manual intervention.

____________

mramakers
Send message
Joined: 20 Jul 04
Posts: 22
Credit: 2,824,284
RAC: 0
Netherlands
Message 1339092 - Posted: 17 Feb 2013, 8:23:53 UTC - in response to Message 1338844.

And it's weekend again. Scheduler request failing time after time.

I guess I was a bit quick to start whining yersterday, because it seems it was only a glitch. Everything is working perfect ever since.
-Keeping fingers crossed-
____________

Profile TRuEQ & TuVaLu
Volunteer tester
Avatar
Send message
Joined: 4 Oct 99
Posts: 464
Credit: 17,829,174
RAC: 3,545
Sweden
Message 1339095 - Posted: 17 Feb 2013, 8:34:37 UTC

Well, my problem seems to be solved.

I have uppgraded to BM beta 7.0.4+ and now getting a funny answer in messages when requesting new work.

2013-02-17 09:29:52 | Moo! Wrapper | Not requesting tasks: don't need
The same goes for SETI tasks and if tasks are in transfer it doesn't ask for more either.... and with alot of stalled transfers...


And work cache is set to 3+1 days and i only have a cue of 2-3 hours....

I hope they are working on this.
I made a thread in Boinc Forum about it

http://boinc.berkeley.edu/dev/forum_thread.php?id=8196&sort=6

I hope they can sort it out.

msattlerProject donor
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38863
Credit: 577,336,168
RAC: 522,342
United States
Message 1339386 - Posted: 19 Feb 2013, 16:08:52 UTC

Well, here we are back after a most unusual outage. Even though the web server went down, the project servers kept going and work continued to flow. Sometimes, it's quite the opposite, LOL.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

I have met a few friends in my life.
Most were cats.

Profile Fred E.Project donor
Volunteer tester
Send message
Joined: 22 Jul 99
Posts: 768
Credit: 24,139,004
RAC: 233
United States
Message 1339387 - Posted: 19 Feb 2013, 16:17:57 UTC

Yes, the project ran well without our gripes and panic posts. Wonder if.... Guess it is time for the usual maintenance window, and I got so many astropulse tasks during the blackout I can make it thru maintenance.

Hope to hear more about the cause of the web server downtime.
____________
Another Fred
Support SETI@home when you search the Web with GoodSearch or shop online with GoodShop.

msattlerProject donor
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38863
Credit: 577,336,168
RAC: 522,342
United States
Message 1339390 - Posted: 19 Feb 2013, 16:20:57 UTC - in response to Message 1339387.

Yes, the project ran well without our gripes and panic posts. Wonder if.... Guess it is time for the usual maintenance window, and I got so many astropulse tasks during the blackout I can make it thru maintenance.

Hope to hear more about the cause of the web server downtime.

Don't know the exact reason it happened, but thinman, the web server, crashed and could not be rebooted by remote. Eric tried. And since yesterday was a campus holiday due to Presidents' Day, nobody was in the lab to restart it.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

I have met a few friends in my life.
Most were cats.

Profile [seti.international] Dirk SadowskiProject donor
Volunteer tester
Avatar
Send message
Joined: 6 Apr 07
Posts: 7056
Credit: 59,947,597
RAC: 22,004
Germany
Message 1339502 - Posted: 20 Feb 2013, 1:17:30 UTC
Last modified: 20 Feb 2013, 1:21:33 UTC

Maybe if you didn't saw it already on the 1st page: http://setiathome.berkeley.edu.


Lab-wide Power Outage This Weekend (Feb 22-24)
Once again we are going offline due to electrical repairs in our entire building. We plan to come down Friday afternoon (15:00 local time) and be back up by Sunday afternoon (12:00 local time). All SETI servers will be unreachable during that span. 19 Feb 2013, 23:58:59 UTC


IIRC, the SAH lab is UTC -08:00.
This mean currently Germany is 9 hours before ..
This would mean Saturday 00:00 to Sunday 21:00 (MET).


* Best regards! :-) * Philip J. Fry formerly Sutaru Tsureku, team seti.international founder. * Optimize your PC for higher RAC. * SETI@home needs your help. *
____________
BR



>Das Deutsche Cafe. The German Cafe.<

Cosmic_Ocean
Avatar
Send message
Joined: 23 Dec 00
Posts: 2245
Credit: 8,584,096
RAC: 4,165
United States
Message 1339822 - Posted: 20 Feb 2013, 21:03:52 UTC

That's cool. My first time ever getting this..

2013-02-20 13:20:06 SETI@home Message from server: This computer has reached a limit on tasks in progress


I was stock-piling for this weekend's outage and I found a proxy that works pretty well for AP DLs.. so I changed from 50% of CPU cores to 100% for an hour or so and then switched back when I got to the limit. I'm good for about 17 days now.
____________

Linux laptop uptime: 1484d 22h 42m
Ended due to UPS failure, found 14 hours after the fact

Rolf
Send message
Joined: 16 Jun 09
Posts: 114
Credit: 7,816,984
RAC: 151
Switzerland
Message 1339858 - Posted: 20 Feb 2013, 22:18:05 UTC - in response to Message 1339502.

Maybe if you didn't saw it already on the 1st page: http://setiathome.berkeley.edu.


Lab-wide Power Outage This Weekend (Feb 22-24)
Once again we are going offline due to electrical repairs in our entire building. We plan to come down Friday afternoon (15:00 local time) and be back up by Sunday afternoon (12:00 local time). All SETI servers will be unreachable during that span. 19 Feb 2013, 23:58:59 UTC


IIRC, the SAH lab is UTC -08:00.
This mean currently Germany is 9 hours before ..
This would mean Saturday 00:00 to Sunday 21:00 (MET).


Why not increase the limits for this special occasion? Double?

bill
Send message
Joined: 16 Jun 99
Posts: 859
Credit: 22,917,942
RAC: 21,724
United States
Message 1339865 - Posted: 20 Feb 2013, 22:55:26 UTC - in response to Message 1339858.

"Why not increase the limits for this special occasion?"

For the same reason they were installed in the first place.

N9JFE David SProject donor
Volunteer tester
Avatar
Send message
Joined: 4 Oct 99
Posts: 11150
Credit: 13,922,185
RAC: 12,706
United States
Message 1339907 - Posted: 21 Feb 2013, 17:28:49 UTC

Well, it looks like we're back from whatever partial outage we had last night.

Anybody get any details of what happened from one of the guys?

____________
David
Sitting on my butt while others boldly go,
Waiting for a message from a small furry creature from Alpha Centauri.


Profile arkaynProject donor
Volunteer tester
Avatar
Send message
Joined: 14 May 99
Posts: 3622
Credit: 48,529,160
RAC: 37,383
United States
Message 1339911 - Posted: 21 Feb 2013, 17:40:05 UTC - in response to Message 1339907.

Well, it looks like we're back from whatever partial outage we had last night.

Anybody get any details of what happened from one of the guys?


Korpela wrote:
Yep, it looks like thinman is down and bruno is hung. Unfortunately
this happened about half an hour after I left work.

____________

msattlerProject donor
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38863
Credit: 577,336,168
RAC: 522,342
United States
Message 1339917 - Posted: 21 Feb 2013, 17:59:29 UTC
Last modified: 21 Feb 2013, 18:02:52 UTC

So far, the servers have come back live and hot. All 9 rigs have reported their uploads and are receiving fresh work!
The kitties are happy campers again, and I can shut the furnace back off.

I do wish the limits could be raised to allow some increased caching for the coming weekend's scheduled outage, but the kitties are not gonna hold their breath on that one.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

I have met a few friends in my life.
Most were cats.

Profile Link
Avatar
Send message
Joined: 18 Sep 03
Posts: 827
Credit: 1,558,821
RAC: 486
Germany
Message 1339921 - Posted: 21 Feb 2013, 18:10:44 UTC - in response to Message 1339865.

"Why not increase the limits for this special occasion?"

For the same reason they were installed in the first place.

Also it would not make sense to increase it, I'm pretty sure the bandwidth will be maxed out until the planned outage, i.e. they will send out as many WUs as they can either way (and also probaly assign a lot of WUs, which can't be downloaded before they shut down).
____________
.

Previous · 1 . . . 15 · 16 · 17 · 18 · 19 · 20 · 21 · Next

Message boards : Number crunching : Panic Mode On (81) Server Problems?

Copyright © 2014 University of California