Panic Mode On (81) Server Problems?


log in

Advanced search

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

Previous · 1 . . . 14 · 15 · 16 · 17 · 18 · 19 · 20 . . . 21 · Next
Author Message
clive G1FYE
Volunteer moderator
Send message
Joined: 4 Nov 04
Posts: 1300
Credit: 23,054,144
RAC: 0
United Kingdom
Message 1337945 - Posted: 14 Feb 2013, 0:13:55 UTC

Looks like someone gave them a 24 hour pass
they deserve a day off every now and then
they have to put up with a lot of bits from all sorts of people.

Tom*
Send message
Joined: 12 Aug 11
Posts: 114
Credit: 4,798,777
RAC: 13,254
United States
Message 1338054 - Posted: 14 Feb 2013, 10:11:53 UTC - in response to Message 1335768.
Last modified: 14 Feb 2013, 10:12:36 UTC

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.


I totally agree whatever tweaks Matt made has made a huge difference in schedular comms, I still need a Proxy to download AP's but can usually do without for Sched and upload/download MB's No need to switch back and forth either as Schedular now answers fairly reliably with the shorter timeouts of my
Proxy.

Can someone please give Matt a pad of post-it notes (any color but canary yellow)
so he can leave tips in case he goes on tour :-)

Thank you again Matt

N9JFE David SProject donor
Volunteer tester
Avatar
Send message
Joined: 4 Oct 99
Posts: 11166
Credit: 13,968,930
RAC: 12,656
United States
Message 1338084 - Posted: 14 Feb 2013, 14:30:37 UTC

Yesterday, the UPS that runs one of my crunchers, the Uverse modem/router, and the radios for my radioreference.com feed, suddenly decided to take a nap. The UPS log shows nothing. It had some event 3-4 weeks ago, then it shows program start yesterday when I turned everything on. I have no idea what happened.

Anyway, the other cruncher, not on that UPS, built up quite a pile of uploads in six hours. Once it was able to reach the internet again, (and here's the point of this post) it sent them all in pretty fast. Then it reported them and asked for more, was resent 14 ghosts, and downloaded those almost as fast as the uploads. So everything was good around 1730 CST. (However, a couple hours later, I looked again and it had a couple of new downloads that were stuck.)

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


msattlerProject donor
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38925
Credit: 579,176,510
RAC: 511,450
United States
Message 1338109 - Posted: 14 Feb 2013, 16:04:55 UTC
Last modified: 14 Feb 2013, 16:05:52 UTC

Looks like Seti is not the only one that has panic modes.
Seems like Boincstats was down sometime yesterday or last night.
Was still down early this morning, but they're back now.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

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

Gone
Send message
Joined: 31 May 99
Posts: 150
Credit: 125,774,760
RAC: 8
United Kingdom
Message 1338656 - Posted: 15 Feb 2013, 23:15:36 UTC

Is it me or is the little blue line having it's traditional weekend dive ?




http://fragment1.berkeley.edu/newcricket/grapher.cgi?target=%2Frouter-interfaces%2Finr-250%2Fgigabitethernet2_3;view=Octets;ranges=d%3Aw
____________

Profile KWSN Ekky Ekky Ekky
Avatar
Send message
Joined: 25 May 99
Posts: 922
Credit: 11,382,996
RAC: 13,107
United Kingdom
Message 1338660 - Posted: 15 Feb 2013, 23:27:10 UTC - in response to Message 1338656.

[quote]Is it me or is the little blue line having it's traditional weekend dive ?

Yep - don't let the team head for them thar hills until it comes back up again!



____________

Gone
Send message
Joined: 31 May 99
Posts: 150
Credit: 125,774,760
RAC: 8
United Kingdom
Message 1338665 - Posted: 15 Feb 2013, 23:39:40 UTC - in response to Message 1338660.

It seems to have done a "Dead Cat Bounce" and is on the rise again......
____________

Iona
Avatar
Send message
Joined: 12 Jul 07
Posts: 551
Credit: 2,776,041
RAC: 2,480
United Kingdom
Message 1338745 - Posted: 16 Feb 2013, 4:25:12 UTC

Uh-oh.....35 minutes trying to report, so far.



____________
Don't take life too seriously, as you'll never come out of it alive!

ExchangeMan
Volunteer tester
Send message
Joined: 9 Jan 00
Posts: 108
Credit: 132,200,534
RAC: 213,283
United States
Message 1338751 - Posted: 16 Feb 2013, 4:32:05 UTC - in response to Message 1338745.

Uh-oh.....35 minutes trying to report, so far.



I've noticed some problems too...

____________

msattlerProject donor
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38925
Credit: 579,176,510
RAC: 511,450
United States
Message 1338767 - Posted: 16 Feb 2013, 5:16:35 UTC
Last modified: 16 Feb 2013, 5:17:10 UTC

It dipped, but came back up.

I still have almost 1800 WUs stored......all I can get. And that's with 9 crunchers online.

S U X
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

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

Profile KWSN Ekky Ekky Ekky
Avatar
Send message
Joined: 25 May 99
Posts: 922
Credit: 11,382,996
RAC: 13,107
United Kingdom
Message 1338819 - Posted: 16 Feb 2013, 8:42:35 UTC - in response to Message 1338767.
Last modified: 16 Feb 2013, 8:48:56 UTC

It dipped, but came back up.

Interesting, these dips.
In fact the blue line seems to be suffering from hiccups, judging by the last few hours.
http://fragment1.berkeley.edu/newcricket/grapher.cgi?target=%2Frouter-interfaces%2Finr-250%2Fgigabitethernet2_3;view=Octets;ranges=d%3Aw[/quote]
[Edit]Yep, there it goes down again. Question is, will it come back up as well?[End Edit]
____________

rob smithProject donor
Volunteer tester
Send message
Joined: 7 Mar 03
Posts: 8315
Credit: 55,331,716
RAC: 75,495
United Kingdom
Message 1338825 - Posted: 16 Feb 2013, 9:03:41 UTC

Yellow fluff alert!!!!

One of those dips is active....
____________
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?

juan BFBProject donor
Volunteer tester
Avatar
Send message
Joined: 16 Mar 07
Posts: 5230
Credit: 285,574,266
RAC: 461,090
Brazil
Message 1338827 - Posted: 16 Feb 2013, 9:10:06 UTC
Last modified: 16 Feb 2013, 9:30:52 UTC

The the blue line of the cricket is falling again...

Prepare for the new "normal weekend msg": project servers may be temporarily down.
____________

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8466
Credit: 48,997,733
RAC: 73,556
United Kingdom
Message 1338833 - Posted: 16 Feb 2013, 9:25:54 UTC - in response to Message 1338827.

The teh blue line of the cricket is falling again...

Prepare for the new "normal weekend msg": project servers may be temporarily down.

Agreed. One of my hosts got through about ten minutes ago, with a few to report, and got 15 new ones in return. So far, so normal.

But the 'sent' time in the database looks like this:

9:08:15
9:08:13
9:08:11
9:08:10
9:08:07
9:08:05
9:08:04
9:08:02
9:07:59
9:07:57
9:07:55
9:07:55
9:07:54
9:07:52
9:07:49

Normally, all the tasks in a batch have the same timestamp, or maybe there's a difference of one second. Now, it seems to be taking two seconds per task. That's one sick database.

All tasks for computer 6910484

juan BFBProject donor
Volunteer tester
Avatar
Send message
Joined: 16 Mar 07
Posts: 5230
Credit: 285,574,266
RAC: 461,090
Brazil
Message 1338836 - Posted: 16 Feb 2013, 9:34:13 UTC
Last modified: 16 Feb 2013, 9:37:35 UTC

Looks like Blue line rise again, Maybe a servers hipcup? or the watchdog awake?

It´s working now. But if you see the graph with atention, on the last 12 hours, each some time the line drops for few minutes and rise again, that´s is not normal.
____________

mramakers
Send message
Joined: 20 Jul 04
Posts: 22
Credit: 2,824,284
RAC: 0
Netherlands
Message 1338844 - Posted: 16 Feb 2013, 11:13:45 UTC
Last modified: 16 Feb 2013, 11:19:33 UTC

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

-Offtopic- How is it possible that some people have a 200 WU cache, while mine is 100 max? I,ve tried different numbers for work and additional work cache, but it doesn't seem to make a difference. I,ve searched the forum, but i could not find any topic about the subject. Is it because I do GPU work only?
____________

Profile MikeProject donor
Volunteer tester
Avatar
Send message
Joined: 17 Feb 01
Posts: 23820
Credit: 32,646,044
RAC: 23,438
Germany
Message 1338846 - Posted: 16 Feb 2013, 11:24:38 UTC - in response to Message 1338844.

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

-Offtopic- How is it possible that some people have a 200 WU cache, while mine is 100 max? I,ve tried different numbers for work and additional work cache, but it doesn't seem to make a difference. I,ve searched the forum, but i could not find any topic about the subject. Is it because I do GPU work only?


Yes.

You can get 100 for CPU plus 100 for GPU.

____________

mramakers
Send message
Joined: 20 Jul 04
Posts: 22
Credit: 2,824,284
RAC: 0
Netherlands
Message 1338847 - Posted: 16 Feb 2013, 11:31:41 UTC - in response to Message 1338846.
Last modified: 16 Feb 2013, 11:31:54 UTC

Thank you.
____________

Profile TRuEQ & TuVaLu
Volunteer tester
Avatar
Send message
Joined: 4 Oct 99
Posts: 469
Credit: 17,846,088
RAC: 3,877
Sweden
Message 1338858 - Posted: 16 Feb 2013, 12:38:18 UTC
Last modified: 16 Feb 2013, 12:43:29 UTC

I've got me a few ap wu's yesterday and today.
A bit of better speed now...about 6-8Kb when it downloads.
Still stalled transfers and server backoffs but not as frequent as before.

And woops we have 16Kb a sec again.

and raising to 24KB a sec

cricket please.....don't move

Profile TRuEQ & TuVaLu
Volunteer tester
Avatar
Send message
Joined: 4 Oct 99
Posts: 469
Credit: 17,846,088
RAC: 3,877
Sweden
Message 1338881 - Posted: 16 Feb 2013, 15:18:29 UTC
Last modified: 16 Feb 2013, 15:18:53 UTC

Now I got me some intresting respons.

2013-02-16 16:16:25 | SETI@home | update requested by user
2013-02-16 16:16:25 | SETI@home | Temporarily failed download of ap_08dc12af_B6_P1_00376_20130216_14751.wu: transient HTTP error
2013-02-16 16:16:25 | SETI@home | Backing off 29 min 29 sec on download of ap_08dc12af_B6_P1_00376_20130216_14751.wu
2013-02-16 16:16:25 | SETI@home | Started download of ap_03ja13ad_B6_P0_00340_20130210_27913.wu
2013-02-16 16:16:27 | SETI@home | Sending scheduler request: Requested by user.
2013-02-16 16:16:27 | SETI@home | Not requesting tasks: some download is stalled
2013-02-16 16:16:36 | SETI@home | Scheduler request completed
2013-02-16 16:16:39 | | Project communication failed: attempting access to reference site
2013-02-16 16:16:41 | | Internet access OK - project servers may be temporarily down.


I am not even try to figure this out....

Previous · 1 . . . 14 · 15 · 16 · 17 · 18 · 19 · 20 . . . 21 · Next

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

Copyright © 2014 University of California