Panic Mode On (46) Server problems


log in

Advanced search

Message boards : Number crunching : Panic Mode On (46) Server problems

Previous · 1 · 2 · 3 · 4 · 5 · 6 . . . 12 · Next
Author Message
Profile Cliff Harding
Volunteer tester
Avatar
Send message
Joined: 18 Aug 99
Posts: 826
Credit: 46,573,912
RAC: 13,664
United States
Message 1093284 - Posted: 4 Apr 2011, 10:45:47 UTC

The d/l server VADER has been in trouble all weekend. I think they attempted to get it going late Friday - early Saturday and it lasted a short time. If you look at the server page you will notice that it was disabled by the staff. I suspect that they will take care of it as soon as someone comes in later this morning.

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 3582
Credit: 98,443,257
RAC: 78,507
United States
Message 1093312 - Posted: 4 Apr 2011, 13:03:59 UTC - in response to Message 1093278.

I do enjoy still using a pre-GPU build of BOINC. Max back-off is 3:59:59.. or so I've observed. Unless the scheduler specifically responds with a different back-off. A couple weeks ago with that extended downtime for..something, I hadn't turned network communications off yet, and saw "scheduler request pending, waiting 18:xx:xx". So it can still happen for scheduler contacts, but not for failed transfers..those max out at 4 hours.

I like in the version I'm running, 6.10.48, where I'll see tasks downloading & then (project back-off 00:30:00) shows up next to them while still downloading. Once one of the downloading tasks finishes the back-off goes away. It just amuses me to see it do that. I would use .58, but I have problems connecting to remote machines with the manager on my work network.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Profile Fred J. Verster
Volunteer tester
Avatar
Send message
Joined: 21 Apr 04
Posts: 3232
Credit: 31,585,541
RAC: 0
Netherlands
Message 1093354 - Posted: 4 Apr 2011, 16:03:40 UTC - in response to Message 1093312.
Last modified: 4 Apr 2011, 16:40:41 UTC


BOINC replica database jocelyn Disabled
download server 2 vader Disabled
ap_splitter1 vader Not Running
ap_splitter2 lando Not Running
ap_splitter3 lando Not Running, as of 4 Apr 2011 | 15:50:06 UTC



UP- & DOWN-Loads, do get though, most of the time.

4-4-2011 13:36:04 SETI@home Started upload of 18fe11ac.29560.19699.4.10.64_1_0
4-4-2011 13:36:05 SETI@home Started download of 18fe11ab.12264.8656.11.10.114
4-4-2011 13:36:06 SETI@home Temporarily failed download of 18fe11ab.12264.8656.11.10.114: HTTP error
4-4-2011 13:36:06 SETI@home Backing off 1 min 0 sec on download of 18fe11ab.12264.8656.11.10.114
4-4-2011 13:36:08 SETI@home Finished upload of 18fe11ac.29560.19699.4.10.64_1_0
4-4-2011 13:37:06 SETI@home Started download of 18fe11ab.12264.8656.11.10.114
4-4-2011 13:37:35 SETI@home Finished download of 18fe11ab.12264.8656.11.10.114
4-4-2011 15:21:58 SETI@home Reporting 1 completed tasks, requesting new tasks
4-4-2011 15:22:03 SETI@home Scheduler request completed: got 1 new tasks
4-4-2011 15:22:05 SETI@home Finished upload of 18fe11ab.29874.4975.8.10.56_1_0
4-4-2011 15:22:05 SETI@home Started download of 18fe11ac.30016.21744.6.10.219
4-4-2011 15:23:01 Project communication failed: attempting access to reference site
4-4-2011 15:23:01 SETI@home Temporarily failed download of 18fe11ac.30016.21744.6.10.219: HTTP error
4-4-2011 15:23:01 SETI@home Backing off 1 min 0 sec on download of 18fe11ac.30016.21744.6.10.219
4-4-2011 15:23:02 Internet access OK - project servers may be temporarily down.
4-4-2011 15:24:02 SETI@home Started download of 18fe11ac.30016.21744.6.10.219
4-4-2011 15:26:12 SETI@home Finished download of 18fe11ac.30016.21744.6.10.219


The upload server bruno Running is apparently not enough,
to handle the (DDOS!?) Requests
The download server 1 anakin is Running
download server 2 vader is Disabled


By the way, this comes from my LT(T2400)
____________


Knight Who Says Ni N!, OUT numbered.................

msattler
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 37486
Credit: 502,995,506
RAC: 567,689
United States
Message 1093390 - Posted: 4 Apr 2011, 18:01:21 UTC

Both download servers now online!!
Kick 'em if you got 'em.

Meow meow.
____________
******************
Just a kittyman kinda guy.

Crunching Seti, loving all of God's kitties.

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

B-Man
Volunteer tester
Send message
Joined: 11 Feb 01
Posts: 253
Credit: 147,366
RAC: 0
United States
Message 1093423 - Posted: 4 Apr 2011, 20:31:12 UTC - in response to Message 1093390.

Both download servers now online!!
Kick 'em if you got 'em.

Meow meow.

Yep and cricket kicked it up a notch when it happened.
____________

Grant (SSSF)
Send message
Joined: 19 Aug 99
Posts: 5566
Credit: 51,634,743
RAC: 44,444
Australia
Message 1093580 - Posted: 5 Apr 2011, 10:49:09 UTC - in response to Message 1091556.
Last modified: 5 Apr 2011, 10:52:19 UTC

Network traffic has just taken a dive.
Server Status page shows plenty of tapes avaiable to split, but not much MB data is going out.

?


EDIT- got my APs & MBs mixed up.
____________
Grant
Darwin NT.

Profile Wiggo
Avatar
Send message
Joined: 24 Jan 00
Posts: 5250
Credit: 83,450,820
RAC: 73,894
Australia
Message 1093643 - Posted: 5 Apr 2011, 15:42:54 UTC - in response to Message 1093580.
Last modified: 5 Apr 2011, 15:44:22 UTC

Network traffic has just taken a dive.
Server Status page shows plenty of tapes avaiable to split, but not much MB data is going out.

?


EDIT- got my APs & MBs mixed up.

Well all I can say for the moment is that all 3 of my PC's are quite happily sated and I'd imagine that most peoples' are by this time. ;)

Cheers.
____________

msattler
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 37486
Credit: 502,995,506
RAC: 567,689
United States
Message 1093648 - Posted: 5 Apr 2011, 15:57:36 UTC - in response to Message 1093643.

Network traffic has just taken a dive.
Server Status page shows plenty of tapes avaiable to split, but not much MB data is going out.

?


EDIT- got my APs & MBs mixed up.

Well all I can say for the moment is that all 3 of my PC's are quite happily sated and I'd imagine that most peoples' are by this time. ;)

Cheers.

The kitties seem to have their kibble bowls all filled up here too.

Hopefully the outage goes well and we can settle back into a smooth workflow again.
____________
******************
Just a kittyman kinda guy.

Crunching Seti, loving all of God's kitties.

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

msattler
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 37486
Credit: 502,995,506
RAC: 567,689
United States
Message 1093740 - Posted: 6 Apr 2011, 2:30:29 UTC

I don't want to jinx things.

But was that not about the fastest recovery from an outage ever???

Bandwidth is settling down already. Checked a few of my crunchers, and they are not asking for new work, so apparently the kitty bowls are full.

This is a good thing...
____________
******************
Just a kittyman kinda guy.

Crunching Seti, loving all of God's kitties.

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

-BeNt-
Avatar
Send message
Joined: 17 Oct 99
Posts: 1234
Credit: 10,116,112
RAC: 0
United States
Message 1093799 - Posted: 6 Apr 2011, 4:43:51 UTC - in response to Message 1093740.

I don't want to jinx things.

But was that not about the fastest recovery from an outage ever???

Bandwidth is settling down already. Checked a few of my crunchers, and they are not asking for new work, so apparently the kitty bowls are full.

This is a good thing...


I'll just put it this way.....it was down? Looking sweet on my end, we're gettin' it done here.
____________
Traveling through space at ~67,000mph!

msattler
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 37486
Credit: 502,995,506
RAC: 567,689
United States
Message 1093917 - Posted: 6 Apr 2011, 15:21:46 UTC

And still lookin' my-t-fine this morning.
____________
******************
Just a kittyman kinda guy.

Crunching Seti, loving all of God's kitties.

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

Sten-Arne
Volunteer tester
Send message
Joined: 1 Nov 08
Posts: 3307
Credit: 16,462,180
RAC: 19,356
Sweden
Message 1094017 - Posted: 6 Apr 2011, 18:16:13 UTC

Whereth areth the AP unitseths? Seemeth liketh no AP unitseths areth beingeth splitteth :-)


____________

DJStarfox
Send message
Joined: 23 May 01
Posts: 1040
Credit: 527,839
RAC: 54
United States
Message 1094069 - Posted: 6 Apr 2011, 20:33:17 UTC - in response to Message 1094017.

Whereth areth the AP unitseths? Seemeth liketh no AP unitseths areth beingeth splitteth :-)


Got a couple yesterday no prob and still crunching them. Funny enough, the AP deadlines are still much earlier than some MB tasks I got, even though the AP tasks take much longer to crunch.

Profile Mike
Volunteer tester
Avatar
Send message
Joined: 17 Feb 01
Posts: 22461
Credit: 29,493,230
RAC: 25,578
Germany
Message 1094070 - Posted: 6 Apr 2011, 20:36:30 UTC

Deadline for AP units is usually 20 days.

____________

Richard Haselgrove
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8276
Credit: 45,026,903
RAC: 13,624
United Kingdom
Message 1094107 - Posted: 6 Apr 2011, 22:25:38 UTC - in response to Message 1094070.

Deadline for AP units is usually 20 days.

All the ones on your host seem to be 25 days?

Sten-Arne
Volunteer tester
Send message
Joined: 1 Nov 08
Posts: 3307
Credit: 16,462,180
RAC: 19,356
Sweden
Message 1094339 - Posted: 7 Apr 2011, 16:29:22 UTC - in response to Message 1094107.

Deadline for AP units is usually 20 days.

All the ones on your host seem to be 25 days?


All my AP tasks have a deadline of 25 days too.
____________

-BeNt-
Avatar
Send message
Joined: 17 Oct 99
Posts: 1234
Credit: 10,116,112
RAC: 0
United States
Message 1094373 - Posted: 7 Apr 2011, 18:02:00 UTC - in response to Message 1094339.

Deadline for AP units is usually 20 days.

All the ones on your host seem to be 25 days?


All my AP tasks have a deadline of 25 days too.


Same here......ew have we beat him in the ground enough yet?!
____________
Traveling through space at ~67,000mph!

Josef W. Segur
Volunteer developer
Volunteer tester
Send message
Joined: 30 Oct 99
Posts: 4143
Credit: 1,005,763
RAC: 271
United States
Message 1094744 - Posted: 8 Apr 2011, 16:07:57 UTC - in response to Message 1094373.

Deadline for AP units is usually 20 days.

All the ones on your host seem to be 25 days?


All my AP tasks have a deadline of 25 days too.


Same here......ew have we beat him in the ground enough yet?!

But the Scheduler won't send an AP task unless it estimates the host can finish it within 19.23076923 days. :-)
Joe

-BeNt-
Avatar
Send message
Joined: 17 Oct 99
Posts: 1234
Credit: 10,116,112
RAC: 0
United States
Message 1094784 - Posted: 8 Apr 2011, 17:36:32 UTC - in response to Message 1094744.


But the Scheduler won't send an AP task unless it estimates the host can finish it within 19.23076923 days. :-)
Joe


Interesting where is that number read from? Messages I take it? Needless to say though that's predicted time to crunch(or finish one, judging if you are fast enough to get one done+ 5 days of padding I would imagine) not the deadline of a work unit downloaded. If it showed you would take 19 days to get one done it would only schedule you one work unit if it should you where completing one everyday in 20 days it would send you 20. Least that's the way it reads to me, the scheduler just wants to make sure you can finish it in time, not set the time it's due.
____________
Traveling through space at ~67,000mph!

Josef W. Segur
Volunteer developer
Volunteer tester
Send message
Joined: 30 Oct 99
Posts: 4143
Credit: 1,005,763
RAC: 271
United States
Message 1094824 - Posted: 8 Apr 2011, 18:51:35 UTC - in response to Message 1094784.


But the Scheduler won't send an AP task unless it estimates the host can finish it within 19.23076923 days. :-)
Joe

Interesting where is that number read from? Messages I take it? Needless to say though that's predicted time to crunch(or finish one, judging if you are fast enough to get one done+ 5 days of padding I would imagine) not the deadline of a work unit downloaded. If it showed you would take 19 days to get one done it would only schedule you one work unit if it should you where completing one everyday in 20 days it would send you 20. Least that's the way it reads to me, the scheduler just wants to make sure you can finish it in time, not set the time it's due.

A feature added to BOINC specifically for AP causes the estimate to be multiplied by 1.3 before comparing to the delay_bound = 25*86400 set by the ap_splitter. That multiplier allows for heavily blanked tasks when the application calculates a lot of shaped noise replacement data, which can cause run time to increase by about 30%.

As you deduced that doesn't reduce the deadline, it simply affects whether the task gets sent or not. Also, the situation is seldom so simple because there are usually other tasks already on the host.
Joe

Previous · 1 · 2 · 3 · 4 · 5 · 6 . . . 12 · Next

Message boards : Number crunching : Panic Mode On (46) Server problems

Copyright © 2014 University of California