Panic Mode On (43) Server problems

Message boards : Number crunching : Panic Mode On (43) Server problems
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 11 · Next

AuthorMessage
AndrewM
Volunteer tester

Send message
Joined: 5 Jan 08
Posts: 369
Credit: 34,275,196
RAC: 0
Australia
Message 1075345 - Posted: 8 Feb 2011, 13:10:53 UTC

What do the Transitioners do? Or rather what are they not doing? How significant is 19 backlog hours?
ID: 1075345 · Report as offensive
Bounce

Send message
Joined: 3 Apr 99
Posts: 66
Credit: 5,604,569
RAC: 0
United States
Message 1075359 - Posted: 8 Feb 2011, 13:48:10 UTC

Backlogs are like warm, familiar comfortors on a cold winter night. We enjoy them and embrace them while wishing we could put them away for the rest of the season.

With all the different HDD failures, it would be interesting to see some stats (by brand) of the different drives S@H uses and their MTBF numbers.
ID: 1075359 · Report as offensive
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14679
Credit: 200,643,578
RAC: 874
United Kingdom
Message 1075365 - Posted: 8 Feb 2011, 14:26:55 UTC - in response to Message 1075359.  

Backlogs are like warm, familiar comfortors on a cold winter night. We enjoy them and embrace them while wishing we could put them away for the rest of the season.

With all the different HDD failures, it would be interesting to see some stats (by brand) of the different drives S@H uses and their MTBF numbers.

Matt has posted somewhere that they have some pretty strong views and strict buying policies, not least because of compatibility problems in the past with their motley collection of motherboards. I'll try and find the reference. In the meantime, for anyone thinking of helping out (as in another adjacent thread) - it would probably be best to wait until an exact specification (ideally, model number) has been posted, or just send earmarked cash. Given that practically everything is in some sort of RAID array, disk matching could be important.
ID: 1075365 · Report as offensive
-BeNt-
Avatar

Send message
Joined: 17 Oct 99
Posts: 1234
Credit: 10,116,112
RAC: 0
United States
Message 1075373 - Posted: 8 Feb 2011, 15:00:46 UTC - in response to Message 1075365.  


With all the different HDD failures, it would be interesting to see some stats (by brand) of the different drives S@H uses and their MTBF numbers.


Yeah it would be interesting for sure to see those numbers. Something tells me they aren't using Maxtors, Hitachi, or Samsung drives. ;)




Traveling through space at ~67,000mph!
ID: 1075373 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1075450 - Posted: 9 Feb 2011, 7:17:32 UTC - in response to Message 1075365.  
Last modified: 9 Feb 2011, 7:18:28 UTC

Backlogs are like warm, familiar comfortors on a cold winter night. We enjoy them and embrace them while wishing we could put them away for the rest of the season.

With all the different HDD failures, it would be interesting to see some stats (by brand) of the different drives S@H uses and their MTBF numbers.

Matt has posted somewhere that they have some pretty strong views and strict buying policies, not least because of compatibility problems in the past with their motley collection of motherboards. I'll try and find the reference. In the meantime, for anyone thinking of helping out (as in another adjacent thread) - it would probably be best to wait until an exact specification (ideally, model number) has been posted, or just send earmarked cash. Given that practically everything is in some sort of RAID array, disk matching could be important.

I believe my brain noodles are thinking Matt said they use Seagates, and preferably at least 750gb. SATA-II. I do not recall reading whether they are the Barracuda XT's or not. Also, the noodles are remembering that this specification is for the drives that transport the raw data from the telescope to the lab. I would imagine they probably try to use Seagate in all the servers, as well.


[edit: Also.. this makes my post count 1337. :D]
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1075450 · Report as offensive
Profile Jack Zhang
Volunteer tester
Avatar

Send message
Joined: 2 Jul 06
Posts: 206
Credit: 6,142,449
RAC: 0
Canada
Message 1075561 - Posted: 9 Feb 2011, 16:54:45 UTC

Seagates run really hot if they don't have good ventilation. Hitachis are much more reliable when it comes to their firmware. (Did you know Western Digital is just Hitachi drives rebranded?)
What if Fiction was Fact and Fact was Fiction and vice versa?
ID: 1075561 · Report as offensive
DJStarfox

Send message
Joined: 23 May 01
Posts: 1066
Credit: 1,226,053
RAC: 2
United States
Message 1075605 - Posted: 9 Feb 2011, 20:27:15 UTC

Yeah, looks like there's a few missing styles or stylesheet(s). Did they perform some kind of upgrade, or perhaps the web server crashed? No news yet.

Hope there's no file corruption causing this.
ID: 1075605 · Report as offensive
DJStarfox

Send message
Joined: 23 May 01
Posts: 1066
Credit: 1,226,053
RAC: 2
United States
Message 1075610 - Posted: 9 Feb 2011, 20:36:35 UTC

HTTP 404: http://setiathome.berkeley.edu/img/post.png

AND

Looks like a bad SVN commit:
The closing head and opening body tags in the HTML are too early. They must be moved to below the last link/stylesheet include.

        </head>
    <body>
<!-- SVN VERSIONS -->
<!-- $Id: translation.inc 21878 2010-07-06 23:31:26Z davea $ -->
<!-- $Id: pm.inc 14019 2007-11-01 23:04:39Z davea $ -->
<!-- $Id: text_transform.inc 22228 2010-08-14 01:49:08Z davea $ -->
<!-- $Id: stats_sites.inc 22859 2011-01-02 03:07:14Z davea $ -->
<!-- $Id: team.inc 22620 2010-11-03 21:48:39Z davea $ -->

<!-- $Id: user.inc 23006 2011-02-08 21:38:16Z davea $ -->
<!-- $Id: profile.inc 22993 2011-02-03 23:27:30Z davea $ -->
<!-- $Id: util.inc 23008 2011-02-09 19:10:10Z davea $ -->
<link rel="shortcut icon" href="images/logo7.ico">
	<link rel="stylesheet" type="text/css" href="white_aux.css">

ID: 1075610 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1075617 - Posted: 9 Feb 2011, 20:52:06 UTC - in response to Message 1075610.  
Last modified: 9 Feb 2011, 21:14:07 UTC

It'll be because someone's been applying some new changesets, like this one: [trac]changeset:23008[/trac]

you can tell it's been applied here because the following has changed here:

Suspend work when non-BOINC CPU usage is above
0 means no restriction
Enforced by version 6.10.30+

Claggy
ID: 1075617 · Report as offensive
Josef W. Segur
Volunteer developer
Volunteer tester

Send message
Joined: 30 Oct 99
Posts: 4504
Credit: 1,414,761
RAC: 0
United States
Message 1075636 - Posted: 9 Feb 2011, 21:39:07 UTC - in response to Message 1075450.  

Backlogs are like warm, familiar comfortors on a cold winter night. We enjoy them and embrace them while wishing we could put them away for the rest of the season.

With all the different HDD failures, it would be interesting to see some stats (by brand) of the different drives S@H uses and their MTBF numbers.

Matt has posted somewhere that they have some pretty strong views and strict buying policies, not least because of compatibility problems in the past with their motley collection of motherboards. I'll try and find the reference. In the meantime, for anyone thinking of helping out (as in another adjacent thread) - it would probably be best to wait until an exact specification (ideally, model number) has been posted, or just send earmarked cash. Given that practically everything is in some sort of RAID array, disk matching could be important.

I believe my brain noodles are thinking Matt said they use Seagates, and preferably at least 750gb. SATA-II. I do not recall reading whether they are the Barracuda XT's or not. Also, the noodles are remembering that this specification is for the drives that transport the raw data from the telescope to the lab. I would imagine they probably try to use Seagate in all the servers, as well.
...

From a newer post by Matt, for transport they're now using 2 TB drives.

Thumper and Bambi have many 500 GB drives, and Sun was supporting those (but may no longer be doing so after becoming part of Oracle?).

Oscar and Carolyn have 1 TB 3 Gb/sec SATA drives, under HP warranty. They're running with 2 root drives, 2 hot spares, and 8 drives in RAID.

Synergy has "5 Seagate Constellation 1TB 6Gb/SAS Hard Drives 7200 RPM".

Replacement drives for the Snap storage server donated by Overland Storage are provided as needed.

I don't know about Gowron, the name suggests it is at least a couple of years old. ISTR mention of the staff building up a storage server from donated components about then, probably would have been 1 TB 3 Gb/s Seagate drives if so.

The original Bruno had a fibre channel array and probably somewhat smaller drives. I'm not sure if the Bruno Back (Feb 01 2011) thread refers to that or Bambi renamed to Bruno.

All in all, I agree with Richard that waiting until Pappa gets more information makes obvious sense for those considering hardware donations. Cash donations of course are always needed, and can be earmarked for drives if you prefer. My own take is that I hope there will be enough unearmarked donations so neither Matt nor Jeff get a pink slip.
                                                                  Joe
ID: 1075636 · Report as offensive
Profile HAL9000
Volunteer tester
Avatar

Send message
Joined: 11 Sep 99
Posts: 6534
Credit: 196,805,888
RAC: 57
United States
Message 1075638 - Posted: 9 Feb 2011, 21:43:07 UTC - in response to Message 1075623.  

We're screwed. Nothing can save us now :-)

Agreed! The real question is did we want anything to actually save us? (:
SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[
ID: 1075638 · Report as offensive
Robert Ribbeck
Avatar

Send message
Joined: 7 Jun 02
Posts: 644
Credit: 5,283,174
RAC: 0
United States
Message 1075643 - Posted: 9 Feb 2011, 21:56:31 UTC
Last modified: 9 Feb 2011, 22:00:18 UTC

please sir might I have some more wu

(Sorry for abusing Oliver Twist)
ID: 1075643 · Report as offensive
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14679
Credit: 200,643,578
RAC: 874
United Kingdom
Message 1075647 - Posted: 9 Feb 2011, 22:05:46 UTC - in response to Message 1075605.  

Yeah, looks like there's a few missing styles or stylesheet(s). Did they perform some kind of upgrade, or perhaps the web server crashed? No news yet.

Hope there's no file corruption causing this.

Have a look at the AQUA message boards. There's been a recent 'new look' there, including (for the first time) icons alongside threads you've already read.

I think what we see here is a planned (but incomplete) style makeover.
ID: 1075647 · Report as offensive
Dave

Send message
Joined: 29 Mar 02
Posts: 778
Credit: 25,001,396
RAC: 0
United Kingdom
Message 1075653 - Posted: 9 Feb 2011, 22:18:22 UTC

Appear able to upload + even download. A bit.
ID: 1075653 · Report as offensive
KB7RZF
Volunteer tester
Avatar

Send message
Joined: 15 Aug 99
Posts: 9549
Credit: 3,308,926
RAC: 2
United States
Message 1075659 - Posted: 9 Feb 2011, 22:40:40 UTC

Nothing for me yet:
2/9/2011 2:37:47 PM SETI@home Sending scheduler request: To fetch work.
2/9/2011 2:37:47 PM SETI@home Requesting new tasks
2/9/2011 2:37:53 PM SETI@home Scheduler request completed: got 0 new tasks
2/9/2011 2:37:53 PM SETI@home Message from server: Project is temporarily shut down for maintenance


Probably cause of the mass pounding the servers are probably getting, cricket is probably maxed, haven't checked. No problem though, got 1 WU that was stuck trying to download for a few days thats now crunching. :-)
ID: 1075659 · Report as offensive
Dave

Send message
Joined: 29 Mar 02
Posts: 778
Credit: 25,001,396
RAC: 0
United Kingdom
Message 1075661 - Posted: 9 Feb 2011, 22:45:34 UTC
Last modified: 9 Feb 2011, 22:48:01 UTC

Cricket just coming to life, ~90% maxed.

Aha + we have new pwitty format discussed above! Isn't it nice when the cloud does it all for you ;).
ID: 1075661 · Report as offensive
AndrewM
Volunteer tester

Send message
Joined: 5 Jan 08
Posts: 369
Credit: 34,275,196
RAC: 0
Australia
Message 1075673 - Posted: 9 Feb 2011, 23:16:21 UTC

Reporting appears to be out still
ID: 1075673 · 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 1075677 - Posted: 9 Feb 2011, 23:41:56 UTC - in response to Message 1075674.  
Last modified: 9 Feb 2011, 23:50:58 UTC

Exactly, out of work, since a very long time, though, but now, not a single SETI MB or AP, yeah in DownLoad, but doesn't come through. HTTP:ERROR.

But made good use of this possebillty, to install the ATI MB & AP app,
from LUNATICs.
And on the Number Crunching Forum.
Vacuum the X9650 CPU COOLER, (well it's a rig Whitout a Case, so a lot of dust, no cooling troubles, f.i. a 850 Watt PSU, doesn't even get 35C, loaded @ 550Watt. Cards run run @ <50% FAN, little noice.

IMO, most PC Cases, latests and 'Gaming' rigs, already have their case adjusted.
Many PSU have died, cause of the (multiple)GPU's and (OC'ed) CPU's.
ID: 1075677 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1075681 - Posted: 9 Feb 2011, 23:56:33 UTC

Yeah, upload and download works. I guess we're going to clear out the limbo-ed transfers before turning the scheduler back on and getting new work assignments. I know some people have had a stuck download since the weekend (I know I had one).
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1075681 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1075732 - Posted: 10 Feb 2011, 4:52:12 UTC

Cricket just face-planted from maxed out to the floor. And the forum list looks to be borked again. [sarcasm] Yaaay! [/sarcasm]
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1075732 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 11 · Next

Message boards : Number crunching : Panic Mode On (43) Server problems


 
©2024 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.